Token | trick |
Token ID | 6908 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
Wolf | +0.040 |
Mo | +0.039 |
cub | +0.039 |
Wilson | +0.038 |
Jo | +0.038 |
Neg logit contributions | |
ets | -0.059 |
issors | -0.056 |
ocus | -0.056 |
similarities | -0.051 |
ols | -0.050 |
Token | - |
Token ID | 12 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
handed | +0.012 |
Wolf | +0.012 |
cub | +0.011 |
Mo | +0.011 |
seat | +0.011 |
Neg logit contributions | |
issors | -0.024 |
ocus | -0.024 |
similarities | -0.024 |
ets | -0.023 |
seventeen | -0.022 |
Token | or |
Token ID | 273 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
cub | +0.021 |
Wolf | +0.020 |
seat | +0.019 |
baby | +0.019 |
therm | +0.019 |
Neg logit contributions | |
issors | -0.029 |
ocus | -0.028 |
similarities | -0.027 |
ets | -0.026 |
seventeen | -0.025 |
Token | - |
Token ID | 12 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
seat | +0.008 |
Wolf | +0.008 |
cub | +0.008 |
distance | +0.008 |
Mo | +0.007 |
Neg logit contributions | |
ocus | -0.013 |
issors | -0.013 |
aces | -0.013 |
ets | -0.013 |
similarities | -0.012 |
Token | t |
Token ID | 83 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
cub | +0.021 |
Wolf | +0.020 |
seat | +0.019 |
baby | +0.019 |
Bear | +0.019 |
Neg logit contributions | |
issors | -0.029 |
ocus | -0.028 |
similarities | -0.027 |
ets | -0.026 |
seventeen | -0.025 |
Token | reating |
Token ID | 34567 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
Wolf | +0.005 |
cub | +0.005 |
Mo | +0.005 |
handed | +0.005 |
Wilson | +0.005 |
Neg logit contributions | |
ets | -0.008 |
similarities | -0.008 |
issors | -0.008 |
ocus | -0.008 |
brushes | -0.007 |
Token | anymore |
Token ID | 7471 |
Feature activation | +6.22e-01 |
Pos logit contributions | |
Wolf | +0.082 |
Mo | +0.076 |
cub | +0.074 |
therm | +0.073 |
eled | +0.072 |
Neg logit contributions | |
ets | -0.144 |
issors | -0.142 |
similarities | -0.140 |
ocus | -0.140 |
aces | -0.135 |
Token | . |
Token ID | 13 |
Feature activation | +1.46e-01 |
Pos logit contributions | |
rolley | +0.010 |
handed | +0.010 |
Wolf | +0.010 |
Mo | +0.009 |
hand | +0.009 |
Neg logit contributions | |
ocus | -0.032 |
similarities | -0.032 |
ets | -0.031 |
issors | -0.031 |
aces | -0.030 |
Token | She |
Token ID | 1375 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
burn | +0.004 |
handed | +0.004 |
Wolf | +0.004 |
Mo | +0.003 |
therm | +0.003 |
Neg logit contributions | |
issors | -0.006 |
ocus | -0.006 |
similarities | -0.006 |
ets | -0.006 |
meanings | -0.006 |
Token | sadly |
Token ID | 21098 |
Feature activation | -3.75e-01 |
Pos logit contributions | |
handed | +0.019 |
Wolf | +0.019 |
Mo | +0.017 |
seat | +0.017 |
hand | +0.017 |
Neg logit contributions | |
ocus | -0.033 |
similarities | -0.033 |
issors | -0.033 |
ets | -0.032 |
seventeen | -0.031 |
Token | put |
Token ID | 1234 |
Feature activation | -2.64e-02 |
Pos logit contributions | |
ocus | +0.016 |
similarities | +0.015 |
issors | +0.015 |
ets | +0.015 |
seventeen | +0.014 |
Neg logit contributions | |
handed | -0.010 |
Wolf | -0.010 |
rolley | -0.009 |
Mo | -0.009 |
therm | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -4.71e-01 |
Pos logit contributions | |
handed | +0.013 |
Wolf | +0.013 |
Mo | +0.012 |
rolley | +0.012 |
seat | +0.012 |
Neg logit contributions | |
issors | -0.032 |
similarities | -0.030 |
ocus | -0.030 |
ets | -0.030 |
seventeen | -0.030 |
Token | elderly |
Token ID | 13830 |
Feature activation | +9.02e-02 |
Pos logit contributions | |
issors | +0.017 |
similarities | +0.017 |
ocus | +0.016 |
ets | +0.016 |
seventeen | +0.015 |
Neg logit contributions | |
Mo | -0.015 |
Wolf | -0.014 |
handed | -0.014 |
hand | -0.014 |
esh | -0.013 |
Token | man |
Token ID | 582 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
Mo | +0.003 |
Rabbit | +0.003 |
Wolf | +0.003 |
Bear | +0.003 |
Bunny | +0.003 |
Neg logit contributions | |
similarities | -0.003 |
ocus | -0.003 |
ets | -0.003 |
ind | -0.003 |
issors | -0.003 |
Token | on |
Token ID | 319 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
ocus | +0.010 |
issors | +0.010 |
ets | +0.010 |
similarities | +0.010 |
aces | +0.009 |
Neg logit contributions | |
Wolf | -0.009 |
Mo | -0.008 |
handed | -0.008 |
Wilson | -0.008 |
rolley | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
handed | +0.013 |
rolley | +0.013 |
burn | +0.012 |
Wolf | +0.012 |
Mo | +0.011 |
Neg logit contributions | |
issors | -0.029 |
similarities | -0.028 |
ocus | -0.027 |
seventeen | -0.027 |
ets | -0.026 |
Token | stret |
Token ID | 5759 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
handed | +0.004 |
Wolf | +0.004 |
Mo | +0.004 |
hand | +0.004 |
seat | +0.004 |
Neg logit contributions | |
issors | -0.005 |
ocus | -0.005 |
similarities | -0.005 |
ets | -0.005 |
seventeen | -0.005 |
Token | cher |
Token ID | 2044 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
Wolf | +0.097 |
Mo | +0.095 |
therm | +0.092 |
baby | +0.092 |
handed | +0.086 |
Neg logit contributions | |
ocus | -0.112 |
issors | -0.108 |
similarities | -0.108 |
ets | -0.104 |
seventeen | -0.103 |
Token | . |
Token ID | 13 |
Feature activation | -7.97e-02 |
Pos logit contributions | |
Wolf | +0.012 |
handed | +0.011 |
Mo | +0.011 |
rolley | +0.009 |
hand | +0.009 |
Neg logit contributions | |
ets | -0.036 |
issors | -0.036 |
ocus | -0.036 |
aces | -0.035 |
ind | -0.034 |
Token | She |
Token ID | 1375 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
issors | +0.003 |
ocus | +0.003 |
similarities | +0.003 |
ets | +0.002 |
seventeen | +0.002 |
Neg logit contributions | |
handed | -0.003 |
burn | -0.003 |
Wolf | -0.003 |
cub | -0.003 |
Mo | -0.003 |
Token | thanked |
Token ID | 26280 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
handed | +0.017 |
Wolf | +0.016 |
Mo | +0.015 |
hand | +0.015 |
rolley | +0.015 |
Neg logit contributions | |
ocus | -0.023 |
similarities | -0.022 |
issors | -0.022 |
ets | -0.022 |
seventeen | -0.021 |
Token | Tim |
Token ID | 5045 |
Feature activation | -7.02e-02 |
Pos logit contributions | |
issors | +0.018 |
similarities | +0.018 |
ocus | +0.017 |
ets | +0.017 |
seventeen | +0.017 |
Neg logit contributions | |
handed | -0.012 |
rolley | -0.011 |
Wolf | -0.011 |
seat | -0.011 |
burn | -0.011 |
Token | frustrated |
Token ID | 14718 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
issors | +0.013 |
similarities | +0.013 |
ocus | +0.013 |
ets | +0.012 |
meanings | +0.012 |
Neg logit contributions | |
Wolf | -0.007 |
Mo | -0.007 |
handed | -0.007 |
seat | -0.006 |
hand | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
handed | +0.008 |
Mo | +0.008 |
Wolf | +0.008 |
burn | +0.007 |
rolley | +0.007 |
Neg logit contributions | |
ets | -0.017 |
ocus | -0.016 |
issors | -0.016 |
aces | -0.015 |
similarities | -0.015 |
Token | started |
Token ID | 2067 |
Feature activation | +6.93e-01 |
Pos logit contributions | |
Wolf | +0.005 |
handed | +0.005 |
cub | +0.005 |
anyway | +0.005 |
baby | +0.004 |
Neg logit contributions | |
issors | -0.009 |
ocus | -0.009 |
similarities | -0.009 |
ets | -0.009 |
seventeen | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
handed | +0.025 |
rolley | +0.025 |
Mo | +0.025 |
Wolf | +0.025 |
hand | +0.023 |
Neg logit contributions | |
similarities | -0.022 |
ocus | -0.021 |
issors | -0.021 |
ets | -0.019 |
meanings | -0.019 |
Token | f |
Token ID | 277 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
issors | +0.006 |
similarities | +0.006 |
ocus | +0.006 |
ets | +0.005 |
seventeen | +0.005 |
Neg logit contributions | |
handed | -0.005 |
Wolf | -0.005 |
Mo | -0.005 |
hand | -0.004 |
rolley | -0.004 |
Token | idget |
Token ID | 17484 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
handed | +0.036 |
Wolf | +0.034 |
anyway | +0.032 |
rolley | +0.031 |
Mo | +0.031 |
Neg logit contributions | |
similarities | -0.063 |
ocus | -0.061 |
issors | -0.061 |
seventeen | -0.059 |
ets | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
handed | +0.078 |
clearing | +0.076 |
Mo | +0.073 |
continuing | +0.071 |
Wolf | +0.071 |
Neg logit contributions | |
ocus | -0.126 |
issors | -0.123 |
ets | -0.123 |
aces | -0.121 |
ems | -0.117 |
Token |
|
Token ID | 198 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
handed | +0.000 |
Wolf | +0.000 |
cub | +0.000 |
Mo | +0.000 |
burn | +0.000 |
Neg logit contributions | |
issors | -0.001 |
similarities | -0.001 |
ocus | -0.001 |
ets | -0.001 |
ind | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
handed | +0.006 |
burn | +0.006 |
therm | +0.006 |
Wolf | +0.006 |
cub | +0.006 |
Neg logit contributions | |
issors | -0.009 |
ocus | -0.008 |
similarities | -0.008 |
ets | -0.008 |
apes | -0.008 |
Token | Her |
Token ID | 9360 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
Wolf | +0.014 |
handed | +0.014 |
Mo | +0.012 |
cub | +0.012 |
anyway | +0.012 |
Neg logit contributions | |
ocus | -0.028 |
issors | -0.028 |
similarities | -0.027 |
ets | -0.027 |
seventeen | -0.026 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
Wolf | +0.016 |
handed | +0.015 |
baby | +0.014 |
cub | +0.014 |
therm | +0.014 |
Neg logit contributions | |
ocus | -0.045 |
issors | -0.045 |
similarities | -0.044 |
ets | -0.044 |
seventeen | -0.043 |
Token | with |
Token ID | 351 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
handed | +0.004 |
Wolf | +0.004 |
Mo | +0.004 |
rolley | +0.004 |
burn | +0.004 |
Neg logit contributions | |
ocus | -0.004 |
issors | -0.004 |
similarities | -0.004 |
ets | -0.004 |
apes | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
issors | +0.018 |
similarities | +0.018 |
seventeen | +0.017 |
ets | +0.017 |
ind | +0.016 |
Neg logit contributions | |
handed | -0.010 |
Mo | -0.009 |
Wolf | -0.009 |
rolley | -0.009 |
hand | -0.009 |
Token | man |
Token ID | 582 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
issors | +0.009 |
ocus | +0.009 |
similarities | +0.009 |
ets | +0.008 |
seventeen | +0.008 |
Neg logit contributions | |
handed | -0.007 |
Wolf | -0.007 |
Mo | -0.006 |
hand | -0.006 |
cub | -0.006 |
Token | on |
Token ID | 319 |
Feature activation | +9.63e-01 |
Pos logit contributions | |
ocus | +0.006 |
issors | +0.006 |
ets | +0.006 |
similarities | +0.006 |
ind | +0.006 |
Neg logit contributions | |
Mo | -0.003 |
Wolf | -0.003 |
handed | -0.003 |
rolley | -0.003 |
Wilson | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +1.00e-01 |
Pos logit contributions | |
handed | +0.022 |
rolley | +0.021 |
Wolf | +0.019 |
Mo | +0.019 |
seat | +0.019 |
Neg logit contributions | |
issors | -0.043 |
similarities | -0.043 |
ocus | -0.041 |
seventeen | -0.041 |
ind | -0.040 |
Token | stret |
Token ID | 5759 |
Feature activation | +3.04e+00 |
Pos logit contributions | |
handed | +0.003 |
Wolf | +0.003 |
Mo | +0.003 |
hand | +0.002 |
rolley | +0.002 |
Neg logit contributions | |
issors | -0.004 |
ocus | -0.004 |
similarities | -0.004 |
seventeen | -0.004 |
ets | -0.004 |
Token | cher |
Token ID | 2044 |
Feature activation | +6.82e-01 |
Pos logit contributions | |
Wolf | +0.093 |
Mo | +0.093 |
baby | +0.089 |
therm | +0.089 |
handed | +0.085 |
Neg logit contributions | |
ocus | -0.110 |
issors | -0.107 |
similarities | -0.103 |
seventeen | -0.101 |
ets | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | -1.73e-01 |
Pos logit contributions | |
handed | +0.012 |
Wolf | +0.012 |
Mo | +0.011 |
Doctor | +0.010 |
hand | +0.010 |
Neg logit contributions | |
issors | -0.034 |
ets | -0.034 |
ocus | -0.034 |
aces | -0.033 |
ind | -0.032 |
Token | The |
Token ID | 383 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
issors | +0.006 |
ocus | +0.006 |
similarities | +0.006 |
seventeen | +0.006 |
ets | +0.006 |
Neg logit contributions | |
handed | -0.006 |
Wolf | -0.005 |
Mo | -0.005 |
burn | -0.005 |
hand | -0.005 |
Token | man |
Token ID | 582 |
Feature activation | -8.34e-01 |
Pos logit contributions | |
Mo | +0.004 |
handed | +0.004 |
Wilson | +0.004 |
Willie | +0.004 |
Rabbit | +0.004 |
Neg logit contributions | |
similarities | -0.005 |
issors | -0.005 |
seventeen | -0.004 |
ets | -0.004 |
brushes | -0.004 |
Token | 's |
Token ID | 338 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
ocus | +0.034 |
issors | +0.034 |
similarities | +0.034 |
ets | +0.032 |
seventeen | +0.032 |
Neg logit contributions | |
handed | -0.023 |
Wolf | -0.022 |
Mo | -0.021 |
seat | -0.020 |
rolley | -0.020 |
Token | said |
Token ID | 531 |
Feature activation | +7.28e-01 |
Pos logit contributions | |
handed | +0.007 |
Wolf | +0.006 |
rolley | +0.006 |
hand | +0.006 |
seat | +0.006 |
Neg logit contributions | |
issors | -0.010 |
ocus | -0.009 |
similarities | -0.009 |
ind | -0.009 |
ets | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
rolley | +0.025 |
handed | +0.024 |
seat | +0.023 |
Mo | +0.021 |
hand | +0.021 |
Neg logit contributions | |
issors | -0.023 |
ind | -0.023 |
similarities | -0.021 |
ige | -0.020 |
draw | -0.020 |
Token | voice |
Token ID | 3809 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
handed | +0.008 |
Wolf | +0.008 |
Mo | +0.007 |
eled | +0.007 |
rolley | +0.007 |
Neg logit contributions | |
seventeen | -0.008 |
similarities | -0.008 |
ind | -0.008 |
ocus | -0.008 |
issors | -0.008 |
Token | on |
Token ID | 319 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
handed | +0.021 |
Wolf | +0.020 |
Mo | +0.020 |
rolley | +0.020 |
burn | +0.017 |
Neg logit contributions | |
ets | -0.050 |
ind | -0.049 |
ocus | -0.049 |
issors | -0.049 |
ols | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | +7.71e-01 |
Pos logit contributions | |
handed | +0.027 |
rolley | +0.024 |
seat | +0.023 |
hand | +0.022 |
Wolf | +0.021 |
Neg logit contributions | |
issors | -0.048 |
similarities | -0.047 |
ocus | -0.045 |
ind | -0.044 |
ets | -0.044 |
Token | other |
Token ID | 584 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
Wolf | +0.023 |
handed | +0.023 |
Mo | +0.022 |
cub | +0.022 |
anyway | +0.021 |
Neg logit contributions | |
issors | -0.030 |
ocus | -0.030 |
similarities | -0.029 |
ets | -0.028 |
seventeen | -0.028 |
Token | end |
Token ID | 886 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
handed | +0.068 |
Wolf | +0.066 |
Mo | +0.064 |
burn | +0.059 |
seat | +0.059 |
Neg logit contributions | |
issors | -0.139 |
ets | -0.134 |
similarities | -0.133 |
ocus | -0.132 |
ind | -0.126 |
Token | . |
Token ID | 13 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
handed | +0.019 |
Wolf | +0.019 |
Mo | +0.015 |
cub | +0.015 |
therm | +0.014 |
Neg logit contributions | |
ocus | -0.098 |
issors | -0.097 |
similarities | -0.096 |
ets | -0.094 |
seventeen | -0.093 |
Token | |
Token ID | 220 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
handed | +0.006 |
burn | +0.005 |
rolley | +0.005 |
Wolf | +0.005 |
Mo | +0.005 |
Neg logit contributions | |
issors | -0.008 |
ocus | -0.008 |
similarities | -0.007 |
ind | -0.007 |
seventeen | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
handed | +0.027 |
elf | +0.027 |
cub | +0.027 |
Wolf | +0.027 |
therm | +0.027 |
Neg logit contributions | |
issors | -0.048 |
ocus | -0.046 |
similarities | -0.042 |
apes | -0.042 |
ets | -0.042 |
Token |
|
Token ID | 198 |
Feature activation | +4.81e-01 |
Pos logit contributions | |
Wolf | +0.006 |
handed | +0.006 |
cub | +0.006 |
burn | +0.005 |
therm | +0.005 |
Neg logit contributions | |
issors | -0.015 |
ocus | -0.015 |
similarities | -0.014 |
seventeen | -0.014 |
ets | -0.014 |
Token | added |
Token ID | 2087 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
handed | +0.002 |
Wolf | +0.002 |
rolley | +0.002 |
Mo | +0.002 |
anyways | +0.002 |
Neg logit contributions | |
similarities | -0.003 |
ocus | -0.003 |
ind | -0.003 |
ets | -0.003 |
draws | -0.003 |
Token | gentle |
Token ID | 10296 |
Feature activation | +8.67e-01 |
Pos logit contributions | |
handed | +0.005 |
Wolf | +0.005 |
Mo | +0.004 |
cub | +0.004 |
seat | +0.004 |
Neg logit contributions | |
ocus | -0.011 |
similarities | -0.011 |
issors | -0.011 |
ets | -0.011 |
seventeen | -0.011 |
Token | kisses |
Token ID | 36544 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Wolf | +0.030 |
handed | +0.030 |
cub | +0.029 |
baby | +0.028 |
therm | +0.028 |
Neg logit contributions | |
issors | -0.030 |
ocus | -0.030 |
similarities | -0.029 |
ets | -0.028 |
seventeen | -0.027 |
Token | while |
Token ID | 981 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
handed | +0.051 |
Wolf | +0.046 |
Mo | +0.044 |
seat | +0.042 |
cub | +0.042 |
Neg logit contributions | |
issors | -0.094 |
similarities | -0.094 |
ets | -0.094 |
ocus | -0.093 |
ind | -0.089 |
Token | smoot |
Token ID | 32746 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
similarities | +0.012 |
ocus | +0.012 |
issors | +0.012 |
ind | +0.012 |
seventeen | +0.011 |
Neg logit contributions | |
handed | -0.009 |
rolley | -0.008 |
seat | -0.007 |
esh | -0.007 |
hand | -0.007 |
Token | hing |
Token ID | 722 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
Wolf | +0.017 |
handed | +0.017 |
cub | +0.016 |
baby | +0.016 |
anyway | +0.016 |
Neg logit contributions | |
ocus | -0.021 |
issors | -0.021 |
ets | -0.020 |
similarities | -0.020 |
seventeen | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
Wolf | +0.091 |
handed | +0.091 |
cub | +0.085 |
Mo | +0.085 |
therm | +0.084 |
Neg logit contributions | |
issors | -0.111 |
ocus | -0.111 |
similarities | -0.110 |
ets | -0.105 |
seventeen | -0.103 |
Token | baby |
Token ID | 5156 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
similarities | +0.015 |
issors | +0.015 |
meanings | +0.014 |
ocus | +0.014 |
seventeen | +0.014 |
Neg logit contributions | |
handed | -0.004 |
Mo | -0.004 |
Wolf | -0.004 |
able | -0.004 |
anyway | -0.004 |
Token | 's |
Token ID | 338 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
handed | +0.017 |
Mo | +0.017 |
Jon | +0.016 |
Son | +0.016 |
rolley | +0.016 |
Neg logit contributions | |
ets | -0.024 |
ocus | -0.024 |
similarities | -0.024 |
aces | -0.024 |
meanings | -0.023 |
Token | hair |
Token ID | 4190 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
issors | +0.013 |
ocus | +0.013 |
similarities | +0.013 |
ets | +0.012 |
seventeen | +0.012 |
Neg logit contributions | |
handed | -0.013 |
Wolf | -0.013 |
Mo | -0.013 |
cub | -0.012 |
anyway | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -2.18e-02 |
Pos logit contributions | |
ocus | +0.019 |
ets | +0.019 |
issors | +0.019 |
similarities | +0.019 |
ind | +0.018 |
Neg logit contributions | |
Wolf | -0.006 |
handed | -0.006 |
Mo | -0.005 |
cub | -0.005 |
rolley | -0.005 |
Token | jar |
Token ID | 17379 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
Wolf | +0.014 |
handed | +0.014 |
cub | +0.013 |
Mo | +0.013 |
baby | +0.013 |
Neg logit contributions | |
issors | -0.020 |
ocus | -0.020 |
similarities | -0.020 |
ets | -0.019 |
seventeen | -0.019 |
Token | red |
Token ID | 445 |
Feature activation | +3.97e-01 |
Pos logit contributions | |
Wolf | +0.002 |
Mo | +0.001 |
handed | +0.001 |
cub | +0.001 |
Wilson | +0.001 |
Neg logit contributions | |
ets | -0.004 |
ocus | -0.003 |
issors | -0.003 |
similarities | -0.003 |
aces | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
Wolf | +0.008 |
handed | +0.008 |
Mo | +0.007 |
seat | +0.007 |
rolley | +0.007 |
Neg logit contributions | |
similarities | -0.019 |
ocus | -0.019 |
ets | -0.019 |
issors | -0.018 |
seventeen | -0.018 |
Token | bottled |
Token ID | 34123 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
Wolf | +0.003 |
handed | +0.003 |
cub | +0.003 |
Mo | +0.003 |
anyway | +0.003 |
Neg logit contributions | |
ocus | -0.004 |
issors | -0.004 |
similarities | -0.004 |
ets | -0.004 |
seventeen | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
issors | +0.043 |
ocus | +0.043 |
similarities | +0.042 |
ets | +0.041 |
seventeen | +0.040 |
Neg logit contributions | |
Wolf | -0.018 |
handed | -0.018 |
cub | -0.016 |
baby | -0.016 |
Mo | -0.016 |
Token | vacuum |
Token ID | 17076 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
issors | +0.004 |
ocus | +0.004 |
similarities | +0.004 |
ets | +0.004 |
seventeen | +0.004 |
Neg logit contributions | |
Wolf | -0.003 |
handed | -0.003 |
cub | -0.003 |
Mo | -0.003 |
anyway | -0.003 |
Token | - |
Token ID | 12 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
Wolf | +0.085 |
handed | +0.084 |
Mo | +0.080 |
cub | +0.080 |
therm | +0.077 |
Neg logit contributions | |
ets | -0.116 |
issors | -0.112 |
ocus | -0.110 |
similarities | -0.110 |
seventeen | -0.103 |
Token | se |
Token ID | 325 |
Feature activation | +6.15e-01 |
Pos logit contributions | |
Wolf | +0.019 |
cub | +0.017 |
seat | +0.017 |
baby | +0.017 |
therm | +0.017 |
Neg logit contributions | |
ocus | -0.027 |
issors | -0.027 |
similarities | -0.026 |
ets | -0.026 |
seventeen | -0.025 |
Token | aled |
Token ID | 3021 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
Wolf | +0.016 |
handed | +0.016 |
Doctor | +0.015 |
seat | +0.015 |
Mo | +0.015 |
Neg logit contributions | |
ocus | -0.026 |
ets | -0.026 |
similarities | -0.025 |
issors | -0.024 |
seventeen | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
Wolf | +0.032 |
handed | +0.032 |
Mo | +0.029 |
cub | +0.028 |
rolley | +0.028 |
Neg logit contributions | |
issors | -0.067 |
ocus | -0.066 |
similarities | -0.066 |
ets | -0.066 |
seventeen | -0.064 |
Token | wrapped |
Token ID | 12908 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
Wolf | +0.013 |
handed | +0.013 |
cub | +0.012 |
Mo | +0.012 |
anyway | +0.011 |
Neg logit contributions | |
ocus | -0.021 |
issors | -0.021 |
similarities | -0.021 |
ets | -0.020 |
seventeen | -0.020 |
Token | One |
Token ID | 3198 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
handed | +0.035 |
Wolf | +0.032 |
cub | +0.031 |
rolley | +0.031 |
baby | +0.030 |
Neg logit contributions | |
similarities | -0.038 |
ocus | -0.037 |
issors | -0.037 |
ind | -0.035 |
apes | -0.034 |
Token | day |
Token ID | 1110 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
similarities | +0.009 |
ocus | +0.009 |
issors | +0.009 |
ets | +0.009 |
ind | +0.008 |
Neg logit contributions | |
handed | -0.009 |
Wolf | -0.008 |
Mo | -0.008 |
hand | -0.008 |
rolley | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
ocus | +0.005 |
issors | +0.005 |
similarities | +0.005 |
ind | +0.005 |
ets | +0.005 |
Neg logit contributions | |
handed | -0.005 |
rolley | -0.005 |
Wolf | -0.004 |
cub | -0.004 |
seat | -0.004 |
Token | when |
Token ID | 618 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
handed | +0.004 |
rolley | +0.003 |
cub | +0.003 |
Wolf | +0.003 |
hand | +0.003 |
Neg logit contributions | |
issors | -0.006 |
similarities | -0.006 |
ocus | -0.006 |
ind | -0.006 |
brushes | -0.005 |
Token | Br |
Token ID | 1709 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
similarities | +0.016 |
ocus | +0.015 |
ind | +0.015 |
issors | +0.015 |
brushes | +0.014 |
Neg logit contributions | |
handed | -0.014 |
rolley | -0.012 |
cub | -0.010 |
hand | -0.010 |
Son | -0.010 |
Token | idget |
Token ID | 17484 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
handed | +0.036 |
Wolf | +0.035 |
cub | +0.033 |
hand | +0.032 |
Mo | +0.032 |
Neg logit contributions | |
issors | -0.065 |
ocus | -0.065 |
similarities | -0.062 |
ets | -0.062 |
aces | -0.058 |
Token | was |
Token ID | 373 |
Feature activation | +8.82e-01 |
Pos logit contributions | |
handed | +0.066 |
Wolf | +0.063 |
Mo | +0.059 |
anyway | +0.058 |
anyways | +0.058 |
Neg logit contributions | |
ocus | -0.132 |
ets | -0.126 |
similarities | -0.126 |
issors | -0.126 |
ind | -0.120 |
Token | walking |
Token ID | 6155 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
handed | +0.021 |
Wolf | +0.021 |
Mo | +0.019 |
cub | +0.019 |
hand | +0.018 |
Neg logit contributions | |
ocus | -0.040 |
issors | -0.040 |
similarities | -0.039 |
ets | -0.038 |
seventeen | -0.037 |
Token | in |
Token ID | 287 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
handed | +0.016 |
Wolf | +0.015 |
therm | +0.014 |
cub | +0.014 |
rolley | +0.014 |
Neg logit contributions | |
ocus | -0.020 |
issors | -0.020 |
similarities | -0.020 |
ets | -0.019 |
ind | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
similarities | +0.032 |
ocus | +0.032 |
ey | +0.032 |
issors | +0.031 |
Puzzles | +0.030 |
Neg logit contributions | |
handed | -0.027 |
rolley | -0.027 |
burn | -0.026 |
eled | -0.024 |
Son | -0.024 |
Token | me |
Token ID | 502 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Wolf | +0.011 |
handed | +0.011 |
cub | +0.010 |
Mo | +0.010 |
anyway | +0.010 |
Neg logit contributions | |
ocus | -0.021 |
issors | -0.021 |
similarities | -0.021 |
ets | -0.020 |
seventeen | -0.020 |
Token | my |
Token ID | 1820 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
ocus | +0.018 |
ets | +0.018 |
issors | +0.018 |
similarities | +0.017 |
ind | +0.017 |
Neg logit contributions | |
handed | -0.012 |
Wolf | -0.010 |
rolley | -0.010 |
Mo | -0.010 |
seat | -0.009 |
Token | smiled |
Token ID | 13541 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
ocus | +0.012 |
ets | +0.012 |
similarities | +0.012 |
ind | +0.012 |
issors | +0.011 |
Neg logit contributions | |
handed | -0.011 |
seat | -0.010 |
rolley | -0.010 |
Wolf | -0.010 |
Mo | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
handed | +0.014 |
Wolf | +0.012 |
Mo | +0.012 |
rolley | +0.012 |
hand | +0.011 |
Neg logit contributions | |
ets | -0.010 |
ind | -0.010 |
similarities | -0.010 |
ocus | -0.010 |
does | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
handed | +0.007 |
rolley | +0.007 |
Wolf | +0.007 |
seat | +0.006 |
Mo | +0.006 |
Neg logit contributions | |
ocus | -0.007 |
similarities | -0.007 |
ind | -0.007 |
ets | -0.007 |
issors | -0.007 |
Token | there |
Token ID | 612 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
handed | +0.031 |
Wolf | +0.030 |
seat | +0.028 |
rolley | +0.028 |
Mo | +0.028 |
Neg logit contributions | |
ocus | -0.053 |
similarities | -0.052 |
issors | -0.052 |
seventeen | -0.050 |
ets | -0.050 |
Token | were |
Token ID | 547 |
Feature activation | +2.88e+00 |
Pos logit contributions | |
handed | +0.041 |
Wolf | +0.036 |
Mo | +0.036 |
seat | +0.035 |
rolley | +0.035 |
Neg logit contributions | |
similarities | -0.081 |
issors | -0.079 |
ocus | -0.078 |
ets | -0.075 |
meanings | -0.075 |
Token | no |
Token ID | 645 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
handed | +0.079 |
rolley | +0.071 |
seat | +0.070 |
Wolf | +0.068 |
Mo | +0.067 |
Neg logit contributions | |
similarities | -0.123 |
issors | -0.118 |
ocus | -0.117 |
meanings | -0.115 |
seventeen | -0.114 |
Token | monsters |
Token ID | 10963 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
handed | +0.074 |
Mo | +0.069 |
Wolf | +0.067 |
rolley | +0.065 |
Wilson | +0.064 |
Neg logit contributions | |
similarities | -0.074 |
ets | -0.071 |
meanings | -0.069 |
issors | -0.068 |
ocus | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | +6.68e-01 |
Pos logit contributions | |
handed | +0.043 |
Wolf | +0.043 |
rolley | +0.040 |
Mo | +0.040 |
therm | +0.039 |
Neg logit contributions | |
ocus | -0.103 |
ets | -0.102 |
issors | -0.101 |
similarities | -0.100 |
seventeen | -0.095 |
Token | Then |
Token ID | 3244 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
Wolf | +0.020 |
handed | +0.020 |
cub | +0.019 |
Mo | +0.019 |
therm | +0.019 |
Neg logit contributions | |
issors | -0.026 |
ocus | -0.026 |
similarities | -0.025 |
ets | -0.024 |
seventeen | -0.024 |
Token | she |
Token ID | 673 |
Feature activation | +1.70e-01 |
Pos logit contributions | |
handed | +0.040 |
rolley | +0.037 |
seat | +0.033 |
Wolf | +0.032 |
Mo | +0.031 |
Neg logit contributions | |
similarities | -0.050 |
ocus | -0.047 |
ind | -0.046 |
issors | -0.046 |
does | -0.045 |
Token | want |
Token ID | 765 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
Wolf | +0.004 |
handed | +0.004 |
rolley | +0.003 |
seat | +0.003 |
Mo | +0.003 |
Neg logit contributions | |
similarities | -0.004 |
issors | -0.004 |
ocus | -0.004 |
ets | -0.004 |
seventeen | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
issors | +0.006 |
ocus | +0.006 |
similarities | +0.006 |
ets | +0.006 |
seventeen | +0.005 |
Neg logit contributions | |
handed | -0.004 |
Wolf | -0.004 |
cub | -0.003 |
Mo | -0.003 |
seat | -0.003 |
Token | go |
Token ID | 467 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Wolf | +0.026 |
handed | +0.025 |
rolley | +0.025 |
seat | +0.025 |
Mo | +0.024 |
Neg logit contributions | |
similarities | -0.025 |
issors | -0.025 |
ocus | -0.024 |
ets | -0.023 |
seventeen | -0.023 |
Token | empty |
Token ID | 6565 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
Wolf | +0.033 |
handed | +0.032 |
Mo | +0.031 |
rolley | +0.031 |
therm | +0.030 |
Neg logit contributions | |
issors | -0.057 |
ocus | -0.057 |
ets | -0.056 |
similarities | -0.056 |
seventeen | -0.053 |
Token | - |
Token ID | 12 |
Feature activation | +8.66e-01 |
Pos logit contributions | |
Wolf | +0.016 |
handed | +0.016 |
cub | +0.014 |
Mo | +0.014 |
anyway | +0.014 |
Neg logit contributions | |
issors | -0.035 |
ocus | -0.035 |
similarities | -0.035 |
ets | -0.034 |
seventeen | -0.033 |
Token | handed |
Token ID | 13638 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
Wolf | +0.008 |
therm | +0.006 |
cub | +0.006 |
baby | +0.006 |
Mo | +0.006 |
Neg logit contributions | |
issors | -0.052 |
ocus | -0.051 |
similarities | -0.050 |
ets | -0.050 |
seventeen | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +3.91e-01 |
Pos logit contributions | |
Wolf | +0.058 |
Mo | +0.058 |
burn | +0.056 |
therm | +0.056 |
rolley | +0.054 |
Neg logit contributions | |
ets | -0.130 |
issors | -0.125 |
ocus | -0.124 |
similarities | -0.123 |
aces | -0.118 |
Token | so |
Token ID | 523 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
Wolf | +0.009 |
handed | +0.009 |
anyway | +0.008 |
cub | +0.008 |
baby | +0.008 |
Neg logit contributions | |
issors | -0.018 |
ocus | -0.018 |
similarities | -0.018 |
ets | -0.017 |
seventeen | -0.017 |
Token | she |
Token ID | 673 |
Feature activation | -2.71e-01 |
Pos logit contributions | |
ocus | +0.013 |
similarities | +0.013 |
issors | +0.013 |
seventeen | +0.012 |
ets | +0.012 |
Neg logit contributions | |
handed | -0.005 |
Wolf | -0.005 |
rolley | -0.005 |
burn | -0.005 |
therm | -0.005 |
Token | sque |
Token ID | 35776 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
ocus | +0.012 |
issors | +0.012 |
similarities | +0.012 |
ets | +0.012 |
seventeen | +0.012 |
Neg logit contributions | |
Wolf | -0.006 |
handed | -0.006 |
Mo | -0.005 |
cub | -0.005 |
therm | -0.005 |
Token | aked |
Token ID | 4335 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
issors | +0.061 |
similarities | +0.060 |
ocus | +0.060 |
seventeen | +0.057 |
ets | +0.056 |
Neg logit contributions | |
handed | -0.061 |
Wolf | -0.060 |
anyway | -0.057 |
cub | -0.057 |
Mo | -0.056 |
Token | - |
Token ID | 12 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
issors | +0.033 |
ocus | +0.033 |
similarities | +0.032 |
ets | +0.031 |
seventeen | +0.031 |
Neg logit contributions | |
handed | -0.020 |
Wolf | -0.019 |
hand | -0.018 |
Mo | -0.018 |
anyway | -0.017 |
Token | hearted |
Token ID | 20122 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
issors | +0.016 |
ocus | +0.016 |
similarities | +0.016 |
ets | +0.015 |
seventeen | +0.015 |
Neg logit contributions | |
Wolf | -0.009 |
handed | -0.009 |
cub | -0.009 |
Mo | -0.008 |
seat | -0.008 |
Token | princess |
Token ID | 21752 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
issors | +0.034 |
ocus | +0.034 |
similarities | +0.034 |
ets | +0.033 |
ind | +0.032 |
Neg logit contributions | |
handed | -0.019 |
Wolf | -0.017 |
hand | -0.017 |
Mo | -0.017 |
anyway | -0.016 |
Token | named |
Token ID | 3706 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
ocus | +0.016 |
ets | +0.015 |
ind | +0.015 |
similarities | +0.014 |
aces | +0.014 |
Neg logit contributions | |
handed | -0.012 |
hand | -0.012 |
colder | -0.011 |
unconscious | -0.011 |
Wolf | -0.011 |
Token | Br |
Token ID | 1709 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
ocus | +0.037 |
issors | +0.037 |
similarities | +0.036 |
ets | +0.035 |
seventeen | +0.034 |
Neg logit contributions | |
Wolf | -0.033 |
handed | -0.032 |
therm | -0.031 |
rolley | -0.030 |
seat | -0.030 |
Token | idget |
Token ID | 17484 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
Wolf | +0.061 |
handed | +0.060 |
cub | +0.058 |
hand | +0.056 |
baby | +0.055 |
Neg logit contributions | |
issors | -0.074 |
ocus | -0.074 |
ets | -0.071 |
similarities | -0.068 |
aces | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
handed | +0.086 |
continuing | +0.078 |
further | +0.076 |
calling | +0.074 |
seat | +0.073 |
Neg logit contributions | |
aces | -0.102 |
ocus | -0.099 |
likes | -0.099 |
ets | -0.099 |
ind | -0.096 |
Token | She |
Token ID | 1375 |
Feature activation | +9.09e-01 |
Pos logit contributions | |
handed | +0.019 |
Wolf | +0.018 |
cub | +0.017 |
burn | +0.017 |
hand | +0.017 |
Neg logit contributions | |
issors | -0.025 |
similarities | -0.024 |
ocus | -0.024 |
ets | -0.023 |
ind | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | +4.50e-03 |
Pos logit contributions | |
Wolf | +0.025 |
cub | +0.025 |
handed | +0.024 |
baby | +0.024 |
Mo | +0.024 |
Neg logit contributions | |
issors | -0.039 |
ocus | -0.038 |
similarities | -0.037 |
seventeen | -0.036 |
ets | -0.035 |
Token | always |
Token ID | 1464 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
handed | +0.000 |
Wolf | +0.000 |
cub | +0.000 |
hand | +0.000 |
Mo | +0.000 |
Neg logit contributions | |
ocus | -0.000 |
issors | -0.000 |
similarities | -0.000 |
ets | -0.000 |
seventeen | -0.000 |
Token | calm |
Token ID | 9480 |
Feature activation | -3.56e-01 |
Pos logit contributions | |
similarities | +0.023 |
ocus | +0.023 |
ind | +0.022 |
issors | +0.022 |
ets | +0.022 |
Neg logit contributions | |
handed | -0.018 |
hand | -0.018 |
rolley | -0.018 |
Wolf | -0.017 |
Mo | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +3.65e-01 |
Pos logit contributions | |
handed | +0.006 |
rolley | +0.006 |
seat | +0.006 |
Wolf | +0.005 |
burn | +0.005 |
Neg logit contributions | |
issors | -0.012 |
similarities | -0.012 |
ocus | -0.012 |
seventeen | -0.012 |
ind | -0.012 |
Token | rock |
Token ID | 3881 |
Feature activation | +5.98e-01 |
Pos logit contributions | |
handed | +0.012 |
Wolf | +0.011 |
hand | +0.011 |
seat | +0.011 |
rolley | +0.011 |
Neg logit contributions | |
ocus | -0.013 |
issors | -0.013 |
seventeen | -0.013 |
ets | -0.013 |
similarities | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
handed | +0.019 |
Wolf | +0.019 |
rolley | +0.018 |
Mo | +0.018 |
hand | +0.018 |
Neg logit contributions | |
ocus | -0.022 |
ets | -0.022 |
issors | -0.021 |
seventeen | -0.020 |
ind | -0.020 |
Token | started |
Token ID | 2067 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
ocus | +0.001 |
issors | +0.001 |
ets | +0.001 |
similarities | +0.001 |
seventeen | +0.001 |
Neg logit contributions | |
handed | -0.001 |
rolley | -0.001 |
Wolf | -0.001 |
hand | -0.001 |
seat | -0.001 |
Token | to |
Token ID | 284 |
Feature activation | +6.97e-03 |
Pos logit contributions | |
rolley | +0.042 |
handed | +0.040 |
seat | +0.037 |
Wolf | +0.037 |
hand | +0.037 |
Neg logit contributions | |
ocus | -0.027 |
similarities | -0.025 |
ind | -0.024 |
issors | -0.023 |
sed | -0.023 |
Token | bleed |
Token ID | 30182 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
rolley | +0.000 |
hand | +0.000 |
handed | +0.000 |
ipt | +0.000 |
seat | +0.000 |
Neg logit contributions | |
ocus | -0.000 |
does | -0.000 |
draw | -0.000 |
similarities | -0.000 |
ets | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | +4.57e-02 |
Pos logit contributions | |
rolley | +0.081 |
handed | +0.081 |
hand | +0.071 |
Son | +0.070 |
seat | +0.069 |
Neg logit contributions | |
ets | -0.117 |
ocus | -0.110 |
aces | -0.108 |
does | -0.107 |
ind | -0.106 |
Token | Billy |
Token ID | 15890 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
Wolf | +0.001 |
handed | +0.001 |
cub | +0.001 |
Mo | +0.001 |
anyway | +0.001 |
Neg logit contributions | |
issors | -0.002 |
ocus | -0.002 |
similarities | -0.002 |
ets | -0.002 |
seventeen | -0.002 |
Token | tried |
Token ID | 3088 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
ocus | +0.012 |
ets | +0.012 |
does | +0.012 |
ind | +0.011 |
issors | +0.011 |
Neg logit contributions | |
handed | -0.013 |
seat | -0.012 |
rolley | -0.012 |
hand | -0.012 |
burn | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
rolley | +0.014 |
handed | +0.014 |
seat | +0.013 |
cub | +0.012 |
Wolf | +0.012 |
Neg logit contributions | |
similarities | -0.010 |
issors | -0.009 |
ocus | -0.009 |
ets | -0.008 |
seventeen | -0.008 |
Token | help |
Token ID | 1037 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
ets | +0.016 |
issors | +0.016 |
similarities | +0.016 |
draw | +0.015 |
ocus | +0.015 |
Neg logit contributions | |
rolley | -0.022 |
seat | -0.021 |
handed | -0.021 |
hand | -0.020 |
Wolf | -0.019 |
Token | asked |
Token ID | 1965 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
handed | +0.014 |
Wolf | +0.014 |
Mo | +0.014 |
cub | +0.013 |
hand | +0.013 |
Neg logit contributions | |
issors | -0.019 |
ocus | -0.018 |
similarities | -0.018 |
ets | -0.018 |
seventeen | -0.017 |
Token | for |
Token ID | 329 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
handed | +0.025 |
Wolf | +0.025 |
Mo | +0.023 |
cub | +0.023 |
therm | +0.023 |
Neg logit contributions | |
issors | -0.036 |
similarities | -0.035 |
ocus | -0.035 |
ets | -0.034 |
seventeen | -0.033 |
Token | a |
Token ID | 257 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
similarities | +0.015 |
issors | +0.015 |
ocus | +0.014 |
seventeen | +0.013 |
ets | +0.013 |
Neg logit contributions | |
Wolf | -0.008 |
handed | -0.008 |
rolley | -0.008 |
Mo | -0.008 |
cub | -0.008 |
Token | band |
Token ID | 4097 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
handed | +0.010 |
Wolf | +0.010 |
Mo | +0.009 |
rolley | +0.009 |
hand | +0.009 |
Neg logit contributions | |
similarities | -0.012 |
issors | -0.012 |
ocus | -0.012 |
seventeen | -0.012 |
ind | -0.011 |
Token | - |
Token ID | 12 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
Wolf | +0.029 |
Mo | +0.028 |
cub | +0.025 |
continuing | +0.025 |
baby | +0.025 |
Neg logit contributions | |
issors | -0.056 |
ets | -0.056 |
ocus | -0.054 |
similarities | -0.053 |
aces | -0.051 |
Token | aid |
Token ID | 1698 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
Wolf | +0.004 |
handed | +0.004 |
cub | +0.004 |
Mo | +0.004 |
baby | +0.004 |
Neg logit contributions | |
issors | -0.005 |
ocus | -0.005 |
similarities | -0.005 |
ets | -0.005 |
seventeen | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -2.55e-01 |
Pos logit contributions | |
handed | +0.060 |
Wolf | +0.057 |
Mo | +0.057 |
eled | +0.050 |
continuing | +0.049 |
Neg logit contributions | |
issors | -0.135 |
ets | -0.132 |
ocus | -0.128 |
similarities | -0.124 |
aces | -0.124 |
Token | Mom |
Token ID | 11254 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
ocus | +0.013 |
ets | +0.013 |
similarities | +0.013 |
issors | +0.012 |
seventeen | +0.012 |
Neg logit contributions | |
Wolf | -0.005 |
another | -0.005 |
handed | -0.005 |
anyway | -0.005 |
baby | -0.004 |
Token | cleaned |
Token ID | 20750 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
ocus | +0.007 |
issors | +0.007 |
similarities | +0.007 |
ets | +0.006 |
seventeen | +0.006 |
Neg logit contributions | |
handed | -0.005 |
Wolf | -0.005 |
Mo | -0.005 |
seat | -0.004 |
cub | -0.004 |
Token | Tom |
Token ID | 4186 |
Feature activation | -4.51e-01 |
Pos logit contributions | |
handed | +0.029 |
Wolf | +0.029 |
cub | +0.027 |
Mo | +0.027 |
seat | +0.026 |
Neg logit contributions | |
issors | -0.064 |
ocus | -0.062 |
similarities | -0.061 |
ets | -0.059 |
seventeen | -0.058 |
Token | 's |
Token ID | 338 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
ocus | +0.018 |
issors | +0.018 |
similarities | +0.018 |
ets | +0.017 |
seventeen | +0.017 |
Neg logit contributions | |
Wolf | -0.013 |
handed | -0.013 |
Mo | -0.012 |
seat | -0.012 |
hand | -0.012 |
Token | � |
Token ID | 6184 |
Feature activation | -5.21e-01 |
Pos logit contributions | |
handed | +0.003 |
Wolf | +0.003 |
rolley | +0.003 |
Mo | +0.003 |
seat | +0.003 |
Neg logit contributions | |
ocus | -0.005 |
issors | -0.005 |
similarities | -0.004 |
seventeen | -0.004 |
ind | -0.004 |
Token | � |
Token ID | 95 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
similarities | +0.016 |
issors | +0.016 |
ocus | +0.016 |
ets | +0.015 |
seventeen | +0.015 |
Neg logit contributions | |
handed | -0.019 |
Wolf | -0.019 |
Mo | -0.018 |
therm | -0.018 |
anyway | -0.018 |
Token | € |
Token ID | 26391 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
similarities | +0.037 |
issors | +0.037 |
ocus | +0.037 |
ets | +0.034 |
seventeen | +0.034 |
Neg logit contributions | |
handed | -0.044 |
Wolf | -0.043 |
anyway | -0.040 |
Mo | -0.040 |
hand | -0.040 |
Token | � |
Token ID | 129 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
Wolf | +0.007 |
handed | +0.007 |
cub | +0.007 |
Mo | +0.007 |
baby | +0.007 |
Neg logit contributions | |
ocus | -0.009 |
issors | -0.009 |
similarities | -0.009 |
ets | -0.009 |
seventeen | -0.009 |
Token | � |
Token ID | 241 |
Feature activation | -9.04e-03 |
Pos logit contributions | |
ocus | +0.030 |
similarities | +0.030 |
issors | +0.030 |
ets | +0.029 |
seventeen | +0.028 |
Neg logit contributions | |
handed | -0.026 |
Wolf | -0.025 |
anyway | -0.024 |
Mo | -0.024 |
therm | -0.023 |
Token | Not |
Token ID | 3673 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
similarities | +0.000 |
ocus | +0.000 |
issors | +0.000 |
seventeen | +0.000 |
ets | +0.000 |
Neg logit contributions | |
handed | -0.000 |
Wolf | -0.000 |
cub | -0.000 |
therm | -0.000 |
burn | -0.000 |
Token | usually |
Token ID | 3221 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
handed | +0.082 |
Wolf | +0.077 |
rolley | +0.075 |
Mo | +0.074 |
seat | +0.073 |
Neg logit contributions | |
similarities | -0.110 |
ocus | -0.109 |
ets | -0.105 |
issors | -0.105 |
seventeen | -0.102 |
Token | - |
Token ID | 532 |
Feature activation | +7.65e-01 |
Pos logit contributions | |
ocus | +0.010 |
issors | +0.010 |
similarities | +0.010 |
ets | +0.010 |
seventeen | +0.009 |
Neg logit contributions | |
handed | -0.008 |
Wolf | -0.008 |
Mo | -0.007 |
cub | -0.007 |
rolley | -0.007 |
Token | they |
Token ID | 484 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Wolf | +0.023 |
handed | +0.023 |
cub | +0.021 |
Mo | +0.021 |
therm | +0.021 |
Neg logit contributions | |
ocus | -0.030 |
issors | -0.030 |
similarities | -0.029 |
ets | -0.028 |
seventeen | -0.028 |
Token | â |
Token ID | 22940 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
Wolf | +0.048 |
handed | +0.048 |
Mo | +0.045 |
cub | +0.045 |
therm | +0.045 |
Neg logit contributions | |
ocus | -0.036 |
issors | -0.036 |
similarities | -0.036 |
ets | -0.034 |
seventeen | -0.033 |
Token | € |
Token ID | 26391 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
similarities | +0.022 |
ocus | +0.022 |
issors | +0.022 |
seventeen | +0.021 |
ets | +0.020 |
Neg logit contributions | |
handed | -0.023 |
Wolf | -0.023 |
anyway | -0.022 |
hand | -0.021 |
Mo | -0.021 |
Token | � |
Token ID | 6184 |
Feature activation | -9.97e-01 |
Pos logit contributions | |
handed | +0.004 |
burn | +0.004 |
Wolf | +0.004 |
Mo | +0.004 |
able | +0.004 |
Neg logit contributions | |
issors | -0.005 |
ocus | -0.005 |
similarities | -0.004 |
seventeen | -0.004 |
ets | -0.004 |
Token | � |
Token ID | 95 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
similarities | +0.033 |
issors | +0.033 |
ocus | +0.032 |
ets | +0.031 |
seventeen | +0.031 |
Neg logit contributions | |
handed | -0.036 |
Wolf | -0.035 |
therm | -0.033 |
Mo | -0.033 |
anyway | -0.033 |
Token | € |
Token ID | 26391 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
issors | +0.041 |
ocus | +0.041 |
similarities | +0.041 |
ets | +0.039 |
seventeen | +0.038 |
Neg logit contributions | |
handed | -0.049 |
Wolf | -0.049 |
cub | -0.046 |
Mo | -0.046 |
anyway | -0.046 |
Token | � |
Token ID | 129 |
Feature activation | -8.43e-01 |
Pos logit contributions | |
handed | +0.002 |
Wolf | +0.002 |
cub | +0.001 |
baby | +0.001 |
anyway | +0.001 |
Neg logit contributions | |
ocus | -0.002 |
issors | -0.002 |
similarities | -0.002 |
ets | -0.002 |
seventeen | -0.002 |
Token | � |
Token ID | 241 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
issors | +0.030 |
ocus | +0.030 |
similarities | +0.030 |
ets | +0.029 |
seventeen | +0.028 |
Neg logit contributions | |
Wolf | -0.027 |
handed | -0.027 |
anyway | -0.025 |
Mo | -0.025 |
therm | -0.025 |
Token | Not |
Token ID | 3673 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
ocus | +0.009 |
similarities | +0.009 |
issors | +0.009 |
seventeen | +0.009 |
ets | +0.009 |
Neg logit contributions | |
Wolf | -0.009 |
handed | -0.009 |
cub | -0.008 |
burn | -0.008 |
Rabbit | -0.008 |
Token | yet |
Token ID | 1865 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
handed | +0.082 |
Wolf | +0.078 |
Mo | +0.075 |
rolley | +0.075 |
cub | +0.073 |
Neg logit contributions | |
ocus | -0.108 |
similarities | -0.108 |
issors | -0.104 |
ets | -0.104 |
seventeen | -0.101 |
Token | , |
Token ID | 11 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
handed | +0.026 |
rolley | +0.025 |
eled | +0.024 |
Wolf | +0.024 |
cub | +0.023 |
Neg logit contributions | |
ocus | -0.045 |
similarities | -0.042 |
issors | -0.041 |
ets | -0.041 |
does | -0.041 |
Token | Alice |
Token ID | 14862 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
handed | +0.007 |
Wolf | +0.007 |
Mo | +0.006 |
cub | +0.006 |
seat | +0.006 |
Neg logit contributions | |
ocus | -0.010 |
similarities | -0.010 |
issors | -0.010 |
ets | -0.010 |
seventeen | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
handed | +0.027 |
Wolf | +0.026 |
Mo | +0.024 |
hand | +0.024 |
burn | +0.024 |
Neg logit contributions | |
ocus | -0.058 |
issors | -0.055 |
ets | -0.055 |
similarities | -0.055 |
ind | -0.053 |
Token | â |
Token ID | 22940 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
issors | +0.024 |
ocus | +0.024 |
similarities | +0.024 |
ets | +0.023 |
seventeen | +0.023 |
Neg logit contributions | |
Wolf | -0.019 |
handed | -0.018 |
baby | -0.017 |
anyway | -0.017 |
cub | -0.017 |
Token | never |
Token ID | 1239 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
ocus | +0.023 |
issors | +0.022 |
similarities | +0.022 |
ets | +0.021 |
seventeen | +0.021 |
Neg logit contributions | |
Wolf | -0.017 |
handed | -0.017 |
cub | -0.016 |
anyway | -0.016 |
baby | -0.016 |
Token | ask |
Token ID | 1265 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
issors | +0.004 |
ocus | +0.004 |
similarities | +0.004 |
seventeen | +0.004 |
ets | +0.004 |
Neg logit contributions | |
Wolf | -0.003 |
handed | -0.003 |
anyway | -0.003 |
cub | -0.003 |
baby | -0.003 |
Token | to |
Token ID | 284 |
Feature activation | +3.77e-01 |
Pos logit contributions | |
handed | +0.005 |
Wolf | +0.005 |
rolley | +0.004 |
Mo | +0.004 |
burn | +0.004 |
Neg logit contributions | |
issors | -0.010 |
similarities | -0.010 |
ocus | -0.009 |
ets | -0.009 |
seventeen | -0.009 |
Token | play |
Token ID | 711 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
Wolf | +0.012 |
handed | +0.012 |
Mo | +0.011 |
cub | +0.011 |
therm | +0.011 |
Neg logit contributions | |
issors | -0.014 |
ocus | -0.014 |
similarities | -0.014 |
ets | -0.014 |
seventeen | -0.013 |
Token | with |
Token ID | 351 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
Wolf | +0.027 |
handed | +0.026 |
Mo | +0.024 |
cub | +0.024 |
therm | +0.024 |
Neg logit contributions | |
ocus | -0.048 |
issors | -0.048 |
similarities | -0.047 |
ets | -0.046 |
seventeen | -0.044 |
Token | switches |
Token ID | 18225 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
burn | +0.005 |
Wolf | +0.005 |
rolley | +0.005 |
handed | +0.005 |
Mo | +0.005 |
Neg logit contributions | |
issors | -0.009 |
similarities | -0.009 |
ocus | -0.009 |
ets | -0.009 |
aces | -0.008 |
Token | again |
Token ID | 757 |
Feature activation | -6.73e-01 |
Pos logit contributions | |
Wolf | +0.054 |
handed | +0.053 |
Mo | +0.051 |
cub | +0.047 |
therm | +0.046 |
Neg logit contributions | |
ocus | -0.134 |
issors | -0.133 |
ets | -0.132 |
similarities | -0.131 |
seventeen | -0.125 |
Token | and |
Token ID | 290 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
ets | +0.033 |
ocus | +0.033 |
similarities | +0.032 |
issors | +0.032 |
apes | +0.031 |
Neg logit contributions | |
handed | -0.012 |
rolley | -0.012 |
Wolf | -0.012 |
burn | -0.011 |
Mo | -0.010 |
Token | never |
Token ID | 1239 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
Wolf | +0.001 |
handed | +0.001 |
cub | +0.001 |
Mo | +0.001 |
therm | +0.001 |
Neg logit contributions | |
ocus | -0.002 |
issors | -0.002 |
similarities | -0.002 |
ets | -0.002 |
seventeen | -0.002 |
Token | disob |
Token ID | 30163 |
Feature activation | +5.05e-01 |
Pos logit contributions | |
Wolf | +0.001 |
handed | +0.001 |
cub | +0.001 |
baby | +0.001 |
anyway | +0.001 |
Neg logit contributions | |
issors | -0.002 |
ocus | -0.002 |
similarities | -0.002 |
seventeen | -0.002 |
ets | -0.002 |
Token | ey |
Token ID | 2959 |
Feature activation | +4.19e-01 |
Pos logit contributions | |
Wolf | +0.016 |
therm | +0.015 |
seat | +0.015 |
rolley | +0.015 |
Doctor | +0.015 |
Neg logit contributions | |
issors | -0.019 |
ocus | -0.018 |
similarities | -0.017 |
ols | -0.017 |
apes | -0.017 |
Token | shiny |
Token ID | 22441 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
Wolf | +0.009 |
handed | +0.009 |
cub | +0.008 |
baby | +0.008 |
Mo | +0.008 |
Neg logit contributions | |
issors | -0.015 |
ocus | -0.015 |
similarities | -0.014 |
ets | -0.014 |
seventeen | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +3.62e-01 |
Pos logit contributions | |
ocus | +0.010 |
ets | +0.010 |
similarities | +0.010 |
issors | +0.010 |
ind | +0.010 |
Neg logit contributions | |
handed | -0.004 |
Wolf | -0.004 |
Mo | -0.003 |
rolley | -0.003 |
hand | -0.003 |
Token | made |
Token ID | 925 |
Feature activation | -8.54e-02 |
Pos logit contributions | |
Wolf | +0.010 |
handed | +0.010 |
baby | +0.009 |
cub | +0.009 |
Mo | +0.009 |
Neg logit contributions | |
issors | -0.015 |
ocus | -0.015 |
similarities | -0.014 |
ets | -0.014 |
seventeen | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
similarities | +0.004 |
ocus | +0.004 |
issors | +0.004 |
ets | +0.004 |
seventeen | +0.004 |
Neg logit contributions | |
handed | -0.002 |
Wolf | -0.002 |
Mo | -0.002 |
seat | -0.002 |
rolley | -0.002 |
Token | z |
Token ID | 1976 |
Feature activation | -5.99e-02 |
Pos logit contributions | |
ocus | +0.010 |
issors | +0.010 |
similarities | +0.010 |
ets | +0.010 |
seventeen | +0.009 |
Neg logit contributions | |
handed | -0.011 |
Wolf | -0.011 |
Mo | -0.010 |
cub | -0.010 |
hand | -0.010 |
Token | ooming |
Token ID | 30602 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
issors | +0.002 |
ocus | +0.002 |
similarities | +0.002 |
ets | +0.002 |
seventeen | +0.002 |
Neg logit contributions | |
Wolf | -0.002 |
handed | -0.002 |
cub | -0.002 |
Mo | -0.002 |
anyway | -0.002 |
Token | sound |
Token ID | 2128 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
handed | +0.068 |
Wolf | +0.068 |
Mo | +0.063 |
therm | +0.059 |
cub | +0.059 |
Neg logit contributions | |
ocus | -0.121 |
similarities | -0.120 |
ets | -0.119 |
issors | -0.118 |
seventeen | -0.114 |
Token | . |
Token ID | 13 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
handed | +0.028 |
Wolf | +0.027 |
rolley | +0.026 |
Mo | +0.025 |
Wilson | +0.023 |
Neg logit contributions | |
ets | -0.064 |
ocus | -0.061 |
ind | -0.059 |
similarities | -0.057 |
seventeen | -0.057 |
Token |
|
Token ID | 198 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
ocus | +0.019 |
issors | +0.019 |
similarities | +0.019 |
ets | +0.018 |
seventeen | +0.018 |
Neg logit contributions | |
Wolf | -0.006 |
handed | -0.006 |
anyway | -0.006 |
cub | -0.006 |
baby | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +9.09e-02 |
Pos logit contributions | |
ocus | +0.012 |
issors | +0.012 |
similarities | +0.012 |
ets | +0.012 |
seventeen | +0.011 |
Neg logit contributions | |
Wolf | -0.006 |
burn | -0.006 |
handed | -0.006 |
therm | -0.006 |
cub | -0.006 |
Token | L |
Token ID | 43 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
handed | +0.002 |
Wolf | +0.002 |
Mo | +0.002 |
cub | +0.002 |
anyway | +0.002 |
Neg logit contributions | |
issors | -0.004 |
ocus | -0.004 |
similarities | -0.004 |
ets | -0.004 |
seventeen | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
Wolf | +0.021 |
Mo | +0.020 |
cub | +0.020 |
handed | +0.020 |
eled | +0.019 |
Neg logit contributions | |
issors | -0.032 |
ets | -0.032 |
ocus | -0.031 |
aces | -0.029 |
does | -0.028 |
Token | put |
Token ID | 1234 |
Feature activation | +3.70e-01 |
Pos logit contributions | |
Wolf | +0.005 |
handed | +0.005 |
baby | +0.005 |
cub | +0.005 |
anyway | +0.005 |
Neg logit contributions | |
ocus | -0.008 |
issors | -0.008 |
similarities | -0.008 |
ets | -0.008 |
seventeen | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
handed | +0.010 |
Wolf | +0.010 |
Mo | +0.009 |
cub | +0.009 |
seat | +0.009 |
Neg logit contributions | |
issors | -0.016 |
ocus | -0.016 |
similarities | -0.015 |
ets | -0.015 |
seventeen | -0.015 |
Token | band |
Token ID | 4097 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
similarities | +0.004 |
issors | +0.004 |
ocus | +0.004 |
ets | +0.004 |
seventeen | +0.004 |
Neg logit contributions | |
Wolf | -0.003 |
handed | -0.003 |
Mo | -0.003 |
hand | -0.003 |
Wilson | -0.003 |
Token | - |
Token ID | 12 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
Wolf | +0.033 |
cub | +0.030 |
handed | +0.030 |
Mo | +0.030 |
Wilson | +0.030 |
Neg logit contributions | |
ocus | -0.044 |
ets | -0.044 |
issors | -0.044 |
similarities | -0.042 |
aces | -0.040 |
Token | aid |
Token ID | 1698 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
Wolf | +0.009 |
cub | +0.008 |
Wilson | +0.008 |
handed | +0.008 |
Mo | +0.008 |
Neg logit contributions | |
ocus | -0.010 |
issors | -0.010 |
similarities | -0.009 |
ets | -0.009 |
seventeen | -0.009 |
Token | on |
Token ID | 319 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
Wolf | +0.092 |
handed | +0.091 |
Mo | +0.087 |
cub | +0.085 |
hand | +0.082 |
Neg logit contributions | |
issors | -0.100 |
ets | -0.099 |
ocus | -0.097 |
similarities | -0.091 |
aces | -0.089 |
Token | it |
Token ID | 340 |
Feature activation | -5.96e-01 |
Pos logit contributions | |
handed | +0.022 |
seat | +0.021 |
Wolf | +0.021 |
rolley | +0.020 |
cub | +0.020 |
Neg logit contributions | |
issors | -0.025 |
ocus | -0.023 |
similarities | -0.023 |
ets | -0.022 |
seventeen | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -4.30e-02 |
Pos logit contributions | |
issors | +0.029 |
ets | +0.029 |
ocus | +0.029 |
similarities | +0.027 |
aces | +0.026 |
Neg logit contributions | |
Wolf | -0.013 |
handed | -0.012 |
Mo | -0.012 |
cub | -0.011 |
seat | -0.011 |
Token | Then |
Token ID | 3244 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
ocus | +0.001 |
issors | +0.001 |
similarities | +0.001 |
ets | +0.001 |
seventeen | +0.001 |
Neg logit contributions | |
Wolf | -0.002 |
cub | -0.001 |
handed | -0.001 |
baby | -0.001 |
anyway | -0.001 |
Token | we |
Token ID | 356 |
Feature activation | +7.46e-02 |
Pos logit contributions | |
handed | +0.012 |
Wolf | +0.012 |
rolley | +0.011 |
Mo | +0.011 |
seat | +0.011 |
Neg logit contributions | |
similarities | -0.011 |
ocus | -0.011 |
issors | -0.011 |
ets | -0.010 |
seventeen | -0.010 |
Token | don |
Token ID | 836 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
issors | +0.016 |
ocus | +0.015 |
similarities | +0.015 |
seventeen | +0.014 |
ets | +0.014 |
Neg logit contributions | |
Wolf | -0.021 |
handed | -0.021 |
cub | -0.020 |
anyway | -0.020 |
therm | -0.020 |
Token | 't |
Token ID | 470 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
issors | +0.028 |
ocus | +0.027 |
ets | +0.024 |
similarities | +0.024 |
ols | +0.024 |
Neg logit contributions | |
handed | -0.033 |
Wolf | -0.032 |
cub | -0.032 |
hand | -0.031 |
seat | -0.031 |
Token | get |
Token ID | 651 |
Feature activation | +9.43e-01 |
Pos logit contributions | |
issors | +0.005 |
ocus | +0.005 |
similarities | +0.005 |
ets | +0.005 |
seventeen | +0.005 |
Neg logit contributions | |
handed | -0.005 |
Wolf | -0.005 |
cub | -0.005 |
Mo | -0.005 |
therm | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
handed | +0.025 |
Wolf | +0.024 |
rolley | +0.023 |
Mo | +0.023 |
Wilson | +0.023 |
Neg logit contributions | |
issors | -0.040 |
ocus | -0.040 |
similarities | -0.039 |
ets | -0.039 |
ind | -0.036 |
Token | sun |
Token ID | 4252 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
handed | +0.006 |
Wolf | +0.006 |
Mo | +0.006 |
cub | +0.005 |
hand | +0.005 |
Neg logit contributions | |
similarities | -0.007 |
issors | -0.007 |
ocus | -0.007 |
ets | -0.007 |
seventeen | -0.006 |
Token | burn |
Token ID | 10899 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
handed | +0.005 |
Wolf | +0.005 |
Mo | +0.005 |
cub | +0.004 |
hand | +0.004 |
Neg logit contributions | |
issors | -0.026 |
ocus | -0.026 |
ets | -0.026 |
similarities | -0.025 |
ind | -0.025 |
Token | ." |
Token ID | 526 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
handed | +0.062 |
Mo | +0.062 |
clearing | +0.058 |
Far | +0.055 |
Wolf | +0.055 |
Neg logit contributions | |
ets | -0.129 |
issors | -0.127 |
aces | -0.119 |
ocus | -0.116 |
ems | -0.115 |
Token | Lily |
Token ID | 20037 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
handed | +0.006 |
Wolf | +0.006 |
anyway | +0.006 |
baby | +0.006 |
anyways | +0.006 |
Neg logit contributions | |
ocus | -0.010 |
issors | -0.010 |
similarities | -0.010 |
seventeen | -0.010 |
ets | -0.010 |
Token | yawn |
Token ID | 40908 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
handed | +0.002 |
Wolf | +0.002 |
Mo | +0.002 |
seat | +0.002 |
cub | +0.002 |
Neg logit contributions | |
ocus | -0.003 |
issors | -0.003 |
similarities | -0.003 |
ets | -0.003 |
seventeen | -0.003 |
Token | ed |
Token ID | 276 |
Feature activation | -5.01e-02 |
Pos logit contributions | |
ets | +0.019 |
ocus | +0.018 |
issors | +0.018 |
seventeen | +0.017 |
ind | +0.017 |
Neg logit contributions | |
handed | -0.018 |
Wolf | -0.018 |
Mo | -0.017 |
seat | -0.017 |
cub | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +3.08e-03 |
Pos logit contributions | |
ocus | +0.002 |
ets | +0.002 |
similarities | +0.002 |
issors | +0.002 |
ind | +0.002 |
Neg logit contributions | |
handed | -0.002 |
Wolf | -0.002 |
Mo | -0.001 |
rolley | -0.001 |
seat | -0.001 |
Token | ™ |
Token ID | 8151 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
Wolf | +0.004 |
handed | +0.004 |
cub | +0.004 |
baby | +0.004 |
therm | +0.004 |
Neg logit contributions | |
ocus | -0.004 |
issors | -0.004 |
similarities | -0.004 |
ets | -0.004 |
seventeen | -0.004 |
Token | s |
Token ID | 82 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
lamb | +0.030 |
therm | +0.030 |
Wolf | +0.030 |
Where | +0.030 |
elf | +0.030 |
Neg logit contributions | |
issors | -0.034 |
ocus | -0.032 |
ets | -0.029 |
ige | -0.028 |
seventeen | -0.028 |
Token | bite |
Token ID | 13197 |
Feature activation | +3.53e-01 |
Pos logit contributions | |
ocus | +0.006 |
similarities | +0.006 |
issors | +0.006 |
ets | +0.006 |
seventeen | +0.005 |
Neg logit contributions | |
handed | -0.004 |
Wolf | -0.004 |
Mo | -0.004 |
seat | -0.004 |
rolley | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
handed | +0.008 |
Wolf | +0.008 |
Mo | +0.007 |
cub | +0.007 |
seat | +0.007 |
Neg logit contributions | |
ocus | -0.016 |
issors | -0.016 |
ets | -0.016 |
similarities | -0.016 |
seventeen | -0.015 |
Token | not |
Token ID | 407 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
handed | +0.024 |
rolley | +0.024 |
Wolf | +0.023 |
seat | +0.023 |
Mo | +0.022 |
Neg logit contributions | |
ocus | -0.036 |
similarities | -0.035 |
issors | -0.035 |
ets | -0.035 |
seventeen | -0.034 |
Token | severe |
Token ID | 6049 |
Feature activation | +2.73e+00 |
Pos logit contributions | |
handed | +0.030 |
rolley | +0.029 |
Wolf | +0.029 |
hand | +0.028 |
seat | +0.028 |
Neg logit contributions | |
ets | -0.044 |
similarities | -0.043 |
ocus | -0.043 |
issors | -0.042 |
seventeen | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +4.34e-01 |
Pos logit contributions | |
Mo | +0.078 |
Wolf | +0.073 |
handed | +0.073 |
rolley | +0.072 |
seat | +0.072 |
Neg logit contributions | |
ets | -0.105 |
similarities | -0.104 |
ocus | -0.102 |
issors | -0.099 |
seventeen | -0.098 |
Token | But |
Token ID | 887 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
Wolf | +0.013 |
handed | +0.013 |
cub | +0.013 |
Mo | +0.013 |
baby | +0.012 |
Neg logit contributions | |
issors | -0.017 |
ocus | -0.016 |
similarities | -0.016 |
ets | -0.016 |
seventeen | -0.015 |
Token | Tom |
Token ID | 4186 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
Wolf | +0.057 |
handed | +0.057 |
cub | +0.052 |
Mo | +0.052 |
therm | +0.051 |
Neg logit contributions | |
ocus | -0.101 |
issors | -0.101 |
similarities | -0.100 |
ets | -0.096 |
seventeen | -0.095 |
Token | realized |
Token ID | 6939 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
ocus | +0.010 |
issors | +0.009 |
similarities | +0.009 |
ets | +0.009 |
seventeen | +0.009 |
Neg logit contributions | |
handed | -0.006 |
Wolf | -0.006 |
seat | -0.005 |
Mo | -0.005 |
rolley | -0.005 |
Token | he |
Token ID | 339 |
Feature activation | -6.82e-01 |
Pos logit contributions | |
ocus | +0.005 |
issors | +0.005 |
similarities | +0.005 |
does | +0.005 |
ets | +0.005 |
Neg logit contributions | |
handed | -0.004 |
rolley | -0.004 |
seat | -0.004 |
burn | -0.004 |
Wolf | -0.004 |
Token | worked |
Token ID | 3111 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
issors | +0.014 |
ocus | +0.013 |
similarities | +0.013 |
ets | +0.013 |
seventeen | +0.013 |
Neg logit contributions | |
Wolf | -0.007 |
handed | -0.007 |
baby | -0.007 |
cub | -0.006 |
anyway | -0.006 |
Token | hard |
Token ID | 1327 |
Feature activation | +6.31e-01 |
Pos logit contributions | |
Wolf | +0.015 |
handed | +0.015 |
cub | +0.014 |
Mo | +0.014 |
baby | +0.014 |
Neg logit contributions | |
issors | -0.022 |
ocus | -0.022 |
similarities | -0.021 |
ets | -0.021 |
seventeen | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
Wolf | +0.013 |
handed | +0.013 |
anyway | +0.012 |
cub | +0.012 |
therm | +0.012 |
Neg logit contributions | |
ocus | -0.030 |
issors | -0.030 |
similarities | -0.030 |
ets | -0.029 |
seventeen | -0.029 |
Token | The |
Token ID | 383 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
issors | +0.010 |
ocus | +0.010 |
similarities | +0.010 |
seventeen | +0.009 |
ets | +0.009 |
Neg logit contributions | |
handed | -0.008 |
Wolf | -0.007 |
burn | -0.007 |
therm | -0.007 |
Mo | -0.007 |
Token | grass |
Token ID | 8701 |
Feature activation | -7.74e-01 |
Pos logit contributions | |
ocus | +0.020 |
issors | +0.020 |
similarities | +0.020 |
ets | +0.020 |
seventeen | +0.019 |
Neg logit contributions | |
Wolf | -0.010 |
handed | -0.010 |
baby | -0.010 |
cub | -0.010 |
therm | -0.009 |
Token | ho |
Token ID | 8873 |
Feature activation | -4.10e+00 |
Pos logit contributions | |
issors | +0.045 |
ocus | +0.043 |
similarities | +0.043 |
ets | +0.042 |
seventeen | +0.041 |
Neg logit contributions | |
Wolf | -0.010 |
handed | -0.009 |
baby | -0.009 |
cub | -0.009 |
anyway | -0.009 |
Token | pper |
Token ID | 2848 |
Feature activation | -9.81e-01 |
Pos logit contributions | |
ocus | +0.156 |
issors | +0.154 |
similarities | +0.148 |
ets | +0.148 |
seventeen | +0.144 |
Neg logit contributions | |
Wolf | -0.132 |
handed | -0.128 |
cub | -0.121 |
Mo | -0.121 |
baby | -0.121 |
Token | was |
Token ID | 373 |
Feature activation | -1.70e-01 |
Pos logit contributions | |
issors | +0.044 |
ocus | +0.044 |
similarities | +0.043 |
ets | +0.042 |
seventeen | +0.041 |
Neg logit contributions | |
Wolf | -0.024 |
handed | -0.023 |
cub | -0.022 |
Mo | -0.021 |
anyway | -0.021 |
Token | spoiled |
Token ID | 34781 |
Feature activation | -7.62e-02 |
Pos logit contributions | |
ocus | +0.007 |
similarities | +0.007 |
issors | +0.007 |
seventeen | +0.007 |
ets | +0.007 |
Neg logit contributions | |
handed | -0.005 |
Wolf | -0.004 |
rolley | -0.004 |
cub | -0.004 |
seat | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +2.50e-01 |
Pos logit contributions | |
ocus | +0.003 |
ets | +0.003 |
issors | +0.003 |
similarities | +0.003 |
aces | +0.003 |
Neg logit contributions | |
handed | -0.002 |
Wolf | -0.002 |
Mo | -0.002 |
rolley | -0.002 |
seat | -0.002 |
Token | didn |
Token ID | 1422 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
handed | +0.007 |
Wolf | +0.007 |
Mo | +0.006 |
cub | +0.006 |
seat | +0.006 |
Neg logit contributions | |
ocus | -0.011 |
issors | -0.011 |
similarities | -0.011 |
ets | -0.010 |
seventeen | -0.010 |
Token | € |
Token ID | 26391 |
Feature activation | -1.18e-01 |
Pos logit contributions | |
similarities | +0.043 |
ocus | +0.042 |
issors | +0.042 |
ets | +0.039 |
narrative | +0.038 |
Neg logit contributions | |
handed | -0.056 |
Wolf | -0.053 |
Mo | -0.051 |
hand | -0.050 |
front | -0.050 |
Token | � |
Token ID | 129 |
Feature activation | -9.70e-01 |
Pos logit contributions | |
issors | +0.005 |
ocus | +0.005 |
similarities | +0.005 |
ets | +0.005 |
seventeen | +0.005 |
Neg logit contributions | |
Wolf | -0.003 |
handed | -0.003 |
cub | -0.003 |
Mo | -0.003 |
anyway | -0.003 |
Token | � |
Token ID | 241 |
Feature activation | -5.13e-01 |
Pos logit contributions | |
ocus | +0.037 |
similarities | +0.036 |
issors | +0.036 |
ets | +0.035 |
seventeen | +0.034 |
Neg logit contributions | |
handed | -0.030 |
Wolf | -0.029 |
Mo | -0.028 |
anyway | -0.028 |
cub | -0.027 |
Token | Gr |
Token ID | 8642 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
ocus | +0.018 |
similarities | +0.018 |
seventeen | +0.018 |
issors | +0.018 |
ind | +0.017 |
Neg logit contributions | |
Wolf | -0.016 |
handed | -0.016 |
therm | -0.016 |
cub | -0.015 |
burn | -0.015 |
Token | ass |
Token ID | 562 |
Feature activation | +2.22e-01 |
Pos logit contributions | |
issors | +0.036 |
ocus | +0.036 |
similarities | +0.036 |
ets | +0.035 |
seventeen | +0.033 |
Neg logit contributions | |
Wolf | -0.036 |
handed | -0.036 |
cub | -0.034 |
Mo | -0.034 |
therm | -0.034 |
Token | ho |
Token ID | 8873 |
Feature activation | -3.78e+00 |
Pos logit contributions | |
handed | +0.006 |
Wolf | +0.006 |
seat | +0.006 |
rolley | +0.006 |
burn | +0.006 |
Neg logit contributions | |
ocus | -0.009 |
issors | -0.009 |
similarities | -0.009 |
ets | -0.009 |
seventeen | -0.009 |
Token | pper |
Token ID | 2848 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
ocus | +0.133 |
issors | +0.124 |
ind | +0.117 |
seventeen | +0.115 |
ets | +0.112 |
Neg logit contributions | |
Wolf | -0.135 |
rolley | -0.132 |
handed | -0.132 |
seat | -0.131 |
baby | -0.130 |
Token | , |
Token ID | 11 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
ocus | +0.010 |
ind | +0.010 |
issors | +0.010 |
ets | +0.010 |
similarities | +0.009 |
Neg logit contributions | |
handed | -0.004 |
rolley | -0.004 |
burn | -0.004 |
Wolf | -0.003 |
seat | -0.003 |
Token | let |
Token ID | 1309 |
Feature activation | +1.92e-01 |
Pos logit contributions | |
issors | +0.017 |
ocus | +0.017 |
similarities | +0.017 |
ets | +0.016 |
seventeen | +0.016 |
Neg logit contributions | |
Wolf | -0.010 |
handed | -0.010 |
cub | -0.009 |
baby | -0.009 |
therm | -0.009 |
Token | â |
Token ID | 22940 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
seat | +0.007 |
continuing | +0.007 |
handed | +0.006 |
hand | +0.006 |
rolley | +0.006 |
Neg logit contributions | |
issors | -0.006 |
ocus | -0.006 |
ets | -0.006 |
ige | -0.005 |
does | -0.005 |
Token | € |
Token ID | 26391 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
ocus | +0.023 |
similarities | +0.022 |
issors | +0.022 |
seventeen | +0.021 |
ets | +0.021 |
Neg logit contributions | |
handed | -0.024 |
Wolf | -0.023 |
anyway | -0.022 |
Mo | -0.022 |
hand | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
handed | +0.005 |
burn | +0.005 |
Wolf | +0.005 |
baby | +0.005 |
therm | +0.005 |
Neg logit contributions | |
ocus | -0.011 |
issors | -0.011 |
similarities | -0.011 |
seventeen | -0.010 |
ets | -0.010 |
Token | The |
Token ID | 464 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
Wolf | +0.016 |
handed | +0.016 |
cub | +0.015 |
therm | +0.015 |
baby | +0.015 |
Neg logit contributions | |
issors | -0.020 |
ocus | -0.020 |
similarities | -0.020 |
ets | -0.019 |
seventeen | -0.019 |
Token | nos |
Token ID | 43630 |
Feature activation | -6.09e-01 |
Pos logit contributions | |
Wolf | +0.003 |
handed | +0.003 |
baby | +0.003 |
cub | +0.003 |
Mo | +0.003 |
Neg logit contributions | |
ocus | -0.004 |
issors | -0.004 |
similarities | -0.004 |
ets | -0.004 |
seventeen | -0.004 |
Token | y |
Token ID | 88 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
ocus | +0.026 |
issors | +0.026 |
ets | +0.025 |
similarities | +0.025 |
seventeen | +0.024 |
Neg logit contributions | |
Wolf | -0.016 |
handed | -0.016 |
therm | -0.015 |
anyway | -0.015 |
anyways | -0.015 |
Token | grass |
Token ID | 8701 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
issors | +0.017 |
ocus | +0.017 |
similarities | +0.016 |
ets | +0.016 |
seventeen | +0.016 |
Neg logit contributions | |
Wolf | -0.007 |
handed | -0.007 |
cub | -0.006 |
baby | -0.006 |
therm | -0.006 |
Token | ho |
Token ID | 8873 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
Wolf | +0.008 |
handed | +0.008 |
cub | +0.007 |
baby | +0.007 |
therm | +0.007 |
Neg logit contributions | |
issors | -0.013 |
ocus | -0.013 |
similarities | -0.013 |
ets | -0.013 |
seventeen | -0.012 |
Token | pper |
Token ID | 2848 |
Feature activation | -5.88e-01 |
Pos logit contributions | |
ocus | +0.123 |
issors | +0.117 |
ets | +0.108 |
seventeen | +0.108 |
ind | +0.108 |
Neg logit contributions | |
Wolf | -0.142 |
handed | -0.137 |
seat | -0.136 |
baby | -0.136 |
rolley | -0.134 |
Token | hopped |
Token ID | 45230 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
issors | +0.027 |
ocus | +0.026 |
similarities | +0.026 |
ets | +0.025 |
seventeen | +0.025 |
Neg logit contributions | |
Wolf | -0.014 |
handed | -0.014 |
cub | -0.013 |
Mo | -0.013 |
baby | -0.013 |
Token | over |
Token ID | 625 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
handed | +0.006 |
Wolf | +0.006 |
cub | +0.006 |
Mo | +0.006 |
therm | +0.006 |
Neg logit contributions | |
issors | -0.012 |
ocus | -0.012 |
similarities | -0.012 |
ets | -0.012 |
seventeen | -0.012 |
Token | to |
Token ID | 284 |
Feature activation | +7.01e-02 |
Pos logit contributions | |
handed | +0.010 |
Wolf | +0.009 |
burn | +0.009 |
therm | +0.009 |
cub | +0.009 |
Neg logit contributions | |
ocus | -0.014 |
similarities | -0.014 |
issors | -0.014 |
ets | -0.014 |
seventeen | -0.013 |
Token | Tom |
Token ID | 4186 |
Feature activation | +5.29e-01 |
Pos logit contributions | |
rolley | +0.002 |
handed | +0.002 |
seat | +0.002 |
burn | +0.002 |
therm | +0.002 |
Neg logit contributions | |
similarities | -0.002 |
issors | -0.002 |
ocus | -0.002 |
ets | -0.002 |
seventeen | -0.002 |
Token | ." |
Token ID | 526 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
issors | +0.022 |
ocus | +0.022 |
ets | +0.020 |
similarities | +0.019 |
agon | +0.019 |
Neg logit contributions | |
handed | -0.015 |
burn | -0.015 |
eled | -0.015 |
Wolf | -0.014 |
cub | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
handed | +0.002 |
burn | +0.002 |
Wolf | +0.002 |
therm | +0.002 |
baby | +0.002 |
Neg logit contributions | |
issors | -0.005 |
ocus | -0.005 |
similarities | -0.005 |
ets | -0.005 |
seventeen | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
burn | +0.006 |
handed | +0.005 |
therm | +0.005 |
Wolf | +0.005 |
rolley | +0.005 |
Neg logit contributions | |
issors | -0.010 |
ocus | -0.010 |
similarities | -0.010 |
seventeen | -0.009 |
apes | -0.009 |
Token | The |
Token ID | 464 |
Feature activation | -6.49e-02 |
Pos logit contributions | |
Wolf | +0.013 |
handed | +0.013 |
seat | +0.012 |
baby | +0.012 |
burn | +0.012 |
Neg logit contributions | |
issors | -0.020 |
similarities | -0.020 |
ocus | -0.020 |
seventeen | -0.019 |
ets | -0.019 |
Token | grass |
Token ID | 8701 |
Feature activation | +2.94e-01 |
Pos logit contributions | |
issors | +0.003 |
similarities | +0.003 |
ocus | +0.003 |
seventeen | +0.003 |
ind | +0.002 |
Neg logit contributions | |
handed | -0.002 |
seat | -0.002 |
Wolf | -0.002 |
hand | -0.002 |
rolley | -0.002 |
Token | ho |
Token ID | 8873 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
Wolf | +0.010 |
cub | +0.009 |
handed | +0.009 |
baby | +0.009 |
anyway | +0.009 |
Neg logit contributions | |
issors | -0.011 |
ocus | -0.011 |
similarities | -0.010 |
ets | -0.010 |
seventeen | -0.010 |
Token | pper |
Token ID | 2848 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
ocus | +0.125 |
issors | +0.123 |
seventeen | +0.114 |
similarities | +0.112 |
ets | +0.111 |
Neg logit contributions | |
Wolf | -0.137 |
handed | -0.132 |
seat | -0.132 |
baby | -0.132 |
therm | -0.128 |
Token | sighed |
Token ID | 21893 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
issors | +0.026 |
ocus | +0.026 |
similarities | +0.026 |
ets | +0.025 |
seventeen | +0.025 |
Neg logit contributions | |
Wolf | -0.013 |
handed | -0.013 |
cub | -0.012 |
anyway | -0.012 |
Mo | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
handed | +0.009 |
Wolf | +0.009 |
Mo | +0.008 |
rolley | +0.008 |
seat | +0.008 |
Neg logit contributions | |
ocus | -0.014 |
similarities | -0.013 |
issors | -0.013 |
ets | -0.013 |
seventeen | -0.013 |
Token | decided |
Token ID | 3066 |
Feature activation | +3.98e-01 |
Pos logit contributions | |
ocus | +0.005 |
similarities | +0.005 |
issors | +0.005 |
ets | +0.005 |
seventeen | +0.005 |
Neg logit contributions | |
handed | -0.004 |
Wolf | -0.004 |
rolley | -0.004 |
seat | -0.004 |
Mo | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +5.59e-02 |
Pos logit contributions | |
handed | +0.012 |
Wolf | +0.012 |
Mo | +0.011 |
seat | +0.011 |
cub | +0.011 |
Neg logit contributions | |
ocus | -0.015 |
similarities | -0.015 |
issors | -0.015 |
ets | -0.015 |
seventeen | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
similarities | +0.031 |
ey | +0.030 |
issors | +0.030 |
brushes | +0.029 |
ind | +0.028 |
Neg logit contributions | |
handed | -0.021 |
Wolf | -0.021 |
rolley | -0.021 |
burn | -0.020 |
cub | -0.020 |
Token | wardrobe |
Token ID | 35593 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
handed | +0.004 |
able | +0.004 |
Wolf | +0.004 |
Mo | +0.004 |
ge | +0.004 |
Neg logit contributions | |
similarities | -0.006 |
issors | -0.006 |
ets | -0.006 |
ocus | -0.006 |
seventeen | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
Wolf | +0.006 |
handed | +0.005 |
Mo | +0.005 |
cub | +0.005 |
baby | +0.005 |
Neg logit contributions | |
ocus | -0.013 |
issors | -0.013 |
ets | -0.012 |
similarities | -0.012 |
seventeen | -0.012 |
Token | few |
Token ID | 1178 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
ocus | +0.008 |
issors | +0.008 |
similarities | +0.008 |
ets | +0.008 |
seventeen | +0.008 |
Neg logit contributions | |
handed | -0.006 |
Wolf | -0.006 |
Mo | -0.006 |
cub | -0.006 |
hand | -0.006 |
Token | days |
Token ID | 1528 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
Wolf | +0.006 |
handed | +0.006 |
burn | +0.005 |
Mo | +0.005 |
Wilson | +0.005 |
Neg logit contributions | |
ocus | -0.006 |
similarities | -0.006 |
ets | -0.006 |
issors | -0.006 |
seventeen | -0.006 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
ocus | +0.029 |
ets | +0.028 |
issors | +0.027 |
similarities | +0.026 |
ind | +0.024 |
Neg logit contributions | |
Wolf | -0.030 |
handed | -0.028 |
Mo | -0.028 |
cub | -0.027 |
burn | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
ocus | +0.186 |
issors | +0.185 |
ets | +0.180 |
similarities | +0.179 |
aces | +0.173 |
Neg logit contributions | |
Wolf | -0.069 |
handed | -0.067 |
Mo | -0.064 |
cub | -0.059 |
therm | -0.058 |
Token | so |
Token ID | 523 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
issors | +0.014 |
ocus | +0.013 |
similarities | +0.013 |
seventeen | +0.013 |
ets | +0.013 |
Neg logit contributions | |
Wolf | -0.006 |
handed | -0.006 |
anyway | -0.006 |
baby | -0.005 |
therm | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | -3.06e-01 |
Pos logit contributions | |
similarities | +0.033 |
ocus | +0.033 |
issors | +0.033 |
meanings | +0.032 |
ind | +0.031 |
Neg logit contributions | |
handed | -0.014 |
Wolf | -0.013 |
rolley | -0.013 |
cub | -0.012 |
burn | -0.012 |
Token | opened |
Token ID | 4721 |
Feature activation | -5.26e-02 |
Pos logit contributions | |
issors | +0.016 |
similarities | +0.016 |
ocus | +0.016 |
seventeen | +0.015 |
ets | +0.015 |
Neg logit contributions | |
Wolf | -0.005 |
handed | -0.005 |
cub | -0.005 |
anyway | -0.005 |
baby | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
ind | +0.002 |
ocus | +0.002 |
issors | +0.002 |
similarities | +0.001 |
brushes | +0.001 |
Neg logit contributions | |
handed | -0.002 |
Wolf | -0.002 |
rolley | -0.002 |
burn | -0.002 |
cub | -0.002 |
Token | ?" |
Token ID | 1701 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
similarities | +0.025 |
issors | +0.025 |
ocus | +0.025 |
seventeen | +0.024 |
ets | +0.024 |
Neg logit contributions | |
anyway | -0.011 |
Wolf | -0.010 |
handed | -0.010 |
. | -0.010 |
! | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +5.37e-01 |
Pos logit contributions | |
burn | +0.018 |
handed | +0.018 |
rolley | +0.017 |
Wolf | +0.017 |
seat | +0.016 |
Neg logit contributions | |
ocus | -0.035 |
issors | -0.035 |
similarities | -0.034 |
seventeen | -0.032 |
ind | -0.032 |
Token |
|
Token ID | 198 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
burn | +0.012 |
rolley | +0.011 |
handed | +0.011 |
seat | +0.011 |
baby | +0.011 |
Neg logit contributions | |
issors | -0.024 |
ocus | -0.024 |
similarities | -0.023 |
seventeen | -0.023 |
ind | -0.022 |
Token | The |
Token ID | 464 |
Feature activation | -8.00e-03 |
Pos logit contributions | |
Wolf | +0.016 |
handed | +0.016 |
seat | +0.015 |
baby | +0.015 |
anyway | +0.015 |
Neg logit contributions | |
ocus | -0.029 |
issors | -0.028 |
similarities | -0.028 |
seventeen | -0.027 |
ets | -0.026 |
Token | grass |
Token ID | 8701 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
issors | +0.000 |
similarities | +0.000 |
ocus | +0.000 |
seventeen | +0.000 |
ind | +0.000 |
Neg logit contributions | |
handed | -0.000 |
seat | -0.000 |
Wolf | -0.000 |
hand | -0.000 |
burn | -0.000 |
Token | ho |
Token ID | 8873 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
Wolf | +0.011 |
cub | +0.010 |
handed | +0.010 |
therm | +0.010 |
baby | +0.010 |
Neg logit contributions | |
issors | -0.011 |
ocus | -0.010 |
similarities | -0.010 |
ets | -0.010 |
seventeen | -0.009 |
Token | pper |
Token ID | 2848 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
ocus | +0.119 |
issors | +0.116 |
seventeen | +0.108 |
ind | +0.103 |
ets | +0.103 |
Neg logit contributions | |
Wolf | -0.139 |
seat | -0.135 |
baby | -0.135 |
handed | -0.133 |
rolley | -0.131 |
Token | said |
Token ID | 531 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
issors | +0.024 |
ocus | +0.024 |
similarities | +0.023 |
ets | +0.023 |
seventeen | +0.022 |
Neg logit contributions | |
Wolf | -0.012 |
handed | -0.012 |
cub | -0.011 |
Mo | -0.011 |
anyway | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
handed | +0.015 |
Wolf | +0.014 |
rolley | +0.014 |
seat | +0.014 |
Mo | +0.013 |
Neg logit contributions | |
ocus | -0.026 |
issors | -0.025 |
similarities | -0.025 |
seventeen | -0.024 |
ets | -0.024 |
Token | " |
Token ID | 366 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
handed | +0.005 |
rolley | +0.005 |
seat | +0.005 |
Wolf | +0.005 |
burn | +0.005 |
Neg logit contributions | |
issors | -0.006 |
ocus | -0.006 |
similarities | -0.006 |
seventeen | -0.006 |
ind | -0.006 |
Token | I |
Token ID | 40 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Wolf | +0.005 |
handed | +0.005 |
Mo | +0.005 |
cub | +0.005 |
anyway | +0.005 |
Neg logit contributions | |
ocus | -0.012 |
issors | -0.012 |
similarities | -0.012 |
ets | -0.012 |
seventeen | -0.011 |
Token | so |
Token ID | 523 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
handed | +0.014 |
rolley | +0.014 |
Wolf | +0.013 |
Mo | +0.013 |
hand | +0.013 |
Neg logit contributions | |
ocus | -0.017 |
ind | -0.017 |
seventeen | -0.016 |
ets | -0.015 |
similarities | -0.015 |
Token | happy |
Token ID | 3772 |
Feature activation | -2.04e-01 |
Pos logit contributions | |
ocus | +0.006 |
similarities | +0.005 |
ind | +0.005 |
seventeen | +0.005 |
ets | +0.005 |
Neg logit contributions | |
Wolf | -0.007 |
handed | -0.006 |
rolley | -0.006 |
hand | -0.006 |
burn | -0.006 |
Token | that |
Token ID | 326 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
ocus | +0.009 |
ets | +0.009 |
similarities | +0.008 |
issors | +0.008 |
apes | +0.008 |
Neg logit contributions | |
handed | -0.005 |
Wolf | -0.005 |
Mo | -0.005 |
burn | -0.005 |
rolley | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +3.93e-03 |
Pos logit contributions | |
similarities | +0.007 |
issors | +0.007 |
ocus | +0.007 |
ind | +0.007 |
seventeen | +0.007 |
Neg logit contributions | |
handed | -0.003 |
rolley | -0.003 |
hand | -0.003 |
Mo | -0.003 |
Wolf | -0.003 |
Token | grass |
Token ID | 8701 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
handed | +0.000 |
Wolf | +0.000 |
cub | +0.000 |
Mo | +0.000 |
anyway | +0.000 |
Neg logit contributions | |
issors | -0.000 |
similarities | -0.000 |
ocus | -0.000 |
ets | -0.000 |
seventeen | -0.000 |
Token | ho |
Token ID | 8873 |
Feature activation | -3.59e+00 |
Pos logit contributions | |
handed | +0.001 |
Wolf | +0.001 |
Mo | +0.000 |
cub | +0.000 |
anyway | +0.000 |
Neg logit contributions | |
ocus | -0.001 |
issors | -0.001 |
similarities | -0.001 |
ets | -0.001 |
seventeen | -0.001 |
Token | pper |
Token ID | 2848 |
Feature activation | -6.89e-01 |
Pos logit contributions | |
ocus | +0.125 |
issors | +0.119 |
ets | +0.113 |
similarities | +0.111 |
seventeen | +0.111 |
Neg logit contributions | |
Wolf | -0.127 |
handed | -0.122 |
seat | -0.121 |
baby | -0.119 |
rolley | -0.119 |
Token | had |
Token ID | 550 |
Feature activation | -6.78e-01 |
Pos logit contributions | |
ocus | +0.027 |
ets | +0.027 |
similarities | +0.027 |
issors | +0.026 |
ind | +0.025 |
Neg logit contributions | |
handed | -0.020 |
Wolf | -0.020 |
burn | -0.018 |
Mo | -0.018 |
rolley | -0.018 |
Token | said |
Token ID | 531 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
similarities | +0.027 |
ocus | +0.027 |
ets | +0.026 |
issors | +0.026 |
ind | +0.025 |
Neg logit contributions | |
Wolf | -0.020 |
handed | -0.020 |
therm | -0.018 |
cub | -0.018 |
rolley | -0.018 |
Token | yes |
Token ID | 3763 |
Feature activation | -5.09e-01 |
Pos logit contributions | |
handed | +0.026 |
Wolf | +0.025 |
rolley | +0.023 |
Mo | +0.023 |
cub | +0.023 |
Neg logit contributions | |
ocus | -0.040 |
similarities | -0.039 |
issors | -0.039 |
seventeen | -0.038 |
ets | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
ets | +0.027 |
ocus | +0.026 |
issors | +0.026 |
similarities | +0.026 |
ind | +0.025 |
Neg logit contributions | |
handed | -0.009 |
seat | -0.008 |
Wolf | -0.008 |
rolley | -0.008 |
eled | -0.007 |
Token | ried |
Token ID | 2228 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
Wolf | +0.015 |
handed | +0.014 |
cub | +0.014 |
baby | +0.014 |
therm | +0.014 |
Neg logit contributions | |
ocus | -0.018 |
issors | -0.017 |
ets | -0.016 |
similarities | -0.016 |
seventeen | -0.016 |
Token | ly |
Token ID | 306 |
Feature activation | +3.52e-02 |
Pos logit contributions | |
Wolf | +0.010 |
handed | +0.010 |
cub | +0.009 |
Mo | +0.009 |
anyway | +0.009 |
Neg logit contributions | |
issors | -0.029 |
ocus | -0.029 |
similarities | -0.028 |
ets | -0.028 |
seventeen | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
Wolf | +0.001 |
handed | +0.001 |
Mo | +0.001 |
rolley | +0.001 |
burn | +0.001 |
Neg logit contributions | |
ocus | -0.001 |
issors | -0.001 |
ets | -0.001 |
similarities | -0.001 |
seventeen | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
handed | +0.006 |
Wolf | +0.005 |
rolley | +0.005 |
burn | +0.005 |
seat | +0.005 |
Neg logit contributions | |
ocus | -0.009 |
similarities | -0.009 |
issors | -0.009 |
ets | -0.009 |
seventeen | -0.009 |
Token | grass |
Token ID | 8701 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
issors | +0.017 |
similarities | +0.017 |
ocus | +0.017 |
seventeen | +0.016 |
ets | +0.016 |
Neg logit contributions | |
handed | -0.010 |
Wolf | -0.010 |
seat | -0.009 |
Mo | -0.009 |
anyway | -0.009 |
Token | ho |
Token ID | 8873 |
Feature activation | -3.49e+00 |
Pos logit contributions | |
handed | +0.004 |
Wolf | +0.004 |
Mo | +0.003 |
cub | +0.003 |
anyway | +0.003 |
Neg logit contributions | |
ocus | -0.005 |
issors | -0.004 |
similarities | -0.004 |
ets | -0.004 |
seventeen | -0.004 |
Token | pper |
Token ID | 2848 |
Feature activation | -6.19e-01 |
Pos logit contributions | |
ocus | +0.112 |
issors | +0.107 |
seventeen | +0.100 |
ets | +0.100 |
ind | +0.095 |
Neg logit contributions | |
Wolf | -0.137 |
seat | -0.130 |
baby | -0.128 |
handed | -0.127 |
rolley | -0.127 |
Token | rushed |
Token ID | 13999 |
Feature activation | +8.41e-02 |
Pos logit contributions | |
ocus | +0.026 |
ets | +0.025 |
issors | +0.024 |
similarities | +0.024 |
ind | +0.023 |
Neg logit contributions | |
Wolf | -0.017 |
handed | -0.017 |
Mo | -0.016 |
rolley | -0.016 |
therm | -0.016 |
Token | over |
Token ID | 625 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
handed | +0.002 |
Wolf | +0.002 |
cub | +0.002 |
therm | +0.002 |
Mo | +0.002 |
Neg logit contributions | |
issors | -0.004 |
ocus | -0.004 |
similarities | -0.004 |
ets | -0.004 |
seventeen | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
handed | +0.005 |
Wolf | +0.004 |
burn | +0.004 |
rolley | +0.004 |
therm | +0.004 |
Neg logit contributions | |
ocus | -0.005 |
similarities | -0.005 |
issors | -0.005 |
ets | -0.005 |
ind | -0.005 |
Token | tried |
Token ID | 3088 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
ocus | +0.001 |
issors | +0.001 |
similarities | +0.001 |
ets | +0.001 |
ind | +0.001 |
Neg logit contributions | |
handed | -0.001 |
Wolf | -0.001 |
rolley | -0.001 |
Mo | -0.001 |
burn | -0.001 |
Token | coins |
Token ID | 10796 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
issors | +0.003 |
ocus | +0.003 |
similarities | +0.003 |
ets | +0.003 |
seventeen | +0.003 |
Neg logit contributions | |
cub | -0.003 |
baby | -0.003 |
Wolf | -0.003 |
one | -0.002 |
handed | -0.002 |
Token | that |
Token ID | 326 |
Feature activation | +5.17e-02 |
Pos logit contributions | |
issors | +0.006 |
ocus | +0.006 |
similarities | +0.006 |
ets | +0.006 |
seventeen | +0.006 |
Neg logit contributions | |
Wolf | -0.001 |
handed | -0.001 |
cub | -0.001 |
anyway | -0.001 |
baby | -0.001 |
Token | people |
Token ID | 661 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
Wolf | +0.001 |
handed | +0.001 |
baby | +0.001 |
cub | +0.001 |
therm | +0.001 |
Neg logit contributions | |
ocus | -0.002 |
issors | -0.002 |
similarities | -0.002 |
ets | -0.002 |
seventeen | -0.002 |
Token | used |
Token ID | 973 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
handed | +0.007 |
Wolf | +0.007 |
cub | +0.007 |
baby | +0.006 |
anyway | +0.006 |
Neg logit contributions | |
issors | -0.010 |
ocus | -0.010 |
similarities | -0.010 |
seventeen | -0.009 |
ets | -0.009 |
Token | long |
Token ID | 890 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
ocus | +0.047 |
issors | +0.046 |
similarities | +0.045 |
seventeen | +0.044 |
ets | +0.043 |
Neg logit contributions | |
Wolf | -0.019 |
baby | -0.019 |
cub | -0.019 |
anyway | -0.019 |
handed | -0.019 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
issors | +0.021 |
similarities | +0.020 |
ocus | +0.020 |
narrative | +0.019 |
seventeen | +0.019 |
Neg logit contributions | |
cub | -0.017 |
. | -0.016 |
Wolf | -0.016 |
one | -0.016 |
therm | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
issors | +0.205 |
ocus | +0.204 |
similarities | +0.202 |
ets | +0.198 |
seventeen | +0.195 |
Neg logit contributions | |
Wolf | -0.034 |
handed | -0.032 |
Mo | -0.026 |
cub | -0.025 |
therm | -0.024 |
Token | They |
Token ID | 1119 |
Feature activation | +4.55e-01 |
Pos logit contributions | |
issors | +0.005 |
ocus | +0.005 |
similarities | +0.005 |
seventeen | +0.005 |
ets | +0.005 |
Neg logit contributions | |
handed | -0.004 |
Wolf | -0.004 |
Mo | -0.003 |
cub | -0.003 |
burn | -0.003 |
Token | saw |
Token ID | 2497 |
Feature activation | -9.08e-01 |
Pos logit contributions | |
Wolf | +0.011 |
handed | +0.011 |
cub | +0.011 |
baby | +0.011 |
anyway | +0.010 |
Neg logit contributions | |
ocus | -0.020 |
issors | -0.020 |
similarities | -0.020 |
ets | -0.019 |
seventeen | -0.019 |
Token | paintings |
Token ID | 21641 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
issors | +0.039 |
ocus | +0.039 |
similarities | +0.038 |
ets | +0.037 |
seventeen | +0.036 |
Neg logit contributions | |
Wolf | -0.024 |
handed | -0.024 |
cub | -0.022 |
baby | -0.022 |
Mo | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -2.00e-02 |
Pos logit contributions | |
issors | +0.001 |
similarities | +0.001 |
ocus | +0.001 |
ets | +0.001 |
seventeen | +0.001 |
Neg logit contributions | |
. | -0.000 |
cub | -0.000 |
one | -0.000 |
baby | -0.000 |
Wolf | -0.000 |
Token | her |
Token ID | 607 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
issors | +0.033 |
similarities | +0.033 |
ocus | +0.033 |
ets | +0.032 |
seventeen | +0.031 |
Neg logit contributions | |
handed | -0.011 |
Wolf | -0.011 |
cub | -0.010 |
Mo | -0.009 |
seat | -0.009 |
Token | birthday |
Token ID | 10955 |
Feature activation | -7.96e-01 |
Pos logit contributions | |
Wolf | +0.013 |
handed | +0.013 |
Mo | +0.011 |
cub | +0.011 |
therm | +0.011 |
Neg logit contributions | |
issors | -0.050 |
ocus | -0.050 |
similarities | -0.050 |
ets | -0.049 |
seventeen | -0.047 |
Token | a |
Token ID | 257 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
issors | +0.044 |
ets | +0.043 |
similarities | +0.043 |
ocus | +0.042 |
ind | +0.040 |
Neg logit contributions | |
Wolf | -0.011 |
handed | -0.011 |
Mo | -0.010 |
cub | -0.009 |
therm | -0.009 |
Token | few |
Token ID | 1178 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
handed | +0.008 |
Wolf | +0.008 |
Mo | +0.008 |
rolley | +0.008 |
seat | +0.008 |
Neg logit contributions | |
similarities | -0.010 |
issors | -0.010 |
ocus | -0.009 |
ets | -0.009 |
seventeen | -0.009 |
Token | days |
Token ID | 1528 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
Wolf | +0.014 |
handed | +0.014 |
Mo | +0.013 |
cub | +0.013 |
therm | +0.012 |
Neg logit contributions | |
issors | -0.018 |
ocus | -0.018 |
similarities | -0.018 |
ets | -0.017 |
seventeen | -0.017 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
ocus | +0.032 |
issors | +0.032 |
ets | +0.031 |
similarities | +0.030 |
ind | +0.029 |
Neg logit contributions | |
Wolf | -0.011 |
handed | -0.010 |
Mo | -0.010 |
cub | -0.009 |
therm | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
issors | +0.190 |
ocus | +0.189 |
similarities | +0.184 |
ets | +0.184 |
aces | +0.179 |
Neg logit contributions | |
Wolf | -0.050 |
handed | -0.046 |
Mo | -0.043 |
cub | -0.038 |
therm | -0.037 |
Token | She |
Token ID | 1375 |
Feature activation | +9.90e-01 |
Pos logit contributions | |
handed | +0.009 |
Wolf | +0.009 |
burn | +0.008 |
therm | +0.008 |
cub | +0.008 |
Neg logit contributions | |
issors | -0.014 |
ocus | -0.014 |
similarities | -0.014 |
ets | -0.014 |
seventeen | -0.013 |
Token | liked |
Token ID | 8288 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
Wolf | +0.023 |
handed | +0.022 |
cub | +0.021 |
baby | +0.021 |
anyway | +0.021 |
Neg logit contributions | |
issors | -0.046 |
ocus | -0.045 |
similarities | -0.045 |
ets | -0.043 |
seventeen | -0.043 |
Token | to |
Token ID | 284 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
Wolf | +0.007 |
handed | +0.007 |
baby | +0.006 |
anyway | +0.006 |
cub | +0.006 |
Neg logit contributions | |
issors | -0.017 |
ocus | -0.017 |
similarities | -0.017 |
ets | -0.017 |
seventeen | -0.016 |
Token | practice |
Token ID | 3357 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Wolf | +0.013 |
handed | +0.012 |
anyway | +0.012 |
baby | +0.012 |
one | +0.012 |
Neg logit contributions | |
ocus | -0.015 |
issors | -0.015 |
similarities | -0.015 |
seventeen | -0.014 |
ets | -0.014 |
Token | of |
Token ID | 286 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
handed | +0.011 |
Wolf | +0.011 |
cub | +0.010 |
anyway | +0.010 |
therm | +0.010 |
Neg logit contributions | |
similarities | -0.027 |
issors | -0.027 |
ocus | -0.026 |
seventeen | -0.025 |
ets | -0.025 |
Token | animals |
Token ID | 4695 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
Wolf | +0.002 |
cub | +0.002 |
baby | +0.002 |
handed | +0.002 |
therm | +0.002 |
Neg logit contributions | |
issors | -0.002 |
ocus | -0.002 |
similarities | -0.002 |
ets | -0.002 |
seventeen | -0.002 |
Token | that |
Token ID | 326 |
Feature activation | -9.09e-01 |
Pos logit contributions | |
Wolf | +0.006 |
handed | +0.006 |
cub | +0.005 |
anyway | +0.005 |
baby | +0.005 |
Neg logit contributions | |
issors | -0.014 |
ocus | -0.014 |
similarities | -0.014 |
ets | -0.013 |
seventeen | -0.013 |
Token | lived |
Token ID | 5615 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
ocus | +0.043 |
issors | +0.042 |
similarities | +0.041 |
seventeen | +0.040 |
ets | +0.040 |
Neg logit contributions | |
Wolf | -0.021 |
handed | -0.020 |
cub | -0.020 |
baby | -0.020 |
anyway | -0.019 |
Token | long |
Token ID | 890 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
Wolf | +0.016 |
handed | +0.016 |
cub | +0.015 |
Mo | +0.015 |
therm | +0.015 |
Neg logit contributions | |
ocus | -0.027 |
issors | -0.027 |
similarities | -0.027 |
ets | -0.026 |
seventeen | -0.026 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
issors | +0.024 |
similarities | +0.024 |
ocus | +0.024 |
seventeen | +0.022 |
ets | +0.022 |
Neg logit contributions | |
handed | -0.009 |
cub | -0.009 |
Wolf | -0.009 |
. | -0.009 |
one | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
issors | +0.189 |
ocus | +0.189 |
similarities | +0.186 |
ets | +0.184 |
seventeen | +0.179 |
Neg logit contributions | |
Wolf | -0.049 |
handed | -0.046 |
Mo | -0.043 |
cub | -0.039 |
therm | -0.038 |
Token | They |
Token ID | 1119 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
Wolf | +0.001 |
another | +0.001 |
baby | +0.001 |
handed | +0.001 |
anyway | +0.001 |
Neg logit contributions | |
ocus | -0.002 |
similarities | -0.002 |
issors | -0.002 |
ets | -0.002 |
seventeen | -0.002 |
Token | saw |
Token ID | 2497 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
Wolf | +0.013 |
cub | +0.013 |
baby | +0.013 |
handed | +0.013 |
anyway | +0.012 |
Neg logit contributions | |
issors | -0.023 |
ocus | -0.023 |
similarities | -0.023 |
ets | -0.022 |
seventeen | -0.022 |
Token | shiny |
Token ID | 22441 |
Feature activation | -7.37e-02 |
Pos logit contributions | |
issors | +0.037 |
ocus | +0.037 |
similarities | +0.036 |
ets | +0.035 |
seventeen | +0.035 |
Neg logit contributions | |
Wolf | -0.023 |
handed | -0.023 |
cub | -0.021 |
baby | -0.021 |
anyway | -0.021 |
Token | rocks |
Token ID | 12586 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
issors | +0.003 |
similarities | +0.003 |
ocus | +0.003 |
seventeen | +0.003 |
narrative | +0.003 |
Neg logit contributions | |
cub | -0.002 |
. | -0.002 |
one | -0.002 |
baby | -0.002 |
therm | -0.002 |
Token | ac |
Token ID | 936 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
ocus | +0.036 |
similarities | +0.035 |
issors | +0.034 |
ets | +0.034 |
ind | +0.034 |
Neg logit contributions | |
Wolf | -0.026 |
handed | -0.026 |
hand | -0.025 |
seat | -0.024 |
burn | -0.024 |
Token | orn |
Token ID | 1211 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
ocus | +0.036 |
issors | +0.035 |
ets | +0.034 |
similarities | +0.034 |
seventeen | +0.032 |
Neg logit contributions | |
Wolf | -0.026 |
handed | -0.025 |
baby | -0.025 |
cub | -0.025 |
hand | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
issors | +0.015 |
ocus | +0.015 |
similarities | +0.015 |
ets | +0.014 |
seventeen | +0.014 |
Neg logit contributions | |
Wolf | -0.008 |
handed | -0.008 |
cub | -0.007 |
anyway | -0.007 |
Mo | -0.007 |
Token | few |
Token ID | 1178 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
similarities | +0.014 |
ocus | +0.014 |
issors | +0.014 |
seventeen | +0.013 |
ets | +0.013 |
Neg logit contributions | |
handed | -0.012 |
Wolf | -0.011 |
hand | -0.011 |
seat | -0.011 |
Mo | -0.010 |
Token | days |
Token ID | 1528 |
Feature activation | -8.36e-01 |
Pos logit contributions | |
Wolf | +0.005 |
handed | +0.005 |
Mo | +0.004 |
burn | +0.004 |
cub | +0.004 |
Neg logit contributions | |
ocus | -0.007 |
issors | -0.007 |
similarities | -0.007 |
ets | -0.007 |
seventeen | -0.007 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
ocus | +0.039 |
issors | +0.039 |
similarities | +0.038 |
ets | +0.037 |
seventeen | +0.036 |
Neg logit contributions | |
Wolf | -0.019 |
handed | -0.019 |
cub | -0.017 |
Mo | -0.017 |
therm | -0.017 |
Token | so |
Token ID | 523 |
Feature activation | -2.98e-01 |
Pos logit contributions | |
issors | +0.186 |
ocus | +0.186 |
similarities | +0.184 |
ets | +0.179 |
seventeen | +0.177 |
Neg logit contributions | |
Wolf | -0.049 |
handed | -0.048 |
cub | -0.041 |
Mo | -0.041 |
anyway | -0.040 |
Token | I |
Token ID | 314 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
issors | +0.011 |
ocus | +0.011 |
similarities | +0.010 |
ets | +0.010 |
seventeen | +0.010 |
Neg logit contributions | |
Wolf | -0.010 |
handed | -0.010 |
cub | -0.009 |
Mo | -0.009 |
baby | -0.009 |
Token | could |
Token ID | 714 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
handed | +0.022 |
Wolf | +0.022 |
anyway | +0.021 |
cub | +0.021 |
baby | +0.020 |
Neg logit contributions | |
issors | -0.021 |
similarities | -0.021 |
ocus | -0.021 |
seventeen | -0.020 |
ets | -0.019 |
Token | have |
Token ID | 423 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
issors | +0.012 |
ocus | +0.012 |
similarities | +0.012 |
seventeen | +0.012 |
ets | +0.012 |
Neg logit contributions | |
handed | -0.009 |
Wolf | -0.008 |
anyway | -0.008 |
baby | -0.008 |
therm | -0.008 |
Token | some |
Token ID | 617 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
Wolf | +0.004 |
handed | +0.004 |
seat | +0.004 |
rolley | +0.004 |
Wilson | +0.004 |
Neg logit contributions | |
ocus | -0.007 |
similarities | -0.007 |
ets | -0.007 |
issors | -0.007 |
ind | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +5.93e-02 |
Pos logit contributions | |
similarities | +0.012 |
ets | +0.012 |
issors | +0.012 |
differences | +0.011 |
ocus | +0.011 |
Neg logit contributions | |
handed | -0.009 |
seat | -0.009 |
rolley | -0.008 |
eled | -0.008 |
unconscious | -0.008 |
Token | pigeon |
Token ID | 46387 |
Feature activation | -1.40e-01 |
Pos logit contributions | |
handed | +0.001 |
Wolf | +0.001 |
Mo | +0.001 |
seat | +0.001 |
rolley | +0.001 |
Neg logit contributions | |
similarities | -0.003 |
issors | -0.002 |
ocus | -0.002 |
ets | -0.002 |
ind | -0.002 |
Token | all |
Token ID | 477 |
Feature activation | -8.50e-02 |
Pos logit contributions | |
ets | +0.006 |
ocus | +0.006 |
similarities | +0.006 |
issors | +0.005 |
ind | +0.005 |
Neg logit contributions | |
Wolf | -0.004 |
Mo | -0.003 |
rolley | -0.003 |
handed | -0.003 |
therm | -0.003 |
Token | those |
Token ID | 883 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ocus | +0.004 |
similarities | +0.004 |
issors | +0.004 |
ets | +0.004 |
seventeen | +0.004 |
Neg logit contributions | |
Wolf | -0.002 |
handed | -0.002 |
Mo | -0.002 |
cub | -0.002 |
therm | -0.002 |
Token | weeks |
Token ID | 2745 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Wolf | +0.005 |
handed | +0.005 |
cub | +0.005 |
baby | +0.004 |
anyway | +0.004 |
Neg logit contributions | |
issors | -0.008 |
ocus | -0.008 |
similarities | -0.008 |
seventeen | -0.008 |
ets | -0.008 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
ocus | +0.049 |
ets | +0.048 |
issors | +0.048 |
similarities | +0.047 |
ind | +0.044 |
Neg logit contributions | |
Wolf | -0.022 |
handed | -0.021 |
Mo | -0.020 |
cub | -0.020 |
therm | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
ocus | +0.176 |
issors | +0.176 |
similarities | +0.175 |
ets | +0.173 |
seventeen | +0.166 |
Neg logit contributions | |
Wolf | -0.057 |
handed | -0.055 |
Mo | -0.052 |
therm | -0.048 |
cub | -0.048 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
similarities | +0.012 |
ocus | +0.012 |
Here | +0.011 |
ind | +0.011 |
issors | +0.011 |
Neg logit contributions | |
handed | -0.011 |
burn | -0.011 |
ge | -0.010 |
able | -0.009 |
anyway | -0.009 |
Token | Mike |
Token ID | 16073 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
handed | +0.004 |
able | +0.004 |
burn | +0.004 |
therm | +0.004 |
baby | +0.004 |
Neg logit contributions | |
ocus | -0.008 |
similarities | -0.007 |
issors | -0.007 |
ets | -0.007 |
does | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -1.95e-01 |
Pos logit contributions | |
Wolf | +0.004 |
handed | +0.004 |
Mo | +0.004 |
therm | +0.004 |
anyway | +0.004 |
Neg logit contributions | |
ocus | -0.007 |
issors | -0.007 |
similarities | -0.007 |
ets | -0.007 |
seventeen | -0.007 |
Token | his |
Token ID | 465 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
issors | +0.010 |
similarities | +0.010 |
ocus | +0.010 |
ets | +0.010 |
seventeen | +0.010 |
Neg logit contributions | |
handed | -0.003 |
Wolf | -0.003 |
anyway | -0.002 |
therm | -0.002 |
Mo | -0.002 |
Token | by |
Token ID | 416 |
Feature activation | -5.37e-01 |
Pos logit contributions | |
issors | +0.025 |
ocus | +0.025 |
similarities | +0.025 |
ets | +0.024 |
seventeen | +0.023 |
Neg logit contributions | |
Wolf | -0.011 |
handed | -0.011 |
cub | -0.010 |
baby | -0.010 |
Mo | -0.010 |
Token | a |
Token ID | 257 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
issors | +0.024 |
ocus | +0.024 |
similarities | +0.023 |
ets | +0.022 |
seventeen | +0.022 |
Neg logit contributions | |
Wolf | -0.013 |
handed | -0.013 |
cub | -0.013 |
baby | -0.012 |
anyway | -0.012 |
Token | famous |
Token ID | 5863 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
issors | +0.009 |
ocus | +0.009 |
similarities | +0.008 |
ets | +0.008 |
seventeen | +0.008 |
Neg logit contributions | |
Wolf | -0.006 |
baby | -0.006 |
handed | -0.005 |
cub | -0.005 |
therm | -0.005 |
Token | artist |
Token ID | 6802 |
Feature activation | -8.11e-01 |
Pos logit contributions | |
issors | +0.005 |
ocus | +0.005 |
similarities | +0.005 |
ets | +0.004 |
seventeen | +0.004 |
Neg logit contributions | |
Wolf | -0.003 |
baby | -0.003 |
cub | -0.003 |
handed | -0.003 |
one | -0.003 |
Token | long |
Token ID | 890 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
ocus | +0.045 |
issors | +0.044 |
ets | +0.044 |
similarities | +0.044 |
ind | +0.042 |
Neg logit contributions | |
Wolf | -0.012 |
handed | -0.012 |
Mo | -0.010 |
therm | -0.009 |
hand | -0.009 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
ocus | +0.031 |
issors | +0.031 |
similarities | +0.031 |
seventeen | +0.030 |
ets | +0.029 |
Neg logit contributions | |
Wolf | -0.016 |
handed | -0.016 |
cub | -0.015 |
baby | -0.015 |
anyway | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
issors | +0.186 |
ocus | +0.185 |
similarities | +0.182 |
ets | +0.181 |
aces | +0.175 |
Neg logit contributions | |
Wolf | -0.050 |
handed | -0.047 |
Mo | -0.044 |
therm | -0.040 |
cub | -0.040 |
Token | |
Token ID | 220 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
issors | +0.007 |
ocus | +0.007 |
similarities | +0.007 |
ets | +0.007 |
seventeen | +0.007 |
Neg logit contributions | |
Wolf | -0.003 |
handed | -0.003 |
cub | -0.002 |
Mo | -0.002 |
anyway | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
Wolf | +0.004 |
handed | +0.004 |
therm | +0.004 |
burn | +0.004 |
cub | +0.004 |
Neg logit contributions | |
issors | -0.008 |
ocus | -0.008 |
similarities | -0.008 |
ets | -0.008 |
apes | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
Wolf | +0.007 |
handed | +0.007 |
burn | +0.006 |
therm | +0.006 |
baby | +0.006 |
Neg logit contributions | |
similarities | -0.015 |
issors | -0.015 |
ocus | -0.015 |
ets | -0.014 |
apes | -0.014 |
Token | One |
Token ID | 3198 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
Wolf | +0.011 |
handed | +0.011 |
Mo | +0.010 |
anyway | +0.010 |
cub | +0.010 |
Neg logit contributions | |
issors | -0.030 |
ocus | -0.030 |
similarities | -0.029 |
ets | -0.029 |
seventeen | -0.029 |
Token | time |
Token ID | 640 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Wolf | +0.024 |
handed | +0.024 |
anyway | +0.023 |
cub | +0.023 |
Mo | +0.023 |
Neg logit contributions | |
issors | -0.025 |
ocus | -0.025 |
similarities | -0.025 |
seventeen | -0.023 |
ets | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
issors | +0.053 |
similarities | +0.052 |
ocus | +0.052 |
ets | +0.051 |
seventeen | +0.050 |
Neg logit contributions | |
Wolf | -0.020 |
handed | -0.019 |
cub | -0.018 |
Mo | -0.018 |
baby | -0.018 |
Token | not |
Token ID | 407 |
Feature activation | -2.67e-01 |
Pos logit contributions | |
issors | +0.023 |
similarities | +0.023 |
ocus | +0.023 |
ets | +0.022 |
seventeen | +0.022 |
Neg logit contributions | |
Wolf | -0.009 |
handed | -0.009 |
cub | -0.008 |
baby | -0.008 |
Mo | -0.008 |
Token | so |
Token ID | 523 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
issors | +0.013 |
ocus | +0.013 |
similarities | +0.013 |
ets | +0.013 |
seventeen | +0.013 |
Neg logit contributions | |
Wolf | -0.005 |
handed | -0.005 |
cub | -0.004 |
Mo | -0.004 |
baby | -0.004 |
Token | long |
Token ID | 890 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
issors | +0.007 |
ocus | +0.007 |
similarities | +0.007 |
ets | +0.007 |
seventeen | +0.007 |
Neg logit contributions | |
Wolf | -0.002 |
handed | -0.002 |
anyway | -0.002 |
Mo | -0.002 |
cub | -0.002 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
handed | +0.005 |
Wolf | +0.004 |
cub | +0.004 |
Mo | +0.004 |
anyway | +0.004 |
Neg logit contributions | |
ocus | -0.010 |
issors | -0.010 |
similarities | -0.010 |
ets | -0.009 |
seventeen | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
ocus | +0.164 |
issors | +0.162 |
similarities | +0.161 |
ets | +0.157 |
aces | +0.154 |
Neg logit contributions | |
Wolf | -0.067 |
handed | -0.066 |
Mo | -0.065 |
rolley | -0.058 |
therm | -0.058 |
Token | there |
Token ID | 612 |
Feature activation | +3.93e-02 |
Pos logit contributions | |
issors | +0.019 |
ocus | +0.019 |
similarities | +0.018 |
ets | +0.018 |
seventeen | +0.018 |
Neg logit contributions | |
Wolf | -0.006 |
baby | -0.005 |
cub | -0.005 |
Mo | -0.005 |
handed | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
handed | +0.001 |
Wolf | +0.001 |
rolley | +0.001 |
burn | +0.001 |
hand | +0.001 |
Neg logit contributions | |
ocus | -0.002 |
similarities | -0.002 |
issors | -0.002 |
ind | -0.002 |
seventeen | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +1.97e-01 |
Pos logit contributions | |
handed | +0.022 |
Wolf | +0.021 |
rolley | +0.019 |
cub | +0.019 |
seat | +0.019 |
Neg logit contributions | |
ocus | -0.067 |
issors | -0.067 |
similarities | -0.067 |
ets | -0.064 |
seventeen | -0.064 |
Token | big |
Token ID | 1263 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
Wolf | +0.004 |
handed | +0.004 |
cub | +0.004 |
baby | +0.004 |
therm | +0.004 |
Neg logit contributions | |
issors | -0.009 |
ocus | -0.009 |
similarities | -0.009 |
ets | -0.009 |
seventeen | -0.009 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
issors | +0.002 |
ocus | +0.002 |
similarities | +0.002 |
ets | +0.002 |
seventeen | +0.002 |
Neg logit contributions | |
handed | -0.002 |
burn | -0.002 |
Wolf | -0.002 |
therm | -0.002 |
cub | -0.002 |
Token | had |
Token ID | 550 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
handed | +0.000 |
Wolf | +0.000 |
cub | +0.000 |
Mo | +0.000 |
therm | +0.000 |
Neg logit contributions | |
ocus | -0.001 |
issors | -0.001 |
similarities | -0.001 |
ets | -0.001 |
seventeen | -0.001 |
Token | planted |
Token ID | 18969 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
ocus | +0.031 |
issors | +0.031 |
similarities | +0.031 |
ets | +0.030 |
seventeen | +0.030 |
Neg logit contributions | |
Wolf | -0.015 |
handed | -0.015 |
cub | -0.014 |
Mo | -0.014 |
therm | -0.013 |
Token | it |
Token ID | 340 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
handed | +0.006 |
Wolf | +0.006 |
cub | +0.005 |
Mo | +0.005 |
therm | +0.005 |
Neg logit contributions | |
ocus | -0.015 |
issors | -0.015 |
similarities | -0.015 |
ets | -0.015 |
seventeen | -0.014 |
Token | weeks |
Token ID | 2745 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
ocus | +0.043 |
issors | +0.043 |
similarities | +0.042 |
ets | +0.041 |
seventeen | +0.040 |
Neg logit contributions | |
Wolf | -0.029 |
handed | -0.029 |
cub | -0.026 |
Mo | -0.026 |
therm | -0.026 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
ocus | +0.046 |
issors | +0.046 |
similarities | +0.045 |
ets | +0.044 |
seventeen | +0.043 |
Neg logit contributions | |
Wolf | -0.029 |
handed | -0.028 |
cub | -0.026 |
Mo | -0.026 |
therm | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
ocus | +0.145 |
issors | +0.144 |
similarities | +0.142 |
ets | +0.140 |
seventeen | +0.135 |
Neg logit contributions | |
Wolf | -0.084 |
handed | -0.082 |
Mo | -0.077 |
cub | -0.075 |
therm | -0.074 |
Token | but |
Token ID | 475 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
handed | +0.001 |
Wolf | +0.001 |
anyway | +0.001 |
baby | +0.001 |
cub | +0.001 |
Neg logit contributions | |
issors | -0.002 |
ocus | -0.002 |
similarities | -0.002 |
seventeen | -0.002 |
ets | -0.002 |
Token | now |
Token ID | 783 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
Wolf | +0.018 |
handed | +0.018 |
cub | +0.016 |
anyway | +0.016 |
baby | +0.016 |
Neg logit contributions | |
issors | -0.051 |
ocus | -0.051 |
similarities | -0.051 |
ets | -0.049 |
seventeen | -0.049 |
Token | she |
Token ID | 673 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
similarities | +0.007 |
ocus | +0.007 |
ets | +0.007 |
issors | +0.007 |
ind | +0.006 |
Neg logit contributions | |
handed | -0.003 |
Wolf | -0.003 |
rolley | -0.003 |
Mo | -0.003 |
seat | -0.003 |
Token | could |
Token ID | 714 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
issors | +0.006 |
ocus | +0.005 |
similarities | +0.005 |
ets | +0.005 |
seventeen | +0.005 |
Neg logit contributions | |
Wolf | -0.003 |
handed | -0.003 |
cub | -0.003 |
Mo | -0.003 |
anyway | -0.003 |
Token | But |
Token ID | 887 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
issors | +0.003 |
ocus | +0.003 |
similarities | +0.003 |
ets | +0.003 |
seventeen | +0.003 |
Neg logit contributions | |
handed | -0.003 |
Wolf | -0.003 |
burn | -0.003 |
therm | -0.003 |
Mo | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
Wolf | +0.024 |
handed | +0.024 |
cub | +0.021 |
baby | +0.021 |
Mo | +0.021 |
Neg logit contributions | |
issors | -0.071 |
ocus | -0.070 |
similarities | -0.070 |
ets | -0.068 |
seventeen | -0.067 |
Token | was |
Token ID | 373 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
issors | +0.033 |
ocus | +0.032 |
similarities | +0.032 |
ets | +0.031 |
seventeen | +0.031 |
Neg logit contributions | |
Wolf | -0.012 |
handed | -0.011 |
cub | -0.010 |
anyway | -0.010 |
baby | -0.010 |
Token | so |
Token ID | 523 |
Feature activation | -2.83e-01 |
Pos logit contributions | |
handed | +0.013 |
Wolf | +0.013 |
rolley | +0.012 |
Mo | +0.012 |
seat | +0.012 |
Neg logit contributions | |
ocus | -0.024 |
issors | -0.023 |
similarities | -0.023 |
seventeen | -0.023 |
ets | -0.023 |
Token | long |
Token ID | 890 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
issors | +0.012 |
ocus | +0.012 |
similarities | +0.012 |
ets | +0.012 |
seventeen | +0.012 |
Neg logit contributions | |
Wolf | -0.007 |
handed | -0.007 |
cub | -0.007 |
Mo | -0.007 |
anyway | -0.007 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.32e+00 |
Pos logit contributions | |
ocus | +0.031 |
issors | +0.031 |
similarities | +0.031 |
ets | +0.030 |
seventeen | +0.029 |
Neg logit contributions | |
Wolf | -0.017 |
handed | -0.017 |
cub | -0.016 |
Mo | -0.016 |
baby | -0.015 |
Token | that |
Token ID | 326 |
Feature activation | +1.39e-01 |
Pos logit contributions | |
ocus | +0.149 |
issors | +0.148 |
similarities | +0.145 |
ets | +0.143 |
seventeen | +0.139 |
Neg logit contributions | |
Wolf | -0.079 |
handed | -0.076 |
Mo | -0.074 |
cub | -0.069 |
seat | -0.069 |
Token | everything |
Token ID | 2279 |
Feature activation | +7.77e-01 |
Pos logit contributions | |
handed | +0.003 |
Wolf | +0.003 |
Mo | +0.003 |
cub | +0.003 |
therm | +0.003 |
Neg logit contributions | |
ocus | -0.007 |
similarities | -0.007 |
issors | -0.007 |
ets | -0.006 |
seventeen | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
handed | +0.017 |
Wolf | +0.017 |
Mo | +0.015 |
cub | +0.015 |
therm | +0.015 |
Neg logit contributions | |
ocus | -0.036 |
issors | -0.036 |
similarities | -0.036 |
ets | -0.035 |
seventeen | -0.034 |
Token | a |
Token ID | 257 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
handed | +0.009 |
Wolf | +0.009 |
rolley | +0.009 |
Mo | +0.009 |
cub | +0.008 |
Neg logit contributions | |
ocus | -0.013 |
issors | -0.013 |
similarities | -0.013 |
ets | -0.012 |
seventeen | -0.012 |
Token | bit |
Token ID | 1643 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ocus | +0.004 |
issors | +0.004 |
similarities | +0.004 |
ets | +0.004 |
seventeen | +0.004 |
Neg logit contributions | |
handed | -0.003 |
Wolf | -0.003 |
Mo | -0.003 |
cub | -0.003 |
anyway | -0.003 |
Token | an |
Token ID | 281 |
Feature activation | -6.29e-02 |
Pos logit contributions | |
handed | +0.021 |
Wolf | +0.021 |
Mo | +0.018 |
cub | +0.018 |
therm | +0.018 |
Neg logit contributions | |
issors | -0.068 |
ocus | -0.068 |
similarities | -0.068 |
ets | -0.066 |
seventeen | -0.065 |
Token | ant |
Token ID | 1885 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
ocus | +0.003 |
issors | +0.003 |
similarities | +0.003 |
ets | +0.002 |
seventeen | +0.002 |
Neg logit contributions | |
Wolf | -0.002 |
handed | -0.002 |
baby | -0.002 |
cub | -0.002 |
therm | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
ocus | +0.032 |
similarities | +0.031 |
issors | +0.031 |
ets | +0.030 |
ind | +0.030 |
Neg logit contributions | |
handed | -0.025 |
hand | -0.023 |
Wolf | -0.023 |
rolley | -0.023 |
burn | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
similarities | +0.019 |
ocus | +0.019 |
ind | +0.018 |
issors | +0.018 |
seventeen | +0.017 |
Neg logit contributions | |
handed | -0.010 |
rolley | -0.009 |
burn | -0.009 |
hand | -0.009 |
Wolf | -0.008 |
Token | grass |
Token ID | 8701 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
handed | +0.007 |
hand | +0.006 |
rolley | +0.006 |
seat | +0.006 |
esh | +0.006 |
Neg logit contributions | |
similarities | -0.008 |
ocus | -0.008 |
ind | -0.008 |
issors | -0.008 |
seventeen | -0.007 |
Token | ho |
Token ID | 8873 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
handed | +0.012 |
Wolf | +0.011 |
Mo | +0.011 |
Doctor | +0.010 |
hand | +0.010 |
Neg logit contributions | |
ocus | -0.018 |
similarities | -0.017 |
issors | -0.017 |
ets | -0.017 |
ind | -0.017 |
Token | pper |
Token ID | 2848 |
Feature activation | -3.19e-01 |
Pos logit contributions | |
ocus | +0.103 |
issors | +0.091 |
ets | +0.088 |
ind | +0.087 |
ige | +0.083 |
Neg logit contributions | |
Wolf | -0.131 |
seat | -0.128 |
rolley | -0.127 |
Doctor | -0.127 |
Where | -0.124 |
Token | . |
Token ID | 13 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
likes | +0.012 |
ocus | +0.012 |
ind | +0.012 |
similarities | +0.012 |
does | +0.012 |
Neg logit contributions | |
handed | -0.010 |
burn | -0.009 |
rolley | -0.009 |
hand | -0.009 |
severe | -0.008 |
Token | The |
Token ID | 383 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
Wolf | +0.015 |
cub | +0.014 |
baby | +0.013 |
handed | +0.013 |
Mo | +0.013 |
Neg logit contributions | |
ocus | -0.022 |
issors | -0.021 |
ets | -0.021 |
similarities | -0.021 |
seventeen | -0.020 |
Token | ant |
Token ID | 1885 |
Feature activation | -8.42e-01 |
Pos logit contributions | |
handed | +0.007 |
Wolf | +0.006 |
cub | +0.006 |
hand | +0.006 |
seat | +0.006 |
Neg logit contributions | |
issors | -0.010 |
similarities | -0.010 |
ocus | -0.010 |
ets | -0.009 |
seventeen | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
issors | +0.038 |
ocus | +0.037 |
similarities | +0.036 |
seventeen | +0.036 |
ets | +0.035 |
Neg logit contributions | |
Wolf | -0.021 |
cub | -0.021 |
anyway | -0.020 |
handed | -0.020 |
baby | -0.020 |
Token | ancestors |
Token ID | 18668 |
Feature activation | -3.76e-01 |
Pos logit contributions | |
handed | +0.033 |
Wolf | +0.033 |
Mo | +0.030 |
cub | +0.030 |
hand | +0.030 |
Neg logit contributions | |
issors | -0.053 |
ocus | -0.053 |
similarities | -0.053 |
ets | -0.051 |
seventeen | -0.049 |
Token | who |
Token ID | 508 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
ocus | +0.019 |
issors | +0.019 |
similarities | +0.019 |
ets | +0.019 |
seventeen | +0.018 |
Neg logit contributions | |
handed | -0.007 |
Wolf | -0.007 |
Mo | -0.006 |
cub | -0.006 |
therm | -0.006 |
Token | sang |
Token ID | 25889 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
Wolf | +0.007 |
handed | +0.007 |
cub | +0.007 |
Mo | +0.007 |
baby | +0.007 |
Neg logit contributions | |
issors | -0.006 |
ocus | -0.006 |
similarities | -0.006 |
ets | -0.005 |
seventeen | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
Wolf | +0.007 |
anyway | +0.006 |
handed | +0.006 |
cub | +0.006 |
baby | +0.006 |
Neg logit contributions | |
issors | -0.017 |
ocus | -0.017 |
similarities | -0.016 |
seventeen | -0.016 |
ets | -0.016 |
Token | long |
Token ID | 890 |
Feature activation | -9.91e-01 |
Pos logit contributions | |
ocus | +0.057 |
issors | +0.057 |
similarities | +0.057 |
ets | +0.056 |
seventeen | +0.054 |
Neg logit contributions | |
Wolf | -0.028 |
handed | -0.028 |
Mo | -0.025 |
cub | -0.025 |
therm | -0.025 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
issors | +0.052 |
ocus | +0.052 |
similarities | +0.051 |
seventeen | +0.050 |
ets | +0.049 |
Neg logit contributions | |
Wolf | -0.016 |
handed | -0.016 |
anyway | -0.014 |
cub | -0.014 |
baby | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
ocus | +0.186 |
issors | +0.186 |
similarities | +0.184 |
ets | +0.180 |
seventeen | +0.176 |
Neg logit contributions | |
Wolf | -0.042 |
handed | -0.041 |
Mo | -0.035 |
cub | -0.034 |
therm | -0.033 |
Token | Would |
Token ID | 10928 |
Feature activation | -8.69e-01 |
Pos logit contributions | |
issors | +0.004 |
ocus | +0.004 |
similarities | +0.004 |
ets | +0.004 |
seventeen | +0.004 |
Neg logit contributions | |
Wolf | -0.004 |
cub | -0.004 |
Mo | -0.004 |
baby | -0.004 |
handed | -0.004 |
Token | you |
Token ID | 345 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
issors | +0.031 |
ocus | +0.030 |
similarities | +0.030 |
ets | +0.029 |
seventeen | +0.028 |
Neg logit contributions | |
Wolf | -0.030 |
handed | -0.029 |
anyway | -0.028 |
cub | -0.028 |
Mo | -0.028 |
Token | like |
Token ID | 588 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
issors | +0.032 |
ocus | +0.030 |
similarities | +0.030 |
seventeen | +0.029 |
ey | +0.028 |
Neg logit contributions | |
one | -0.027 |
another | -0.026 |
anyway | -0.026 |
soon | -0.026 |
. | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
issors | +0.079 |
ocus | +0.077 |
similarities | +0.075 |
seventeen | +0.074 |
ets | +0.073 |
Neg logit contributions | |
Wolf | -0.033 |
anyway | -0.031 |
another | -0.031 |
one | -0.031 |
baby | -0.030 |
Token | who |
Token ID | 508 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
handed | +0.003 |
hand | +0.002 |
rolley | +0.002 |
Wolf | +0.002 |
Mo | +0.002 |
Neg logit contributions | |
similarities | -0.005 |
issors | -0.005 |
ocus | -0.004 |
ets | -0.004 |
ind | -0.004 |
Token | had |
Token ID | 550 |
Feature activation | -3.71e-01 |
Pos logit contributions | |
Wolf | +0.018 |
handed | +0.018 |
cub | +0.017 |
therm | +0.017 |
baby | +0.017 |
Neg logit contributions | |
issors | -0.020 |
ocus | -0.020 |
similarities | -0.020 |
seventeen | -0.019 |
ets | -0.019 |
Token | passed |
Token ID | 3804 |
Feature activation | +4.20e-01 |
Pos logit contributions | |
similarities | +0.016 |
ocus | +0.015 |
ets | +0.014 |
issors | +0.014 |
seventeen | +0.014 |
Neg logit contributions | |
Wolf | -0.010 |
Mo | -0.010 |
handed | -0.009 |
rolley | -0.009 |
Wilson | -0.009 |
Token | away |
Token ID | 1497 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
Wolf | +0.010 |
handed | +0.010 |
Mo | +0.009 |
cub | +0.009 |
burn | +0.009 |
Neg logit contributions | |
issors | -0.018 |
similarities | -0.018 |
ocus | -0.018 |
ets | -0.018 |
seventeen | -0.017 |
Token | long |
Token ID | 890 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Wolf | +0.005 |
handed | +0.005 |
Mo | +0.005 |
burn | +0.005 |
rolley | +0.004 |
Neg logit contributions | |
ets | -0.009 |
ocus | -0.009 |
similarities | -0.009 |
issors | -0.009 |
meanings | -0.008 |
Token | ago |
Token ID | 2084 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
handed | +0.005 |
Wolf | +0.005 |
cub | +0.005 |
baby | +0.005 |
therm | +0.005 |
Neg logit contributions | |
issors | -0.008 |
ocus | -0.008 |
similarities | -0.008 |
seventeen | -0.008 |
ets | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
issors | +0.168 |
ocus | +0.166 |
ets | +0.164 |
similarities | +0.164 |
aces | +0.163 |
Neg logit contributions | |
Wolf | -0.060 |
Mo | -0.057 |
handed | -0.057 |
rolley | -0.050 |
therm | -0.049 |
Token | One |
Token ID | 1881 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
handed | +0.009 |
burn | +0.008 |
Wolf | +0.008 |
Mo | +0.008 |
able | +0.008 |
Neg logit contributions | |
issors | -0.012 |
similarities | -0.012 |
ocus | -0.011 |
seventeen | -0.011 |
ets | -0.011 |
Token | day |
Token ID | 1110 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
handed | +0.002 |
Wolf | +0.002 |
Mo | +0.002 |
hand | +0.002 |
anyway | +0.002 |
Neg logit contributions | |
ocus | -0.003 |
similarities | -0.003 |
issors | -0.003 |
ets | -0.003 |
seventeen | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
ocus | +0.001 |
similarities | +0.001 |
issors | +0.001 |
seventeen | +0.001 |
ind | +0.001 |
Neg logit contributions | |
handed | -0.001 |
rolley | -0.001 |
Wolf | -0.001 |
Mo | -0.001 |
seat | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
handed | +0.007 |
rolley | +0.006 |
Wolf | +0.006 |
Mo | +0.005 |
hand | +0.005 |
Neg logit contributions | |
similarities | -0.014 |
issors | -0.014 |
ocus | -0.014 |
seventeen | -0.014 |
ind | -0.014 |
Token | ." |
Token ID | 526 |
Feature activation | +5.46e-03 |
Pos logit contributions | |
issors | +0.011 |
ocus | +0.011 |
similarities | +0.011 |
ets | +0.011 |
seventeen | +0.010 |
Neg logit contributions | |
Wolf | -0.005 |
handed | -0.005 |
Mo | -0.005 |
therm | -0.005 |
cub | -0.005 |
Token | Sue |
Token ID | 26089 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
handed | +0.000 |
Wolf | +0.000 |
burn | +0.000 |
therm | +0.000 |
Mo | +0.000 |
Neg logit contributions | |
issors | -0.000 |
ocus | -0.000 |
similarities | -0.000 |
ets | -0.000 |
seventeen | -0.000 |
Token | agreed |
Token ID | 4987 |
Feature activation | -5.48e-01 |
Pos logit contributions | |
Wolf | +0.013 |
handed | +0.013 |
cub | +0.012 |
anyway | +0.012 |
baby | +0.012 |
Neg logit contributions | |
issors | -0.021 |
ocus | -0.020 |
similarities | -0.020 |
ets | -0.019 |
seventeen | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -7.25e-01 |
Pos logit contributions | |
issors | +0.021 |
ets | +0.021 |
similarities | +0.021 |
ocus | +0.021 |
seventeen | +0.019 |
Neg logit contributions | |
Wolf | -0.016 |
handed | -0.016 |
Mo | -0.016 |
seat | -0.015 |
rolley | -0.015 |
Token | " |
Token ID | 366 |
Feature activation | -2.10e-01 |
Pos logit contributions | |
issors | +0.030 |
ocus | +0.030 |
similarities | +0.030 |
ets | +0.029 |
seventeen | +0.028 |
Neg logit contributions | |
handed | -0.020 |
Wolf | -0.019 |
Mo | -0.018 |
cub | -0.018 |
therm | -0.018 |
Token | That |
Token ID | 2504 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ocus | +0.008 |
issors | +0.008 |
similarities | +0.007 |
ets | +0.007 |
seventeen | +0.007 |
Neg logit contributions | |
handed | -0.007 |
Wolf | -0.007 |
anyway | -0.006 |
Mo | -0.006 |
hand | -0.006 |
Token | 's |
Token ID | 338 |
Feature activation | +1.90e-01 |
Pos logit contributions | |
handed | +0.053 |
Wolf | +0.049 |
Mo | +0.048 |
seat | +0.048 |
hand | +0.047 |
Neg logit contributions | |
similarities | -0.055 |
ocus | -0.054 |
issors | -0.053 |
ets | -0.052 |
ind | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
handed | +0.006 |
Wolf | +0.006 |
rolley | +0.005 |
seat | +0.005 |
hand | +0.005 |
Neg logit contributions | |
issors | -0.008 |
similarities | -0.008 |
ocus | -0.007 |
seventeen | -0.007 |
ind | -0.007 |
Token | good |
Token ID | 922 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
handed | +0.012 |
Wolf | +0.012 |
hand | +0.011 |
rolley | +0.011 |
seat | +0.011 |
Neg logit contributions | |
similarities | -0.014 |
issors | -0.014 |
ocus | -0.014 |
seventeen | -0.013 |
ets | -0.013 |
Token | idea |
Token ID | 2126 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
handed | +0.006 |
Wolf | +0.006 |
cub | +0.006 |
Mo | +0.006 |
hand | +0.006 |
Neg logit contributions | |
issors | -0.006 |
ocus | -0.006 |
similarities | -0.006 |
ets | -0.006 |
seventeen | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
ocus | +0.057 |
issors | +0.056 |
similarities | +0.056 |
ets | +0.055 |
seventeen | +0.054 |
Neg logit contributions | |
handed | -0.018 |
Wolf | -0.017 |
Mo | -0.016 |
cub | -0.015 |
seat | -0.015 |
Token | upon |
Token ID | 2402 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
ocus | +0.042 |
issors | +0.042 |
similarities | +0.041 |
ets | +0.039 |
ind | +0.036 |
Neg logit contributions | |
handed | -0.049 |
Wolf | -0.048 |
Mo | -0.045 |
cub | -0.045 |
burn | -0.045 |
Token | a |
Token ID | 257 |
Feature activation | +6.63e-01 |
Pos logit contributions | |
ocus | +0.047 |
similarities | +0.047 |
ets | +0.045 |
issors | +0.045 |
aces | +0.044 |
Neg logit contributions | |
Wolf | -0.029 |
handed | -0.028 |
rolley | -0.027 |
burn | -0.027 |
Mo | -0.026 |
Token | time |
Token ID | 640 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
Wolf | +0.022 |
handed | +0.021 |
anyway | +0.021 |
cub | +0.021 |
baby | +0.020 |
Neg logit contributions | |
ocus | -0.024 |
issors | -0.024 |
similarities | -0.024 |
seventeen | -0.022 |
ets | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -5.78e-01 |
Pos logit contributions | |
issors | +0.055 |
similarities | +0.055 |
ocus | +0.055 |
ets | +0.053 |
seventeen | +0.052 |
Neg logit contributions | |
Wolf | -0.022 |
handed | -0.021 |
cub | -0.019 |
baby | -0.019 |
anyway | -0.019 |
Token | there |
Token ID | 612 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
issors | +0.028 |
ocus | +0.028 |
similarities | +0.028 |
ets | +0.027 |
seventeen | +0.027 |
Neg logit contributions | |
Wolf | -0.012 |
handed | -0.011 |
cub | -0.011 |
baby | -0.010 |
Mo | -0.010 |
Token | were |
Token ID | 547 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
similarities | +0.011 |
ocus | +0.011 |
issors | +0.010 |
ets | +0.010 |
seventeen | +0.010 |
Neg logit contributions | |
handed | -0.005 |
Wolf | -0.005 |
burn | -0.005 |
rolley | -0.004 |
Mo | -0.004 |
Token | two |
Token ID | 734 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
baby | +0.020 |
Wolf | +0.019 |
handed | +0.016 |
another | +0.016 |
one | +0.015 |
Neg logit contributions | |
issors | -0.115 |
ocus | -0.114 |
ets | -0.112 |
similarities | -0.112 |
seventeen | -0.107 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
Wolf | +0.028 |
handed | +0.027 |
cub | +0.025 |
Mo | +0.025 |
anyway | +0.024 |
Neg logit contributions | |
issors | -0.062 |
ocus | -0.062 |
similarities | -0.062 |
ets | -0.060 |
seventeen | -0.059 |
Token | called |
Token ID | 1444 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
handed | +0.005 |
rolley | +0.005 |
therm | +0.005 |
burn | +0.005 |
Wolf | +0.005 |
Neg logit contributions | |
issors | -0.004 |
apes | -0.004 |
similarities | -0.004 |
ocus | -0.004 |
nations | -0.004 |
Token | Tom |
Token ID | 4186 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
issors | +0.008 |
ocus | +0.008 |
similarities | +0.008 |
ets | +0.008 |
seventeen | +0.008 |
Neg logit contributions | |
handed | -0.007 |
Wolf | -0.007 |
therm | -0.007 |
Mo | -0.007 |
cub | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
handed | +0.018 |
Wolf | +0.018 |
Mo | +0.018 |
therm | +0.017 |
hand | +0.017 |
Neg logit contributions | |
ets | -0.016 |
issors | -0.016 |
ocus | -0.016 |
similarities | -0.015 |
apes | -0.015 |
Token | He |
Token ID | 679 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
issors | +0.006 |
ocus | +0.006 |
similarities | +0.006 |
ets | +0.005 |
seventeen | +0.005 |
Neg logit contributions | |
handed | -0.004 |
Wolf | -0.004 |
burn | -0.004 |
Mo | -0.004 |
therm | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
handed | +0.010 |
Wolf | +0.009 |
seat | +0.009 |
burn | +0.009 |
hand | +0.008 |
Neg logit contributions | |
ocus | -0.014 |
issors | -0.014 |
similarities | -0.014 |
ets | -0.014 |
seventeen | -0.013 |
Token | taken |
Token ID | 2077 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
handed | +0.004 |
rolley | +0.004 |
hand | +0.004 |
Mo | +0.004 |
seat | +0.003 |
Neg logit contributions | |
ocus | -0.005 |
seventeen | -0.005 |
issors | -0.005 |
similarities | -0.005 |
ets | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
ets | +0.012 |
issors | +0.011 |
similarities | +0.011 |
ocus | +0.011 |
seventeen | +0.011 |
Neg logit contributions | |
handed | -0.006 |
burn | -0.006 |
rolley | -0.006 |
Wolf | -0.006 |
Mo | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | +5.56e-02 |
Pos logit contributions | |
burn | +0.004 |
rolley | +0.004 |
Mo | +0.004 |
eled | +0.004 |
m | +0.004 |
Neg logit contributions | |
similarities | -0.005 |
issors | -0.005 |
ocus | -0.005 |
draw | -0.005 |
does | -0.005 |
Token | hospital |
Token ID | 4436 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
seat | +0.001 |
handed | +0.001 |
burn | +0.001 |
Mo | +0.001 |
Wolf | +0.001 |
Neg logit contributions | |
issors | -0.002 |
similarities | -0.002 |
ocus | -0.002 |
seventeen | -0.002 |
meanings | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +3.05e-02 |
Pos logit contributions | |
Wolf | +0.038 |
handed | +0.037 |
Mo | +0.036 |
rolley | +0.035 |
burn | +0.034 |
Neg logit contributions | |
ocus | -0.061 |
issors | -0.060 |
ets | -0.059 |
similarities | -0.059 |
seventeen | -0.056 |
Token | but |
Token ID | 475 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
handed | +0.001 |
Wolf | +0.001 |
Mo | +0.001 |
cub | +0.001 |
hand | +0.001 |
Neg logit contributions | |
issors | -0.001 |
ocus | -0.001 |
similarities | -0.001 |
ets | -0.001 |
seventeen | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
handed | +0.022 |
burn | +0.020 |
Wolf | +0.020 |
Mo | +0.019 |
rolley | +0.019 |
Neg logit contributions | |
ocus | -0.062 |
similarities | -0.061 |
issors | -0.061 |
ets | -0.059 |
seventeen | -0.059 |
Token | was |
Token ID | 373 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
ocus | +0.007 |
similarities | +0.007 |
issors | +0.007 |
ets | +0.007 |
does | +0.006 |
Neg logit contributions | |
handed | -0.004 |
seat | -0.004 |
rolley | -0.004 |
Wolf | -0.003 |
burn | -0.003 |
Token | too |
Token ID | 1165 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
handed | +0.022 |
rolley | +0.020 |
hand | +0.018 |
seat | +0.018 |
Wolf | +0.017 |
Neg logit contributions | |
seventeen | -0.022 |
issors | -0.022 |
similarities | -0.022 |
ocus | -0.022 |
ind | -0.022 |
Token | friends |
Token ID | 2460 |
Feature activation | +6.99e-02 |
Pos logit contributions | |
handed | +0.017 |
Wolf | +0.016 |
therm | +0.015 |
burn | +0.015 |
rolley | +0.015 |
Neg logit contributions | |
similarities | -0.028 |
ocus | -0.027 |
issors | -0.027 |
ets | -0.026 |
seventeen | -0.025 |
Token | ! |
Token ID | 0 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
handed | +0.002 |
therm | +0.001 |
rolley | +0.001 |
burn | +0.001 |
Mo | +0.001 |
Neg logit contributions | |
ets | -0.003 |
similarities | -0.003 |
ocus | -0.003 |
aces | -0.003 |
ind | -0.003 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
issors | +0.008 |
similarities | +0.008 |
ocus | +0.008 |
ets | +0.008 |
ols | +0.007 |
Neg logit contributions | |
handed | -0.007 |
therm | -0.006 |
ge | -0.006 |
able | -0.006 |
burn | -0.006 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
handed | +0.009 |
able | +0.009 |
burn | +0.009 |
therm | +0.009 |
rolley | +0.008 |
Neg logit contributions | |
ocus | -0.012 |
ets | -0.011 |
does | -0.011 |
similarities | -0.011 |
aces | -0.011 |
Token | there |
Token ID | 612 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
ocus | +0.040 |
issors | +0.039 |
similarities | +0.039 |
ets | +0.037 |
ind | +0.034 |
Neg logit contributions | |
handed | -0.051 |
Wolf | -0.049 |
hand | -0.047 |
Mo | -0.047 |
therm | -0.047 |
Token | were |
Token ID | 547 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
similarities | +0.001 |
ocus | +0.001 |
does | +0.001 |
ind | +0.001 |
seventeen | +0.001 |
Neg logit contributions | |
handed | -0.001 |
burn | -0.001 |
rolley | -0.001 |
Wolf | -0.001 |
therm | -0.001 |
Token | two |
Token ID | 734 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Wolf | +0.039 |
baby | +0.036 |
handed | +0.036 |
cub | +0.034 |
anyway | +0.034 |
Neg logit contributions | |
issors | -0.092 |
ocus | -0.090 |
similarities | -0.089 |
ets | -0.086 |
seventeen | -0.086 |
Token | little |
Token ID | 1310 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
handed | +0.026 |
Wolf | +0.026 |
Mo | +0.023 |
hand | +0.023 |
cub | +0.023 |
Neg logit contributions | |
issors | -0.053 |
ocus | -0.053 |
similarities | -0.053 |
ets | -0.052 |
seventeen | -0.051 |
Token | girls |
Token ID | 4813 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
handed | +0.008 |
Wolf | +0.007 |
Mo | +0.007 |
hand | +0.006 |
anyway | +0.006 |
Neg logit contributions | |
ocus | -0.014 |
issors | -0.014 |
similarities | -0.014 |
ets | -0.013 |
seventeen | -0.013 |
Token | who |
Token ID | 508 |
Feature activation | +3.10e-01 |
Pos logit contributions | |
handed | +0.021 |
Wolf | +0.019 |
rolley | +0.019 |
Mo | +0.018 |
burn | +0.018 |
Neg logit contributions | |
ocus | -0.029 |
issors | -0.029 |
similarities | -0.029 |
ets | -0.028 |
ind | -0.027 |
Token | loved |
Token ID | 6151 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
Wolf | +0.011 |
handed | +0.011 |
therm | +0.011 |
Mo | +0.011 |
rolley | +0.010 |
Neg logit contributions | |
similarities | -0.010 |
ocus | -0.010 |
issors | -0.010 |
ets | -0.010 |
seventeen | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +2.81e-01 |
Pos logit contributions | |
Wolf | +0.020 |
handed | +0.019 |
cub | +0.017 |
Mo | +0.017 |
therm | +0.017 |
Neg logit contributions | |
issors | -0.047 |
ocus | -0.047 |
similarities | -0.046 |
ets | -0.045 |
seventeen | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
burn | +0.007 |
Mo | +0.007 |
Wolf | +0.006 |
rolley | +0.006 |
therm | +0.006 |
Neg logit contributions | |
similarities | -0.012 |
issors | -0.012 |
ocus | -0.012 |
ets | -0.012 |
nations | -0.011 |
Token | toy |
Token ID | 13373 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
Wolf | +0.011 |
handed | +0.010 |
Mo | +0.010 |
cub | +0.010 |
seat | +0.010 |
Neg logit contributions | |
issors | -0.015 |
similarities | -0.014 |
ocus | -0.014 |
seventeen | -0.014 |
ets | -0.014 |
Token | shop |
Token ID | 6128 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
Mo | +0.029 |
Wolf | +0.029 |
burn | +0.028 |
handed | +0.026 |
therm | +0.026 |
Neg logit contributions | |
issors | -0.053 |
ocus | -0.052 |
ets | -0.050 |
similarities | -0.050 |
nations | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +2.16e-01 |
Pos logit contributions | |
Wolf | +0.011 |
Mo | +0.011 |
burn | +0.010 |
handed | +0.010 |
therm | +0.010 |
Neg logit contributions | |
issors | -0.017 |
ocus | -0.017 |
similarities | -0.016 |
ets | -0.016 |
seventeen | -0.016 |
Token | But |
Token ID | 887 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Wolf | +0.006 |
handed | +0.006 |
cub | +0.005 |
anyway | +0.005 |
baby | +0.005 |
Neg logit contributions | |
ocus | -0.009 |
similarities | -0.009 |
issors | -0.009 |
ets | -0.009 |
seventeen | -0.009 |
Token | when |
Token ID | 618 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
Wolf | +0.027 |
handed | +0.025 |
anyway | +0.023 |
cub | +0.023 |
baby | +0.023 |
Neg logit contributions | |
issors | -0.099 |
ocus | -0.099 |
similarities | -0.098 |
ets | -0.096 |
seventeen | -0.095 |
Token | he |
Token ID | 339 |
Feature activation | +3.19e-01 |
Pos logit contributions | |
ocus | +0.010 |
similarities | +0.010 |
issors | +0.010 |
ets | +0.009 |
seventeen | +0.009 |
Neg logit contributions | |
handed | -0.003 |
Wolf | -0.003 |
rolley | -0.003 |
Mo | -0.002 |
cub | -0.002 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
Wolf | +0.008 |
handed | +0.008 |
Mo | +0.007 |
burn | +0.007 |
cub | +0.007 |
Neg logit contributions | |
ocus | -0.014 |
issors | -0.014 |
similarities | -0.014 |
ets | -0.013 |
seventeen | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
issors | +0.023 |
ocus | +0.023 |
similarities | +0.023 |
ets | +0.023 |
seventeen | +0.022 |
Neg logit contributions | |
Wolf | -0.012 |
Mo | -0.012 |
handed | -0.012 |
burn | -0.012 |
seat | -0.012 |
Token | prices |
Token ID | 4536 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
issors | +0.001 |
ocus | +0.001 |
similarities | +0.001 |
ets | +0.001 |
seventeen | +0.001 |
Neg logit contributions | |
Wolf | -0.001 |
handed | -0.001 |
Mo | -0.001 |
cub | -0.001 |
anyway | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
issors | +0.044 |
ocus | +0.043 |
similarities | +0.042 |
ets | +0.042 |
seventeen | +0.040 |
Neg logit contributions | |
Wolf | -0.022 |
handed | -0.022 |
Mo | -0.020 |
hand | -0.020 |
rolley | -0.020 |
Token | He |
Token ID | 679 |
Feature activation | +1.37e-01 |
Pos logit contributions | |
Wolf | +0.000 |
handed | +0.000 |
cub | +0.000 |
anyway | +0.000 |
seat | +0.000 |
Neg logit contributions | |
ocus | -0.001 |
issors | -0.001 |
similarities | -0.001 |
ets | -0.001 |
seventeen | -0.001 |
Token | never |
Token ID | 1239 |
Feature activation | -5.43e-01 |
Pos logit contributions | |
Wolf | +0.004 |
handed | +0.004 |
cub | +0.004 |
anyway | +0.004 |
Mo | +0.004 |
Neg logit contributions | |
issors | -0.005 |
ocus | -0.005 |
similarities | -0.005 |
ets | -0.005 |
seventeen | -0.005 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
ocus | +0.021 |
similarities | +0.021 |
issors | +0.021 |
ets | +0.020 |
seventeen | +0.019 |
Neg logit contributions | |
Wolf | -0.016 |
handed | -0.016 |
Mo | -0.015 |
cub | -0.015 |
hand | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +4.76e-01 |
Pos logit contributions | |
Wolf | +0.005 |
handed | +0.005 |
cub | +0.005 |
baby | +0.005 |
anyway | +0.005 |
Neg logit contributions | |
issors | -0.009 |
ocus | -0.009 |
similarities | -0.009 |
seventeen | -0.008 |
ets | -0.008 |
Token | do |
Token ID | 466 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
Wolf | +0.017 |
handed | +0.017 |
rolley | +0.017 |
Mo | +0.016 |
seat | +0.016 |
Neg logit contributions | |
similarities | -0.015 |
ocus | -0.015 |
issors | -0.015 |
ets | -0.014 |
seventeen | -0.013 |
Token | any |
Token ID | 597 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
handed | +0.015 |
Wolf | +0.015 |
rolley | +0.015 |
Mo | +0.014 |
seat | +0.014 |
Neg logit contributions | |
ocus | -0.024 |
similarities | -0.024 |
ets | -0.023 |
issors | -0.023 |
meanings | -0.022 |
Token | work |
Token ID | 670 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
handed | +0.028 |
Wolf | +0.028 |
Mo | +0.027 |
hand | +0.026 |
rolley | +0.026 |
Neg logit contributions | |
similarities | -0.035 |
ocus | -0.035 |
issors | -0.035 |
ets | -0.035 |
seventeen | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
ocus | +0.009 |
issors | +0.009 |
similarities | +0.009 |
ets | +0.009 |
seventeen | +0.009 |
Neg logit contributions | |
Wolf | -0.005 |
handed | -0.004 |
Mo | -0.004 |
cub | -0.004 |
therm | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +4.49e-01 |
Pos logit contributions | |
Wolf | +0.002 |
handed | +0.002 |
cub | +0.002 |
anyway | +0.002 |
Mo | +0.002 |
Neg logit contributions | |
ocus | -0.009 |
issors | -0.009 |
similarities | -0.009 |
ets | -0.009 |
seventeen | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
handed | +0.009 |
Wolf | +0.009 |
burn | +0.008 |
therm | +0.008 |
cub | +0.008 |
Neg logit contributions | |
issors | -0.021 |
similarities | -0.021 |
ocus | -0.021 |
ets | -0.020 |
seventeen | -0.019 |
Token | important |
Token ID | 1593 |
Feature activation | -9.63e-04 |
Pos logit contributions | |
ocus | +0.007 |
issors | +0.007 |
similarities | +0.007 |
seventeen | +0.006 |
ets | +0.006 |
Neg logit contributions | |
Wolf | -0.005 |
handed | -0.005 |
anyway | -0.004 |
cub | -0.004 |
baby | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
ocus | +0.000 |
issors | +0.000 |
seventeen | +0.000 |
similarities | +0.000 |
ind | +0.000 |
Neg logit contributions | |
Wolf | -0.000 |
anyway | -0.000 |
handed | -0.000 |
baby | -0.000 |
anyways | -0.000 |
Token | forgive |
Token ID | 20927 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
ocus | +0.016 |
seventeen | +0.015 |
issors | +0.015 |
ets | +0.014 |
similarities | +0.014 |
Neg logit contributions | |
Wolf | -0.010 |
anyway | -0.009 |
baby | -0.009 |
one | -0.009 |
handed | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +6.97e-01 |
Pos logit contributions | |
ocus | +0.028 |
issors | +0.027 |
similarities | +0.027 |
seventeen | +0.027 |
ets | +0.026 |
Neg logit contributions | |
Wolf | -0.015 |
handed | -0.014 |
anyway | -0.014 |
cub | -0.014 |
baby | -0.014 |
Token | work |
Token ID | 670 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
soon | +0.017 |
anyway | +0.017 |
baby | +0.017 |
another | +0.017 |
Wolf | +0.017 |
Neg logit contributions | |
ocus | -0.032 |
issors | -0.031 |
seventeen | -0.030 |
ets | -0.030 |
aces | -0.029 |
Token | together |
Token ID | 1978 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
Wolf | +0.017 |
handed | +0.017 |
cub | +0.015 |
Mo | +0.015 |
therm | +0.015 |
Neg logit contributions | |
issors | -0.034 |
ocus | -0.034 |
similarities | -0.034 |
ets | -0.033 |
seventeen | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | +1.94e-01 |
Pos logit contributions | |
Wolf | +0.006 |
handed | +0.006 |
cub | +0.005 |
anyway | +0.004 |
Mo | +0.004 |
Neg logit contributions | |
issors | -0.037 |
ocus | -0.037 |
similarities | -0.037 |
ets | -0.036 |
seventeen | -0.036 |
Token | make |
Token ID | 787 |
Feature activation | +8.17e-02 |
Pos logit contributions | |
handed | +0.006 |
Wolf | +0.006 |
anyway | +0.005 |
another | +0.005 |
. | +0.005 |
Neg logit contributions | |
ocus | -0.008 |
issors | -0.008 |
seventeen | -0.007 |
ets | -0.007 |
similarities | -0.007 |
Token | things |
Token ID | 1243 |
Feature activation | +8.34e-01 |
Pos logit contributions | |
Wolf | +0.002 |
handed | +0.002 |
Mo | +0.002 |
cub | +0.002 |
seat | +0.002 |
Neg logit contributions | |
issors | -0.003 |
similarities | -0.003 |
ocus | -0.003 |
ets | -0.003 |
seventeen | -0.003 |
Token | better |
Token ID | 1365 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
handed | +0.012 |
Wolf | +0.011 |
anyway | +0.011 |
baby | +0.010 |
therm | +0.010 |
Neg logit contributions | |
issors | -0.046 |
ocus | -0.045 |
similarities | -0.045 |
seventeen | -0.044 |
ets | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | -5.81e-01 |
Pos logit contributions | |
issors | +0.007 |
similarities | +0.007 |
ocus | +0.007 |
ets | +0.007 |
seventeen | +0.007 |
Neg logit contributions | |
Wolf | -0.001 |
handed | -0.001 |
Mo | -0.001 |
cub | -0.001 |
therm | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +3.40e-01 |
Pos logit contributions | |
Wolf | +0.003 |
handed | +0.003 |
cub | +0.003 |
Mo | +0.003 |
therm | +0.003 |
Neg logit contributions | |
issors | -0.006 |
ocus | -0.006 |
similarities | -0.006 |
ets | -0.006 |
seventeen | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
Wolf | +0.008 |
handed | +0.008 |
cub | +0.008 |
burn | +0.008 |
therm | +0.007 |
Neg logit contributions | |
issors | -0.015 |
similarities | -0.015 |
ocus | -0.015 |
ets | -0.014 |
apes | -0.014 |
Token | So |
Token ID | 2396 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
Wolf | +0.012 |
handed | +0.012 |
cub | +0.011 |
Mo | +0.011 |
anyway | +0.011 |
Neg logit contributions | |
issors | -0.020 |
ocus | -0.020 |
similarities | -0.020 |
ets | -0.020 |
seventeen | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | -1.13e-01 |
Pos logit contributions | |
Wolf | +0.020 |
handed | +0.020 |
baby | +0.019 |
anyway | +0.019 |
cub | +0.018 |
Neg logit contributions | |
ocus | -0.041 |
issors | -0.041 |
similarities | -0.041 |
seventeen | -0.039 |
ets | -0.039 |
Token | Lily |
Token ID | 20037 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
issors | +0.005 |
ocus | +0.005 |
similarities | +0.005 |
ets | +0.004 |
seventeen | +0.004 |
Neg logit contributions | |
Wolf | -0.003 |
handed | -0.003 |
cub | -0.003 |
Mo | -0.003 |
therm | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +6.62e-02 |
Pos logit contributions | |
Wolf | +0.002 |
handed | +0.002 |
anyway | +0.002 |
cub | +0.002 |
baby | +0.002 |
Neg logit contributions | |
issors | -0.005 |
similarities | -0.005 |
ocus | -0.005 |
seventeen | -0.004 |
ets | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
handed | +0.001 |
Wolf | +0.001 |
rolley | +0.001 |
Mo | +0.001 |
seat | +0.001 |
Neg logit contributions | |
issors | -0.003 |
similarities | -0.003 |
ocus | -0.003 |
ets | -0.003 |
meanings | -0.003 |
Token | mom |
Token ID | 1995 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
handed | +0.007 |
Wolf | +0.007 |
Mo | +0.006 |
cub | +0.006 |
hand | +0.006 |
Neg logit contributions | |
issors | -0.015 |
similarities | -0.015 |
ocus | -0.015 |
ets | -0.014 |
seventeen | -0.014 |
Token | had |
Token ID | 550 |
Feature activation | -2.23e-01 |
Pos logit contributions | |
issors | +0.001 |
ocus | +0.001 |
similarities | +0.001 |
ets | +0.001 |
seventeen | +0.001 |
Neg logit contributions | |
Wolf | -0.001 |
handed | -0.001 |
cub | -0.001 |
Mo | -0.001 |
anyway | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
issors | +0.012 |
ocus | +0.012 |
similarities | +0.012 |
ets | +0.012 |
seventeen | +0.011 |
Neg logit contributions | |
anyway | -0.003 |
another | -0.003 |
handed | -0.003 |
Wolf | -0.003 |
one | -0.003 |
Token | bath |
Token ID | 7837 |
Feature activation | +8.44e-01 |
Pos logit contributions | |
ocus | +0.018 |
issors | +0.018 |
similarities | +0.018 |
ets | +0.017 |
seventeen | +0.017 |
Neg logit contributions | |
Wolf | -0.016 |
handed | -0.016 |
cub | -0.015 |
baby | -0.015 |
Mo | -0.015 |
Token | 're |
Token ID | 821 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
Wolf | +0.028 |
handed | +0.027 |
cub | +0.026 |
Mo | +0.026 |
baby | +0.026 |
Neg logit contributions | |
issors | -0.025 |
ocus | -0.025 |
similarities | -0.025 |
ets | -0.023 |
seventeen | -0.023 |
Token | going |
Token ID | 1016 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
handed | +0.003 |
Wolf | +0.003 |
hand | +0.003 |
rolley | +0.003 |
Mo | +0.002 |
Neg logit contributions | |
ocus | -0.005 |
similarities | -0.005 |
issors | -0.005 |
ets | -0.005 |
ind | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +7.64e-02 |
Pos logit contributions | |
handed | +0.001 |
Wolf | +0.001 |
Mo | +0.001 |
cub | +0.001 |
therm | +0.001 |
Neg logit contributions | |
ocus | -0.001 |
issors | -0.001 |
similarities | -0.001 |
ets | -0.001 |
seventeen | -0.001 |
Token | stay |
Token ID | 2652 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
handed | +0.003 |
rolley | +0.002 |
Wolf | +0.002 |
hand | +0.002 |
therm | +0.002 |
Neg logit contributions | |
similarities | -0.003 |
ocus | -0.003 |
ind | -0.002 |
issors | -0.002 |
seventeen | -0.002 |
Token | in |
Token ID | 287 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
Wolf | +0.007 |
handed | +0.007 |
cub | +0.006 |
Mo | +0.006 |
therm | +0.006 |
Neg logit contributions | |
issors | -0.012 |
ocus | -0.012 |
similarities | -0.012 |
ets | -0.011 |
seventeen | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
ocus | +0.015 |
similarities | +0.015 |
ets | +0.014 |
issors | +0.014 |
ind | +0.014 |
Neg logit contributions | |
handed | -0.009 |
Wolf | -0.009 |
Mo | -0.008 |
burn | -0.008 |
rolley | -0.008 |
Token | hotel |
Token ID | 7541 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Wolf | +0.030 |
handed | +0.029 |
Mo | +0.029 |
burn | +0.029 |
Wilson | +0.028 |
Neg logit contributions | |
ocus | -0.032 |
similarities | -0.031 |
ets | -0.031 |
seventeen | -0.029 |
issors | -0.029 |
Token | !" |
Token ID | 2474 |
Feature activation | -5.93e-02 |
Pos logit contributions | |
Wolf | +0.024 |
handed | +0.023 |
Mo | +0.023 |
therm | +0.021 |
cub | +0.021 |
Neg logit contributions | |
ocus | -0.046 |
ets | -0.046 |
issors | -0.045 |
similarities | -0.044 |
seventeen | -0.043 |
Token |
|
Token ID | 198 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
issors | +0.002 |
ets | +0.002 |
ocus | +0.002 |
similarities | +0.002 |
Salad | +0.002 |
Neg logit contributions | |
handed | -0.002 |
Wolf | -0.002 |
burn | -0.001 |
Mo | -0.001 |
therm | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
Wolf | +0.003 |
handed | +0.003 |
burn | +0.003 |
therm | +0.002 |
ting | +0.002 |
Neg logit contributions | |
issors | -0.004 |
similarities | -0.004 |
ocus | -0.004 |
apes | -0.004 |
seventeen | -0.004 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Wolf | +0.007 |
handed | +0.006 |
cub | +0.006 |
therm | +0.006 |
baby | +0.006 |
Neg logit contributions | |
issors | -0.014 |
similarities | -0.014 |
ocus | -0.014 |
seventeen | -0.013 |
ets | -0.013 |
Token | It |
Token ID | 632 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
ocus | +0.012 |
issors | +0.012 |
similarities | +0.012 |
ets | +0.012 |
seventeen | +0.011 |
Neg logit contributions | |
Wolf | -0.018 |
handed | -0.017 |
cub | -0.017 |
Mo | -0.017 |
therm | -0.016 |
Token | has |
Token ID | 468 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
Wolf | +0.006 |
handed | +0.006 |
cub | +0.005 |
therm | +0.005 |
baby | +0.005 |
Neg logit contributions | |
issors | -0.007 |
ocus | -0.007 |
similarities | -0.006 |
ets | -0.006 |
seventeen | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -3.98e-01 |
Pos logit contributions | |
issors | +0.020 |
ocus | +0.019 |
similarities | +0.019 |
ets | +0.018 |
seventeen | +0.018 |
Neg logit contributions | |
Wolf | -0.006 |
handed | -0.006 |
baby | -0.006 |
cub | -0.006 |
therm | -0.005 |
Token | lot |
Token ID | 1256 |
Feature activation | +1.57e-01 |
Pos logit contributions | |
issors | +0.016 |
ocus | +0.016 |
similarities | +0.016 |
ets | +0.015 |
apes | +0.015 |
Neg logit contributions | |
Wolf | -0.012 |
therm | -0.012 |
baby | -0.012 |
cub | -0.011 |
anyway | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
handed | +0.004 |
Wolf | +0.004 |
cub | +0.003 |
anyway | +0.003 |
therm | +0.003 |
Neg logit contributions | |
issors | -0.007 |
similarities | -0.007 |
ocus | -0.007 |
ets | -0.007 |
seventeen | -0.007 |
Token | memories |
Token ID | 9846 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
Wolf | +0.044 |
therm | +0.044 |
handed | +0.043 |
baby | +0.043 |
cub | +0.043 |
Neg logit contributions | |
issors | -0.054 |
ocus | -0.054 |
similarities | -0.052 |
seventeen | -0.051 |
ets | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
Wolf | +0.017 |
handed | +0.017 |
cub | +0.015 |
anyway | +0.015 |
baby | +0.015 |
Neg logit contributions | |
issors | -0.041 |
similarities | -0.041 |
ocus | -0.041 |
seventeen | -0.039 |
ets | -0.039 |
Token | But |
Token ID | 887 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
issors | +0.015 |
ocus | +0.015 |
similarities | +0.015 |
ets | +0.014 |
seventeen | +0.014 |
Neg logit contributions | |
Wolf | -0.021 |
handed | -0.021 |
cub | -0.020 |
Mo | -0.020 |
anyway | -0.019 |
Token | it |
Token ID | 340 |
Feature activation | -3.92e-01 |
Pos logit contributions | |
Wolf | +0.037 |
baby | +0.035 |
cub | +0.034 |
anyway | +0.034 |
one | +0.034 |
Neg logit contributions | |
issors | -0.083 |
ocus | -0.082 |
ets | -0.081 |
similarities | -0.081 |
seventeen | -0.078 |
Token | is |
Token ID | 318 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
issors | +0.016 |
similarities | +0.015 |
ocus | +0.015 |
seventeen | +0.015 |
ige | +0.014 |
Neg logit contributions | |
cub | -0.012 |
Wolf | -0.012 |
Bear | -0.012 |
therm | -0.011 |
baby | -0.011 |
Token | not |
Token ID | 407 |
Feature activation | +6.32e-01 |
Pos logit contributions | |
Wolf | +0.001 |
handed | +0.001 |
cub | +0.001 |
Mo | +0.001 |
anyway | +0.001 |
Neg logit contributions | |
issors | -0.001 |
ocus | -0.001 |
similarities | -0.001 |
ets | -0.001 |
seventeen | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
Wolf | +0.014 |
Mo | +0.013 |
rolley | +0.012 |
handed | +0.012 |
hand | +0.012 |
Neg logit contributions | |
issors | -0.026 |
ocus | -0.025 |
draw | -0.025 |
ets | -0.024 |
apes | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
ocus | +0.010 |
issors | +0.010 |
similarities | +0.009 |
seventeen | +0.009 |
ey | +0.009 |
Neg logit contributions | |
handed | -0.010 |
burn | -0.010 |
Wolf | -0.009 |
able | -0.009 |
hand | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -1.22e-01 |
Pos logit contributions | |
ocus | +0.013 |
issors | +0.013 |
similarities | +0.013 |
seventeen | +0.011 |
apes | +0.011 |
Neg logit contributions | |
burn | -0.010 |
handed | -0.009 |
able | -0.009 |
ting | -0.009 |
cub | -0.009 |
Token | He |
Token ID | 1544 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
ocus | +0.005 |
issors | +0.005 |
similarities | +0.005 |
seventeen | +0.005 |
ets | +0.005 |
Neg logit contributions | |
Wolf | -0.003 |
cub | -0.003 |
handed | -0.003 |
burn | -0.003 |
baby | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
issors | +0.009 |
similarities | +0.008 |
ocus | +0.008 |
ets | +0.008 |
seventeen | +0.008 |
Neg logit contributions | |
Wolf | -0.004 |
cub | -0.004 |
handed | -0.004 |
baby | -0.004 |
therm | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -4.73e-01 |
Pos logit contributions | |
issors | +0.015 |
ets | +0.015 |
similarities | +0.015 |
ocus | +0.015 |
apes | +0.014 |
Neg logit contributions | |
Wolf | -0.004 |
baby | -0.004 |
his | -0.004 |
another | -0.004 |
anyway | -0.004 |
Token | " |
Token ID | 366 |
Feature activation | -7.79e-02 |
Pos logit contributions | |
ocus | +0.021 |
issors | +0.021 |
similarities | +0.020 |
ets | +0.019 |
seventeen | +0.019 |
Neg logit contributions | |
handed | -0.012 |
Wolf | -0.012 |
Mo | -0.011 |
cub | -0.011 |
rolley | -0.011 |
Token | Don |
Token ID | 3987 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
similarities | +0.003 |
issors | +0.003 |
ocus | +0.003 |
seventeen | +0.003 |
ets | +0.003 |
Neg logit contributions | |
Wolf | -0.002 |
handed | -0.002 |
cub | -0.002 |
anyway | -0.002 |
able | -0.002 |
Token | 't |
Token ID | 470 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
issors | +0.009 |
ocus | +0.009 |
similarities | +0.009 |
ets | +0.009 |
seventeen | +0.009 |
Neg logit contributions | |
handed | -0.008 |
Wolf | -0.008 |
cub | -0.008 |
seat | -0.008 |
rolley | -0.008 |
Token | worry |
Token ID | 5490 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
Wolf | +0.003 |
handed | +0.003 |
cub | +0.003 |
Mo | +0.003 |
anyway | +0.003 |
Neg logit contributions | |
issors | -0.005 |
ocus | -0.005 |
similarities | -0.005 |
ets | -0.005 |
seventeen | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -4.30e-01 |
Pos logit contributions | |
handed | +0.012 |
rolley | +0.011 |
seat | +0.010 |
eled | +0.010 |
Mo | +0.010 |
Neg logit contributions | |
ocus | -0.014 |
issors | -0.013 |
similarities | -0.013 |
ets | -0.013 |
seventeen | -0.012 |
Token | shield |
Token ID | 7614 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
ocus | +0.005 |
issors | +0.005 |
similarities | +0.005 |
ets | +0.005 |
apes | +0.005 |
Neg logit contributions | |
baby | -0.003 |
Wolf | -0.003 |
cub | -0.003 |
therm | -0.003 |
front | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
Wolf | +0.003 |
handed | +0.003 |
cub | +0.003 |
Mo | +0.003 |
therm | +0.002 |
Neg logit contributions | |
issors | -0.005 |
ocus | -0.005 |
similarities | -0.005 |
ets | -0.005 |
seventeen | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -3.30e-01 |
Pos logit contributions | |
ocus | +0.023 |
similarities | +0.022 |
issors | +0.022 |
ets | +0.022 |
seventeen | +0.021 |
Neg logit contributions | |
handed | -0.017 |
Wolf | -0.016 |
rolley | -0.015 |
hand | -0.015 |
Mo | -0.015 |
Token | scarf |
Token ID | 36953 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
ocus | +0.015 |
issors | +0.014 |
similarities | +0.014 |
ets | +0.014 |
seventeen | +0.013 |
Neg logit contributions | |
Wolf | -0.009 |
baby | -0.009 |
cub | -0.009 |
therm | -0.008 |
handed | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -5.54e-01 |
Pos logit contributions | |
handed | +0.022 |
Wolf | +0.022 |
rolley | +0.020 |
Mo | +0.020 |
seat | +0.019 |
Neg logit contributions | |
ocus | -0.052 |
ets | -0.051 |
issors | -0.050 |
similarities | -0.050 |
seventeen | -0.049 |
Token | making |
Token ID | 1642 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
ocus | +0.024 |
issors | +0.024 |
similarities | +0.024 |
ets | +0.023 |
seventeen | +0.023 |
Neg logit contributions | |
handed | -0.014 |
Wolf | -0.014 |
Mo | -0.012 |
cub | -0.012 |
rolley | -0.012 |
Token | holes |
Token ID | 10421 |
Feature activation | +3.42e-01 |
Pos logit contributions | |
ocus | +0.052 |
similarities | +0.051 |
issors | +0.051 |
ets | +0.050 |
seventeen | +0.049 |
Neg logit contributions | |
handed | -0.025 |
Wolf | -0.025 |
Mo | -0.022 |
cub | -0.022 |
therm | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | -2.68e-01 |
Pos logit contributions | |
Wolf | +0.007 |
handed | +0.007 |
cub | +0.006 |
Mo | +0.006 |
therm | +0.006 |
Neg logit contributions | |
ocus | -0.017 |
issors | -0.017 |
similarities | -0.017 |
ets | -0.016 |
seventeen | -0.016 |
Token | r |
Token ID | 374 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
issors | +0.010 |
ocus | +0.010 |
similarities | +0.010 |
ets | +0.010 |
seventeen | +0.009 |
Neg logit contributions | |
Wolf | -0.008 |
handed | -0.008 |
cub | -0.008 |
baby | -0.008 |
therm | -0.008 |
Token | ips |
Token ID | 2419 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
Wolf | +0.006 |
handed | +0.006 |
cub | +0.006 |
baby | +0.006 |
therm | +0.006 |
Neg logit contributions | |
ocus | -0.005 |
issors | -0.005 |
similarities | -0.005 |
ets | -0.005 |
seventeen | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
handed | +0.005 |
Wolf | +0.005 |
Mo | +0.004 |
rolley | +0.004 |
cub | +0.004 |
Neg logit contributions | |
ocus | -0.014 |
issors | -0.014 |
similarities | -0.013 |
ets | -0.013 |
seventeen | -0.013 |
Token | on |
Token ID | 319 |
Feature activation | +9.07e-02 |
Pos logit contributions | |
Wolf | +0.006 |
handed | +0.006 |
Mo | +0.005 |
cub | +0.005 |
rolley | +0.005 |
Neg logit contributions | |
ocus | -0.009 |
issors | -0.009 |
similarities | -0.008 |
ets | -0.008 |
seventeen | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | +2.90e-01 |
Pos logit contributions | |
handed | +0.002 |
Wolf | +0.002 |
burn | +0.002 |
rolley | +0.002 |
Mo | +0.001 |
Neg logit contributions | |
similarities | -0.004 |
ocus | -0.004 |
issors | -0.004 |
seventeen | -0.004 |
ets | -0.004 |
Token | journey |
Token ID | 7002 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
Wolf | +0.009 |
handed | +0.009 |
Mo | +0.008 |
seat | +0.008 |
rolley | +0.008 |
Neg logit contributions | |
issors | -0.011 |
similarities | -0.011 |
ocus | -0.011 |
ets | -0.010 |
seventeen | -0.010 |
Token | home |
Token ID | 1363 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
issors | +0.030 |
ets | +0.030 |
ocus | +0.030 |
similarities | +0.029 |
seventeen | +0.028 |
Neg logit contributions | |
Wolf | -0.018 |
handed | -0.017 |
Mo | -0.016 |
therm | -0.016 |
burn | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
ocus | +0.031 |
ets | +0.030 |
issors | +0.030 |
similarities | +0.029 |
aces | +0.029 |
Neg logit contributions | |
Wolf | -0.022 |
Mo | -0.021 |
burn | -0.020 |
handed | -0.020 |
therm | -0.019 |
Token | Jack |
Token ID | 3619 |
Feature activation | -9.15e-01 |
Pos logit contributions | |
issors | +0.014 |
ocus | +0.013 |
similarities | +0.013 |
ets | +0.013 |
seventeen | +0.012 |
Neg logit contributions | |
burn | -0.009 |
Wolf | -0.009 |
handed | -0.009 |
therm | -0.009 |
Mo | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | +6.78e-03 |
Pos logit contributions | |
ocus | +0.040 |
ets | +0.039 |
similarities | +0.038 |
issors | +0.038 |
ind | +0.037 |
Neg logit contributions | |
handed | -0.023 |
Wolf | -0.023 |
therm | -0.021 |
burn | -0.021 |
Mo | -0.020 |
Token | so |
Token ID | 523 |
Feature activation | -6.20e-01 |
Pos logit contributions | |
handed | +0.000 |
Wolf | +0.000 |
rolley | +0.000 |
Mo | +0.000 |
hand | +0.000 |
Neg logit contributions | |
ocus | -0.000 |
ind | -0.000 |
seventeen | -0.000 |
similarities | -0.000 |
ets | -0.000 |
Token | excited |
Token ID | 6568 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
ocus | +0.023 |
similarities | +0.022 |
seventeen | +0.021 |
issors | +0.021 |
ind | +0.021 |
Neg logit contributions | |
Wolf | -0.021 |
handed | -0.019 |
burn | -0.019 |
Mo | -0.019 |
therm | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
ocus | +0.018 |
issors | +0.018 |
ets | +0.018 |
similarities | +0.018 |
seventeen | +0.017 |
Neg logit contributions | |
Wolf | -0.009 |
handed | -0.009 |
Mo | -0.008 |
cub | -0.008 |
therm | -0.008 |
Token | show |
Token ID | 905 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
Wolf | +0.007 |
handed | +0.007 |
cub | +0.006 |
Mo | +0.006 |
therm | +0.006 |
Neg logit contributions | |
issors | -0.006 |
ocus | -0.006 |
similarities | -0.006 |
ets | -0.006 |
seventeen | -0.006 |
Token | flew |
Token ID | 13112 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
Wolf | +0.001 |
handed | +0.001 |
cub | +0.001 |
baby | +0.001 |
anyway | +0.001 |
Neg logit contributions | |
issors | -0.003 |
ocus | -0.003 |
similarities | -0.002 |
ets | -0.002 |
seventeen | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
handed | +0.022 |
Wolf | +0.022 |
cub | +0.020 |
therm | +0.019 |
Mo | +0.019 |
Neg logit contributions | |
ocus | -0.048 |
issors | -0.048 |
similarities | -0.047 |
ets | -0.046 |
seventeen | -0.045 |
Token | a |
Token ID | 257 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
Wolf | +0.006 |
handed | +0.005 |
therm | +0.005 |
Mo | +0.005 |
rolley | +0.005 |
Neg logit contributions | |
similarities | -0.010 |
ocus | -0.010 |
issors | -0.010 |
ets | -0.009 |
seventeen | -0.009 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +3.13e-01 |
Pos logit contributions | |
Wolf | +0.018 |
handed | +0.017 |
Mo | +0.017 |
burn | +0.016 |
hand | +0.016 |
Neg logit contributions | |
ocus | -0.021 |
similarities | -0.021 |
issors | -0.020 |
ets | -0.020 |
seventeen | -0.020 |
Token | place |
Token ID | 1295 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
Wolf | +0.009 |
handed | +0.009 |
cub | +0.009 |
Mo | +0.008 |
anyway | +0.008 |
Neg logit contributions | |
issors | -0.012 |
ocus | -0.012 |
similarities | -0.012 |
ets | -0.012 |
seventeen | -0.012 |
Token | far |
Token ID | 1290 |
Feature activation | -6.17e-01 |
Pos logit contributions | |
Wolf | +0.011 |
handed | +0.010 |
Mo | +0.009 |
cub | +0.009 |
therm | +0.009 |
Neg logit contributions | |
ocus | -0.030 |
similarities | -0.029 |
issors | -0.029 |
ets | -0.029 |
ind | -0.028 |
Token | away |
Token ID | 1497 |
Feature activation | +7.30e-01 |
Pos logit contributions | |
ets | +0.027 |
issors | +0.026 |
ocus | +0.026 |
similarities | +0.025 |
ols | +0.024 |
Neg logit contributions | |
Wolf | -0.016 |
handed | -0.015 |
Mo | -0.015 |
cub | -0.014 |
burn | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
Wolf | +0.015 |
burn | +0.014 |
Mo | +0.014 |
therm | +0.014 |
eled | +0.013 |
Neg logit contributions | |
ets | -0.035 |
ocus | -0.034 |
similarities | -0.034 |
nations | -0.033 |
ind | -0.031 |
Token | Jane |
Token ID | 12091 |
Feature activation | +4.33e-02 |
Pos logit contributions | |
ocus | +0.006 |
issors | +0.006 |
similarities | +0.006 |
seventeen | +0.006 |
ets | +0.005 |
Neg logit contributions | |
Wolf | -0.005 |
handed | -0.005 |
baby | -0.005 |
anyway | -0.005 |
cub | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
handed | +0.001 |
Wolf | +0.001 |
Mo | +0.001 |
therm | +0.001 |
cub | +0.001 |
Neg logit contributions | |
ocus | -0.002 |
issors | -0.002 |
similarities | -0.002 |
ets | -0.002 |
seventeen | -0.002 |
Token | Pete |
Token ID | 17542 |
Feature activation | -1.52e-01 |
Pos logit contributions | |
Wolf | +0.008 |
handed | +0.008 |
baby | +0.008 |
cub | +0.008 |
Mo | +0.008 |
Neg logit contributions | |
ocus | -0.015 |
issors | -0.015 |
similarities | -0.015 |
seventeen | -0.015 |
ets | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | +8.29e-01 |
Pos logit contributions | |
similarities | +0.045 |
ocus | +0.044 |
issors | +0.043 |
ets | +0.043 |
aces | +0.042 |
Neg logit contributions | |
Wolf | -0.022 |
handed | -0.021 |
rolley | -0.020 |
hand | -0.020 |
Mo | -0.020 |
Token | time |
Token ID | 640 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Wolf | +0.025 |
anyway | +0.024 |
cub | +0.024 |
handed | +0.024 |
baby | +0.024 |
Neg logit contributions | |
ocus | -0.032 |
issors | -0.032 |
similarities | -0.031 |
seventeen | -0.029 |
meanings | -0.029 |
Token | there |
Token ID | 612 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
issors | +0.060 |
similarities | +0.059 |
ocus | +0.059 |
ets | +0.058 |
seventeen | +0.056 |
Neg logit contributions | |
Wolf | -0.023 |
handed | -0.022 |
cub | -0.020 |
baby | -0.020 |
anyway | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
ocus | +0.010 |
similarities | +0.010 |
does | +0.010 |
ind | +0.009 |
issors | +0.009 |
Neg logit contributions | |
handed | -0.008 |
rolley | -0.008 |
burn | -0.008 |
Wolf | -0.007 |
able | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +3.64e-01 |
Pos logit contributions | |
Wolf | +0.010 |
handed | +0.009 |
baby | +0.009 |
another | +0.008 |
anyway | +0.008 |
Neg logit contributions | |
similarities | -0.060 |
issors | -0.060 |
ocus | -0.060 |
ets | -0.058 |
seventeen | -0.057 |
Token | mouse |
Token ID | 10211 |
Feature activation | -9.05e-01 |
Pos logit contributions | |
Wolf | +0.007 |
handed | +0.007 |
cub | +0.007 |
baby | +0.007 |
Mo | +0.006 |
Neg logit contributions | |
issors | -0.018 |
ocus | -0.018 |
similarities | -0.018 |
ets | -0.017 |
seventeen | -0.017 |
Token | who |
Token ID | 508 |
Feature activation | +3.12e-01 |
Pos logit contributions | |
ocus | +0.035 |
issors | +0.033 |
similarities | +0.033 |
ets | +0.033 |
ind | +0.032 |
Neg logit contributions | |
handed | -0.027 |
hand | -0.026 |
Wolf | -0.025 |
rolley | -0.025 |
seat | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
handed | +0.012 |
Wolf | +0.012 |
hand | +0.011 |
seat | +0.011 |
rolley | +0.011 |
Neg logit contributions | |
similarities | -0.009 |
ocus | -0.009 |
issors | -0.009 |
ets | -0.009 |
ind | -0.008 |
Token | very |
Token ID | 845 |
Feature activation | -6.70e-01 |
Pos logit contributions | |
handed | +0.005 |
hand | +0.004 |
Wolf | +0.004 |
rolley | +0.004 |
seat | +0.004 |
Neg logit contributions | |
ocus | -0.011 |
issors | -0.011 |
similarities | -0.011 |
ets | -0.010 |
ind | -0.010 |
Token | troubled |
Token ID | 17840 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
issors | +0.032 |
ocus | +0.031 |
similarities | +0.031 |
ets | +0.030 |
seventeen | +0.030 |
Neg logit contributions | |
Wolf | -0.015 |
baby | -0.015 |
handed | -0.015 |
cub | -0.014 |
therm | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | +4.72e-01 |
Pos logit contributions | |
handed | +0.003 |
Mo | +0.003 |
rolley | +0.003 |
hand | +0.003 |
eled | +0.003 |
Neg logit contributions | |
ets | -0.005 |
aces | -0.004 |
ocus | -0.004 |
issors | -0.004 |
meanings | -0.004 |
Token | shared |
Token ID | 4888 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
Wolf | +0.003 |
soon | +0.003 |
cub | +0.003 |
baby | +0.003 |
Mo | +0.003 |
Neg logit contributions | |
ocus | -0.006 |
issors | -0.006 |
seventeen | -0.005 |
similarities | -0.005 |
ets | -0.005 |
Token | everything |
Token ID | 2279 |
Feature activation | +7.25e-03 |
Pos logit contributions | |
ocus | +0.053 |
issors | +0.052 |
seventeen | +0.050 |
ets | +0.049 |
similarities | +0.048 |
Neg logit contributions | |
another | -0.011 |
baby | -0.009 |
his | -0.009 |
one | -0.009 |
. | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
handed | +0.000 |
Wolf | +0.000 |
anyway | +0.000 |
cub | +0.000 |
baby | +0.000 |
Neg logit contributions | |
issors | -0.000 |
ocus | -0.000 |
similarities | -0.000 |
seventeen | -0.000 |
ets | -0.000 |
Token | even |
Token ID | 772 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
issors | +0.028 |
ocus | +0.027 |
seventeen | +0.026 |
meanings | +0.025 |
ides | +0.024 |
Neg logit contributions | |
his | -0.008 |
soon | -0.008 |
anyway | -0.008 |
baby | -0.007 |
another | -0.007 |
Token | their |
Token ID | 511 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
issors | +0.059 |
ocus | +0.059 |
similarities | +0.056 |
seventeen | +0.056 |
ets | +0.054 |
Neg logit contributions | |
another | -0.012 |
soon | -0.012 |
anyway | -0.012 |
baby | -0.011 |
his | -0.011 |
Token | sp |
Token ID | 599 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
ocus | +0.007 |
issors | +0.006 |
seventeen | +0.006 |
ets | +0.006 |
ind | +0.006 |
Neg logit contributions | |
baby | -0.004 |
cub | -0.004 |
Wolf | -0.004 |
therm | -0.004 |
another | -0.004 |
Token | oons |
Token ID | 13022 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
similarities | +0.082 |
issors | +0.080 |
ind | +0.079 |
ocus | +0.078 |
seventeen | +0.077 |
Neg logit contributions | |
handed | -0.103 |
rolley | -0.100 |
therm | -0.096 |
Wolf | -0.095 |
anyway | -0.095 |
Token | . |
Token ID | 13 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
ocus | +0.017 |
similarities | +0.017 |
issors | +0.016 |
ets | +0.016 |
seventeen | +0.015 |
Neg logit contributions | |
Wolf | -0.010 |
handed | -0.010 |
Mo | -0.009 |
cub | -0.009 |
therm | -0.009 |
Token | The |
Token ID | 383 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
issors | +0.015 |
ocus | +0.015 |
similarities | +0.015 |
ets | +0.014 |
seventeen | +0.014 |
Neg logit contributions | |
Wolf | -0.005 |
handed | -0.005 |
cub | -0.005 |
Mo | -0.005 |
therm | -0.005 |
Token | end |
Token ID | 886 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
ocus | +0.017 |
issors | +0.017 |
ets | +0.017 |
similarities | +0.016 |
seventeen | +0.016 |
Neg logit contributions | |
Wolf | -0.005 |
baby | -0.005 |
therm | -0.005 |
cub | -0.005 |
handed | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -3.67e-01 |
Pos logit contributions | |
handed | +0.004 |
Wolf | +0.004 |
eled | +0.004 |
Mo | +0.004 |
rolley | +0.004 |
Neg logit contributions | |
ets | -0.013 |
similarities | -0.013 |
ocus | -0.013 |
issors | -0.012 |
apes | -0.012 |
Token | |
Token ID | 220 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
handed | +0.035 |
rolley | +0.033 |
Wolf | +0.033 |
burn | +0.033 |
Mo | +0.031 |
Neg logit contributions | |
issors | -0.043 |
similarities | -0.042 |
ocus | -0.041 |
ind | -0.039 |
apes | -0.039 |
Token |
|
Token ID | 198 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
Wolf | +0.037 |
handed | +0.037 |
burn | +0.037 |
lamb | +0.036 |
hand | +0.036 |
Neg logit contributions | |
issors | -0.069 |
ocus | -0.064 |
similarities | -0.061 |
apes | -0.060 |
ets | -0.059 |
Token |
|
Token ID | 198 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
Wolf | +0.018 |
burn | +0.018 |
handed | +0.018 |
lamb | +0.017 |
cub | +0.017 |
Neg logit contributions | |
issors | -0.031 |
ocus | -0.029 |
similarities | -0.029 |
apes | -0.028 |
ind | -0.027 |
Token | " |
Token ID | 1 |
Feature activation | -2.86e-01 |
Pos logit contributions | |
Wolf | +0.024 |
handed | +0.023 |
cub | +0.022 |
baby | +0.021 |
seat | +0.021 |
Neg logit contributions | |
issors | -0.036 |
ocus | -0.035 |
similarities | -0.035 |
ets | -0.033 |
seventeen | -0.033 |
Token | My |
Token ID | 3666 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
ocus | +0.016 |
ets | +0.016 |
issors | +0.016 |
similarities | +0.015 |
seventeen | +0.015 |
Neg logit contributions | |
handed | -0.005 |
Wolf | -0.004 |
therm | -0.004 |
anyway | -0.004 |
baby | -0.004 |
Token | sp |
Token ID | 599 |
Feature activation | -2.29e+00 |
Pos logit contributions | |
Wolf | +0.018 |
handed | +0.018 |
cub | +0.017 |
baby | +0.017 |
anyway | +0.017 |
Neg logit contributions | |
issors | -0.018 |
ocus | -0.018 |
similarities | -0.017 |
ets | -0.017 |
seventeen | -0.016 |
Token | ade |
Token ID | 671 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
similarities | +0.092 |
ind | +0.088 |
seventeen | +0.085 |
la | +0.085 |
culture | +0.079 |
Neg logit contributions | |
us | -0.066 |
handed | -0.065 |
rolley | -0.064 |
anyway | -0.062 |
therm | -0.062 |
Token | is |
Token ID | 318 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
handed | +0.010 |
Wolf | +0.010 |
therm | +0.010 |
anyway | +0.010 |
baby | +0.010 |
Neg logit contributions | |
similarities | -0.011 |
issors | -0.011 |
ocus | -0.011 |
seventeen | -0.010 |
ets | -0.010 |
Token | broken |
Token ID | 5445 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
Wolf | +0.004 |
handed | +0.004 |
anyway | +0.004 |
therm | +0.004 |
cub | +0.004 |
Neg logit contributions | |
ocus | -0.006 |
issors | -0.006 |
similarities | -0.006 |
ets | -0.006 |
seventeen | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | -8.63e-02 |
Pos logit contributions | |
handed | +0.021 |
Wolf | +0.021 |
Mo | +0.020 |
hand | +0.019 |
cub | +0.019 |
Neg logit contributions | |
issors | -0.037 |
ocus | -0.036 |
ets | -0.035 |
similarities | -0.035 |
seventeen | -0.034 |
Token | Mom |
Token ID | 11254 |
Feature activation | +3.58e-03 |
Pos logit contributions | |
ocus | +0.005 |
issors | +0.005 |
ets | +0.005 |
similarities | +0.004 |
seventeen | +0.004 |
Neg logit contributions | |
baby | -0.002 |
Wolf | -0.002 |
his | -0.002 |
anyway | -0.002 |
therm | -0.002 |
Token | cal |
Token ID | 2386 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Wolf | +0.004 |
handed | +0.004 |
Mo | +0.004 |
cub | +0.003 |
hand | +0.003 |
Neg logit contributions | |
ocus | -0.015 |
ets | -0.015 |
similarities | -0.015 |
issors | -0.015 |
seventeen | -0.015 |
Token | mer |
Token ID | 647 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
Wolf | +0.037 |
handed | +0.037 |
Mo | +0.035 |
cub | +0.035 |
therm | +0.034 |
Neg logit contributions | |
ocus | -0.037 |
issors | -0.037 |
similarities | -0.036 |
ets | -0.035 |
seventeen | -0.034 |
Token | ." |
Token ID | 526 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
issors | +0.092 |
ocus | +0.092 |
similarities | +0.090 |
ets | +0.090 |
seventeen | +0.086 |
Neg logit contributions | |
Wolf | -0.039 |
handed | -0.038 |
Mo | -0.036 |
therm | -0.035 |
cub | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
Wolf | +0.006 |
handed | +0.006 |
cub | +0.006 |
Mo | +0.006 |
anyway | +0.005 |
Neg logit contributions | |
issors | -0.010 |
ocus | -0.010 |
similarities | -0.010 |
ets | -0.009 |
seventeen | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +4.48e-01 |
Pos logit contributions | |
handed | +0.002 |
burn | +0.002 |
Wolf | +0.002 |
rolley | +0.002 |
therm | +0.002 |
Neg logit contributions | |
ocus | -0.005 |
similarities | -0.005 |
issors | -0.005 |
ets | -0.005 |
seventeen | -0.005 |
Token | P |
Token ID | 47 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Wolf | +0.010 |
handed | +0.010 |
cub | +0.009 |
baby | +0.009 |
therm | +0.009 |
Neg logit contributions | |
ocus | -0.021 |
issors | -0.021 |
similarities | -0.021 |
ets | -0.020 |
seventeen | -0.020 |
Token | aco |
Token ID | 10602 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
issors | +0.078 |
ocus | +0.078 |
similarities | +0.077 |
ets | +0.073 |
seventeen | +0.072 |
Neg logit contributions | |
Wolf | -0.083 |
handed | -0.082 |
cub | -0.078 |
Mo | -0.077 |
anyway | -0.076 |
Token | and |
Token ID | 290 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
ocus | +0.018 |
issors | +0.018 |
similarities | +0.017 |
ets | +0.017 |
seventeen | +0.017 |
Neg logit contributions | |
Wolf | -0.010 |
handed | -0.010 |
Mo | -0.009 |
cub | -0.009 |
therm | -0.009 |
Token | Felix |
Token ID | 29721 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
similarities | +0.006 |
issors | +0.006 |
ocus | +0.006 |
ind | +0.005 |
meanings | +0.005 |
Neg logit contributions | |
handed | -0.004 |
rolley | -0.004 |
anyways | -0.004 |
able | -0.004 |
hand | -0.004 |
Token | ate |
Token ID | 15063 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
Wolf | +0.033 |
handed | +0.033 |
Mo | +0.030 |
cub | +0.030 |
therm | +0.030 |
Neg logit contributions | |
issors | -0.046 |
ocus | -0.046 |
similarities | -0.046 |
ets | -0.044 |
seventeen | -0.043 |
Token | their |
Token ID | 511 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
handed | +0.002 |
Wolf | +0.002 |
Mo | +0.002 |
rolley | +0.002 |
seat | +0.002 |
Neg logit contributions | |
similarities | -0.004 |
issors | -0.004 |
ocus | -0.004 |
seventeen | -0.004 |
ets | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
issors | +0.043 |
similarities | +0.042 |
ocus | +0.042 |
ets | +0.040 |
seventeen | +0.039 |
Neg logit contributions | |
another | -0.009 |
one | -0.008 |
cub | -0.008 |
Wolf | -0.008 |
baby | -0.008 |
Token | puzzle |
Token ID | 15027 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
issors | +0.033 |
ets | +0.032 |
ocus | +0.032 |
similarities | +0.032 |
apes | +0.030 |
Neg logit contributions | |
baby | -0.023 |
cub | -0.022 |
therm | -0.022 |
Wolf | -0.022 |
bear | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -9.14e-01 |
Pos logit contributions | |
similarities | +0.045 |
issors | +0.044 |
ocus | +0.043 |
seventeen | +0.041 |
ets | +0.041 |
Neg logit contributions | |
. | -0.017 |
handed | -0.017 |
cub | -0.016 |
Wolf | -0.016 |
one | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
issors | +0.052 |
similarities | +0.050 |
ocus | +0.049 |
ets | +0.048 |
apes | +0.046 |
Neg logit contributions | |
one | -0.015 |
another | -0.015 |
his | -0.013 |
baby | -0.013 |
cub | -0.013 |
Token | cr |
Token ID | 1067 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
issors | +0.032 |
ocus | +0.031 |
ets | +0.031 |
similarities | +0.030 |
apes | +0.028 |
Neg logit contributions | |
baby | -0.024 |
cub | -0.023 |
therm | -0.023 |
Wolf | -0.023 |
bear | -0.022 |
Token | ay |
Token ID | 323 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
similarities | +0.046 |
issors | +0.038 |
narrative | +0.037 |
ocus | +0.037 |
culture | +0.036 |
Neg logit contributions | |
Wolf | -0.058 |
seat | -0.057 |
! | -0.057 |
therm | -0.057 |
front | -0.056 |
Token | on |
Token ID | 261 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
similarities | +0.121 |
issors | +0.118 |
ocus | +0.115 |
ets | +0.111 |
seventeen | +0.109 |
Neg logit contributions | |
Wolf | -0.068 |
handed | -0.066 |
therm | -0.065 |
baby | -0.064 |
cub | -0.064 |
Token | , |
Token ID | 11 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
similarities | +0.064 |
issors | +0.063 |
ocus | +0.062 |
seventeen | +0.060 |
ets | +0.059 |
Neg logit contributions | |
Wolf | -0.022 |
handed | -0.022 |
cub | -0.021 |
baby | -0.020 |
anyway | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -8.27e-01 |
Pos logit contributions | |
issors | +0.048 |
similarities | +0.047 |
ocus | +0.046 |
ets | +0.044 |
narrative | +0.043 |
Neg logit contributions | |
one | -0.013 |
another | -0.013 |
. | -0.011 |
his | -0.011 |
soon | -0.011 |
Token | dinosaur |
Token ID | 28257 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
issors | +0.033 |
ocus | +0.032 |
ets | +0.032 |
similarities | +0.032 |
apes | +0.029 |
Neg logit contributions | |
baby | -0.027 |
cub | -0.026 |
therm | -0.025 |
Wolf | -0.025 |
bear | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
similarities | +0.056 |
issors | +0.056 |
ocus | +0.054 |
seventeen | +0.052 |
ets | +0.052 |
Neg logit contributions | |
Wolf | -0.021 |
cub | -0.020 |
baby | -0.020 |
handed | -0.020 |
. | -0.020 |
Token | me |
Token ID | 502 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
similarities | +0.028 |
ocus | +0.027 |
issors | +0.027 |
ets | +0.026 |
ind | +0.025 |
Neg logit contributions | |
handed | -0.021 |
Wolf | -0.020 |
rolley | -0.019 |
seat | -0.019 |
Mo | -0.019 |
Token | ." |
Token ID | 526 |
Feature activation | -4.09e-01 |
Pos logit contributions | |
ocus | +0.107 |
ets | +0.107 |
similarities | +0.106 |
issors | +0.102 |
ind | +0.097 |
Neg logit contributions | |
handed | -0.048 |
Wolf | -0.048 |
Mo | -0.044 |
therm | -0.043 |
rolley | -0.043 |
Token | The |
Token ID | 383 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
ocus | +0.020 |
issors | +0.020 |
similarities | +0.020 |
ets | +0.019 |
seventeen | +0.019 |
Neg logit contributions | |
handed | -0.008 |
Wolf | -0.008 |
cub | -0.007 |
Mo | -0.007 |
therm | -0.007 |
Token | cricket |
Token ID | 18836 |
Feature activation | -8.23e-01 |
Pos logit contributions | |
issors | +0.012 |
ocus | +0.012 |
similarities | +0.012 |
ets | +0.011 |
seventeen | +0.011 |
Neg logit contributions | |
handed | -0.014 |
Wolf | -0.014 |
Mo | -0.013 |
cub | -0.013 |
hand | -0.013 |
Token | ch |
Token ID | 442 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
ocus | +0.033 |
similarities | +0.033 |
issors | +0.033 |
ets | +0.032 |
seventeen | +0.031 |
Neg logit contributions | |
handed | -0.023 |
Wolf | -0.023 |
Mo | -0.021 |
therm | -0.021 |
cub | -0.021 |
Token | ir |
Token ID | 343 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
similarities | +0.058 |
issors | +0.058 |
seventeen | +0.056 |
ocus | +0.054 |
ets | +0.053 |
Neg logit contributions | |
Wolf | -0.064 |
handed | -0.063 |
eled | -0.063 |
Mo | -0.062 |
baby | -0.062 |
Token | ped |
Token ID | 9124 |
Feature activation | -4.76e-01 |
Pos logit contributions | |
ocus | +0.099 |
issors | +0.099 |
similarities | +0.098 |
ets | +0.094 |
seventeen | +0.093 |
Neg logit contributions | |
Wolf | -0.069 |
handed | -0.069 |
cub | -0.064 |
Mo | -0.063 |
therm | -0.063 |
Token | and |
Token ID | 290 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
similarities | +0.020 |
ocus | +0.019 |
ets | +0.019 |
issors | +0.019 |
ind | +0.019 |
Neg logit contributions | |
handed | -0.013 |
Wolf | -0.012 |
rolley | -0.012 |
Mo | -0.012 |
therm | -0.012 |
Token | waved |
Token ID | 26834 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
similarities | +0.018 |
ocus | +0.018 |
ind | +0.017 |
issors | +0.017 |
ets | +0.017 |
Neg logit contributions | |
handed | -0.014 |
Wolf | -0.013 |
rolley | -0.013 |
hand | -0.012 |
seat | -0.012 |
Token | back |
Token ID | 736 |
Feature activation | +4.23e-02 |
Pos logit contributions | |
handed | +0.003 |
Wolf | +0.003 |
Mo | +0.003 |
therm | +0.003 |
cub | +0.003 |
Neg logit contributions | |
similarities | -0.004 |
ocus | -0.004 |
issors | -0.004 |
ets | -0.004 |
seventeen | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -5.95e-01 |
Pos logit contributions | |
handed | +0.001 |
Wolf | +0.001 |
rolley | +0.001 |
Mo | +0.001 |
Son | +0.001 |
Neg logit contributions | |
ocus | -0.002 |
similarities | -0.002 |
ets | -0.002 |
issors | -0.002 |
ind | -0.002 |