Token | there |
Token ID | 612 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
gust | +0.002 |
epad | +0.002 |
ago | +0.002 |
ents | +0.002 |
joy | +0.002 |
Neg logit contributions | |
P | -0.001 |
me | -0.001 |
bo | -0.001 |
Mom | -0.001 |
Mo | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -8.16e-03 |
Pos logit contributions | |
P | +0.010 |
bo | +0.007 |
Mo | +0.006 |
na | +0.006 |
me | +0.006 |
Neg logit contributions | |
gust | -0.032 |
ago | -0.032 |
joy | -0.029 |
epad | -0.029 |
ents | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
gust | +0.000 |
ago | +0.000 |
epad | +0.000 |
ents | +0.000 |
joy | +0.000 |
Neg logit contributions | |
P | -0.000 |
me | -0.000 |
Mom | -0.000 |
bo | -0.000 |
M | -0.000 |
Token | do |
Token ID | 466 |
Feature activation | +5.45e-01 |
Pos logit contributions | |
P | +0.004 |
bo | +0.004 |
me | +0.004 |
Mom | +0.003 |
Mo | +0.003 |
Neg logit contributions | |
gust | -0.007 |
ago | -0.007 |
epad | -0.007 |
joy | -0.006 |
ents | -0.006 |
Token | od |
Token ID | 375 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
P | +0.013 |
Mom | +0.012 |
me | +0.012 |
bo | +0.012 |
yourself | +0.011 |
Neg logit contributions | |
gust | -0.029 |
ago | -0.027 |
epad | -0.025 |
joy | -0.025 |
ents | -0.024 |
Token | le |
Token ID | 293 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
P | +0.006 |
bo | +0.005 |
me | +0.005 |
Mom | +0.005 |
Mo | +0.005 |
Neg logit contributions | |
gust | -0.009 |
ago | -0.009 |
epad | -0.009 |
joy | -0.008 |
ents | -0.008 |
Token | who |
Token ID | 508 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
P | +0.119 |
bo | +0.109 |
Mom | +0.109 |
inct | +0.107 |
Hey | +0.106 |
Neg logit contributions | |
ago | -0.151 |
gust | -0.151 |
epad | -0.137 |
ents | -0.130 |
pieces | -0.130 |
Token | wanted |
Token ID | 2227 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
P | +0.007 |
inct | +0.006 |
omi | +0.006 |
Mom | +0.006 |
me | +0.006 |
Neg logit contributions | |
ago | -0.008 |
gust | -0.008 |
epad | -0.008 |
ents | -0.007 |
joy | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
gust | +0.019 |
ago | +0.019 |
epad | +0.018 |
joy | +0.017 |
ents | +0.017 |
Neg logit contributions | |
P | -0.013 |
me | -0.012 |
bo | -0.012 |
Mom | -0.011 |
Mo | -0.011 |
Token | make |
Token ID | 787 |
Feature activation | +6.71e-01 |
Pos logit contributions | |
gust | +0.018 |
epad | +0.017 |
ago | +0.017 |
ents | +0.016 |
pieces | +0.015 |
Neg logit contributions | |
P | -0.017 |
bo | -0.015 |
Mo | -0.015 |
inct | -0.015 |
sy | -0.015 |
Token | something |
Token ID | 1223 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
P | +0.019 |
me | +0.016 |
bo | +0.016 |
Mom | +0.016 |
Mo | +0.015 |
Neg logit contributions | |
gust | -0.034 |
ago | -0.033 |
epad | -0.033 |
joy | -0.031 |
ents | -0.031 |
Token | little |
Token ID | 1310 |
Feature activation | +8.82e-02 |
Pos logit contributions | |
P | +0.007 |
bo | +0.006 |
me | +0.006 |
Mom | +0.006 |
Mo | +0.006 |
Neg logit contributions | |
gust | -0.013 |
ago | -0.013 |
epad | -0.012 |
joy | -0.012 |
ents | -0.012 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
P | +0.003 |
bo | +0.002 |
me | +0.002 |
inct | +0.002 |
Mo | +0.002 |
Neg logit contributions | |
gust | -0.004 |
ago | -0.004 |
epad | -0.004 |
joy | -0.004 |
ents | -0.004 |
Token | named |
Token ID | 3706 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
gust | +0.012 |
ago | +0.012 |
epad | +0.012 |
ents | +0.011 |
joy | +0.011 |
Neg logit contributions | |
P | -0.006 |
me | -0.005 |
bo | -0.005 |
Mom | -0.005 |
Mo | -0.005 |
Token | Ann |
Token ID | 5506 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
gust | +0.063 |
epad | +0.062 |
joy | +0.060 |
ago | +0.059 |
accomplishment | +0.056 |
Neg logit contributions | |
me | -0.040 |
P | -0.035 |
Mom | -0.035 |
bo | -0.031 |
M | -0.031 |
Token | abel |
Token ID | 9608 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
P | +0.002 |
me | +0.001 |
bo | +0.001 |
Mom | +0.001 |
Mo | +0.001 |
Neg logit contributions | |
gust | -0.003 |
ago | -0.003 |
epad | -0.003 |
joy | -0.002 |
ents | -0.002 |
Token | le |
Token ID | 293 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
P | +0.017 |
bo | +0.015 |
me | +0.015 |
Mom | +0.014 |
ey | +0.014 |
Neg logit contributions | |
gust | -0.032 |
ago | -0.031 |
epad | -0.031 |
joy | -0.029 |
ents | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -2.52e-01 |
Pos logit contributions | |
P | +0.115 |
bo | +0.099 |
me | +0.098 |
Mom | +0.096 |
Mo | +0.096 |
Neg logit contributions | |
gust | -0.165 |
ago | -0.162 |
epad | -0.152 |
ents | -0.147 |
joy | -0.144 |
Token | She |
Token ID | 1375 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
gust | +0.013 |
ago | +0.013 |
epad | +0.013 |
joy | +0.012 |
pieces | +0.012 |
Neg logit contributions | |
P | -0.006 |
me | -0.006 |
bo | -0.006 |
Mom | -0.006 |
Mo | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
gust | +0.009 |
ago | +0.008 |
epad | +0.007 |
ents | +0.007 |
joy | +0.006 |
Neg logit contributions | |
inct | -0.009 |
P | -0.008 |
ey | -0.008 |
han | -0.008 |
yourself | -0.008 |
Token | very |
Token ID | 845 |
Feature activation | +8.81e-01 |
Pos logit contributions | |
P | +0.003 |
bo | +0.002 |
me | +0.002 |
Mom | +0.002 |
Mo | +0.002 |
Neg logit contributions | |
gust | -0.005 |
ago | -0.005 |
epad | -0.005 |
ents | -0.005 |
joy | -0.005 |
Token | obedient |
Token ID | 41652 |
Feature activation | +9.16e-01 |
Pos logit contributions | |
P | +0.034 |
bo | +0.031 |
me | +0.031 |
Mom | +0.030 |
Mo | +0.030 |
Neg logit contributions | |
gust | -0.035 |
ago | -0.034 |
epad | -0.032 |
ents | -0.030 |
joy | -0.030 |
Token | out |
Token ID | 503 |
Feature activation | -1.84e-01 |
Pos logit contributions | |
ago | +0.014 |
ents | +0.012 |
gust | +0.011 |
epad | +0.011 |
theirs | +0.011 |
Neg logit contributions | |
P | -0.015 |
omi | -0.012 |
scar | -0.012 |
Marcus | -0.012 |
na | -0.012 |
Token | , |
Token ID | 11 |
Feature activation | -6.10e-02 |
Pos logit contributions | |
ago | +0.009 |
gust | +0.009 |
epad | +0.008 |
ents | +0.008 |
joy | +0.008 |
Neg logit contributions | |
P | -0.006 |
bo | -0.005 |
Mom | -0.005 |
Mo | -0.005 |
na | -0.005 |
Token | you |
Token ID | 345 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
ago | +0.003 |
gust | +0.003 |
ents | +0.002 |
epad | +0.002 |
joy | +0.002 |
Neg logit contributions | |
P | -0.002 |
bo | -0.002 |
Mo | -0.002 |
na | -0.002 |
inct | -0.002 |
Token | little |
Token ID | 1310 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
ago | +0.008 |
gust | +0.008 |
epad | +0.007 |
ents | +0.007 |
joy | +0.007 |
Neg logit contributions | |
P | -0.006 |
Mom | -0.005 |
bo | -0.005 |
Mo | -0.005 |
omi | -0.005 |
Token | r |
Token ID | 374 |
Feature activation | -5.57e-01 |
Pos logit contributions | |
gust | +0.011 |
ago | +0.011 |
epad | +0.011 |
ents | +0.010 |
joy | +0.010 |
Neg logit contributions | |
P | -0.008 |
me | -0.008 |
bo | -0.008 |
Mom | -0.007 |
ey | -0.007 |
Token | asc |
Token ID | 3372 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
ago | +0.023 |
ents | +0.021 |
gust | +0.021 |
joy | +0.020 |
epad | +0.020 |
Neg logit contributions | |
P | -0.019 |
me | -0.019 |
na | -0.018 |
Mom | -0.018 |
Mouse | -0.017 |
Token | als |
Token ID | 874 |
Feature activation | +5.47e-02 |
Pos logit contributions | |
P | +0.164 |
Mom | +0.153 |
bo | +0.149 |
But | +0.143 |
Mo | +0.142 |
Neg logit contributions | |
gust | -0.125 |
ago | -0.121 |
joy | -0.109 |
ents | -0.107 |
epad | -0.098 |
Token | ," |
Token ID | 553 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
P | +0.002 |
bo | +0.001 |
Mom | +0.001 |
Mo | +0.001 |
na | +0.001 |
Neg logit contributions | |
ago | -0.003 |
gust | -0.003 |
ents | -0.003 |
epad | -0.002 |
joy | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
P | +0.014 |
bo | +0.013 |
Mo | +0.012 |
me | +0.012 |
sy | +0.012 |
Neg logit contributions | |
gust | -0.014 |
ago | -0.013 |
epad | -0.012 |
ents | -0.012 |
joy | -0.012 |
Token | driver |
Token ID | 4639 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
P | +0.005 |
bo | +0.004 |
Mo | +0.004 |
na | +0.004 |
ey | +0.004 |
Neg logit contributions | |
gust | -0.009 |
ago | -0.009 |
epad | -0.009 |
joy | -0.008 |
ents | -0.008 |
Token | said |
Token ID | 531 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
P | +0.005 |
me | +0.004 |
Mom | +0.004 |
Mo | +0.004 |
bo | +0.004 |
Neg logit contributions | |
gust | -0.009 |
ago | -0.009 |
epad | -0.008 |
ents | -0.008 |
joy | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
P | +0.017 |
bo | +0.015 |
Mo | +0.014 |
ey | +0.014 |
me | +0.014 |
Neg logit contributions | |
gust | -0.027 |
ago | -0.026 |
epad | -0.025 |
joy | -0.024 |
ents | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
ago | +0.017 |
gust | +0.016 |
epad | +0.015 |
ents | +0.015 |
joy | +0.015 |
Neg logit contributions | |
P | -0.012 |
bo | -0.010 |
ey | -0.010 |
na | -0.010 |
sy | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +3.02e-01 |
Pos logit contributions | |
P | +0.006 |
bo | +0.006 |
na | +0.005 |
ey | +0.005 |
me | +0.005 |
Neg logit contributions | |
ago | -0.016 |
gust | -0.016 |
epad | -0.014 |
ents | -0.014 |
joy | -0.014 |
Token | Ann |
Token ID | 18858 |
Feature activation | +7.86e-01 |
Pos logit contributions | |
bo | +0.007 |
fl | +0.007 |
an | +0.007 |
inct | +0.007 |
na | +0.007 |
Neg logit contributions | |
ago | -0.015 |
gust | -0.014 |
ents | -0.014 |
epad | -0.013 |
joy | -0.013 |
Token | abel |
Token ID | 9608 |
Feature activation | +8.01e-01 |
Pos logit contributions | |
P | +0.026 |
Mom | +0.022 |
Mo | +0.022 |
bo | +0.021 |
Mouse | +0.021 |
Neg logit contributions | |
gust | -0.036 |
ago | -0.036 |
ents | -0.033 |
epad | -0.033 |
joy | -0.032 |
Token | le |
Token ID | 293 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
P | +0.025 |
Mom | +0.023 |
Mo | +0.022 |
bo | +0.020 |
Mouse | +0.020 |
Neg logit contributions | |
gust | -0.038 |
ago | -0.037 |
ents | -0.033 |
epad | -0.033 |
joy | -0.032 |
Token | 's |
Token ID | 338 |
Feature activation | -7.35e-01 |
Pos logit contributions | |
P | +0.108 |
Mom | +0.093 |
Mo | +0.089 |
bo | +0.085 |
Mouse | +0.081 |
Neg logit contributions | |
gust | -0.176 |
ago | -0.175 |
ents | -0.161 |
epad | -0.154 |
joy | -0.150 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.65e-01 |
Pos logit contributions | |
gust | +0.034 |
ago | +0.032 |
epad | +0.032 |
joy | +0.030 |
ents | +0.030 |
Neg logit contributions | |
P | -0.024 |
bo | -0.022 |
me | -0.022 |
Mom | -0.021 |
Mo | -0.020 |
Token | carefully |
Token ID | 7773 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
P | +0.008 |
Mom | +0.007 |
Mo | +0.007 |
bo | +0.007 |
inct | +0.006 |
Neg logit contributions | |
ago | -0.013 |
gust | -0.013 |
epad | -0.012 |
ents | -0.012 |
joy | -0.011 |
Token | unp |
Token ID | 8593 |
Feature activation | +7.81e-01 |
Pos logit contributions | |
P | +0.043 |
bo | +0.037 |
Mom | +0.037 |
me | +0.036 |
Mo | +0.036 |
Neg logit contributions | |
gust | -0.066 |
ago | -0.065 |
epad | -0.064 |
ents | -0.060 |
joy | -0.059 |
Token | acked |
Token ID | 6021 |
Feature activation | +2.92e+00 |
Pos logit contributions | |
P | +0.025 |
Mom | +0.023 |
me | +0.023 |
Mo | +0.022 |
bo | +0.022 |
Neg logit contributions | |
ago | -0.034 |
gust | -0.033 |
epad | -0.033 |
ents | -0.032 |
joy | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +6.83e-02 |
Pos logit contributions | |
P | +0.015 |
bo | +0.013 |
Mom | +0.013 |
me | +0.013 |
Mo | +0.013 |
Neg logit contributions | |
gust | -0.035 |
ago | -0.034 |
epad | -0.033 |
joy | -0.031 |
ents | -0.031 |
Token | |
Token ID | 220 |
Feature activation | -8.03e-01 |
Pos logit contributions | |
P | +0.002 |
bo | +0.002 |
na | +0.002 |
ey | +0.002 |
Mo | +0.002 |
Neg logit contributions | |
ago | -0.003 |
gust | -0.003 |
epad | -0.003 |
ents | -0.003 |
joy | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
ago | +0.045 |
gust | +0.045 |
epad | +0.043 |
ents | +0.042 |
joy | +0.041 |
Neg logit contributions | |
P | -0.017 |
bo | -0.014 |
me | -0.014 |
na | -0.013 |
Mo | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
P | +0.007 |
bo | +0.006 |
me | +0.006 |
na | +0.006 |
ey | +0.006 |
Neg logit contributions | |
gust | -0.020 |
ago | -0.020 |
epad | -0.019 |
ents | -0.019 |
joy | -0.019 |
Token | Bel |
Token ID | 12193 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
bo | +0.010 |
P | +0.009 |
an | +0.009 |
ey | +0.009 |
inct | +0.009 |
Neg logit contributions | |
ago | -0.018 |
gust | -0.018 |
epad | -0.017 |
ents | -0.017 |
pieces | -0.017 |
Token | le |
Token ID | 293 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
P | +0.039 |
me | +0.036 |
bo | +0.035 |
ey | +0.033 |
na | +0.033 |
Neg logit contributions | |
gust | -0.063 |
ago | -0.060 |
epad | -0.059 |
joy | -0.058 |
ents | -0.055 |
Token | was |
Token ID | 373 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
P | +0.093 |
Mom | +0.079 |
Mo | +0.077 |
bo | +0.071 |
yourself | +0.070 |
Neg logit contributions | |
ago | -0.187 |
gust | -0.183 |
ents | -0.170 |
epad | -0.157 |
pieces | -0.157 |
Token | proud |
Token ID | 6613 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
P | +0.005 |
bo | +0.005 |
me | +0.005 |
Mom | +0.005 |
Mo | +0.005 |
Neg logit contributions | |
gust | -0.008 |
ago | -0.007 |
epad | -0.007 |
joy | -0.007 |
ents | -0.007 |
Token | of |
Token ID | 286 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
gust | +0.009 |
ago | +0.009 |
epad | +0.008 |
ents | +0.008 |
joy | +0.008 |
Neg logit contributions | |
P | -0.010 |
bo | -0.010 |
me | -0.009 |
Mom | -0.009 |
Mo | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
gust | +0.024 |
ago | +0.023 |
epad | +0.023 |
ents | +0.021 |
joy | +0.021 |
Neg logit contributions | |
P | -0.015 |
me | -0.014 |
bo | -0.013 |
Mom | -0.013 |
Mo | -0.013 |
Token | achievement |
Token ID | 13293 |
Feature activation | -5.55e-01 |
Pos logit contributions | |
gust | +0.009 |
ago | +0.008 |
epad | +0.008 |
ents | +0.008 |
joy | +0.008 |
Neg logit contributions | |
P | -0.006 |
me | -0.005 |
bo | -0.005 |
Mom | -0.005 |
na | -0.005 |
Token | game |
Token ID | 983 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
P | +0.001 |
bo | +0.001 |
Mom | +0.001 |
me | +0.001 |
Mo | +0.001 |
Neg logit contributions | |
gust | -0.001 |
epad | -0.001 |
ago | -0.001 |
ents | -0.001 |
joy | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
P | +0.030 |
bo | +0.027 |
Mo | +0.027 |
inct | +0.026 |
Mom | +0.026 |
Neg logit contributions | |
ago | -0.042 |
gust | -0.040 |
epad | -0.039 |
ents | -0.037 |
pieces | -0.035 |
Token | me |
Token ID | 502 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
P | +0.008 |
bo | +0.007 |
na | +0.007 |
inct | +0.007 |
Mo | +0.006 |
Neg logit contributions | |
ago | -0.013 |
gust | -0.013 |
epad | -0.012 |
ents | -0.012 |
joy | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
P | +0.041 |
Mom | +0.036 |
bo | +0.034 |
Mo | +0.034 |
Hey | +0.033 |
Neg logit contributions | |
ago | -0.068 |
epad | -0.064 |
gust | -0.064 |
ents | -0.062 |
joy | -0.059 |
Token | El |
Token ID | 2574 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
ago | +0.010 |
ents | +0.009 |
gust | +0.009 |
epad | +0.009 |
pieces | +0.008 |
Neg logit contributions | |
P | -0.012 |
an | -0.010 |
sy | -0.010 |
omi | -0.010 |
bo | -0.010 |
Token | le |
Token ID | 293 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
P | +0.062 |
Mom | +0.057 |
me | +0.055 |
bo | +0.054 |
Mo | +0.053 |
Neg logit contributions | |
gust | -0.096 |
ago | -0.095 |
epad | -0.089 |
joy | -0.087 |
ents | -0.085 |
Token | was |
Token ID | 373 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
P | +0.107 |
Mom | +0.098 |
Mo | +0.094 |
Mouse | +0.086 |
Ang | +0.084 |
Neg logit contributions | |
ago | -0.180 |
gust | -0.168 |
ents | -0.155 |
epad | -0.152 |
pieces | -0.147 |
Token | very |
Token ID | 845 |
Feature activation | +8.03e-01 |
Pos logit contributions | |
P | +0.004 |
bo | +0.003 |
Mom | +0.003 |
me | +0.003 |
Mo | +0.003 |
Neg logit contributions | |
gust | -0.006 |
ago | -0.006 |
epad | -0.005 |
joy | -0.005 |
ents | -0.005 |
Token | excited |
Token ID | 6568 |
Feature activation | -3.82e-01 |
Pos logit contributions | |
P | +0.033 |
bo | +0.030 |
Mom | +0.029 |
Mo | +0.029 |
me | +0.029 |
Neg logit contributions | |
gust | -0.031 |
ago | -0.030 |
epad | -0.028 |
joy | -0.026 |
ents | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | -4.62e-01 |
Pos logit contributions | |
ago | +0.017 |
gust | +0.017 |
epad | +0.016 |
ents | +0.016 |
joy | +0.015 |
Neg logit contributions | |
P | -0.013 |
Mom | -0.012 |
bo | -0.011 |
Mouse | -0.011 |
Mo | -0.011 |
Token | hear |
Token ID | 3285 |
Feature activation | +4.46e-01 |
Pos logit contributions | |
gust | +0.018 |
ago | +0.018 |
epad | +0.018 |
pieces | +0.016 |
accomplishment | +0.016 |
Neg logit contributions | |
P | -0.019 |
bo | -0.016 |
inct | -0.016 |
Mom | -0.016 |
M | -0.016 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
gust | +0.006 |
ago | +0.005 |
epad | +0.005 |
joy | +0.005 |
ents | +0.005 |
Neg logit contributions | |
P | -0.003 |
bo | -0.003 |
inct | -0.003 |
me | -0.003 |
Mom | -0.003 |
Token | named |
Token ID | 3706 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
gust | +0.016 |
ago | +0.016 |
epad | +0.015 |
ents | +0.015 |
joy | +0.014 |
Neg logit contributions | |
P | -0.009 |
me | -0.007 |
bo | -0.007 |
Mo | -0.007 |
Mom | -0.007 |
Token | A |
Token ID | 317 |
Feature activation | -6.12e-02 |
Pos logit contributions | |
gust | +0.078 |
epad | +0.077 |
joy | +0.074 |
ago | +0.074 |
accomplishment | +0.070 |
Neg logit contributions | |
me | -0.050 |
P | -0.046 |
Mom | -0.044 |
M | -0.040 |
bo | -0.039 |
Token | ire |
Token ID | 557 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
gust | +0.003 |
ago | +0.003 |
epad | +0.003 |
joy | +0.003 |
ents | +0.003 |
Neg logit contributions | |
P | -0.002 |
bo | -0.002 |
me | -0.002 |
Mom | -0.001 |
ey | -0.001 |
Token | l |
Token ID | 75 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
ago | +0.010 |
gust | +0.010 |
epad | +0.009 |
ents | +0.009 |
pieces | +0.009 |
Neg logit contributions | |
P | -0.008 |
me | -0.007 |
Mom | -0.007 |
bo | -0.007 |
Mo | -0.007 |
Token | le |
Token ID | 293 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
P | +0.016 |
me | +0.015 |
bo | +0.014 |
Mom | +0.014 |
Mo | +0.013 |
Neg logit contributions | |
gust | -0.026 |
ago | -0.026 |
epad | -0.025 |
ents | -0.024 |
joy | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -3.25e-01 |
Pos logit contributions | |
P | +0.119 |
inct | +0.108 |
yourself | +0.108 |
bo | +0.107 |
me | +0.106 |
Neg logit contributions | |
ago | -0.150 |
gust | -0.146 |
epad | -0.126 |
joy | -0.121 |
ents | -0.120 |
Token | She |
Token ID | 1375 |
Feature activation | -1.43e-01 |
Pos logit contributions | |
gust | +0.018 |
ago | +0.017 |
epad | +0.017 |
joy | +0.016 |
ents | +0.016 |
Neg logit contributions | |
P | -0.008 |
me | -0.007 |
Mom | -0.007 |
bo | -0.007 |
Mo | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
gust | +0.005 |
ago | +0.005 |
epad | +0.005 |
ents | +0.004 |
joy | +0.004 |
Neg logit contributions | |
inct | -0.005 |
P | -0.005 |
ey | -0.005 |
yourself | -0.005 |
han | -0.004 |
Token | 3 |
Token ID | 513 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
gust | +0.003 |
ago | +0.003 |
epad | +0.003 |
ents | +0.003 |
joy | +0.003 |
Neg logit contributions | |
P | -0.002 |
bo | -0.001 |
me | -0.001 |
Mom | -0.001 |
Mo | -0.001 |
Token | years |
Token ID | 812 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
gust | +0.042 |
ago | +0.041 |
ents | +0.039 |
joy | +0.037 |
epad | +0.037 |
Neg logit contributions | |
P | -0.043 |
Mom | -0.039 |
bo | -0.039 |
inct | -0.039 |
Hey | -0.039 |
Token | torn |
Token ID | 12445 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
P | +0.004 |
bo | +0.004 |
Mo | +0.004 |
Mom | +0.003 |
me | +0.003 |
Neg logit contributions | |
gust | -0.006 |
ago | -0.005 |
epad | -0.005 |
joy | -0.005 |
ents | -0.005 |
Token | book |
Token ID | 1492 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
P | +0.013 |
Mo | +0.011 |
bo | +0.011 |
me | +0.011 |
Mom | +0.011 |
Neg logit contributions | |
gust | -0.020 |
ago | -0.019 |
epad | -0.018 |
joy | -0.017 |
ents | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
P | +0.005 |
me | +0.005 |
bo | +0.004 |
Mom | +0.004 |
was | +0.004 |
Neg logit contributions | |
gust | -0.020 |
ago | -0.020 |
epad | -0.019 |
joy | -0.019 |
ents | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +4.64e-02 |
Pos logit contributions | |
P | +0.004 |
me | +0.003 |
bo | +0.003 |
Mom | +0.003 |
Mo | +0.003 |
Neg logit contributions | |
gust | -0.007 |
ago | -0.007 |
epad | -0.007 |
joy | -0.006 |
ents | -0.006 |
Token | unw |
Token ID | 7379 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
P | +0.002 |
bo | +0.001 |
me | +0.001 |
Mom | +0.001 |
Mo | +0.001 |
Neg logit contributions | |
gust | -0.002 |
ago | -0.002 |
epad | -0.002 |
joy | -0.002 |
ents | -0.002 |
Token | ra |
Token ID | 430 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
P | +0.034 |
bo | +0.030 |
me | +0.030 |
Mom | +0.029 |
ey | +0.027 |
Neg logit contributions | |
gust | -0.070 |
ago | -0.068 |
epad | -0.067 |
joy | -0.063 |
ents | -0.062 |
Token | pped |
Token ID | 1496 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
P | +0.111 |
me | +0.101 |
bo | +0.101 |
Mom | +0.096 |
ey | +0.093 |
Neg logit contributions | |
gust | -0.171 |
ago | -0.162 |
epad | -0.159 |
joy | -0.152 |
ents | -0.147 |
Token | box |
Token ID | 3091 |
Feature activation | +7.50e-01 |
Pos logit contributions | |
P | +0.034 |
bo | +0.029 |
me | +0.028 |
Mom | +0.028 |
Mo | +0.027 |
Neg logit contributions | |
gust | -0.061 |
ago | -0.059 |
epad | -0.058 |
joy | -0.054 |
ents | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +5.31e-02 |
Pos logit contributions | |
me | +0.013 |
bo | +0.012 |
Mom | +0.011 |
P | +0.011 |
was | +0.011 |
Neg logit contributions | |
gust | -0.044 |
ago | -0.041 |
joy | -0.041 |
epad | -0.041 |
pieces | -0.040 |
Token | She |
Token ID | 1375 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
P | +0.002 |
bo | +0.002 |
ey | +0.002 |
me | +0.001 |
sy | +0.001 |
Neg logit contributions | |
gust | -0.002 |
ago | -0.002 |
epad | -0.002 |
joy | -0.002 |
ents | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
P | +0.005 |
bo | +0.005 |
Mo | +0.005 |
ey | +0.004 |
Mom | +0.004 |
Neg logit contributions | |
gust | -0.008 |
ago | -0.008 |
ents | -0.008 |
epad | -0.008 |
joy | -0.007 |
Token | you |
Token ID | 345 |
Feature activation | +6.58e-02 |
Pos logit contributions | |
P | +0.003 |
bo | +0.003 |
Mom | +0.003 |
me | +0.003 |
Mo | +0.003 |
Neg logit contributions | |
gust | -0.006 |
ago | -0.006 |
epad | -0.006 |
ents | -0.005 |
joy | -0.005 |
Token | doing |
Token ID | 1804 |
Feature activation | +7.05e-01 |
Pos logit contributions | |
P | +0.003 |
bo | +0.003 |
Mo | +0.003 |
Mom | +0.003 |
Mouse | +0.003 |
Neg logit contributions | |
ago | -0.002 |
gust | -0.002 |
epad | -0.002 |
joy | -0.002 |
ents | -0.002 |
Token | here |
Token ID | 994 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
P | +0.021 |
bo | +0.020 |
Mo | +0.019 |
Mouse | +0.018 |
H | +0.018 |
Neg logit contributions | |
ago | -0.036 |
gust | -0.034 |
epad | -0.033 |
joy | -0.031 |
anymore | -0.030 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
P | +0.037 |
Mo | +0.033 |
bo | +0.033 |
inct | +0.030 |
Mouse | +0.029 |
Neg logit contributions | |
gust | -0.069 |
ago | -0.069 |
epad | -0.063 |
anymore | -0.060 |
ents | -0.060 |
Token | El |
Token ID | 2574 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
P | +0.036 |
sy | +0.032 |
an | +0.032 |
bo | +0.032 |
Mo | +0.031 |
Neg logit contributions | |
gust | -0.044 |
ago | -0.041 |
ents | -0.037 |
epad | -0.037 |
joy | -0.036 |
Token | le |
Token ID | 293 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
P | +0.067 |
Mom | +0.062 |
Mo | +0.058 |
me | +0.057 |
W | +0.057 |
Neg logit contributions | |
ago | -0.082 |
gust | -0.079 |
ents | -0.072 |
epad | -0.071 |
joy | -0.071 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
P | +0.114 |
Mo | +0.100 |
W | +0.097 |
yourself | +0.096 |
Mouse | +0.096 |
Neg logit contributions | |
gust | -0.161 |
ago | -0.159 |
ents | -0.148 |
epad | -0.145 |
joy | -0.132 |
Token | the |
Token ID | 262 |
Feature activation | +7.76e-03 |
Pos logit contributions | |
P | +0.012 |
bo | +0.010 |
an | +0.010 |
Mom | +0.010 |
Hey | +0.009 |
Neg logit contributions | |
gust | -0.015 |
ago | -0.015 |
epad | -0.014 |
joy | -0.014 |
ents | -0.013 |
Token | figure |
Token ID | 3785 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
P | +0.000 |
bo | +0.000 |
Mo | +0.000 |
ey | +0.000 |
na | +0.000 |
Neg logit contributions | |
gust | -0.000 |
ago | -0.000 |
epad | -0.000 |
joy | -0.000 |
ents | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
P | +0.027 |
bo | +0.025 |
me | +0.025 |
Mom | +0.023 |
na | +0.022 |
Neg logit contributions | |
gust | -0.056 |
ago | -0.053 |
epad | -0.052 |
joy | -0.050 |
ents | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
ago | +0.014 |
gust | +0.013 |
ents | +0.013 |
joy | +0.012 |
epad | +0.012 |
Neg logit contributions | |
P | -0.009 |
an | -0.008 |
bo | -0.008 |
ey | -0.008 |
yourself | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ago | +0.026 |
gust | +0.026 |
epad | +0.024 |
ents | +0.024 |
joy | +0.024 |
Neg logit contributions | |
P | -0.018 |
bo | -0.016 |
ey | -0.015 |
me | -0.015 |
na | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
P | +0.003 |
bo | +0.002 |
na | +0.002 |
ey | +0.002 |
me | +0.002 |
Neg logit contributions | |
ago | -0.006 |
gust | -0.006 |
ents | -0.006 |
epad | -0.006 |
joy | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | +6.46e-01 |
Pos logit contributions | |
fl | +0.003 |
bo | +0.003 |
inct | +0.003 |
an | +0.003 |
na | +0.003 |
Neg logit contributions | |
ago | -0.006 |
gust | -0.005 |
ents | -0.005 |
epad | -0.005 |
joy | -0.005 |
Token | Le |
Token ID | 3123 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
sy | +0.017 |
an | +0.017 |
me | +0.017 |
ey | +0.016 |
bo | +0.016 |
Neg logit contributions | |
gust | -0.030 |
ago | -0.028 |
epad | -0.027 |
joy | -0.026 |
ents | -0.025 |
Token | - |
Token ID | 12 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
ago | +0.096 |
gust | +0.095 |
epad | +0.090 |
joy | +0.088 |
ents | +0.087 |
Neg logit contributions | |
P | -0.047 |
me | -0.041 |
Mom | -0.040 |
bo | -0.039 |
Mo | -0.037 |
Token | le |
Token ID | 293 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
ago | +0.008 |
gust | +0.007 |
epad | +0.007 |
ents | +0.007 |
joy | +0.007 |
Neg logit contributions | |
P | -0.006 |
me | -0.005 |
ey | -0.005 |
Mo | -0.005 |
bo | -0.005 |
Token | - |
Token ID | 12 |
Feature activation | -3.86e-01 |
Pos logit contributions | |
P | +0.116 |
Mom | +0.110 |
Mo | +0.100 |
H | +0.095 |
Ang | +0.094 |
Neg logit contributions | |
ago | -0.163 |
gust | -0.162 |
ents | -0.142 |
epad | -0.139 |
joy | -0.138 |
Token | le |
Token ID | 293 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
ago | +0.016 |
epad | +0.016 |
gust | +0.016 |
ents | +0.015 |
joy | +0.014 |
Neg logit contributions | |
P | -0.013 |
me | -0.012 |
ey | -0.011 |
Mo | -0.011 |
Mom | -0.011 |
Token | opard |
Token ID | 15478 |
Feature activation | -4.02e-01 |
Pos logit contributions | |
P | +0.110 |
Mom | +0.104 |
Mo | +0.093 |
H | +0.090 |
W | +0.088 |
Neg logit contributions | |
gust | -0.159 |
ago | -0.157 |
ents | -0.138 |
epad | -0.135 |
pieces | -0.134 |
Token | ," |
Token ID | 553 |
Feature activation | +4.06e-01 |
Pos logit contributions | |
gust | +0.019 |
ago | +0.019 |
ents | +0.017 |
epad | +0.016 |
joy | +0.016 |
Neg logit contributions | |
P | -0.012 |
Mom | -0.012 |
Mo | -0.010 |
H | -0.010 |
Ang | -0.010 |
Token | she |
Token ID | 673 |
Feature activation | -7.47e-01 |
Pos logit contributions | |
P | +0.018 |
sy | +0.017 |
bo | +0.017 |
inct | +0.016 |
urous | +0.016 |
Neg logit contributions | |
gust | -0.014 |
ago | -0.013 |
ents | -0.011 |
joy | -0.011 |
epad | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +3.23e-01 |
Pos logit contributions | |
P | +0.007 |
bo | +0.006 |
me | +0.006 |
Mom | +0.005 |
Mo | +0.005 |
Neg logit contributions | |
gust | -0.014 |
ago | -0.013 |
epad | -0.013 |
joy | -0.012 |
ents | -0.012 |
Token | she |
Token ID | 673 |
Feature activation | -3.91e-02 |
Pos logit contributions | |
P | +0.012 |
me | +0.011 |
bo | +0.011 |
Mom | +0.010 |
Mo | +0.010 |
Neg logit contributions | |
gust | -0.014 |
ago | -0.013 |
epad | -0.013 |
ents | -0.012 |
joy | -0.012 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
gust | +0.002 |
ago | +0.002 |
epad | +0.002 |
joy | +0.002 |
ents | +0.002 |
Neg logit contributions | |
P | -0.001 |
me | -0.001 |
bo | -0.001 |
Mom | -0.001 |
Mo | -0.001 |
Token | something |
Token ID | 1223 |
Feature activation | -7.39e-01 |
Pos logit contributions | |
P | +0.004 |
me | +0.004 |
bo | +0.004 |
Mom | +0.004 |
Mo | +0.004 |
Neg logit contributions | |
ago | -0.010 |
gust | -0.010 |
epad | -0.009 |
ents | -0.009 |
joy | -0.009 |
Token | tick |
Token ID | 4378 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
gust | +0.036 |
ago | +0.036 |
epad | +0.035 |
joy | +0.034 |
ents | +0.033 |
Neg logit contributions | |
P | -0.021 |
me | -0.019 |
bo | -0.018 |
Mom | -0.018 |
Mo | -0.017 |
Token | le |
Token ID | 293 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
P | +0.066 |
Mom | +0.062 |
Mo | +0.058 |
me | +0.058 |
Mouse | +0.058 |
Neg logit contributions | |
gust | -0.096 |
ago | -0.084 |
epad | -0.083 |
ents | -0.081 |
anymore | -0.078 |
Token | her |
Token ID | 607 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
P | +0.101 |
bo | +0.087 |
me | +0.086 |
Mom | +0.085 |
Mo | +0.081 |
Neg logit contributions | |
gust | -0.178 |
ago | -0.173 |
epad | -0.169 |
joy | -0.159 |
ents | -0.158 |
Token | nose |
Token ID | 9686 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
P | +0.015 |
me | +0.012 |
bo | +0.012 |
Mom | +0.012 |
Mo | +0.012 |
Neg logit contributions | |
gust | -0.026 |
ago | -0.025 |
epad | -0.024 |
ents | -0.023 |
joy | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +3.81e-01 |
Pos logit contributions | |
gust | +0.007 |
ago | +0.006 |
epad | +0.006 |
joy | +0.006 |
ents | +0.006 |
Neg logit contributions | |
P | -0.004 |
me | -0.003 |
bo | -0.003 |
Mom | -0.003 |
Mo | -0.003 |
Token | She |
Token ID | 1375 |
Feature activation | +3.28e-01 |
Pos logit contributions | |
P | +0.013 |
bo | +0.012 |
me | +0.011 |
Mom | +0.011 |
ey | +0.011 |
Neg logit contributions | |
gust | -0.017 |
ago | -0.016 |
epad | -0.016 |
joy | -0.015 |
ents | -0.015 |
Token | sne |
Token ID | 10505 |
Feature activation | +1.85e+00 |
Pos logit contributions | |
P | +0.012 |
ey | +0.010 |
na | +0.010 |
inct | +0.010 |
bo | +0.010 |
Neg logit contributions | |
gust | -0.014 |
ago | -0.013 |
ents | -0.013 |
epad | -0.012 |
joy | -0.012 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
gust | +0.005 |
ago | +0.005 |
epad | +0.005 |
ents | +0.004 |
joy | +0.004 |
Neg logit contributions | |
P | -0.003 |
bo | -0.003 |
ey | -0.003 |
me | -0.003 |
Mom | -0.003 |
Token | she |
Token ID | 673 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
P | +0.007 |
bo | +0.006 |
Mom | +0.006 |
me | +0.006 |
ey | +0.006 |
Neg logit contributions | |
gust | -0.012 |
ago | -0.011 |
epad | -0.010 |
joy | -0.010 |
ents | -0.010 |
Token | started |
Token ID | 2067 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
gust | +0.018 |
ago | +0.017 |
epad | +0.017 |
ents | +0.016 |
joy | +0.016 |
Neg logit contributions | |
P | -0.013 |
bo | -0.011 |
me | -0.011 |
Mom | -0.011 |
Mo | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -3.10e-01 |
Pos logit contributions | |
gust | +0.020 |
ago | +0.019 |
epad | +0.019 |
ents | +0.017 |
joy | +0.017 |
Neg logit contributions | |
P | -0.016 |
me | -0.014 |
bo | -0.014 |
Mom | -0.014 |
Mo | -0.013 |
Token | tick |
Token ID | 4378 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
gust | +0.013 |
ago | +0.011 |
epad | +0.011 |
ents | +0.010 |
joy | +0.010 |
Neg logit contributions | |
P | -0.013 |
Mom | -0.011 |
bo | -0.011 |
Mo | -0.010 |
H | -0.010 |
Token | le |
Token ID | 293 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
Mom | +0.079 |
P | +0.074 |
man | +0.071 |
Look | +0.070 |
Mo | +0.068 |
Neg logit contributions | |
gust | -0.091 |
pieces | -0.072 |
ents | -0.070 |
anymore | -0.069 |
joy | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
P | +0.119 |
Mom | +0.101 |
bo | +0.101 |
Mo | +0.094 |
me | +0.093 |
Neg logit contributions | |
gust | -0.165 |
ago | -0.157 |
epad | -0.152 |
ents | -0.145 |
joy | -0.145 |
Token | she |
Token ID | 673 |
Feature activation | -3.26e-01 |
Pos logit contributions | |
P | +0.009 |
bo | +0.008 |
Mom | +0.007 |
me | +0.007 |
Mo | +0.007 |
Neg logit contributions | |
gust | -0.010 |
ago | -0.009 |
epad | -0.009 |
ents | -0.008 |
joy | -0.008 |
Token | sne |
Token ID | 10505 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
gust | +0.015 |
ago | +0.014 |
ents | +0.013 |
epad | +0.013 |
joy | +0.013 |
Neg logit contributions | |
P | -0.011 |
Mom | -0.009 |
Mo | -0.009 |
bo | -0.009 |
ey | -0.009 |
Token | ez |
Token ID | 8471 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
P | +0.060 |
me | +0.057 |
Mom | +0.056 |
na | +0.054 |
Mo | +0.052 |
Neg logit contributions | |
gust | -0.071 |
ago | -0.069 |
epad | -0.065 |
ents | -0.062 |
joy | -0.060 |
Token | ed |
Token ID | 276 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
P | +0.020 |
me | +0.019 |
Mom | +0.018 |
bo | +0.018 |
Mo | +0.017 |
Neg logit contributions | |
gust | -0.029 |
ago | -0.028 |
epad | -0.027 |
ents | -0.026 |
joy | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
P | +0.017 |
bo | +0.016 |
me | +0.015 |
Mom | +0.014 |
Mo | +0.014 |
Neg logit contributions | |
gust | -0.036 |
ago | -0.035 |
epad | -0.034 |
joy | -0.033 |
ents | -0.032 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
P | +0.010 |
me | +0.009 |
Mom | +0.009 |
bo | +0.008 |
M | +0.008 |
Neg logit contributions | |
gust | -0.012 |
ago | -0.012 |
epad | -0.012 |
ents | -0.011 |
joy | -0.011 |
Token | felt |
Token ID | 2936 |
Feature activation | +1.56e-01 |
Pos logit contributions | |
ago | +0.009 |
gust | +0.008 |
epad | +0.008 |
ents | +0.008 |
joy | +0.008 |
Neg logit contributions | |
P | -0.006 |
Mo | -0.006 |
Mouse | -0.005 |
inct | -0.005 |
omi | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
P | +0.004 |
me | +0.004 |
bo | +0.004 |
Mom | +0.004 |
was | +0.004 |
Neg logit contributions | |
ago | -0.008 |
gust | -0.007 |
epad | -0.007 |
ents | -0.007 |
pieces | -0.007 |
Token | tick |
Token ID | 4378 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
P | +0.006 |
me | +0.006 |
bo | +0.005 |
Mom | +0.005 |
na | +0.005 |
Neg logit contributions | |
ago | -0.012 |
gust | -0.012 |
epad | -0.011 |
ents | -0.011 |
joy | -0.011 |
Token | le |
Token ID | 293 |
Feature activation | +3.53e+00 |
Pos logit contributions | |
P | +0.070 |
Mom | +0.068 |
Mo | +0.065 |
Mouse | +0.062 |
Ang | +0.060 |
Neg logit contributions | |
gust | -0.098 |
ago | -0.085 |
epad | -0.085 |
pieces | -0.079 |
anymore | -0.078 |
Token | in |
Token ID | 287 |
Feature activation | +4.16e-02 |
Pos logit contributions | |
P | +0.090 |
bo | +0.076 |
Mom | +0.075 |
me | +0.073 |
Mo | +0.072 |
Neg logit contributions | |
gust | -0.189 |
ago | -0.184 |
epad | -0.179 |
joy | -0.168 |
ents | -0.166 |
Token | her |
Token ID | 607 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
P | +0.001 |
bo | +0.001 |
ey | +0.001 |
na | +0.001 |
Mo | +0.001 |
Neg logit contributions | |
gust | -0.002 |
ago | -0.002 |
epad | -0.002 |
joy | -0.002 |
ents | -0.002 |
Token | nose |
Token ID | 9686 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
P | +0.016 |
bo | +0.015 |
Mo | +0.014 |
Mom | +0.014 |
me | +0.014 |
Neg logit contributions | |
gust | -0.022 |
ago | -0.021 |
epad | -0.020 |
joy | -0.019 |
ents | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
gust | +0.009 |
ago | +0.009 |
epad | +0.009 |
ents | +0.008 |
joy | +0.008 |
Neg logit contributions | |
P | -0.007 |
bo | -0.006 |
me | -0.006 |
Mom | -0.006 |
Mo | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
P | +0.013 |
bo | +0.012 |
ey | +0.011 |
Mo | +0.011 |
Mom | +0.011 |
Neg logit contributions | |
gust | -0.019 |
ago | -0.018 |
epad | -0.017 |
ents | -0.016 |
joy | -0.016 |
Token | sneak |
Token ID | 20528 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
P | +0.006 |
Mo | +0.005 |
Mom | +0.005 |
bo | +0.005 |
M | +0.005 |
Neg logit contributions | |
gust | -0.007 |
ago | -0.007 |
epad | -0.007 |
ents | -0.007 |
pieces | -0.006 |
Token | behind |
Token ID | 2157 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
P | +0.055 |
bo | +0.048 |
me | +0.047 |
Mom | +0.046 |
Mo | +0.044 |
Neg logit contributions | |
gust | -0.107 |
ago | -0.105 |
epad | -0.102 |
ents | -0.097 |
joy | -0.097 |
Token | her |
Token ID | 607 |
Feature activation | +6.14e-01 |
Pos logit contributions | |
me | +0.009 |
P | +0.008 |
Mom | +0.008 |
was | +0.007 |
bo | +0.007 |
Neg logit contributions | |
epad | -0.023 |
gust | -0.023 |
ago | -0.022 |
ents | -0.021 |
pieces | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | -8.77e-03 |
Pos logit contributions | |
P | +0.015 |
me | +0.014 |
bo | +0.014 |
Mom | +0.013 |
ey | +0.012 |
Neg logit contributions | |
gust | -0.032 |
ago | -0.031 |
epad | -0.031 |
joy | -0.029 |
ents | -0.029 |
Token | tick |
Token ID | 4378 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
gust | +0.000 |
ago | +0.000 |
epad | +0.000 |
ents | +0.000 |
joy | +0.000 |
Neg logit contributions | |
P | -0.000 |
Mo | -0.000 |
bo | -0.000 |
Mom | -0.000 |
M | -0.000 |
Token | le |
Token ID | 293 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
P | +0.088 |
Mo | +0.085 |
Mom | +0.085 |
na | +0.082 |
Mouse | +0.080 |
Neg logit contributions | |
gust | -0.081 |
ago | -0.073 |
epad | -0.069 |
ents | -0.069 |
pieces | -0.066 |
Token | her |
Token ID | 607 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
P | +0.112 |
bo | +0.097 |
me | +0.095 |
Mom | +0.094 |
Mo | +0.092 |
Neg logit contributions | |
gust | -0.165 |
ago | -0.162 |
epad | -0.157 |
joy | -0.147 |
ents | -0.147 |
Token | . |
Token ID | 13 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
P | +0.016 |
me | +0.015 |
bo | +0.015 |
Mom | +0.014 |
ey | +0.013 |
Neg logit contributions | |
gust | -0.030 |
ago | -0.029 |
epad | -0.028 |
joy | -0.027 |
ents | -0.027 |
Token | They |
Token ID | 1119 |
Feature activation | +2.07e-01 |
Pos logit contributions | |
P | +0.002 |
bo | +0.002 |
me | +0.002 |
Mom | +0.002 |
Mo | +0.002 |
Neg logit contributions | |
gust | -0.004 |
ago | -0.003 |
epad | -0.003 |
joy | -0.003 |
ents | -0.003 |
Token | use |
Token ID | 779 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
P | +0.009 |
Mo | +0.007 |
Mom | +0.007 |
M | +0.007 |
na | +0.007 |
Neg logit contributions | |
gust | -0.008 |
ago | -0.008 |
epad | -0.007 |
ents | -0.007 |
pieces | -0.007 |
Token | their |
Token ID | 511 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
me | +0.035 |
P | +0.033 |
Mom | +0.030 |
bo | +0.030 |
Mo | +0.027 |
Neg logit contributions | |
gust | -0.075 |
ago | -0.073 |
epad | -0.072 |
joy | -0.068 |
ents | -0.067 |
Token | play |
Token ID | 711 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
gust | +0.017 |
ago | +0.017 |
epad | +0.016 |
pieces | +0.014 |
joy | +0.014 |
Neg logit contributions | |
P | -0.015 |
bo | -0.014 |
Mom | -0.013 |
Mo | -0.013 |
inct | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +9.49e-02 |
Pos logit contributions | |
gust | +0.017 |
ago | +0.015 |
epad | +0.015 |
joy | +0.015 |
pieces | +0.014 |
Neg logit contributions | |
bo | -0.010 |
na | -0.009 |
P | -0.009 |
Mo | -0.009 |
Mom | -0.009 |
Token | One |
Token ID | 1881 |
Feature activation | -5.42e-01 |
Pos logit contributions | |
P | +0.003 |
bo | +0.003 |
ey | +0.002 |
Mom | +0.002 |
me | +0.002 |
Neg logit contributions | |
ago | -0.005 |
gust | -0.004 |
joy | -0.004 |
epad | -0.004 |
ents | -0.004 |
Token | day |
Token ID | 1110 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
gust | +0.021 |
ago | +0.020 |
epad | +0.019 |
joy | +0.017 |
ents | +0.017 |
Neg logit contributions | |
P | -0.022 |
bo | -0.020 |
me | -0.020 |
Mo | -0.019 |
ey | -0.019 |
Token | El |
Token ID | 2574 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
P | +0.017 |
bo | +0.016 |
Mom | +0.015 |
me | +0.014 |
an | +0.014 |
Neg logit contributions | |
gust | -0.024 |
ago | -0.023 |
joy | -0.021 |
epad | -0.021 |
ents | -0.020 |
Token | le |
Token ID | 293 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
P | +0.054 |
me | +0.047 |
bo | +0.047 |
Mom | +0.047 |
Mo | +0.045 |
Neg logit contributions | |
gust | -0.102 |
ago | -0.100 |
epad | -0.096 |
joy | -0.092 |
ents | -0.091 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.37e-01 |
Pos logit contributions | |
P | +0.103 |
Mo | +0.103 |
Mouse | +0.100 |
inct | +0.097 |
yourself | +0.095 |
Neg logit contributions | |
ago | -0.160 |
gust | -0.149 |
ents | -0.137 |
epad | -0.126 |
pieces | -0.122 |
Token | in |
Token ID | 287 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
gust | +0.017 |
ago | +0.016 |
epad | +0.015 |
ents | +0.015 |
joy | +0.015 |
Neg logit contributions | |
P | -0.010 |
bo | -0.009 |
ey | -0.008 |
Mom | -0.008 |
me | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
gust | +0.003 |
ago | +0.003 |
epad | +0.003 |
joy | +0.002 |
ents | +0.002 |
Neg logit contributions | |
P | -0.002 |
bo | -0.002 |
me | -0.001 |
Mom | -0.001 |
Mo | -0.001 |
Token | sky |
Token ID | 6766 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
ey | +0.012 |
na | +0.011 |
Mo | +0.010 |
bo | +0.010 |
inct | +0.010 |
Neg logit contributions | |
gust | -0.010 |
ago | -0.008 |
joy | -0.008 |
epad | -0.007 |
rainy | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +1.41e-01 |
Pos logit contributions | |
P | +0.000 |
bo | +0.000 |
me | +0.000 |
Mom | +0.000 |
Mo | +0.000 |
Neg logit contributions | |
gust | -0.000 |
ago | -0.000 |
epad | -0.000 |
joy | -0.000 |
ents | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
P | +0.012 |
Mom | +0.010 |
bo | +0.010 |
Mo | +0.010 |
me | +0.009 |
Neg logit contributions | |
ago | -0.016 |
gust | -0.015 |
epad | -0.014 |
ents | -0.014 |
joy | -0.014 |
Token | They |
Token ID | 1119 |
Feature activation | +2.71e-01 |
Pos logit contributions | |
ago | +0.006 |
gust | +0.006 |
ents | +0.005 |
joy | +0.005 |
epad | +0.005 |
Neg logit contributions | |
P | -0.004 |
bo | -0.004 |
sy | -0.004 |
na | -0.004 |
ey | -0.004 |
Token | help |
Token ID | 1037 |
Feature activation | +6.51e-01 |
Pos logit contributions | |
P | +0.010 |
Mom | +0.009 |
bo | +0.009 |
Mo | +0.009 |
inct | +0.008 |
Neg logit contributions | |
gust | -0.011 |
ago | -0.011 |
epad | -0.010 |
ents | -0.010 |
pieces | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | +4.09e-01 |
Pos logit contributions | |
P | +0.026 |
bo | +0.023 |
inct | +0.023 |
sy | +0.022 |
Mo | +0.022 |
Neg logit contributions | |
gust | -0.026 |
ago | -0.023 |
epad | -0.022 |
ents | -0.022 |
theirs | -0.022 |
Token | get |
Token ID | 651 |
Feature activation | +9.38e-01 |
Pos logit contributions | |
P | +0.015 |
bo | +0.012 |
Hey | +0.012 |
Mo | +0.012 |
Mom | +0.012 |
Neg logit contributions | |
ago | -0.018 |
epad | -0.018 |
gust | -0.018 |
ents | -0.017 |
theirs | -0.016 |
Token | rid |
Token ID | 5755 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
P | +0.028 |
Mo | +0.024 |
Mom | +0.023 |
na | +0.023 |
bo | +0.023 |
Neg logit contributions | |
gust | -0.045 |
epad | -0.042 |
ago | -0.042 |
ents | -0.041 |
theirs | -0.040 |
Token | of |
Token ID | 286 |
Feature activation | -4.36e-01 |
Pos logit contributions | |
P | +0.175 |
bo | +0.158 |
Mom | +0.158 |
Mo | +0.157 |
me | +0.157 |
Neg logit contributions | |
gust | -0.103 |
ago | -0.099 |
epad | -0.090 |
ents | -0.084 |
pieces | -0.077 |
Token | the |
Token ID | 262 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
gust | +0.022 |
ago | +0.022 |
epad | +0.021 |
ents | +0.020 |
joy | +0.020 |
Neg logit contributions | |
P | -0.012 |
me | -0.011 |
bo | -0.010 |
Mom | -0.010 |
Mo | -0.010 |
Token | other |
Token ID | 584 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
gust | +0.007 |
ago | +0.007 |
epad | +0.006 |
joy | +0.006 |
ents | +0.006 |
Neg logit contributions | |
P | -0.004 |
bo | -0.003 |
me | -0.003 |
Mom | -0.003 |
Mo | -0.003 |
Token | fle |
Token ID | 5104 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
gust | +0.007 |
epad | +0.007 |
ago | +0.007 |
ents | +0.007 |
joy | +0.007 |
Neg logit contributions | |
P | -0.004 |
me | -0.004 |
bo | -0.004 |
Mom | -0.004 |
ey | -0.003 |
Token | as |
Token ID | 292 |
Feature activation | +7.11e-01 |
Pos logit contributions | |
gust | +0.093 |
ago | +0.090 |
epad | +0.087 |
joy | +0.082 |
ents | +0.082 |
Neg logit contributions | |
P | -0.065 |
me | -0.058 |
bo | -0.058 |
Mom | -0.056 |
Mo | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
P | +0.019 |
bo | +0.018 |
me | +0.017 |
Mom | +0.016 |
Mo | +0.016 |
Neg logit contributions | |
gust | -0.038 |
ago | -0.037 |
epad | -0.035 |
joy | -0.034 |
ents | -0.033 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
P | +0.010 |
me | +0.009 |
Mom | +0.009 |
M | +0.008 |
bo | +0.008 |
Neg logit contributions | |
ago | -0.014 |
epad | -0.014 |
gust | -0.014 |
ents | -0.013 |
joy | -0.013 |
Token | felt |
Token ID | 2936 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
ago | +0.012 |
gust | +0.011 |
ents | +0.010 |
epad | +0.010 |
joy | +0.010 |
Neg logit contributions | |
Mo | -0.008 |
P | -0.008 |
Mouse | -0.008 |
inct | -0.008 |
Mom | -0.007 |
Token | something |
Token ID | 1223 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
P | +0.007 |
me | +0.007 |
bo | +0.006 |
Mom | +0.006 |
M | +0.006 |
Neg logit contributions | |
ago | -0.011 |
gust | -0.011 |
epad | -0.011 |
ents | -0.010 |
pieces | -0.010 |
Token | tick |
Token ID | 4378 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
gust | +0.035 |
ago | +0.033 |
epad | +0.032 |
joy | +0.030 |
ents | +0.030 |
Neg logit contributions | |
P | -0.022 |
bo | -0.020 |
me | -0.020 |
Mom | -0.020 |
Mo | -0.019 |
Token | le |
Token ID | 293 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
Mom | +0.076 |
Mo | +0.071 |
P | +0.071 |
inct | +0.070 |
Mouse | +0.070 |
Neg logit contributions | |
gust | -0.084 |
anymore | -0.067 |
ents | -0.067 |
ago | -0.067 |
epad | -0.066 |
Token | her |
Token ID | 607 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
P | +0.109 |
Mom | +0.094 |
bo | +0.093 |
Mo | +0.090 |
me | +0.089 |
Neg logit contributions | |
gust | -0.166 |
ago | -0.162 |
epad | -0.156 |
joy | -0.145 |
ents | -0.144 |
Token | fur |
Token ID | 9230 |
Feature activation | -1.59e-02 |
Pos logit contributions | |
P | +0.015 |
Mo | +0.012 |
bo | +0.012 |
Mom | +0.012 |
Hey | +0.012 |
Neg logit contributions | |
gust | -0.018 |
ago | -0.017 |
epad | -0.016 |
joy | -0.015 |
ents | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e-01 |
Pos logit contributions | |
gust | +0.001 |
ago | +0.001 |
epad | +0.001 |
ents | +0.001 |
joy | +0.001 |
Neg logit contributions | |
P | -0.001 |
Mom | -0.000 |
Mo | -0.000 |
bo | -0.000 |
me | -0.000 |
Token | She |
Token ID | 1375 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
P | +0.004 |
bo | +0.004 |
me | +0.004 |
Mom | +0.004 |
ey | +0.004 |
Neg logit contributions | |
gust | -0.007 |
ago | -0.006 |
epad | -0.006 |
ents | -0.006 |
joy | -0.006 |
Token | scratched |
Token ID | 37468 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
P | +0.004 |
ey | +0.004 |
inct | +0.004 |
Mo | +0.004 |
na | +0.004 |
Neg logit contributions | |
gust | -0.005 |
ents | -0.004 |
ago | -0.004 |
epad | -0.004 |
joy | -0.004 |
Token | kid |
Token ID | 5141 |
Feature activation | +3.25e-01 |
Pos logit contributions | |
gust | +0.030 |
ago | +0.029 |
epad | +0.028 |
ents | +0.027 |
joy | +0.027 |
Neg logit contributions | |
P | -0.019 |
me | -0.018 |
bo | -0.017 |
Mom | -0.017 |
Mo | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +2.85e-02 |
Pos logit contributions | |
P | +0.010 |
bo | +0.008 |
me | +0.008 |
Mom | +0.008 |
Mo | +0.008 |
Neg logit contributions | |
gust | -0.016 |
ago | -0.016 |
epad | -0.015 |
ents | -0.014 |
joy | -0.014 |
Token | He |
Token ID | 679 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
P | +0.001 |
bo | +0.001 |
me | +0.001 |
ey | +0.001 |
Mo | +0.001 |
Neg logit contributions | |
gust | -0.001 |
ago | -0.001 |
epad | -0.001 |
joy | -0.001 |
ents | -0.001 |
Token | could |
Token ID | 714 |
Feature activation | +1.76e-01 |
Pos logit contributions | |
gust | +0.005 |
ago | +0.005 |
ents | +0.005 |
epad | +0.005 |
joy | +0.004 |
Neg logit contributions | |
P | -0.004 |
Mo | -0.003 |
Mom | -0.003 |
bo | -0.003 |
yourself | -0.003 |
Token | jugg |
Token ID | 24873 |
Feature activation | -2.79e-01 |
Pos logit contributions | |
P | +0.007 |
inct | +0.005 |
Mo | +0.005 |
bo | +0.005 |
sy | +0.005 |
Neg logit contributions | |
gust | -0.008 |
epad | -0.007 |
ago | -0.007 |
ents | -0.007 |
theirs | -0.006 |
Token | le |
Token ID | 293 |
Feature activation | +3.51e+00 |
Pos logit contributions | |
gust | +0.014 |
ago | +0.013 |
epad | +0.013 |
ents | +0.012 |
joy | +0.012 |
Neg logit contributions | |
P | -0.008 |
me | -0.007 |
bo | -0.007 |
Mom | -0.007 |
Mo | -0.007 |
Token | balls |
Token ID | 11333 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
P | +0.107 |
bo | +0.093 |
Mom | +0.092 |
me | +0.090 |
Mo | +0.089 |
Neg logit contributions | |
gust | -0.168 |
ago | -0.166 |
epad | -0.159 |
ents | -0.152 |
joy | -0.151 |
Token | and |
Token ID | 290 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
gust | +0.069 |
ago | +0.067 |
epad | +0.065 |
joy | +0.063 |
ents | +0.062 |
Neg logit contributions | |
P | -0.029 |
me | -0.025 |
bo | -0.025 |
Mom | -0.023 |
ey | -0.022 |
Token | make |
Token ID | 787 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
P | +0.004 |
me | +0.004 |
bo | +0.004 |
Mom | +0.004 |
Mo | +0.003 |
Neg logit contributions | |
gust | -0.006 |
ago | -0.006 |
epad | -0.006 |
joy | -0.005 |
ents | -0.005 |
Token | funny |
Token ID | 8258 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
P | +0.025 |
me | +0.023 |
bo | +0.023 |
Mom | +0.021 |
Mo | +0.021 |
Neg logit contributions | |
gust | -0.040 |
ago | -0.040 |
epad | -0.038 |
joy | -0.036 |
ents | -0.036 |
Token | faces |
Token ID | 6698 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
P | +0.048 |
me | +0.043 |
bo | +0.043 |
Mom | +0.042 |
Mo | +0.041 |
Neg logit contributions | |
gust | -0.059 |
ago | -0.057 |
epad | -0.056 |
joy | -0.052 |
ents | -0.052 |
Token | He |
Token ID | 679 |
Feature activation | -4.63e-02 |
Pos logit contributions | |
P | +0.001 |
bo | +0.001 |
me | +0.001 |
Mom | +0.001 |
Mo | +0.001 |
Neg logit contributions | |
gust | -0.003 |
ago | -0.003 |
epad | -0.002 |
joy | -0.002 |
ents | -0.002 |
Token | named |
Token ID | 3706 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ago | +0.002 |
gust | +0.002 |
ents | +0.002 |
epad | +0.002 |
joy | +0.002 |
Neg logit contributions | |
P | -0.002 |
Mom | -0.001 |
inct | -0.001 |
yourself | -0.001 |
Mo | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
gust | +0.060 |
ago | +0.058 |
epad | +0.055 |
ents | +0.054 |
joy | +0.052 |
Neg logit contributions | |
P | -0.050 |
Mom | -0.042 |
bo | -0.042 |
sy | -0.039 |
na | -0.039 |
Token | Ann |
Token ID | 5506 |
Feature activation | -9.47e-02 |
Pos logit contributions | |
P | +0.008 |
bo | +0.007 |
Mom | +0.006 |
me | +0.006 |
Hey | +0.006 |
Neg logit contributions | |
ago | -0.011 |
gust | -0.011 |
joy | -0.010 |
epad | -0.010 |
ents | -0.010 |
Token | abel |
Token ID | 9608 |
Feature activation | +5.07e-01 |
Pos logit contributions | |
gust | +0.005 |
ago | +0.005 |
epad | +0.005 |
joy | +0.004 |
ents | +0.004 |
Neg logit contributions | |
P | -0.003 |
me | -0.002 |
bo | -0.002 |
Mom | -0.002 |
Mo | -0.002 |
Token | le |
Token ID | 293 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
P | +0.012 |
me | +0.011 |
bo | +0.011 |
ey | +0.010 |
na | +0.010 |
Neg logit contributions | |
gust | -0.027 |
epad | -0.026 |
ago | -0.026 |
joy | -0.025 |
ents | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +4.77e-02 |
Pos logit contributions | |
P | +0.091 |
bo | +0.076 |
Mom | +0.075 |
me | +0.073 |
Mo | +0.070 |
Neg logit contributions | |
gust | -0.185 |
ago | -0.183 |
epad | -0.174 |
joy | -0.168 |
ents | -0.167 |
Token | One |
Token ID | 1881 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
P | +0.001 |
bo | +0.001 |
me | +0.001 |
ey | +0.001 |
na | +0.001 |
Neg logit contributions | |
ago | -0.002 |
gust | -0.002 |
epad | -0.002 |
ents | -0.002 |
joy | -0.002 |
Token | day |
Token ID | 1110 |
Feature activation | +7.70e-01 |
Pos logit contributions | |
gust | +0.032 |
ago | +0.031 |
epad | +0.027 |
ents | +0.026 |
pieces | +0.025 |
Neg logit contributions | |
P | -0.037 |
bo | -0.033 |
Mom | -0.033 |
me | -0.032 |
Mo | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
P | +0.026 |
bo | +0.025 |
an | +0.023 |
Mom | +0.022 |
Mouse | +0.022 |
Neg logit contributions | |
gust | -0.035 |
ago | -0.034 |
epad | -0.031 |
joy | -0.031 |
ents | -0.029 |
Token | Jim |
Token ID | 5395 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
P | +0.014 |
bo | +0.013 |
an | +0.012 |
Mom | +0.012 |
sy | +0.012 |
Neg logit contributions | |
gust | -0.010 |
ago | -0.009 |
epad | -0.009 |
joy | -0.009 |
ents | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | +5.44e-02 |
Pos logit contributions | |
P | +0.076 |
inct | +0.070 |
ey | +0.070 |
na | +0.069 |
an | +0.067 |
Neg logit contributions | |
gust | -0.089 |
ago | -0.080 |
epad | -0.078 |
joy | -0.076 |
ents | -0.074 |
Token | shiny |
Token ID | 22441 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
P | +0.002 |
bo | +0.002 |
ey | +0.002 |
na | +0.002 |
Mo | +0.002 |
Neg logit contributions | |
gust | -0.003 |
epad | -0.002 |
ago | -0.002 |
joy | -0.002 |
ents | -0.002 |
Token | saddle |
Token ID | 33083 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
gust | +0.002 |
ago | +0.002 |
epad | +0.002 |
joy | +0.002 |
accomplishment | +0.002 |
Neg logit contributions | |
P | -0.002 |
bo | -0.002 |
Mo | -0.002 |
ey | -0.002 |
na | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
gust | +0.047 |
ago | +0.046 |
epad | +0.045 |
ents | +0.043 |
joy | +0.042 |
Neg logit contributions | |
P | -0.019 |
me | -0.016 |
bo | -0.016 |
Mom | -0.015 |
Mo | -0.015 |
Token | brid |
Token ID | 38265 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
P | +0.003 |
bo | +0.003 |
me | +0.003 |
na | +0.003 |
ey | +0.003 |
Neg logit contributions | |
gust | -0.004 |
ago | -0.004 |
epad | -0.004 |
ents | -0.004 |
joy | -0.004 |
Token | le |
Token ID | 293 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
gust | +0.079 |
ago | +0.074 |
epad | +0.073 |
joy | +0.070 |
ents | +0.068 |
Neg logit contributions | |
bo | -0.048 |
P | -0.048 |
me | -0.043 |
ey | -0.043 |
Mom | -0.042 |
Token | on |
Token ID | 319 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
P | +0.086 |
me | +0.074 |
bo | +0.073 |
Mom | +0.071 |
Mo | +0.067 |
Neg logit contributions | |
gust | -0.188 |
ago | -0.184 |
epad | -0.179 |
joy | -0.170 |
ents | -0.170 |
Token | him |
Token ID | 683 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
gust | +0.013 |
ago | +0.012 |
epad | +0.012 |
ents | +0.011 |
joy | +0.011 |
Neg logit contributions | |
P | -0.012 |
bo | -0.010 |
ey | -0.010 |
sy | -0.010 |
an | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
P | +0.026 |
Mom | +0.022 |
me | +0.022 |
bo | +0.022 |
Mo | +0.021 |
Neg logit contributions | |
gust | -0.040 |
ago | -0.039 |
epad | -0.038 |
ents | -0.036 |
joy | -0.035 |
Token | Finally |
Token ID | 9461 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
ago | +0.001 |
gust | +0.001 |
joy | +0.001 |
epad | +0.001 |
ents | +0.001 |
Neg logit contributions | |
P | -0.001 |
bo | -0.001 |
an | -0.001 |
ey | -0.001 |
sy | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +3.65e-03 |
Pos logit contributions | |
P | +0.011 |
bo | +0.010 |
Mom | +0.010 |
me | +0.010 |
ey | +0.010 |
Neg logit contributions | |
gust | -0.019 |
ago | -0.018 |
epad | -0.017 |
joy | -0.016 |
ents | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
P | +0.023 |
bo | +0.020 |
me | +0.020 |
Mom | +0.020 |
Mo | +0.019 |
Neg logit contributions | |
gust | -0.033 |
ago | -0.032 |
epad | -0.031 |
joy | -0.029 |
ents | -0.029 |
Token | rest |
Token ID | 1334 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
gust | +0.014 |
ago | +0.013 |
epad | +0.013 |
ents | +0.012 |
joy | +0.012 |
Neg logit contributions | |
P | -0.011 |
me | -0.010 |
bo | -0.010 |
Mom | -0.009 |
na | -0.009 |
Token | of |
Token ID | 286 |
Feature activation | -6.64e-01 |
Pos logit contributions | |
gust | +0.043 |
epad | +0.041 |
ago | +0.040 |
joy | +0.038 |
ents | +0.037 |
Neg logit contributions | |
P | -0.033 |
me | -0.031 |
bo | -0.030 |
Mom | -0.029 |
ey | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | -3.70e-01 |
Pos logit contributions | |
gust | +0.035 |
epad | +0.034 |
ago | +0.034 |
ents | +0.033 |
joy | +0.031 |
Neg logit contributions | |
me | -0.016 |
P | -0.015 |
Mom | -0.014 |
bo | -0.013 |
Mo | -0.012 |
Token | or |
Token ID | 393 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
gust | +0.016 |
ago | +0.015 |
epad | +0.015 |
ents | +0.014 |
joy | +0.014 |
Neg logit contributions | |
P | -0.013 |
me | -0.012 |
bo | -0.012 |
Mom | -0.011 |
Mo | -0.011 |
Token | nam |
Token ID | 7402 |
Feature activation | -5.94e+00 |
Pos logit contributions | |
P | +0.006 |
me | +0.006 |
bo | +0.006 |
Mom | +0.006 |
ey | +0.006 |
Neg logit contributions | |
gust | -0.010 |
ago | -0.010 |
epad | -0.009 |
joy | -0.009 |
ents | -0.009 |
Token | ents |
Token ID | 658 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
gust | +0.114 |
ago | +0.080 |
joy | +0.078 |
accomplishment | +0.070 |
epad | +0.069 |
Neg logit contributions | |
P | -0.367 |
bo | -0.363 |
Mom | -0.358 |
me | -0.344 |
ey | -0.339 |
Token | onto |
Token ID | 4291 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
gust | +0.118 |
epad | +0.110 |
ago | +0.109 |
joy | +0.109 |
ents | +0.103 |
Neg logit contributions | |
bo | -0.040 |
P | -0.039 |
me | -0.039 |
was | -0.037 |
ey | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
P | +0.029 |
bo | +0.025 |
Mom | +0.024 |
me | +0.024 |
Mo | +0.024 |
Neg logit contributions | |
gust | -0.037 |
ago | -0.036 |
epad | -0.034 |
joy | -0.032 |
ents | -0.031 |
Token | tree |
Token ID | 5509 |
Feature activation | -6.39e-01 |
Pos logit contributions | |
gust | +0.015 |
ago | +0.015 |
epad | +0.014 |
joy | +0.013 |
ents | +0.013 |
Neg logit contributions | |
P | -0.012 |
bo | -0.011 |
me | -0.011 |
Mom | -0.011 |
Mo | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -5.53e-01 |
Pos logit contributions | |
gust | +0.034 |
ago | +0.032 |
epad | +0.032 |
joy | +0.031 |
ents | +0.030 |
Neg logit contributions | |
P | -0.015 |
me | -0.015 |
bo | -0.014 |
Mom | -0.013 |
ey | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -4.84e-01 |
Pos logit contributions | |
P | +0.001 |
Mom | +0.001 |
bo | +0.001 |
me | +0.001 |
Mo | +0.001 |
Neg logit contributions | |
ago | -0.001 |
gust | -0.001 |
epad | -0.001 |
ents | -0.001 |
joy | -0.001 |
Token | Lily |
Token ID | 20037 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
gust | +0.022 |
ago | +0.020 |
epad | +0.019 |
ents | +0.019 |
joy | +0.018 |
Neg logit contributions | |
P | -0.017 |
Mom | -0.015 |
Mo | -0.014 |
bo | -0.014 |
me | -0.014 |
Token | felt |
Token ID | 2936 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
gust | +0.041 |
ago | +0.039 |
ents | +0.039 |
epad | +0.038 |
joy | +0.036 |
Neg logit contributions | |
P | -0.029 |
Mo | -0.024 |
Mom | -0.024 |
Mouse | -0.023 |
inct | -0.023 |
Token | even |
Token ID | 772 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
P | +0.011 |
Mom | +0.010 |
Mo | +0.010 |
bo | +0.010 |
ey | +0.009 |
Neg logit contributions | |
gust | -0.010 |
ago | -0.009 |
epad | -0.009 |
ents | -0.008 |
joy | -0.008 |
Token | sad |
Token ID | 6507 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
P | +0.023 |
me | +0.022 |
bo | +0.022 |
Mom | +0.020 |
was | +0.019 |
Neg logit contributions | |
ago | -0.031 |
gust | -0.030 |
epad | -0.029 |
joy | -0.027 |
ents | -0.027 |
Token | der |
Token ID | 1082 |
Feature activation | -5.72e+00 |
Pos logit contributions | |
gust | +0.031 |
ago | +0.030 |
epad | +0.028 |
ents | +0.027 |
joy | +0.027 |
Neg logit contributions | |
P | -0.025 |
bo | -0.022 |
Mom | -0.022 |
Mo | -0.021 |
ey | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -9.46e-01 |
Pos logit contributions | |
gust | +0.265 |
ago | +0.260 |
epad | +0.250 |
joy | +0.236 |
ents | +0.236 |
Neg logit contributions | |
P | -0.181 |
bo | -0.162 |
me | -0.161 |
Mom | -0.158 |
Mo | -0.152 |
Token | From |
Token ID | 3574 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
ago | +0.046 |
gust | +0.046 |
joy | +0.042 |
epad | +0.041 |
ents | +0.041 |
Neg logit contributions | |
P | -0.029 |
ey | -0.025 |
bo | -0.025 |
sy | -0.024 |
Mo | -0.023 |
Token | that |
Token ID | 326 |
Feature activation | -7.99e-02 |
Pos logit contributions | |
P | +0.026 |
bo | +0.025 |
Mouse | +0.024 |
inct | +0.024 |
sy | +0.024 |
Neg logit contributions | |
gust | -0.019 |
ago | -0.017 |
ents | -0.015 |
accomplishment | -0.015 |
joy | -0.014 |
Token | day |
Token ID | 1110 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
gust | +0.003 |
ago | +0.003 |
epad | +0.003 |
joy | +0.003 |
accomplishment | +0.002 |
Neg logit contributions | |
P | -0.003 |
bo | -0.003 |
me | -0.003 |
Mo | -0.003 |
Mom | -0.003 |
Token | on |
Token ID | 319 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
P | +0.011 |
me | +0.010 |
bo | +0.010 |
Mom | +0.010 |
Mo | +0.010 |
Neg logit contributions | |
gust | -0.026 |
ago | -0.024 |
epad | -0.024 |
joy | -0.023 |
ents | -0.022 |
Token | never |
Token ID | 1239 |
Feature activation | +2.79e-01 |
Pos logit contributions | |
gust | +0.001 |
ago | +0.001 |
epad | +0.001 |
ents | +0.001 |
joy | +0.001 |
Neg logit contributions | |
P | -0.001 |
bo | -0.001 |
me | -0.001 |
Mom | -0.001 |
Mo | -0.001 |
Token | played |
Token ID | 2826 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
me | +0.007 |
bo | +0.007 |
P | +0.007 |
was | +0.006 |
ey | +0.006 |
Neg logit contributions | |
gust | -0.014 |
ago | -0.014 |
epad | -0.013 |
joy | -0.013 |
pieces | -0.013 |
Token | with |
Token ID | 351 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
gust | +0.025 |
ago | +0.024 |
epad | +0.023 |
joy | +0.023 |
ents | +0.022 |
Neg logit contributions | |
P | -0.011 |
bo | -0.009 |
Mom | -0.009 |
me | -0.009 |
Mo | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
P | +0.010 |
bo | +0.009 |
me | +0.009 |
Mom | +0.009 |
Mo | +0.008 |
Neg logit contributions | |
gust | -0.013 |
ago | -0.013 |
epad | -0.012 |
ents | -0.011 |
joy | -0.011 |
Token | or |
Token ID | 393 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
gust | +0.006 |
ago | +0.006 |
epad | +0.006 |
ents | +0.005 |
joy | +0.005 |
Neg logit contributions | |
P | -0.005 |
me | -0.005 |
bo | -0.005 |
Mom | -0.005 |
Mo | -0.004 |
Token | nam |
Token ID | 7402 |
Feature activation | -5.52e+00 |
Pos logit contributions | |
me | +0.015 |
P | +0.013 |
bo | +0.013 |
was | +0.012 |
Mom | +0.012 |
Neg logit contributions | |
gust | -0.024 |
ago | -0.023 |
epad | -0.022 |
joy | -0.022 |
ents | -0.021 |
Token | ents |
Token ID | 658 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
gust | +0.102 |
ago | +0.073 |
joy | +0.071 |
accomplishment | +0.062 |
epad | +0.061 |
Neg logit contributions | |
P | -0.347 |
bo | -0.344 |
Mom | -0.338 |
me | -0.327 |
ey | -0.317 |
Token | again |
Token ID | 757 |
Feature activation | -8.51e-01 |
Pos logit contributions | |
gust | +0.081 |
ago | +0.073 |
joy | +0.070 |
epad | +0.070 |
ents | +0.067 |
Neg logit contributions | |
bo | -0.048 |
was | -0.048 |
me | -0.047 |
away | -0.044 |
P | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
gust | +0.044 |
ago | +0.042 |
epad | +0.042 |
ents | +0.040 |
joy | +0.039 |
Neg logit contributions | |
P | -0.023 |
me | -0.021 |
bo | -0.020 |
Mom | -0.019 |
ey | -0.018 |
Token | They |
Token ID | 1119 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
ago | +0.011 |
gust | +0.011 |
epad | +0.010 |
joy | +0.010 |
ents | +0.010 |
Neg logit contributions | |
P | -0.005 |
bo | -0.004 |
me | -0.004 |
na | -0.004 |
Mom | -0.004 |
Token | still |
Token ID | 991 |
Feature activation | +9.52e-01 |
Pos logit contributions | |
P | +0.011 |
me | +0.010 |
bo | +0.010 |
Mom | +0.010 |
Mo | +0.010 |
Neg logit contributions | |
gust | -0.015 |
ago | -0.014 |
epad | -0.014 |
ents | -0.013 |
joy | -0.013 |
Token | time |
Token ID | 640 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
P | +0.021 |
bo | +0.020 |
Mom | +0.019 |
Mo | +0.019 |
Mouse | +0.018 |
Neg logit contributions | |
gust | -0.025 |
ago | -0.024 |
epad | -0.022 |
joy | -0.022 |
accomplishment | -0.020 |
Token | playing |
Token ID | 2712 |
Feature activation | -6.59e-04 |
Pos logit contributions | |
gust | +0.016 |
epad | +0.015 |
ago | +0.015 |
ents | +0.014 |
joy | +0.014 |
Neg logit contributions | |
P | -0.010 |
me | -0.010 |
bo | -0.009 |
Mom | -0.008 |
ey | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | +9.90e-02 |
Pos logit contributions | |
gust | +0.000 |
ago | +0.000 |
epad | +0.000 |
joy | +0.000 |
pieces | +0.000 |
Neg logit contributions | |
bo | -0.000 |
P | -0.000 |
Mom | -0.000 |
Mo | -0.000 |
na | -0.000 |
Token | her |
Token ID | 607 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
P | +0.003 |
me | +0.002 |
bo | +0.002 |
Mom | +0.002 |
Mo | +0.002 |
Neg logit contributions | |
gust | -0.005 |
ago | -0.005 |
epad | -0.005 |
ents | -0.005 |
joy | -0.005 |
Token | or |
Token ID | 393 |
Feature activation | +1.19e-01 |
Pos logit contributions | |
gust | +0.017 |
ago | +0.016 |
epad | +0.016 |
joy | +0.015 |
ents | +0.015 |
Neg logit contributions | |
P | -0.012 |
bo | -0.011 |
me | -0.010 |
Mom | -0.010 |
Mo | -0.010 |
Token | nam |
Token ID | 7402 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
P | +0.004 |
me | +0.004 |
bo | +0.004 |
Mom | +0.004 |
Mo | +0.004 |
Neg logit contributions | |
gust | -0.005 |
ago | -0.005 |
epad | -0.005 |
ents | -0.004 |
joy | -0.004 |
Token | ents |
Token ID | 658 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
gust | +0.097 |
ago | +0.073 |
joy | +0.065 |
epad | +0.059 |
accomplishment | +0.055 |
Neg logit contributions | |
P | -0.352 |
bo | -0.339 |
Mom | -0.337 |
me | -0.330 |
ey | -0.317 |
Token | and |
Token ID | 290 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
gust | +0.121 |
joy | +0.110 |
epad | +0.109 |
ago | +0.109 |
ents | +0.105 |
Neg logit contributions | |
P | -0.037 |
bo | -0.035 |
was | -0.035 |
me | -0.034 |
ey | -0.031 |
Token | making |
Token ID | 1642 |
Feature activation | +2.08e-01 |
Pos logit contributions | |
gust | +0.009 |
ago | +0.008 |
epad | +0.008 |
joy | +0.008 |
ents | +0.008 |
Neg logit contributions | |
P | -0.006 |
me | -0.005 |
Mom | -0.005 |
bo | -0.005 |
was | -0.005 |
Token | her |
Token ID | 607 |
Feature activation | -1.55e-01 |
Pos logit contributions | |
P | +0.006 |
me | +0.006 |
bo | +0.005 |
Mom | +0.005 |
Mo | +0.005 |
Neg logit contributions | |
gust | -0.010 |
ago | -0.010 |
epad | -0.010 |
joy | -0.009 |
ents | -0.009 |
Token | special |
Token ID | 2041 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
gust | +0.007 |
ago | +0.007 |
epad | +0.007 |
ents | +0.006 |
joy | +0.006 |
Neg logit contributions | |
me | -0.004 |
P | -0.004 |
bo | -0.004 |
was | -0.004 |
Mom | -0.004 |
Token | she |
Token ID | 673 |
Feature activation | -8.31e-01 |
Pos logit contributions | |
gust | +0.062 |
ago | +0.059 |
epad | +0.058 |
ents | +0.054 |
joy | +0.054 |
Neg logit contributions | |
P | -0.048 |
me | -0.045 |
bo | -0.043 |
Mom | -0.042 |
na | -0.040 |
Token | had |
Token ID | 550 |
Feature activation | -3.80e-01 |
Pos logit contributions | |
gust | +0.039 |
ago | +0.038 |
epad | +0.037 |
joy | +0.035 |
ents | +0.035 |
Neg logit contributions | |
P | -0.026 |
me | -0.023 |
bo | -0.023 |
Mom | -0.022 |
Mo | -0.021 |
Token | with |
Token ID | 351 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
gust | +0.018 |
ago | +0.017 |
epad | +0.016 |
ents | +0.016 |
joy | +0.015 |
Neg logit contributions | |
P | -0.012 |
me | -0.011 |
bo | -0.011 |
Mom | -0.011 |
ey | -0.010 |
Token | her |
Token ID | 607 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
gust | +0.013 |
ago | +0.013 |
epad | +0.013 |
joy | +0.012 |
ents | +0.012 |
Neg logit contributions | |
P | -0.007 |
me | -0.006 |
bo | -0.006 |
Mom | -0.006 |
Mo | -0.006 |
Token | or |
Token ID | 393 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
gust | +0.012 |
ago | +0.012 |
epad | +0.012 |
ents | +0.011 |
joy | +0.011 |
Neg logit contributions | |
P | -0.008 |
me | -0.008 |
Mom | -0.007 |
bo | -0.007 |
na | -0.007 |
Token | nam |
Token ID | 7402 |
Feature activation | -5.50e+00 |
Pos logit contributions | |
gust | +0.001 |
ago | +0.001 |
epad | +0.001 |
ents | +0.001 |
joy | +0.001 |
Neg logit contributions | |
P | -0.001 |
me | -0.001 |
bo | -0.001 |
Mom | -0.001 |
Mo | -0.001 |
Token | ents |
Token ID | 658 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
gust | +0.093 |
ago | +0.063 |
joy | +0.056 |
epad | +0.053 |
accomplishment | +0.052 |
Neg logit contributions | |
P | -0.348 |
bo | -0.342 |
Mom | -0.339 |
me | -0.335 |
ey | -0.319 |
Token | . |
Token ID | 13 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
gust | +0.117 |
ago | +0.108 |
epad | +0.107 |
joy | +0.103 |
ents | +0.101 |
Neg logit contributions | |
me | -0.050 |
P | -0.050 |
bo | -0.048 |
was | -0.045 |
ey | -0.042 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.75e-01 |
Pos logit contributions | |
gust | +0.022 |
ago | +0.022 |
epad | +0.021 |
joy | +0.020 |
ents | +0.020 |
Neg logit contributions | |
P | -0.010 |
bo | -0.008 |
me | -0.008 |
ey | -0.008 |
Mom | -0.008 |
Token | Once |
Token ID | 7454 |
Feature activation | +1.02e-01 |
Pos logit contributions | |
ago | +0.050 |
gust | +0.048 |
joy | +0.046 |
epad | +0.044 |
ents | +0.042 |
Neg logit contributions | |
P | -0.025 |
an | -0.021 |
bo | -0.021 |
me | -0.021 |
Mom | -0.020 |
Token | upon |
Token ID | 2402 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
me | +0.003 |
was | +0.003 |
P | +0.003 |
Mom | +0.003 |
bo | +0.003 |
Neg logit contributions | |
epad | -0.005 |
gust | -0.004 |
pieces | -0.004 |
ago | -0.004 |
ents | -0.004 |
Token | Then |
Token ID | 6423 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
bo | +0.013 |
ey | +0.012 |
an | +0.012 |
P | +0.012 |
me | +0.012 |
Neg logit contributions | |
ago | -0.023 |
gust | -0.023 |
ents | -0.022 |
epad | -0.021 |
pieces | -0.021 |
Token | something |
Token ID | 1223 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
P | +0.020 |
bo | +0.019 |
an | +0.018 |
Mom | +0.017 |
Mo | +0.017 |
Neg logit contributions | |
gust | -0.024 |
ago | -0.024 |
epad | -0.022 |
joy | -0.021 |
pieces | -0.020 |
Token | even |
Token ID | 772 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
gust | +0.018 |
ago | +0.016 |
epad | +0.016 |
ents | +0.015 |
joy | +0.015 |
Neg logit contributions | |
P | -0.015 |
bo | -0.013 |
Mom | -0.013 |
ey | -0.013 |
Mo | -0.013 |
Token | we |
Token ID | 356 |
Feature activation | -2.36e-01 |
Pos logit contributions | |
P | +0.032 |
me | +0.030 |
bo | +0.028 |
was | +0.026 |
Mom | +0.025 |
Neg logit contributions | |
ago | -0.050 |
gust | -0.049 |
epad | -0.047 |
joy | -0.047 |
ents | -0.045 |
Token | ir |
Token ID | 343 |
Feature activation | -1.39e-01 |
Pos logit contributions | |
ago | +0.010 |
gust | +0.010 |
epad | +0.009 |
ents | +0.009 |
pieces | +0.008 |
Neg logit contributions | |
P | -0.009 |
Mom | -0.008 |
bo | -0.007 |
Mo | -0.007 |
omi | -0.007 |
Token | der |
Token ID | 1082 |
Feature activation | -5.46e+00 |
Pos logit contributions | |
gust | +0.007 |
ago | +0.006 |
epad | +0.006 |
ents | +0.006 |
joy | +0.006 |
Neg logit contributions | |
P | -0.004 |
me | -0.004 |
bo | -0.004 |
Mom | -0.004 |
Mo | -0.003 |
Token | happened |
Token ID | 3022 |
Feature activation | -6.15e-01 |
Pos logit contributions | |
gust | +0.255 |
ago | +0.250 |
epad | +0.241 |
ents | +0.227 |
joy | +0.226 |
Neg logit contributions | |
P | -0.171 |
bo | -0.153 |
me | -0.152 |
Mom | -0.149 |
Mo | -0.143 |
Token | . |
Token ID | 13 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
ago | +0.029 |
gust | +0.028 |
epad | +0.027 |
joy | +0.026 |
ents | +0.025 |
Neg logit contributions | |
P | -0.020 |
bo | -0.017 |
Mom | -0.017 |
me | -0.017 |
Mo | -0.016 |
Token | The |
Token ID | 383 |
Feature activation | -1.67e-01 |
Pos logit contributions | |
ago | +0.013 |
gust | +0.012 |
ents | +0.012 |
epad | +0.011 |
joy | +0.011 |
Neg logit contributions | |
P | -0.012 |
bo | -0.011 |
an | -0.011 |
me | -0.010 |
sy | -0.010 |
Token | animal |
Token ID | 5044 |
Feature activation | +4.08e-01 |
Pos logit contributions | |
gust | +0.008 |
ago | +0.008 |
epad | +0.007 |
joy | +0.007 |
ents | +0.007 |
Neg logit contributions | |
P | -0.005 |
bo | -0.005 |
Mom | -0.005 |
me | -0.005 |
Mo | -0.005 |
Token | suddenly |
Token ID | 6451 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
P | +0.012 |
Mom | +0.010 |
Mo | +0.010 |
bo | +0.009 |
H | +0.009 |
Neg logit contributions | |
gust | -0.021 |
ago | -0.020 |
ents | -0.019 |
epad | -0.017 |
pieces | -0.017 |
Token | a |
Token ID | 257 |
Feature activation | -1.52e-02 |
Pos logit contributions | |
P | +0.009 |
me | +0.009 |
Mom | +0.008 |
bo | +0.008 |
M | +0.007 |
Neg logit contributions | |
gust | -0.015 |
ago | -0.014 |
epad | -0.014 |
joy | -0.014 |
pieces | -0.013 |
Token | box |
Token ID | 3091 |
Feature activation | +6.35e-01 |
Pos logit contributions | |
gust | +0.001 |
ago | +0.001 |
epad | +0.001 |
joy | +0.001 |
ents | +0.001 |
Neg logit contributions | |
P | -0.000 |
bo | -0.000 |
ey | -0.000 |
Mo | -0.000 |
me | -0.000 |
Token | of |
Token ID | 286 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
P | +0.024 |
me | +0.022 |
bo | +0.022 |
Mom | +0.021 |
Mo | +0.020 |
Neg logit contributions | |
gust | -0.026 |
ago | -0.025 |
epad | -0.024 |
joy | -0.023 |
ents | -0.022 |
Token | shiny |
Token ID | 22441 |
Feature activation | -8.41e-02 |
Pos logit contributions | |
gust | +0.021 |
ago | +0.020 |
epad | +0.019 |
ents | +0.018 |
joy | +0.017 |
Neg logit contributions | |
P | -0.021 |
bo | -0.020 |
ey | -0.019 |
Mo | -0.018 |
na | -0.018 |
Token | or |
Token ID | 393 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
gust | +0.003 |
ago | +0.003 |
epad | +0.003 |
ents | +0.003 |
joy | +0.003 |
Neg logit contributions | |
P | -0.004 |
bo | -0.003 |
Mo | -0.003 |
Mom | -0.003 |
ey | -0.003 |
Token | nam |
Token ID | 7402 |
Feature activation | -5.45e+00 |
Pos logit contributions | |
P | +0.010 |
me | +0.009 |
Mom | +0.009 |
bo | +0.009 |
Mo | +0.009 |
Neg logit contributions | |
gust | -0.006 |
ago | -0.006 |
epad | -0.006 |
joy | -0.005 |
ents | -0.005 |
Token | ents |
Token ID | 658 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
gust | +0.096 |
joy | +0.070 |
ago | +0.068 |
accomplishment | +0.060 |
epad | +0.058 |
Neg logit contributions | |
P | -0.341 |
Mom | -0.334 |
bo | -0.333 |
me | -0.323 |
M | -0.310 |
Token | that |
Token ID | 326 |
Feature activation | +6.81e-02 |
Pos logit contributions | |
gust | +0.118 |
joy | +0.108 |
epad | +0.106 |
ago | +0.105 |
accomplishment | +0.100 |
Neg logit contributions | |
P | -0.033 |
bo | -0.032 |
me | -0.031 |
was | -0.029 |
sy | -0.027 |
Token | spark |
Token ID | 9009 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
P | +0.003 |
bo | +0.002 |
Mo | +0.002 |
ey | +0.002 |
Mom | +0.002 |
Neg logit contributions | |
gust | -0.003 |
ago | -0.003 |
epad | -0.002 |
ents | -0.002 |
joy | -0.002 |
Token | led |
Token ID | 992 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
gust | +0.010 |
ago | +0.010 |
epad | +0.010 |
joy | +0.009 |
ents | +0.009 |
Neg logit contributions | |
P | -0.010 |
me | -0.009 |
bo | -0.009 |
Mom | -0.009 |
Mo | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | -7.43e-02 |
Pos logit contributions | |
P | +0.028 |
me | +0.024 |
bo | +0.023 |
Mom | +0.022 |
Mo | +0.021 |
Neg logit contributions | |
gust | -0.071 |
ago | -0.069 |
epad | -0.067 |
ents | -0.064 |
joy | -0.064 |
Token | to |
Token ID | 284 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
gust | +0.059 |
ago | +0.058 |
epad | +0.056 |
joy | +0.053 |
ents | +0.053 |
Neg logit contributions | |
P | -0.036 |
bo | -0.032 |
me | -0.031 |
Mom | -0.031 |
Mo | -0.030 |
Token | help |
Token ID | 1037 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
gust | +0.022 |
ago | +0.022 |
epad | +0.021 |
pieces | +0.018 |
joy | +0.018 |
Neg logit contributions | |
P | -0.020 |
bo | -0.017 |
me | -0.017 |
Mo | -0.017 |
inct | -0.016 |
Token | sort |
Token ID | 3297 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
gust | +0.012 |
epad | +0.012 |
ago | +0.012 |
ents | +0.011 |
joy | +0.011 |
Neg logit contributions | |
P | -0.009 |
bo | -0.008 |
Mom | -0.007 |
Mo | -0.007 |
Hey | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
P | +0.052 |
bo | +0.047 |
Mo | +0.045 |
pee | +0.044 |
Mouse | +0.043 |
Neg logit contributions | |
gust | -0.063 |
ago | -0.059 |
epad | -0.058 |
ents | -0.056 |
joy | -0.056 |
Token | or |
Token ID | 393 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
gust | +0.009 |
ago | +0.009 |
epad | +0.008 |
joy | +0.008 |
ents | +0.008 |
Neg logit contributions | |
P | -0.008 |
bo | -0.007 |
me | -0.007 |
Mom | -0.007 |
Mo | -0.007 |
Token | nam |
Token ID | 7402 |
Feature activation | -5.38e+00 |
Pos logit contributions | |
P | +0.009 |
me | +0.009 |
Mom | +0.008 |
bo | +0.008 |
ey | +0.008 |
Neg logit contributions | |
gust | -0.008 |
ago | -0.007 |
epad | -0.007 |
joy | -0.007 |
ents | -0.007 |
Token | ents |
Token ID | 658 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
gust | +0.096 |
ago | +0.077 |
joy | +0.066 |
epad | +0.062 |
accomplishment | +0.054 |
Neg logit contributions | |
P | -0.342 |
Mom | -0.330 |
bo | -0.328 |
me | -0.322 |
ey | -0.312 |
Token | . |
Token ID | 13 |
Feature activation | -3.74e-01 |
Pos logit contributions | |
gust | +0.114 |
joy | +0.104 |
epad | +0.104 |
ago | +0.103 |
ents | +0.097 |
Neg logit contributions | |
was | -0.036 |
me | -0.034 |
bo | -0.032 |
P | -0.032 |
ey | -0.029 |
Token | She |
Token ID | 1375 |
Feature activation | -1.15e-03 |
Pos logit contributions | |
gust | +0.020 |
epad | +0.019 |
ago | +0.019 |
ents | +0.018 |
joy | +0.018 |
Neg logit contributions | |
P | -0.009 |
me | -0.008 |
Mom | -0.008 |
bo | -0.008 |
M | -0.007 |
Token | picked |
Token ID | 6497 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
gust | +0.000 |
ago | +0.000 |
ents | +0.000 |
epad | +0.000 |
joy | +0.000 |
Neg logit contributions | |
P | -0.000 |
bo | -0.000 |
Mo | -0.000 |
ey | -0.000 |
Mom | -0.000 |
Token | up |
Token ID | 510 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
P | +0.018 |
bo | +0.016 |
me | +0.016 |
Mom | +0.015 |
Mo | +0.015 |
Neg logit contributions | |
gust | -0.030 |
ago | -0.029 |
epad | -0.028 |
joy | -0.027 |
ents | -0.027 |
Token | can |
Token ID | 460 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
gust | +0.006 |
ago | +0.006 |
epad | +0.006 |
ents | +0.005 |
joy | +0.005 |
Neg logit contributions | |
P | -0.005 |
bo | -0.004 |
me | -0.004 |
Mo | -0.004 |
ey | -0.004 |
Token | we |
Token ID | 356 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
P | +0.040 |
sy | +0.035 |
Mo | +0.035 |
ey | +0.035 |
bo | +0.035 |
Neg logit contributions | |
gust | -0.032 |
ago | -0.030 |
ents | -0.028 |
epad | -0.027 |
pieces | -0.026 |
Token | have |
Token ID | 423 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
gust | +0.018 |
ago | +0.018 |
epad | +0.017 |
ents | +0.017 |
pieces | +0.016 |
Neg logit contributions | |
P | -0.016 |
Mo | -0.014 |
omi | -0.014 |
bo | -0.014 |
inct | -0.014 |
Token | some |
Token ID | 617 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
me | +0.003 |
P | +0.003 |
Mom | +0.002 |
bo | +0.002 |
yourself | +0.002 |
Neg logit contributions | |
gust | -0.006 |
epad | -0.006 |
ago | -0.006 |
joy | -0.005 |
pieces | -0.005 |
Token | or |
Token ID | 393 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
gust | +0.061 |
ago | +0.059 |
epad | +0.057 |
ents | +0.053 |
joy | +0.053 |
Neg logit contributions | |
P | -0.052 |
bo | -0.048 |
me | -0.047 |
Mom | -0.046 |
Mo | -0.045 |
Token | nam |
Token ID | 7402 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
P | +0.003 |
me | +0.003 |
bo | +0.003 |
Mom | +0.003 |
Mo | +0.003 |
Neg logit contributions | |
gust | -0.003 |
ago | -0.002 |
epad | -0.002 |
joy | -0.002 |
ents | -0.002 |
Token | ents |
Token ID | 658 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
gust | +0.093 |
joy | +0.068 |
ago | +0.066 |
accomplishment | +0.058 |
epad | +0.056 |
Neg logit contributions | |
P | -0.340 |
bo | -0.335 |
Mom | -0.331 |
me | -0.324 |
ey | -0.311 |
Token | for |
Token ID | 329 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
gust | +0.108 |
ago | +0.104 |
epad | +0.102 |
joy | +0.098 |
ents | +0.096 |
Neg logit contributions | |
P | -0.047 |
me | -0.042 |
bo | -0.042 |
Mom | -0.039 |
ey | -0.036 |
Token | our |
Token ID | 674 |
Feature activation | +8.68e-02 |
Pos logit contributions | |
gust | +0.013 |
ago | +0.012 |
epad | +0.012 |
joy | +0.011 |
ents | +0.011 |
Neg logit contributions | |
P | -0.007 |
me | -0.006 |
bo | -0.006 |
Mom | -0.006 |
Mo | -0.005 |
Token | snow |
Token ID | 6729 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
me | +0.003 |
P | +0.003 |
Mom | +0.003 |
bo | +0.002 |
na | +0.002 |
Neg logit contributions | |
gust | -0.004 |
ago | -0.004 |
epad | -0.004 |
joy | -0.003 |
ents | -0.003 |
Token | man |
Token ID | 805 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
gust | +0.068 |
ago | +0.067 |
epad | +0.064 |
ents | +0.062 |
joy | +0.060 |
Neg logit contributions | |
P | -0.025 |
Mo | -0.021 |
H | -0.019 |
Mom | -0.019 |
Mouse | -0.019 |
Token | still |
Token ID | 991 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
P | +0.028 |
Mom | +0.023 |
Mo | +0.023 |
bo | +0.022 |
Mouse | +0.021 |
Neg logit contributions | |
gust | -0.038 |
ago | -0.036 |
epad | -0.034 |
ents | -0.033 |
joy | -0.032 |
Token | remembered |
Token ID | 12086 |
Feature activation | +2.04e-01 |
Pos logit contributions | |
P | +0.032 |
me | +0.028 |
bo | +0.028 |
Mom | +0.028 |
Mo | +0.027 |
Neg logit contributions | |
gust | -0.047 |
ago | -0.046 |
epad | -0.045 |
joy | -0.042 |
ents | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | -3.51e-01 |
Pos logit contributions | |
P | +0.007 |
bo | +0.006 |
Mom | +0.006 |
me | +0.006 |
Mo | +0.006 |
Neg logit contributions | |
gust | -0.009 |
ago | -0.009 |
epad | -0.008 |
joy | -0.008 |
ents | -0.008 |
Token | big |
Token ID | 1263 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
gust | +0.016 |
ago | +0.015 |
epad | +0.015 |
joy | +0.014 |
ents | +0.014 |
Neg logit contributions | |
P | -0.012 |
bo | -0.011 |
me | -0.011 |
Mom | -0.010 |
Mo | -0.010 |
Token | aer |
Token ID | 9551 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
gust | +0.006 |
ago | +0.006 |
epad | +0.006 |
joy | +0.005 |
ents | +0.005 |
Neg logit contributions | |
P | -0.004 |
me | -0.004 |
bo | -0.004 |
Mom | -0.004 |
Mo | -0.004 |
Token | opl |
Token ID | 20106 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
gust | +0.090 |
epad | +0.084 |
ago | +0.084 |
joy | +0.080 |
theirs | +0.077 |
Neg logit contributions | |
P | -0.061 |
bo | -0.059 |
me | -0.055 |
na | -0.052 |
Mom | -0.052 |
Token | ane |
Token ID | 1531 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
gust | +0.215 |
ago | +0.197 |
epad | +0.195 |
joy | +0.184 |
ents | +0.176 |
Neg logit contributions | |
P | -0.210 |
bo | -0.194 |
Mom | -0.187 |
me | -0.185 |
na | -0.183 |
Token | flying |
Token ID | 7348 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
gust | +0.030 |
ago | +0.029 |
epad | +0.029 |
joy | +0.027 |
ents | +0.027 |
Neg logit contributions | |
P | -0.016 |
me | -0.014 |
bo | -0.014 |
Mom | -0.013 |
Mo | -0.013 |
Token | high |
Token ID | 1029 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
gust | +0.079 |
ago | +0.077 |
epad | +0.075 |
joy | +0.071 |
ents | +0.070 |
Neg logit contributions | |
P | -0.047 |
bo | -0.040 |
Mom | -0.040 |
me | -0.038 |
Mo | -0.038 |
Token | in |
Token ID | 287 |
Feature activation | -1.23e-01 |
Pos logit contributions | |
ago | +0.085 |
gust | +0.084 |
epad | +0.079 |
joy | +0.075 |
ents | +0.075 |
Neg logit contributions | |
P | -0.050 |
Mom | -0.044 |
bo | -0.042 |
Mo | -0.042 |
me | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
gust | +0.006 |
ago | +0.006 |
epad | +0.005 |
joy | +0.005 |
ents | +0.005 |
Neg logit contributions | |
P | -0.004 |
bo | -0.004 |
me | -0.003 |
Mom | -0.003 |
Mo | -0.003 |
Token | he |
Token ID | 339 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
me | +0.000 |
P | +0.000 |
Mom | +0.000 |
bo | +0.000 |
was | +0.000 |
Neg logit contributions | |
gust | -0.000 |
ago | -0.000 |
epad | -0.000 |
joy | -0.000 |
ents | -0.000 |
Token | especially |
Token ID | 2592 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
ago | +0.019 |
gust | +0.019 |
epad | +0.018 |
ents | +0.017 |
joy | +0.016 |
Neg logit contributions | |
P | -0.013 |
Mom | -0.011 |
Mo | -0.011 |
Hey | -0.010 |
bo | -0.010 |
Token | liked |
Token ID | 8288 |
Feature activation | -3.73e-01 |
Pos logit contributions | |
gust | +0.002 |
ago | +0.002 |
epad | +0.002 |
ents | +0.002 |
joy | +0.002 |
Neg logit contributions | |
P | -0.001 |
me | -0.001 |
bo | -0.001 |
Mom | -0.001 |
ey | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -1.74e-02 |
Pos logit contributions | |
gust | +0.018 |
ago | +0.017 |
epad | +0.017 |
ents | +0.016 |
joy | +0.016 |
Neg logit contributions | |
me | -0.011 |
P | -0.011 |
bo | -0.010 |
Mom | -0.009 |
was | -0.009 |
Token | or |
Token ID | 393 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
gust | +0.001 |
ago | +0.001 |
epad | +0.001 |
joy | +0.001 |
ents | +0.001 |
Neg logit contributions | |
P | -0.001 |
bo | -0.001 |
Mom | -0.001 |
me | -0.001 |
Mo | -0.001 |
Token | nam |
Token ID | 7402 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
me | +0.008 |
P | +0.008 |
bo | +0.007 |
Mom | +0.007 |
was | +0.007 |
Neg logit contributions | |
gust | -0.011 |
ago | -0.011 |
epad | -0.011 |
ents | -0.010 |
joy | -0.010 |
Token | ents |
Token ID | 658 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
gust | +0.093 |
ago | +0.070 |
joy | +0.066 |
epad | +0.056 |
accomplishment | +0.054 |
Neg logit contributions | |
P | -0.336 |
bo | -0.332 |
Mom | -0.328 |
me | -0.317 |
ey | -0.310 |
Token | he |
Token ID | 339 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
gust | +0.110 |
joy | +0.101 |
ago | +0.101 |
epad | +0.100 |
ents | +0.095 |
Neg logit contributions | |
bo | -0.037 |
P | -0.035 |
was | -0.034 |
me | -0.034 |
ey | -0.030 |
Token | kept |
Token ID | 4030 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
gust | +0.022 |
ago | +0.022 |
epad | +0.021 |
ents | +0.020 |
joy | +0.019 |
Neg logit contributions | |
P | -0.015 |
Mom | -0.013 |
bo | -0.013 |
me | -0.013 |
Mo | -0.013 |
Token | around |
Token ID | 1088 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
P | +0.005 |
bo | +0.004 |
me | +0.004 |
Mom | +0.004 |
Mo | +0.004 |
Neg logit contributions | |
gust | -0.007 |
ago | -0.007 |
epad | -0.007 |
joy | -0.006 |
ents | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
P | +0.009 |
me | +0.008 |
bo | +0.007 |
Mom | +0.007 |
ey | +0.007 |
Neg logit contributions | |
gust | -0.020 |
ago | -0.019 |
epad | -0.019 |
ents | -0.018 |
joy | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
gust | +0.001 |
ago | +0.001 |
epad | +0.001 |
ents | +0.001 |
joy | +0.001 |
Neg logit contributions | |
P | -0.001 |
me | -0.001 |
bo | -0.001 |
Mom | -0.001 |
Mo | -0.001 |
Token | look |
Token ID | 804 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
gust | +0.013 |
ago | +0.013 |
epad | +0.013 |
ents | +0.012 |
pieces | +0.011 |
Neg logit contributions | |
P | -0.010 |
bo | -0.009 |
Mom | -0.009 |
Mo | -0.009 |
me | -0.009 |
Token | at |
Token ID | 379 |
Feature activation | -7.05e-01 |
Pos logit contributions | |
P | +0.017 |
bo | +0.016 |
Mo | +0.015 |
Mom | +0.015 |
Mouse | +0.015 |
Neg logit contributions | |
gust | -0.015 |
ago | -0.014 |
epad | -0.014 |
ents | -0.014 |
joy | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
gust | +0.032 |
ago | +0.031 |
epad | +0.030 |
ents | +0.029 |
joy | +0.028 |
Neg logit contributions | |
P | -0.024 |
bo | -0.021 |
Mom | -0.020 |
na | -0.020 |
Mo | -0.019 |
Token | or |
Token ID | 393 |
Feature activation | +1.89e-01 |
Pos logit contributions | |
P | +0.002 |
bo | +0.002 |
Mo | +0.002 |
na | +0.002 |
ey | +0.002 |
Neg logit contributions | |
gust | -0.002 |
ago | -0.002 |
epad | -0.002 |
ents | -0.002 |
joy | -0.002 |
Token | nam |
Token ID | 7402 |
Feature activation | -5.34e+00 |
Pos logit contributions | |
P | +0.010 |
me | +0.010 |
bo | +0.009 |
Mom | +0.009 |
ey | +0.009 |
Neg logit contributions | |
gust | -0.005 |
ago | -0.005 |
epad | -0.004 |
ents | -0.004 |
joy | -0.004 |
Token | ents |
Token ID | 658 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
gust | +0.081 |
ago | +0.063 |
joy | +0.051 |
epad | +0.049 |
accomplishment | +0.041 |
Neg logit contributions | |
P | -0.351 |
bo | -0.339 |
Mom | -0.337 |
me | -0.332 |
ey | -0.322 |
Token | on |
Token ID | 319 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
gust | +0.116 |
joy | +0.110 |
ago | +0.103 |
epad | +0.101 |
accomplishment | +0.099 |
Neg logit contributions | |
was | -0.020 |
bo | -0.020 |
me | -0.020 |
ey | -0.019 |
with | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +2.58e-02 |
Pos logit contributions | |
gust | +0.012 |
ago | +0.011 |
epad | +0.011 |
joy | +0.010 |
ents | +0.010 |
Neg logit contributions | |
P | -0.007 |
me | -0.006 |
bo | -0.006 |
Mom | -0.006 |
Mo | -0.006 |
Token | tree |
Token ID | 5509 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
P | +0.001 |
bo | +0.001 |
Mo | +0.001 |
Mom | +0.001 |
ey | +0.001 |
Neg logit contributions | |
gust | -0.001 |
ago | -0.001 |
epad | -0.001 |
ents | -0.001 |
joy | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
gust | +0.020 |
joy | +0.019 |
epad | +0.019 |
ago | +0.018 |
accomplishment | +0.018 |
Neg logit contributions | |
me | -0.007 |
P | -0.007 |
bo | -0.006 |
was | -0.006 |
ey | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -1.69e-02 |
Pos logit contributions | |
P | +0.048 |
bo | +0.042 |
Mom | +0.041 |
me | +0.040 |
Mo | +0.039 |
Neg logit contributions | |
ago | -0.076 |
gust | -0.074 |
epad | -0.072 |
ents | -0.068 |
joy | -0.068 |
Token | play |
Token ID | 711 |
Feature activation | +6.33e-01 |
Pos logit contributions | |
gust | +0.001 |
ago | +0.001 |
epad | +0.001 |
ents | +0.001 |
joy | +0.001 |
Neg logit contributions | |
P | -0.001 |
bo | -0.001 |
Mom | -0.001 |
Mo | -0.001 |
na | -0.000 |
Token | with |
Token ID | 351 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
P | +0.016 |
bo | +0.014 |
Mom | +0.014 |
Mo | +0.013 |
me | +0.013 |
Neg logit contributions | |
gust | -0.033 |
ago | -0.032 |
epad | -0.031 |
joy | -0.030 |
ents | -0.029 |
Token | your |
Token ID | 534 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
P | +0.022 |
bo | +0.019 |
na | +0.019 |
Mom | +0.018 |
inct | +0.018 |
Neg logit contributions | |
gust | -0.029 |
ago | -0.029 |
epad | -0.026 |
ents | -0.026 |
theirs | -0.026 |
Token | or |
Token ID | 393 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
P | +0.021 |
bo | +0.019 |
Mom | +0.018 |
na | +0.018 |
Mo | +0.018 |
Neg logit contributions | |
gust | -0.027 |
ago | -0.026 |
epad | -0.024 |
joy | -0.024 |
ents | -0.022 |
Token | nam |
Token ID | 7402 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
P | +0.018 |
bo | +0.016 |
me | +0.015 |
Mom | +0.015 |
Mo | +0.015 |
Neg logit contributions | |
gust | -0.029 |
ago | -0.028 |
epad | -0.027 |
ents | -0.026 |
joy | -0.026 |
Token | ents |
Token ID | 658 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
gust | +0.105 |
ago | +0.079 |
joy | +0.074 |
accomplishment | +0.066 |
epad | +0.065 |
Neg logit contributions | |
P | -0.336 |
bo | -0.325 |
Mom | -0.320 |
me | -0.311 |
ey | -0.301 |
Token | . |
Token ID | 13 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
gust | +0.096 |
epad | +0.086 |
joy | +0.085 |
ago | +0.085 |
ents | +0.082 |
Neg logit contributions | |
P | -0.035 |
me | -0.034 |
bo | -0.033 |
was | -0.030 |
ey | -0.029 |
Token | Maybe |
Token ID | 6674 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
ago | +0.011 |
gust | +0.010 |
epad | +0.010 |
ents | +0.009 |
joy | +0.009 |
Neg logit contributions | |
P | -0.009 |
bo | -0.008 |
na | -0.007 |
me | -0.007 |
sy | -0.007 |
Token | you |
Token ID | 345 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
P | +0.021 |
bo | +0.019 |
me | +0.019 |
Mo | +0.018 |
Mom | +0.018 |
Neg logit contributions | |
gust | -0.019 |
ago | -0.019 |
epad | -0.018 |
ents | -0.016 |
joy | -0.016 |
Token | can |
Token ID | 460 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
P | +0.006 |
me | +0.005 |
bo | +0.005 |
Mom | +0.005 |
Mo | +0.005 |
Neg logit contributions | |
gust | -0.010 |
ago | -0.010 |
epad | -0.010 |
ents | -0.009 |
joy | -0.009 |
Token | All |
Token ID | 1439 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
gust | +0.014 |
ago | +0.014 |
epad | +0.013 |
joy | +0.013 |
ents | +0.013 |
Neg logit contributions | |
P | -0.007 |
bo | -0.006 |
me | -0.006 |
Mom | -0.006 |
Mo | -0.006 |
Token | of |
Token ID | 286 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
gust | +0.004 |
ago | +0.004 |
epad | +0.004 |
joy | +0.004 |
ents | +0.004 |
Neg logit contributions | |
P | -0.004 |
me | -0.004 |
bo | -0.004 |
Mom | -0.003 |
Mo | -0.003 |
Token | these |
Token ID | 777 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
gust | +0.018 |
ago | +0.018 |
epad | +0.017 |
joy | +0.016 |
ents | +0.016 |
Neg logit contributions | |
P | -0.011 |
bo | -0.010 |
me | -0.009 |
Mom | -0.009 |
na | -0.009 |
Token | lovely |
Token ID | 14081 |
Feature activation | +2.32e-01 |
Pos logit contributions | |
P | +0.010 |
me | +0.009 |
bo | +0.009 |
Mom | +0.009 |
Mo | +0.008 |
Neg logit contributions | |
gust | -0.015 |
ago | -0.015 |
epad | -0.014 |
joy | -0.013 |
ents | -0.013 |
Token | or |
Token ID | 393 |
Feature activation | +2.36e-01 |
Pos logit contributions | |
P | +0.007 |
me | +0.006 |
bo | +0.006 |
Mom | +0.006 |
Mo | +0.005 |
Neg logit contributions | |
gust | -0.012 |
ago | -0.011 |
epad | -0.011 |
ents | -0.010 |
joy | -0.010 |
Token | nam |
Token ID | 7402 |
Feature activation | -5.33e+00 |
Pos logit contributions | |
me | +0.011 |
P | +0.011 |
bo | +0.011 |
Mom | +0.011 |
was | +0.010 |
Neg logit contributions | |
gust | -0.007 |
ago | -0.006 |
epad | -0.006 |
joy | -0.006 |
ents | -0.005 |
Token | ents |
Token ID | 658 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
gust | +0.088 |
ago | +0.059 |
joy | +0.055 |
epad | +0.053 |
accomplishment | +0.049 |
Neg logit contributions | |
P | -0.345 |
bo | -0.335 |
Mom | -0.331 |
me | -0.326 |
ey | -0.315 |
Token | reminded |
Token ID | 14516 |
Feature activation | -1.91e-01 |
Pos logit contributions | |
gust | +0.101 |
epad | +0.094 |
ago | +0.094 |
joy | +0.092 |
ents | +0.088 |
Neg logit contributions | |
P | -0.049 |
bo | -0.047 |
me | -0.046 |
was | -0.045 |
ey | -0.042 |
Token | him |
Token ID | 683 |
Feature activation | +7.47e-01 |
Pos logit contributions | |
gust | +0.008 |
ago | +0.008 |
epad | +0.008 |
ents | +0.007 |
joy | +0.007 |
Neg logit contributions | |
P | -0.007 |
bo | -0.006 |
Mom | -0.006 |
inct | -0.005 |
Mo | -0.005 |
Token | of |
Token ID | 286 |
Feature activation | -4.87e-01 |
Pos logit contributions | |
P | +0.028 |
bo | +0.025 |
me | +0.025 |
Mom | +0.025 |
Mo | +0.024 |
Neg logit contributions | |
gust | -0.031 |
ago | -0.030 |
epad | -0.029 |
ents | -0.027 |
joy | -0.027 |
Token | the |
Token ID | 262 |
Feature activation | -9.44e-02 |
Pos logit contributions | |
gust | +0.023 |
ago | +0.022 |
epad | +0.022 |
ents | +0.020 |
joy | +0.020 |
Neg logit contributions | |
P | -0.015 |
me | -0.014 |
bo | -0.014 |
Mom | -0.013 |
Mo | -0.013 |
Token | 't |
Token ID | 470 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
gust | +0.034 |
epad | +0.034 |
ago | +0.034 |
ents | +0.032 |
joy | +0.031 |
Neg logit contributions | |
P | -0.015 |
me | -0.014 |
Mom | -0.013 |
bo | -0.012 |
M | -0.012 |
Token | know |
Token ID | 760 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
P | +0.024 |
me | +0.022 |
bo | +0.021 |
Mom | +0.021 |
Mo | +0.020 |
Neg logit contributions | |
gust | -0.034 |
ago | -0.033 |
epad | -0.032 |
joy | -0.030 |
ents | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
P | +0.014 |
bo | +0.013 |
me | +0.013 |
Mom | +0.013 |
Mo | +0.012 |
Neg logit contributions | |
gust | -0.017 |
ago | -0.016 |
epad | -0.016 |
ents | -0.015 |
joy | -0.015 |
Token | rh |
Token ID | 9529 |
Feature activation | -3.50e+00 |
Pos logit contributions | |
gust | +0.021 |
ago | +0.020 |
epad | +0.019 |
joy | +0.018 |
ents | +0.017 |
Neg logit contributions | |
P | -0.016 |
bo | -0.014 |
Mom | -0.014 |
Mo | -0.014 |
ey | -0.013 |
Token | in |
Token ID | 259 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
gust | +0.199 |
ago | +0.192 |
epad | +0.189 |
joy | +0.178 |
ents | +0.177 |
Neg logit contributions | |
P | -0.081 |
bo | -0.069 |
me | -0.066 |
ey | -0.063 |
Mom | -0.062 |
Token | oc |
Token ID | 420 |
Feature activation | -5.31e+00 |
Pos logit contributions | |
P | +0.019 |
Mom | +0.017 |
Mo | +0.015 |
me | +0.015 |
yourself | +0.015 |
Neg logit contributions | |
gust | -0.023 |
ago | -0.022 |
epad | -0.021 |
joy | -0.020 |
ents | -0.020 |
Token | eros |
Token ID | 27498 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
gust | +0.238 |
ago | +0.237 |
epad | +0.226 |
joy | +0.219 |
ents | +0.218 |
Neg logit contributions | |
P | -0.175 |
Mom | -0.153 |
me | -0.151 |
bo | -0.149 |
Mo | -0.147 |
Token | was |
Token ID | 373 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
ago | +0.015 |
gust | +0.015 |
epad | +0.014 |
ents | +0.014 |
joy | +0.014 |
Neg logit contributions | |
P | -0.006 |
Mom | -0.005 |
bo | -0.004 |
Mo | -0.004 |
Ang | -0.004 |
Token | wild |
Token ID | 4295 |
Feature activation | -7.68e-01 |
Pos logit contributions | |
gust | +0.018 |
ago | +0.018 |
epad | +0.017 |
ents | +0.016 |
joy | +0.016 |
Neg logit contributions | |
P | -0.014 |
me | -0.012 |
bo | -0.012 |
Mom | -0.012 |
Mo | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
gust | +0.037 |
ago | +0.037 |
epad | +0.035 |
joy | +0.034 |
ents | +0.033 |
Neg logit contributions | |
P | -0.024 |
Mom | -0.021 |
bo | -0.020 |
me | -0.019 |
Mo | -0.019 |
Token | Can |
Token ID | 1680 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
ago | +0.030 |
gust | +0.029 |
ents | +0.026 |
joy | +0.026 |
epad | +0.025 |
Neg logit contributions | |
P | -0.026 |
bo | -0.023 |
sy | -0.023 |
ey | -0.022 |
an | -0.022 |
Token | at |
Token ID | 379 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
P | +0.044 |
me | +0.041 |
bo | +0.040 |
Mom | +0.038 |
ey | +0.037 |
Neg logit contributions | |
gust | -0.045 |
ago | -0.043 |
epad | -0.042 |
ents | -0.039 |
joy | -0.038 |
Token | all |
Token ID | 477 |
Feature activation | -2.44e-01 |
Pos logit contributions | |
gust | +0.028 |
ago | +0.027 |
epad | +0.027 |
ents | +0.025 |
joy | +0.025 |
Neg logit contributions | |
P | -0.017 |
me | -0.015 |
bo | -0.015 |
Mom | -0.014 |
Mo | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -1.43e-02 |
Pos logit contributions | |
gust | +0.011 |
ago | +0.011 |
epad | +0.011 |
joy | +0.010 |
ents | +0.010 |
Neg logit contributions | |
P | -0.008 |
me | -0.007 |
bo | -0.007 |
Mom | -0.007 |
Mo | -0.006 |
Token | different |
Token ID | 1180 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
gust | +0.001 |
ago | +0.001 |
epad | +0.001 |
joy | +0.001 |
accomplishment | +0.000 |
Neg logit contributions | |
P | -0.001 |
bo | -0.001 |
Mom | -0.000 |
Mo | -0.000 |
pee | -0.000 |
Token | or |
Token ID | 393 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
P | +0.021 |
bo | +0.019 |
Mom | +0.018 |
Mo | +0.017 |
me | +0.017 |
Neg logit contributions | |
ago | -0.025 |
gust | -0.025 |
epad | -0.024 |
joy | -0.023 |
ents | -0.022 |
Token | nam |
Token ID | 7402 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
me | +0.011 |
P | +0.010 |
Mom | +0.010 |
was | +0.010 |
bo | +0.010 |
Neg logit contributions | |
gust | -0.006 |
ago | -0.006 |
epad | -0.006 |
ents | -0.005 |
joy | -0.005 |
Token | ents |
Token ID | 658 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
gust | +0.088 |
ago | +0.063 |
joy | +0.053 |
epad | +0.053 |
accomplishment | +0.046 |
Neg logit contributions | |
P | -0.341 |
bo | -0.333 |
Mom | -0.331 |
me | -0.322 |
ey | -0.316 |
Token | and |
Token ID | 290 |
Feature activation | -6.57e-02 |
Pos logit contributions | |
gust | +0.109 |
epad | +0.099 |
joy | +0.098 |
ago | +0.096 |
ents | +0.092 |
Neg logit contributions | |
was | -0.033 |
me | -0.031 |
bo | -0.030 |
ey | -0.029 |
P | -0.029 |
Token | adm |
Token ID | 6178 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
gust | +0.003 |
ago | +0.002 |
epad | +0.002 |
ents | +0.002 |
joy | +0.002 |
Neg logit contributions | |
me | -0.002 |
P | -0.002 |
Mom | -0.002 |
was | -0.002 |
bo | -0.002 |
Token | iring |
Token ID | 3428 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
gust | +0.070 |
ago | +0.068 |
epad | +0.066 |
ents | +0.063 |
joy | +0.062 |
Neg logit contributions | |
P | -0.048 |
bo | -0.043 |
me | -0.043 |
Mom | -0.042 |
Mo | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -9.92e-02 |
Pos logit contributions | |
P | +0.063 |
me | +0.058 |
bo | +0.057 |
Mom | +0.055 |
Mo | +0.053 |
Neg logit contributions | |
gust | -0.095 |
ago | -0.092 |
epad | -0.090 |
ents | -0.084 |
joy | -0.084 |
Token | car |
Token ID | 1097 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
gust | +0.004 |
ago | +0.004 |
epad | +0.004 |
joy | +0.004 |
ents | +0.004 |
Neg logit contributions | |
P | -0.003 |
bo | -0.003 |
me | -0.003 |
Mom | -0.002 |
Mo | -0.002 |
Token | made |
Token ID | 925 |
Feature activation | +2.69e-02 |
Pos logit contributions | |
me | +0.002 |
P | +0.002 |
bo | +0.002 |
was | +0.002 |
ey | +0.001 |
Neg logit contributions | |
gust | -0.004 |
ago | -0.004 |
epad | -0.004 |
joy | -0.004 |
ents | -0.003 |
Token | him |
Token ID | 683 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
P | +0.001 |
bo | +0.001 |
Mom | +0.001 |
me | +0.001 |
Mo | +0.001 |
Neg logit contributions | |
gust | -0.001 |
ago | -0.001 |
epad | -0.001 |
joy | -0.001 |
ents | -0.001 |
Token | even |
Token ID | 772 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
P | +0.023 |
bo | +0.022 |
me | +0.022 |
Mom | +0.020 |
ey | +0.020 |
Neg logit contributions | |
gust | -0.038 |
ago | -0.037 |
epad | -0.035 |
joy | -0.034 |
ents | -0.033 |
Token | sad |
Token ID | 6507 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
me | +0.023 |
P | +0.021 |
bo | +0.020 |
was | +0.020 |
p | +0.019 |
Neg logit contributions | |
ago | -0.031 |
gust | -0.030 |
epad | -0.028 |
joy | -0.028 |
ents | -0.027 |
Token | der |
Token ID | 1082 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
gust | +0.030 |
ago | +0.029 |
epad | +0.028 |
joy | +0.027 |
ents | +0.027 |
Neg logit contributions | |
P | -0.020 |
bo | -0.017 |
me | -0.017 |
Mom | -0.017 |
Mo | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -5.46e-01 |
Pos logit contributions | |
gust | +0.262 |
epad | +0.248 |
ago | +0.247 |
joy | +0.233 |
ents | +0.231 |
Neg logit contributions | |
P | -0.157 |
me | -0.142 |
bo | -0.139 |
Mom | -0.131 |
ey | -0.127 |
Token | He |
Token ID | 679 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
ago | +0.026 |
gust | +0.026 |
joy | +0.024 |
ents | +0.024 |
epad | +0.024 |
Neg logit contributions | |
P | -0.017 |
bo | -0.014 |
ey | -0.013 |
sy | -0.013 |
an | -0.013 |
Token | asked |
Token ID | 1965 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
gust | +0.012 |
ago | +0.011 |
ents | +0.010 |
epad | +0.010 |
joy | +0.009 |
Neg logit contributions | |
P | -0.011 |
Mo | -0.009 |
Mom | -0.009 |
yourself | -0.009 |
Ron | -0.008 |
Token | everyone |
Token ID | 2506 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
P | +0.011 |
bo | +0.009 |
Mom | +0.009 |
me | +0.008 |
Mo | +0.008 |
Neg logit contributions | |
gust | -0.018 |
ago | -0.018 |
epad | -0.017 |
joy | -0.017 |
ents | -0.016 |
Token | if |
Token ID | 611 |
Feature activation | +4.19e-02 |
Pos logit contributions | |
P | +0.021 |
bo | +0.019 |
me | +0.019 |
Mom | +0.019 |
Mo | +0.018 |
Neg logit contributions | |
gust | -0.024 |
ago | -0.023 |
epad | -0.022 |
joy | -0.021 |
ents | -0.021 |
Token | who |
Token ID | 508 |
Feature activation | +1.74e-01 |
Pos logit contributions | |
gust | +0.021 |
ago | +0.020 |
epad | +0.019 |
ents | +0.019 |
joy | +0.018 |
Neg logit contributions | |
P | -0.011 |
bo | -0.009 |
me | -0.009 |
Mo | -0.009 |
Mom | -0.009 |
Token | liked |
Token ID | 8288 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
P | +0.005 |
me | +0.004 |
Mom | +0.004 |
bo | +0.004 |
Mo | +0.004 |
Neg logit contributions | |
gust | -0.009 |
ago | -0.008 |
epad | -0.008 |
joy | -0.008 |
ents | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -5.16e-01 |
Pos logit contributions | |
gust | +0.031 |
ago | +0.031 |
epad | +0.030 |
pieces | +0.028 |
ents | +0.028 |
Neg logit contributions | |
P | -0.016 |
me | -0.016 |
Mom | -0.013 |
bo | -0.013 |
was | -0.012 |
Token | collect |
Token ID | 2824 |
Feature activation | +6.21e-01 |
Pos logit contributions | |
gust | +0.024 |
ago | +0.023 |
epad | +0.022 |
ents | +0.021 |
joy | +0.021 |
Neg logit contributions | |
P | -0.017 |
bo | -0.015 |
me | -0.015 |
Mom | -0.015 |
Mo | -0.014 |
Token | or |
Token ID | 393 |
Feature activation | +1.29e-01 |
Pos logit contributions | |
P | +0.022 |
Mom | +0.022 |
bo | +0.022 |
na | +0.021 |
Mo | +0.021 |
Neg logit contributions | |
gust | -0.024 |
ago | -0.023 |
ents | -0.022 |
epad | -0.022 |
joy | -0.021 |
Token | nam |
Token ID | 7402 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
P | +0.008 |
me | +0.007 |
Mom | +0.007 |
bo | +0.007 |
ey | +0.007 |
Neg logit contributions | |
gust | -0.003 |
ago | -0.002 |
epad | -0.002 |
joy | -0.002 |
ents | -0.002 |
Token | ents |
Token ID | 658 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
gust | +0.094 |
ago | +0.075 |
joy | +0.069 |
epad | +0.063 |
accomplishment | +0.057 |
Neg logit contributions | |
P | -0.338 |
bo | -0.327 |
Mom | -0.322 |
me | -0.319 |
ey | -0.306 |
Token | . |
Token ID | 13 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
gust | +0.118 |
joy | +0.109 |
epad | +0.106 |
ago | +0.103 |
accomplishment | +0.103 |
Neg logit contributions | |
was | -0.027 |
bo | -0.027 |
P | -0.026 |
me | -0.025 |
ey | -0.021 |
Token | Everywhere |
Token ID | 48201 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
gust | +0.006 |
epad | +0.006 |
ago | +0.006 |
joy | +0.006 |
accomplishment | +0.006 |
Neg logit contributions | |
me | -0.002 |
Mom | -0.002 |
P | -0.002 |
M | -0.002 |
bo | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
P | +0.044 |
me | +0.042 |
bo | +0.040 |
Mom | +0.040 |
na | +0.037 |
Neg logit contributions | |
gust | -0.042 |
epad | -0.041 |
ago | -0.041 |
ents | -0.038 |
joy | -0.038 |
Token | went |
Token ID | 1816 |
Feature activation | +9.15e-02 |
Pos logit contributions | |
gust | +0.037 |
ago | +0.036 |
epad | +0.035 |
ents | +0.033 |
joy | +0.033 |
Neg logit contributions | |
P | -0.016 |
me | -0.014 |
bo | -0.013 |
Mom | -0.013 |
Mo | -0.012 |
Token | This |
Token ID | 770 |
Feature activation | +8.70e-01 |
Pos logit contributions | |
gust | +0.021 |
ago | +0.021 |
epad | +0.019 |
ents | +0.019 |
joy | +0.019 |
Neg logit contributions | |
P | -0.015 |
bo | -0.014 |
Mom | -0.013 |
ey | -0.013 |
me | -0.013 |
Token | made |
Token ID | 925 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
P | +0.022 |
Mom | +0.020 |
bo | +0.019 |
ey | +0.018 |
pee | +0.018 |
Neg logit contributions | |
gust | -0.048 |
ago | -0.044 |
joy | -0.040 |
epad | -0.040 |
ents | -0.040 |
Token | her |
Token ID | 607 |
Feature activation | -1.46e-01 |
Pos logit contributions | |
P | +0.004 |
bo | +0.004 |
Mom | +0.004 |
ey | +0.004 |
na | +0.003 |
Neg logit contributions | |
gust | -0.006 |
ago | -0.005 |
epad | -0.005 |
ents | -0.005 |
joy | -0.005 |
Token | even |
Token ID | 772 |
Feature activation | +6.91e-01 |
Pos logit contributions | |
gust | +0.007 |
ago | +0.007 |
epad | +0.006 |
joy | +0.006 |
ents | +0.006 |
Neg logit contributions | |
P | -0.005 |
me | -0.004 |
bo | -0.004 |
Mom | -0.004 |
Mo | -0.004 |
Token | glad |
Token ID | 9675 |
Feature activation | -7.98e-01 |
Pos logit contributions | |
me | +0.024 |
P | +0.024 |
bo | +0.022 |
was | +0.022 |
p | +0.020 |
Neg logit contributions | |
ago | -0.029 |
epad | -0.028 |
gust | -0.028 |
joy | -0.026 |
ents | -0.026 |
Token | der |
Token ID | 1082 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
gust | +0.034 |
ago | +0.033 |
epad | +0.031 |
joy | +0.030 |
ents | +0.029 |
Neg logit contributions | |
P | -0.030 |
bo | -0.027 |
Mom | -0.026 |
Mo | -0.025 |
ey | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
gust | +0.243 |
ago | +0.235 |
epad | +0.229 |
joy | +0.215 |
ents | +0.215 |
Neg logit contributions | |
P | -0.172 |
me | -0.155 |
bo | -0.153 |
Mom | -0.148 |
Mo | -0.143 |
Token | she |
Token ID | 673 |
Feature activation | -7.53e-01 |
Pos logit contributions | |
gust | +0.005 |
ago | +0.005 |
epad | +0.004 |
ents | +0.004 |
joy | +0.004 |
Neg logit contributions | |
P | -0.004 |
me | -0.003 |
bo | -0.003 |
Mom | -0.003 |
Mo | -0.003 |
Token | smiled |
Token ID | 13541 |
Feature activation | -5.65e-01 |
Pos logit contributions | |
gust | +0.029 |
ents | +0.027 |
ago | +0.027 |
epad | +0.025 |
joy | +0.024 |
Neg logit contributions | |
P | -0.029 |
Mom | -0.025 |
inct | -0.024 |
Mo | -0.024 |
yourself | -0.024 |
Token | with |
Token ID | 351 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
gust | +0.027 |
ago | +0.026 |
epad | +0.025 |
joy | +0.024 |
ents | +0.024 |
Neg logit contributions | |
P | -0.018 |
bo | -0.016 |
me | -0.015 |
Mom | -0.015 |
Mo | -0.014 |
Token | joy |
Token ID | 8716 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
gust | +0.004 |
ago | +0.004 |
epad | +0.004 |
ents | +0.004 |
joy | +0.004 |
Neg logit contributions | |
P | -0.004 |
me | -0.004 |
bo | -0.003 |
Mom | -0.003 |
Mo | -0.003 |
Token | take |
Token ID | 1011 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
epad | +0.018 |
ago | +0.017 |
gust | +0.017 |
pieces | +0.015 |
accomplishment | +0.015 |
Neg logit contributions | |
P | -0.021 |
Mo | -0.018 |
bo | -0.018 |
M | -0.017 |
H | -0.017 |
Token | one |
Token ID | 530 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
P | +0.038 |
Mom | +0.036 |
an | +0.033 |
Mo | +0.033 |
bo | +0.033 |
Neg logit contributions | |
gust | -0.050 |
ago | -0.048 |
epad | -0.047 |
joy | -0.045 |
pieces | -0.044 |
Token | of |
Token ID | 286 |
Feature activation | -5.12e-01 |
Pos logit contributions | |
gust | +0.021 |
ago | +0.019 |
epad | +0.019 |
ents | +0.018 |
pieces | +0.017 |
Neg logit contributions | |
P | -0.021 |
bo | -0.019 |
Mo | -0.019 |
Mom | -0.019 |
ey | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +2.93e-02 |
Pos logit contributions | |
gust | +0.025 |
ago | +0.024 |
epad | +0.024 |
joy | +0.023 |
ents | +0.022 |
Neg logit contributions | |
P | -0.016 |
bo | -0.014 |
Mom | -0.013 |
me | -0.013 |
Mo | -0.012 |
Token | or |
Token ID | 393 |
Feature activation | +9.42e-02 |
Pos logit contributions | |
P | +0.001 |
me | +0.001 |
Mom | +0.001 |
bo | +0.001 |
na | +0.001 |
Neg logit contributions | |
gust | -0.001 |
ago | -0.001 |
epad | -0.001 |
ents | -0.001 |
joy | -0.001 |
Token | nam |
Token ID | 7402 |
Feature activation | -5.28e+00 |
Pos logit contributions | |
P | +0.004 |
bo | +0.004 |
me | +0.004 |
Mom | +0.004 |
Mo | +0.004 |
Neg logit contributions | |
gust | -0.003 |
ago | -0.003 |
epad | -0.003 |
ents | -0.003 |
joy | -0.003 |
Token | ents |
Token ID | 658 |
Feature activation | -2.02e+00 |
Pos logit contributions | |
gust | +0.087 |
ago | +0.062 |
joy | +0.056 |
epad | +0.052 |
accomplishment | +0.048 |
Neg logit contributions | |
P | -0.340 |
bo | -0.331 |
Mom | -0.329 |
me | -0.322 |
ey | -0.314 |
Token | outside |
Token ID | 2354 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
gust | +0.106 |
ago | +0.100 |
epad | +0.099 |
joy | +0.096 |
ents | +0.093 |
Neg logit contributions | |
P | -0.050 |
me | -0.047 |
bo | -0.046 |
ey | -0.041 |
was | -0.041 |
Token | for |
Token ID | 329 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
gust | +0.028 |
ago | +0.027 |
epad | +0.026 |
ents | +0.025 |
joy | +0.025 |
Neg logit contributions | |
P | -0.014 |
me | -0.013 |
bo | -0.012 |
Mom | -0.012 |
ey | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | -9.41e-02 |
Pos logit contributions | |
gust | +0.017 |
ago | +0.016 |
epad | +0.016 |
ents | +0.015 |
joy | +0.015 |
Neg logit contributions | |
P | -0.008 |
me | -0.007 |
bo | -0.007 |
Mom | -0.007 |
Mo | -0.006 |
Token | walk |
Token ID | 2513 |
Feature activation | -8.71e-01 |
Pos logit contributions | |
gust | +0.004 |
ago | +0.004 |
epad | +0.004 |
ents | +0.004 |
joy | +0.003 |
Neg logit contributions | |
P | -0.003 |
me | -0.003 |
bo | -0.003 |
Mom | -0.003 |
Mo | -0.003 |
Token | she |
Token ID | 673 |
Feature activation | -4.69e-01 |
Pos logit contributions | |
P | +0.016 |
bo | +0.014 |
me | +0.014 |
Mom | +0.014 |
Mo | +0.014 |
Neg logit contributions | |
gust | -0.013 |
ago | -0.012 |
epad | -0.012 |
ents | -0.011 |
joy | -0.011 |
Token | said |
Token ID | 531 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
gust | +0.023 |
ago | +0.021 |
ents | +0.021 |
epad | +0.021 |
joy | +0.019 |
Neg logit contributions | |
P | -0.014 |
Mo | -0.012 |
bo | -0.012 |
Mom | -0.012 |
ey | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e-01 |
Pos logit contributions | |
gust | +0.040 |
ago | +0.039 |
pieces | +0.038 |
epad | +0.038 |
ents | +0.037 |
Neg logit contributions | |
me | -0.007 |
bo | -0.006 |
Mom | -0.006 |
with | -0.005 |
up | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
gust | +0.005 |
ago | +0.005 |
epad | +0.005 |
joy | +0.005 |
ents | +0.005 |
Neg logit contributions | |
P | -0.005 |
bo | -0.005 |
me | -0.005 |
Mom | -0.004 |
Mo | -0.004 |
Token | We |
Token ID | 1135 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
gust | +0.015 |
ago | +0.015 |
epad | +0.015 |
joy | +0.014 |
ents | +0.014 |
Neg logit contributions | |
P | -0.005 |
me | -0.004 |
bo | -0.004 |
Mo | -0.004 |
na | -0.004 |
Token | will |
Token ID | 481 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
P | +0.027 |
Mo | +0.024 |
omi | +0.023 |
Mom | +0.023 |
M | +0.023 |
Neg logit contributions | |
ago | -0.028 |
gust | -0.027 |
epad | -0.026 |
ents | -0.024 |
anymore | -0.024 |
Token | leave |
Token ID | 2666 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
P | +0.059 |
Hey | +0.049 |
Mo | +0.048 |
bo | +0.047 |
H | +0.046 |
Neg logit contributions | |
ago | -0.064 |
epad | -0.061 |
gust | -0.059 |
ents | -0.054 |
accomplishment | -0.052 |
Token | them |
Token ID | 606 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
P | +0.026 |
bo | +0.023 |
sy | +0.022 |
na | +0.022 |
Mo | +0.022 |
Neg logit contributions | |
gust | -0.033 |
ago | -0.033 |
epad | -0.030 |
joy | -0.029 |
ents | -0.029 |
Token | alone |
Token ID | 3436 |
Feature activation | +7.02e-01 |
Pos logit contributions | |
P | +0.010 |
me | +0.010 |
bo | +0.009 |
Mom | +0.008 |
ey | +0.008 |
Neg logit contributions | |
gust | -0.023 |
epad | -0.021 |
ago | -0.021 |
joy | -0.020 |
ents | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
P | +0.017 |
me | +0.016 |
bo | +0.015 |
Mom | +0.015 |
ey | +0.014 |
Neg logit contributions | |
gust | -0.038 |
epad | -0.036 |
ago | -0.035 |
ents | -0.034 |
joy | -0.033 |
Token | But |
Token ID | 887 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
ago | +0.005 |
gust | +0.004 |
epad | +0.004 |
joy | +0.004 |
ents | +0.004 |
Neg logit contributions | |
P | -0.005 |
bo | -0.005 |
na | -0.005 |
Mo | -0.005 |
sy | -0.005 |
Token | Okay |
Token ID | 16454 |
Feature activation | +9.06e-01 |
Pos logit contributions | |
sy | +0.021 |
na | +0.020 |
ey | +0.019 |
P | +0.019 |
me | +0.019 |
Neg logit contributions | |
gust | -0.033 |
epad | -0.032 |
ago | -0.032 |
joy | -0.030 |
theirs | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
P | +0.035 |
Mo | +0.028 |
bo | +0.028 |
Mouse | +0.027 |
H | +0.027 |
Neg logit contributions | |
gust | -0.041 |
ago | -0.039 |
epad | -0.035 |
joy | -0.035 |
ents | -0.034 |
Token | okay |
Token ID | 8788 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
P | +0.002 |
bo | +0.002 |
Mo | +0.002 |
ey | +0.002 |
sy | +0.002 |
Neg logit contributions | |
gust | -0.002 |
ago | -0.002 |
epad | -0.002 |
ents | -0.002 |
joy | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | +2.14e-03 |
Pos logit contributions | |
P | +0.038 |
sy | +0.030 |
bo | +0.029 |
Mo | +0.029 |
H | +0.029 |
Neg logit contributions | |
gust | -0.049 |
ago | -0.045 |
ents | -0.041 |
epad | -0.041 |
anymore | -0.040 |
Token | I |
Token ID | 314 |
Feature activation | -4.80e-02 |
Pos logit contributions | |
P | +0.000 |
bo | +0.000 |
Mo | +0.000 |
Mom | +0.000 |
ey | +0.000 |
Neg logit contributions | |
gust | -0.000 |
ago | -0.000 |
epad | -0.000 |
ents | -0.000 |
joy | -0.000 |
Token | 'll |
Token ID | 1183 |
Feature activation | +2.22e+00 |
Pos logit contributions | |
ago | +0.002 |
gust | +0.002 |
epad | +0.002 |
joy | +0.002 |
anymore | +0.002 |
Neg logit contributions | |
P | -0.002 |
Mo | -0.001 |
na | -0.001 |
bo | -0.001 |
omi | -0.001 |
Token | go |
Token ID | 467 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
P | +0.105 |
Hey | +0.088 |
inct | +0.085 |
urous | +0.085 |
H | +0.084 |
Neg logit contributions | |
ago | -0.072 |
epad | -0.070 |
gust | -0.067 |
anymore | -0.064 |
ents | -0.057 |
Token | !" |
Token ID | 2474 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
P | +0.004 |
Mo | +0.003 |
inct | +0.003 |
Mouse | +0.003 |
na | +0.003 |
Neg logit contributions | |
ago | -0.005 |
epad | -0.004 |
gust | -0.004 |
ents | -0.004 |
joy | -0.004 |
Token | Ben |
Token ID | 3932 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
P | +0.032 |
Mo | +0.030 |
bo | +0.029 |
sy | +0.029 |
na | +0.029 |
Neg logit contributions | |
gust | -0.025 |
ago | -0.024 |
epad | -0.021 |
joy | -0.021 |
ents | -0.020 |
Token | said |
Token ID | 531 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
gust | +0.018 |
ents | +0.018 |
ago | +0.018 |
epad | +0.016 |
joy | +0.016 |
Neg logit contributions | |
P | -0.017 |
Mo | -0.016 |
yourself | -0.015 |
Mom | -0.014 |
Mouse | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
gust | +0.029 |
ago | +0.028 |
epad | +0.027 |
ents | +0.026 |
pieces | +0.026 |
Neg logit contributions | |
bo | -0.010 |
me | -0.009 |
P | -0.009 |
Mom | -0.009 |
was | -0.008 |
Token | that |
Token ID | 326 |
Feature activation | +5.52e-02 |
Pos logit contributions | |
P | +0.026 |
bo | +0.025 |
Mouse | +0.023 |
pee | +0.023 |
inct | +0.023 |
Neg logit contributions | |
gust | -0.021 |
ago | -0.021 |
ents | -0.019 |
accomplishment | -0.018 |
joy | -0.017 |
Token | day |
Token ID | 1110 |
Feature activation | +4.57e-01 |
Pos logit contributions | |
P | +0.002 |
bo | +0.002 |
Mom | +0.002 |
me | +0.002 |
Mo | +0.002 |
Neg logit contributions | |
gust | -0.002 |
ago | -0.002 |
epad | -0.002 |
joy | -0.002 |
accomplishment | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
P | +0.012 |
bo | +0.011 |
me | +0.011 |
Mom | +0.011 |
Mo | +0.010 |
Neg logit contributions | |
gust | -0.023 |
ago | -0.022 |
epad | -0.022 |
joy | -0.020 |
ents | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
gust | +0.020 |
ago | +0.020 |
joy | +0.017 |
epad | +0.017 |
accomplishment | +0.017 |
Neg logit contributions | |
P | -0.016 |
bo | -0.015 |
Mom | -0.014 |
Mouse | -0.013 |
an | -0.013 |
Token | the |
Token ID | 262 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
gust | +0.009 |
ago | +0.009 |
epad | +0.009 |
ents | +0.008 |
joy | +0.008 |
Neg logit contributions | |
P | -0.004 |
me | -0.004 |
Mom | -0.004 |
was | -0.004 |
na | -0.004 |
Token | two |
Token ID | 734 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
P | +0.000 |
me | +0.000 |
Mom | +0.000 |
bo | +0.000 |
na | +0.000 |
Neg logit contributions | |
gust | -0.001 |
ago | -0.001 |
epad | -0.001 |
ents | -0.001 |
joy | -0.001 |
Token | friends |
Token ID | 2460 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
P | +0.047 |
me | +0.045 |
was | +0.042 |
Mom | +0.041 |
p | +0.038 |
Neg logit contributions | |
ago | -0.088 |
epad | -0.088 |
gust | -0.078 |
sing | -0.075 |
joy | -0.075 |
Token | played |
Token ID | 2826 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
P | +0.033 |
Mom | +0.029 |
me | +0.029 |
bo | +0.029 |
Mo | +0.028 |
Neg logit contributions | |
ago | -0.039 |
gust | -0.039 |
epad | -0.037 |
ents | -0.035 |
joy | -0.034 |
Token | together |
Token ID | 1978 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
gust | +0.047 |
ago | +0.045 |
epad | +0.044 |
ents | +0.041 |
joy | +0.041 |
Neg logit contributions | |
P | -0.034 |
me | -0.031 |
bo | -0.030 |
Mom | -0.030 |
Mo | -0.029 |
Token | often |
Token ID | 1690 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
gust | +0.017 |
ago | +0.016 |
epad | +0.016 |
joy | +0.015 |
ents | +0.015 |
Neg logit contributions | |
P | -0.008 |
me | -0.007 |
ey | -0.006 |
was | -0.006 |
bo | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
gust | +0.007 |
epad | +0.007 |
ago | +0.007 |
ents | +0.007 |
joy | +0.007 |
Neg logit contributions | |
P | -0.002 |
me | -0.002 |
ey | -0.002 |
bo | -0.002 |
was | -0.002 |
Token | 't |
Token ID | 470 |
Feature activation | +4.97e-01 |
Pos logit contributions | |
gust | +0.020 |
ago | +0.019 |
epad | +0.019 |
ents | +0.018 |
joy | +0.017 |
Neg logit contributions | |
P | -0.010 |
me | -0.008 |
bo | -0.008 |
ey | -0.008 |
Mom | -0.008 |
Token | sure |
Token ID | 1654 |
Feature activation | +5.54e-01 |
Pos logit contributions | |
P | +0.012 |
me | +0.012 |
bo | +0.011 |
Mo | +0.010 |
ey | +0.010 |
Neg logit contributions | |
gust | -0.026 |
ago | -0.025 |
epad | -0.024 |
pieces | -0.024 |
ents | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +1.93e-01 |
Pos logit contributions | |
me | +0.016 |
P | +0.015 |
was | +0.014 |
yourself | +0.014 |
bo | +0.013 |
Neg logit contributions | |
gust | -0.028 |
epad | -0.025 |
ago | -0.024 |
joy | -0.024 |
pieces | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
P | +0.005 |
bo | +0.004 |
me | +0.004 |
ey | +0.004 |
na | +0.004 |
Neg logit contributions | |
gust | -0.010 |
ago | -0.010 |
joy | -0.010 |
epad | -0.009 |
ents | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +7.20e-01 |
Pos logit contributions | |
P | +0.018 |
bo | +0.016 |
me | +0.015 |
inct | +0.015 |
ey | +0.015 |
Neg logit contributions | |
gust | -0.036 |
ago | -0.036 |
ents | -0.034 |
epad | -0.033 |
joy | -0.033 |
Token | So |
Token ID | 2396 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
omi | +0.022 |
fl | +0.022 |
amb | +0.021 |
P | +0.021 |
iron | +0.020 |
Neg logit contributions | |
gust | -0.028 |
ents | -0.027 |
ago | -0.027 |
epad | -0.024 |
ways | -0.023 |
Token | he |
Token ID | 339 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
P | +0.062 |
bo | +0.057 |
Mom | +0.052 |
Mo | +0.052 |
ey | +0.052 |
Neg logit contributions | |
gust | -0.081 |
ago | -0.074 |
epad | -0.067 |
joy | -0.066 |
ents | -0.064 |
Token | bent |
Token ID | 17157 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
gust | +0.001 |
ents | +0.001 |
ago | +0.001 |
epad | +0.001 |
joy | +0.001 |
Neg logit contributions | |
yourself | -0.001 |
P | -0.001 |
Mom | -0.001 |
omi | -0.001 |
Mouse | -0.001 |
Token | down |
Token ID | 866 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
P | +0.017 |
H | +0.015 |
bo | +0.015 |
Mom | +0.015 |
na | +0.014 |
Neg logit contributions | |
gust | -0.019 |
ago | -0.018 |
joy | -0.018 |
epad | -0.018 |
ents | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
P | +0.014 |
bo | +0.013 |
me | +0.012 |
Mom | +0.012 |
Mo | +0.012 |
Neg logit contributions | |
gust | -0.025 |
ago | -0.025 |
epad | -0.023 |
joy | -0.023 |
ents | -0.023 |
Token | take |
Token ID | 1011 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
gust | +0.015 |
epad | +0.015 |
ago | +0.015 |
ents | +0.014 |
joy | +0.014 |
Neg logit contributions | |
P | -0.011 |
bo | -0.009 |
Mom | -0.009 |
Mo | -0.009 |
sy | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -2.35e-01 |
Pos logit contributions | |
P | +0.004 |
Mom | +0.003 |
bo | +0.003 |
yourself | +0.003 |
Mo | +0.003 |
Neg logit contributions | |
gust | -0.006 |
ago | -0.006 |
ents | -0.005 |
joy | -0.005 |
pieces | -0.005 |
Token | very |
Token ID | 845 |
Feature activation | +5.20e-01 |
Pos logit contributions | |
gust | +0.011 |
ago | +0.010 |
epad | +0.010 |
joy | +0.009 |
ents | +0.009 |
Neg logit contributions | |
P | -0.008 |
bo | -0.007 |
me | -0.007 |
Mom | -0.007 |
Mo | -0.007 |
Token | excited |
Token ID | 6568 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
P | +0.023 |
bo | +0.021 |
me | +0.020 |
Mom | +0.020 |
Mo | +0.020 |
Neg logit contributions | |
gust | -0.018 |
ago | -0.018 |
epad | -0.017 |
joy | -0.016 |
ents | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
gust | +0.039 |
ago | +0.038 |
epad | +0.037 |
ents | +0.035 |
joy | +0.035 |
Neg logit contributions | |
P | -0.017 |
me | -0.017 |
bo | -0.015 |
Mom | -0.014 |
na | -0.014 |
Token | qu |
Token ID | 627 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
P | +0.002 |
me | +0.002 |
bo | +0.002 |
Mom | +0.002 |
Mo | +0.002 |
Neg logit contributions | |
gust | -0.003 |
ago | -0.003 |
epad | -0.003 |
ents | -0.002 |
joy | -0.002 |
Token | acked |
Token ID | 6021 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
P | +0.042 |
Mom | +0.039 |
me | +0.038 |
na | +0.038 |
Mo | +0.038 |
Neg logit contributions | |
gust | -0.051 |
ago | -0.047 |
ents | -0.046 |
epad | -0.045 |
pieces | -0.044 |
Token | with |
Token ID | 351 |
Feature activation | +8.73e-04 |
Pos logit contributions | |
P | +0.083 |
bo | +0.074 |
me | +0.071 |
Mom | +0.070 |
Mo | +0.068 |
Neg logit contributions | |
gust | -0.133 |
ago | -0.128 |
epad | -0.125 |
joy | -0.120 |
ents | -0.117 |
Token | joy |
Token ID | 8716 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
P | +0.000 |
bo | +0.000 |
me | +0.000 |
Mom | +0.000 |
Mo | +0.000 |
Neg logit contributions | |
gust | -0.000 |
ago | -0.000 |
epad | -0.000 |
joy | -0.000 |
ents | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
gust | +0.027 |
ago | +0.025 |
epad | +0.025 |
ents | +0.024 |
pieces | +0.024 |
Neg logit contributions | |
P | -0.012 |
me | -0.012 |
bo | -0.011 |
Mo | -0.010 |
na | -0.010 |
Token | They |
Token ID | 1119 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
gust | +0.011 |
ago | +0.010 |
epad | +0.010 |
ents | +0.010 |
joy | +0.009 |
Neg logit contributions | |
P | -0.006 |
me | -0.005 |
bo | -0.005 |
Mom | -0.005 |
Mo | -0.005 |
Token | all |
Token ID | 477 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
P | +0.004 |
bo | +0.004 |
me | +0.004 |
Mom | +0.003 |
Mo | +0.003 |
Neg logit contributions | |
gust | -0.006 |
ago | -0.005 |
epad | -0.005 |
ents | -0.005 |
joy | -0.005 |
Token | said |
Token ID | 531 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
gust | +0.003 |
ago | +0.003 |
epad | +0.003 |
joy | +0.003 |
ents | +0.003 |
Neg logit contributions | |
P | -0.002 |
bo | -0.002 |
Mom | -0.002 |
Mo | -0.002 |
an | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
gust | +0.040 |
ago | +0.039 |
epad | +0.037 |
joy | +0.036 |
ents | +0.035 |
Neg logit contributions | |
P | -0.027 |
bo | -0.024 |
Mom | -0.024 |
me | -0.023 |
Mo | -0.022 |
Token | " |
Token ID | 366 |
Feature activation | -3.67e-02 |
Pos logit contributions | |
gust | +0.004 |
ago | +0.003 |
epad | +0.003 |
joy | +0.003 |
ents | +0.003 |
Neg logit contributions | |
P | -0.005 |
bo | -0.004 |
me | -0.004 |
Mom | -0.004 |
Mo | -0.004 |
Token | It |
Token ID | 1026 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
ago | +0.002 |
epad | +0.002 |
gust | +0.002 |
ents | +0.002 |
pieces | +0.002 |
Neg logit contributions | |
me | -0.001 |
P | -0.001 |
ey | -0.001 |
an | -0.001 |
bear | -0.001 |
Token | 's |
Token ID | 338 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
ago | +0.053 |
gust | +0.052 |
epad | +0.051 |
ents | +0.050 |
pieces | +0.048 |
Neg logit contributions | |
P | -0.040 |
Mom | -0.034 |
Mo | -0.031 |
omi | -0.028 |
M | -0.028 |
Token | Match |
Token ID | 13225 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
ago | +0.010 |
gust | +0.010 |
epad | +0.009 |
theirs | +0.009 |
ents | +0.009 |
Neg logit contributions | |
P | -0.009 |
bo | -0.007 |
Mouse | -0.007 |
Mom | -0.007 |
amb | -0.007 |
Token | Day |
Token ID | 3596 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
ago | +0.068 |
gust | +0.068 |
epad | +0.065 |
ents | +0.062 |
joy | +0.061 |
Neg logit contributions | |
P | -0.045 |
Mom | -0.040 |
bo | -0.039 |
me | -0.039 |
Mo | -0.037 |
Token | ! |
Token ID | 0 |
Feature activation | -3.39e-01 |
Pos logit contributions | |
ago | +0.032 |
gust | +0.032 |
epad | +0.030 |
joy | +0.029 |
ents | +0.028 |
Neg logit contributions | |
P | -0.018 |
bo | -0.016 |
Mom | -0.016 |
Mo | -0.015 |
me | -0.015 |
Token | Every |
Token ID | 3887 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
ago | +0.013 |
gust | +0.011 |
epad | +0.011 |
ents | +0.011 |
pieces | +0.010 |
Neg logit contributions | |
P | -0.015 |
an | -0.012 |
bo | -0.012 |
sy | -0.012 |
Mo | -0.012 |
Token | Sunday |
Token ID | 3502 |
Feature activation | +3.46e-03 |
Pos logit contributions | |
P | +0.026 |
bo | +0.023 |
me | +0.022 |
Mom | +0.022 |
Mo | +0.022 |
Neg logit contributions | |
gust | -0.032 |
ago | -0.031 |
epad | -0.030 |
joy | -0.028 |
ents | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -7.45e-02 |
Pos logit contributions | |
P | +0.000 |
bo | +0.000 |
Mom | +0.000 |
Mo | +0.000 |
M | +0.000 |
Neg logit contributions | |
ago | -0.000 |
gust | -0.000 |
epad | -0.000 |
ents | -0.000 |
joy | -0.000 |
Token | Alex |
Token ID | 4422 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
P | +0.002 |
bo | +0.002 |
me | +0.002 |
Mom | +0.002 |
ey | +0.002 |
Neg logit contributions | |
gust | -0.004 |
ago | -0.004 |
epad | -0.004 |
joy | -0.004 |
ents | -0.003 |
Token | went |
Token ID | 1816 |
Feature activation | -9.67e-02 |
Pos logit contributions | |
inct | +0.020 |
Mouse | +0.020 |
P | +0.020 |
Mo | +0.019 |
Mom | +0.018 |
Neg logit contributions | |
ago | -0.029 |
gust | -0.026 |
joy | -0.024 |
epad | -0.022 |
ents | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | -3.20e-01 |
Pos logit contributions | |
gust | +0.004 |
ago | +0.004 |
epad | +0.004 |
joy | +0.004 |
ents | +0.004 |
Neg logit contributions | |
P | -0.003 |
bo | -0.003 |
Mom | -0.003 |
Mo | -0.003 |
Mouse | -0.003 |
Token | the |
Token ID | 262 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
gust | +0.014 |
ago | +0.013 |
epad | +0.013 |
joy | +0.012 |
ents | +0.012 |
Neg logit contributions | |
P | -0.012 |
bo | -0.010 |
sy | -0.010 |
Mom | -0.010 |
inct | -0.010 |
Token | park |
Token ID | 3952 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
bo | +0.012 |
sy | +0.012 |
P | +0.012 |
ey | +0.012 |
Mo | +0.012 |
Neg logit contributions | |
gust | -0.014 |
ago | -0.013 |
ents | -0.012 |
epad | -0.012 |
pieces | -0.012 |
Token | with |
Token ID | 351 |
Feature activation | +6.39e-02 |
Pos logit contributions | |
gust | +0.019 |
epad | +0.018 |
ago | +0.018 |
ents | +0.017 |
joy | +0.017 |
Neg logit contributions | |
P | -0.004 |
me | -0.004 |
bo | -0.003 |
Mom | -0.003 |
was | -0.003 |
Token | his |
Token ID | 465 |
Feature activation | +6.83e-01 |
Pos logit contributions | |
P | +0.002 |
bo | +0.002 |
na | +0.002 |
inct | +0.001 |
ey | +0.001 |
Neg logit contributions | |
gust | -0.003 |
ago | -0.003 |
epad | -0.003 |
joy | -0.003 |
ents | -0.003 |
Token | mom |
Token ID | 1995 |
Feature activation | +6.34e-01 |
Pos logit contributions | |
bo | +0.022 |
P | +0.022 |
na | +0.020 |
ey | +0.020 |
inct | +0.020 |
Neg logit contributions | |
gust | -0.030 |
ago | -0.028 |
joy | -0.027 |
epad | -0.025 |
ents | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
P | +0.019 |
bo | +0.017 |
me | +0.017 |
Mo | +0.017 |
Mom | +0.016 |
Neg logit contributions | |
ago | -0.029 |
gust | -0.029 |
epad | -0.028 |
ents | -0.027 |
joy | -0.027 |
Token | His |
Token ID | 2399 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
P | +0.004 |
me | +0.004 |
bo | +0.003 |
Mom | +0.003 |
Mo | +0.003 |
Neg logit contributions | |
gust | -0.007 |
ago | -0.007 |
epad | -0.007 |
joy | -0.006 |
ents | -0.006 |
Token | mom |
Token ID | 1995 |
Feature activation | +5.72e-01 |
Pos logit contributions | |
P | +0.013 |
bo | +0.012 |
ey | +0.011 |
na | +0.011 |
Mo | +0.011 |
Neg logit contributions | |
gust | -0.016 |
ago | -0.015 |
joy | -0.014 |
epad | -0.014 |
accomplishment | -0.013 |
Token | him |
Token ID | 683 |
Feature activation | +6.37e-01 |
Pos logit contributions | |
gust | +0.004 |
ago | +0.004 |
epad | +0.004 |
ents | +0.004 |
joy | +0.004 |
Neg logit contributions | |
P | -0.002 |
me | -0.002 |
bo | -0.002 |
Mom | -0.002 |
Mo | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | +7.71e-02 |
Pos logit contributions | |
P | +0.017 |
bo | +0.015 |
me | +0.015 |
Mom | +0.014 |
Mo | +0.014 |
Neg logit contributions | |
gust | -0.033 |
ago | -0.032 |
epad | -0.031 |
joy | -0.030 |
ents | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +5.13e-03 |
Pos logit contributions | |
P | +0.003 |
bo | +0.002 |
Mom | +0.002 |
me | +0.002 |
Mo | +0.002 |
Neg logit contributions | |
gust | -0.003 |
ago | -0.003 |
epad | -0.003 |
joy | -0.003 |
ents | -0.003 |
Token | bear |
Token ID | 6842 |
Feature activation | +2.25e-01 |
Pos logit contributions | |
P | +0.000 |
bo | +0.000 |
Mom | +0.000 |
me | +0.000 |
ey | +0.000 |
Neg logit contributions | |
gust | -0.000 |
ago | -0.000 |
epad | -0.000 |
joy | -0.000 |
ents | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | -1.97e-01 |
Pos logit contributions | |
P | +0.006 |
me | +0.005 |
bo | +0.005 |
Mom | +0.005 |
Mo | +0.005 |
Neg logit contributions | |
gust | -0.011 |
ago | -0.011 |
epad | -0.011 |
ents | -0.010 |
joy | -0.010 |
Token | so |
Token ID | 523 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
gust | +0.009 |
ago | +0.008 |
epad | +0.008 |
joy | +0.008 |
ents | +0.008 |
Neg logit contributions | |
P | -0.007 |
me | -0.006 |
bo | -0.006 |
Mom | -0.006 |
Mo | -0.006 |
Token | grateful |
Token ID | 14066 |
Feature activation | -5.93e-01 |
Pos logit contributions | |
P | +0.010 |
me | +0.009 |
bo | +0.009 |
Mom | +0.009 |
na | +0.008 |
Neg logit contributions | |
gust | -0.011 |
ago | -0.010 |
epad | -0.010 |
joy | -0.009 |
ents | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
ago | +0.024 |
gust | +0.023 |
epad | +0.022 |
joy | +0.021 |
ents | +0.021 |
Neg logit contributions | |
P | -0.023 |
bo | -0.021 |
Mom | -0.020 |
me | -0.020 |
Mo | -0.020 |
Token | them |
Token ID | 606 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
ago | +0.022 |
gust | +0.022 |
epad | +0.021 |
joy | +0.020 |
pieces | +0.019 |
Neg logit contributions | |
P | -0.016 |
bo | -0.013 |
Mom | -0.013 |
Mo | -0.013 |
me | -0.013 |
Token | for |
Token ID | 329 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
P | +0.005 |
Mom | +0.004 |
bo | +0.004 |
me | +0.004 |
Mo | +0.004 |
Neg logit contributions | |
gust | -0.006 |
ago | -0.006 |
epad | -0.006 |
joy | -0.005 |
ents | -0.005 |
Token | welcoming |
Token ID | 22516 |
Feature activation | -5.35e-01 |
Pos logit contributions | |
gust | +0.016 |
ago | +0.015 |
epad | +0.015 |
ents | +0.014 |
joy | +0.014 |
Neg logit contributions | |
P | -0.011 |
me | -0.010 |
bo | -0.010 |
Mom | -0.010 |
Mo | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
gust | +0.008 |
ago | +0.008 |
epad | +0.007 |
ents | +0.007 |
joy | +0.007 |
Neg logit contributions | |
P | -0.006 |
bo | -0.006 |
me | -0.006 |
Mom | -0.006 |
Mo | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
P | +0.009 |
bo | +0.008 |
me | +0.008 |
Mom | +0.008 |
Mo | +0.007 |
Neg logit contributions | |
gust | -0.008 |
ago | -0.008 |
epad | -0.008 |
joy | -0.007 |
ents | -0.007 |
Token | Can |
Token ID | 6090 |
Feature activation | -9.71e-02 |
Pos logit contributions | |
sy | +0.008 |
inct | +0.008 |
na | +0.008 |
ate | +0.008 |
an | +0.008 |
Neg logit contributions | |
joy | -0.008 |
gust | -0.008 |
ago | -0.008 |
ents | -0.008 |
epad | -0.008 |
Token | I |
Token ID | 314 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
gust | +0.004 |
ago | +0.004 |
ents | +0.003 |
epad | +0.003 |
joy | +0.003 |
Neg logit contributions | |
P | -0.004 |
sy | -0.003 |
bo | -0.003 |
ey | -0.003 |
Mo | -0.003 |
Token | pet |
Token ID | 4273 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
inct | +0.009 |
omi | +0.009 |
P | +0.009 |
na | +0.009 |
Ang | +0.008 |
Neg logit contributions | |
gust | -0.005 |
ago | -0.005 |
ents | -0.004 |
theirs | -0.004 |
anymore | -0.004 |
Token | your |
Token ID | 534 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
sy | +0.072 |
P | +0.069 |
inct | +0.069 |
na | +0.065 |
Ang | +0.064 |
Neg logit contributions | |
gust | -0.067 |
ents | -0.062 |
theirs | -0.058 |
ago | -0.058 |
anymore | -0.058 |
Token | dog |
Token ID | 3290 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
P | +0.019 |
bo | +0.017 |
me | +0.016 |
Mom | +0.016 |
na | +0.015 |
Neg logit contributions | |
gust | -0.034 |
ago | -0.033 |
epad | -0.032 |
joy | -0.031 |
ents | -0.030 |
Token | ?" |
Token ID | 1701 |
Feature activation | -3.97e-01 |
Pos logit contributions | |
P | +0.012 |
Mo | +0.011 |
Mom | +0.011 |
bo | +0.010 |
na | +0.010 |
Neg logit contributions | |
gust | -0.023 |
ago | -0.022 |
epad | -0.021 |
ents | -0.020 |
joy | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
gust | +0.017 |
ago | +0.015 |
joy | +0.014 |
ents | +0.014 |
epad | +0.014 |
Neg logit contributions | |
P | -0.015 |
sy | -0.013 |
bo | -0.013 |
an | -0.013 |
inct | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
inct | +0.020 |
an | +0.019 |
sy | +0.019 |
asc | +0.018 |
P | +0.018 |
Neg logit contributions | |
gust | -0.026 |
ents | -0.023 |
ago | -0.023 |
joy | -0.021 |
pieces | -0.019 |
Token | The |
Token ID | 464 |
Feature activation | +4.99e-01 |
Pos logit contributions | |
inct | +0.018 |
an | +0.017 |
sy | +0.017 |
asc | +0.016 |
ate | +0.016 |
Neg logit contributions | |
gust | -0.026 |
ents | -0.023 |
ago | -0.021 |
sidelines | -0.021 |
pieces | -0.020 |
Token | very |
Token ID | 845 |
Feature activation | +5.23e-01 |
Pos logit contributions | |
gust | +0.031 |
ago | +0.029 |
epad | +0.028 |
pieces | +0.027 |
ents | +0.027 |
Neg logit contributions | |
P | -0.014 |
me | -0.014 |
was | -0.012 |
bo | -0.012 |
Mo | -0.012 |
Token | much |
Token ID | 881 |
Feature activation | -2.31e+00 |
Pos logit contributions | |
P | +0.024 |
bo | +0.022 |
me | +0.022 |
Mom | +0.021 |
Mo | +0.021 |
Neg logit contributions | |
gust | -0.017 |
ago | -0.017 |
epad | -0.017 |
joy | -0.016 |
ents | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
gust | +0.130 |
epad | +0.124 |
ago | +0.124 |
joy | +0.117 |
pieces | +0.116 |
Neg logit contributions | |
P | -0.051 |
me | -0.048 |
bo | -0.044 |
Mom | -0.041 |
Mo | -0.041 |
Token | He |
Token ID | 679 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
gust | +0.008 |
ago | +0.008 |
epad | +0.008 |
joy | +0.007 |
pieces | +0.007 |
Neg logit contributions | |
P | -0.003 |
me | -0.003 |
bo | -0.003 |
Mom | -0.003 |
Mo | -0.003 |
Token | would |
Token ID | 561 |
Feature activation | +2.75e-01 |
Pos logit contributions | |
ago | +0.012 |
gust | +0.011 |
epad | +0.011 |
ents | +0.010 |
joy | +0.009 |
Neg logit contributions | |
P | -0.010 |
Mom | -0.009 |
inct | -0.009 |
me | -0.009 |
omi | -0.009 |
Token | always |
Token ID | 1464 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
P | +0.009 |
Mom | +0.008 |
bo | +0.008 |
Mo | +0.008 |
na | +0.008 |
Neg logit contributions | |
gust | -0.012 |
ago | -0.012 |
epad | -0.012 |
ents | -0.011 |
pieces | -0.010 |
Token | carry |
Token ID | 3283 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
ago | +0.002 |
gust | +0.002 |
epad | +0.002 |
ents | +0.002 |
joy | +0.001 |
Neg logit contributions | |
P | -0.001 |
Mom | -0.001 |
Mo | -0.001 |
M | -0.001 |
bo | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | -8.66e-01 |
Pos logit contributions | |
P | +0.029 |
bo | +0.026 |
Mom | +0.025 |
na | +0.025 |
me | +0.024 |
Neg logit contributions | |
gust | -0.037 |
ago | -0.036 |
epad | -0.034 |
ents | -0.033 |
joy | -0.032 |
Token | with |
Token ID | 351 |
Feature activation | -2.92e-02 |
Pos logit contributions | |
gust | +0.030 |
ago | +0.029 |
epad | +0.029 |
ents | +0.026 |
joy | +0.026 |
Neg logit contributions | |
P | -0.037 |
bo | -0.034 |
me | -0.034 |
Mom | -0.034 |
Mo | -0.032 |
Token | him |
Token ID | 683 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
gust | +0.002 |
ago | +0.001 |
epad | +0.001 |
ents | +0.001 |
joy | +0.001 |
Neg logit contributions | |
P | -0.001 |
bo | -0.001 |
na | -0.001 |
Mom | -0.001 |
me | -0.001 |
Token | wherever |
Token ID | 14530 |
Feature activation | -2.50e-02 |
Pos logit contributions | |
P | +0.027 |
me | +0.025 |
bo | +0.024 |
Mom | +0.023 |
Mo | +0.023 |
Neg logit contributions | |
gust | -0.038 |
ago | -0.037 |
epad | -0.036 |
joy | -0.034 |
ents | -0.033 |
Token | blinking |
Token ID | 43196 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
gust | +0.006 |
ago | +0.006 |
epad | +0.005 |
joy | +0.005 |
ents | +0.005 |
Neg logit contributions | |
P | -0.007 |
bo | -0.006 |
Mom | -0.006 |
me | -0.006 |
na | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +1.80e-02 |
Pos logit contributions | |
P | +0.013 |
bo | +0.011 |
Mom | +0.011 |
Mo | +0.010 |
na | +0.010 |
Neg logit contributions | |
gust | -0.023 |
ago | -0.023 |
epad | -0.022 |
joy | -0.021 |
ents | -0.021 |
Token | dancing |
Token ID | 15360 |
Feature activation | +7.46e-01 |
Pos logit contributions | |
P | +0.000 |
bo | +0.000 |
Mom | +0.000 |
me | +0.000 |
Mo | +0.000 |
Neg logit contributions | |
gust | -0.001 |
ago | -0.001 |
epad | -0.001 |
joy | -0.001 |
ents | -0.001 |
Token | away |
Token ID | 1497 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
P | +0.021 |
bo | +0.018 |
Mom | +0.018 |
me | +0.017 |
Mo | +0.017 |
Neg logit contributions | |
gust | -0.038 |
ago | -0.037 |
epad | -0.036 |
joy | -0.034 |
ents | -0.034 |
Token | getting |
Token ID | 1972 |
Feature activation | -9.76e-01 |
Pos logit contributions | |
P | +0.070 |
me | +0.061 |
bo | +0.061 |
Mom | +0.059 |
Mo | +0.056 |
Neg logit contributions | |
gust | -0.127 |
ago | -0.124 |
epad | -0.121 |
joy | -0.114 |
ents | -0.114 |
Token | further |
Token ID | 2252 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
gust | +0.039 |
ago | +0.038 |
epad | +0.037 |
joy | +0.034 |
ents | +0.034 |
Neg logit contributions | |
P | -0.037 |
me | -0.034 |
bo | -0.034 |
Mom | -0.033 |
Mo | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | +2.84e-01 |
Pos logit contributions | |
gust | +0.101 |
ago | +0.100 |
epad | +0.096 |
joy | +0.091 |
ents | +0.091 |
Neg logit contributions | |
P | -0.048 |
Mom | -0.039 |
bo | -0.039 |
me | -0.039 |
Mo | -0.037 |
Token | further |
Token ID | 2252 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
me | +0.010 |
was | +0.009 |
P | +0.009 |
Mom | +0.009 |
bo | +0.009 |
Neg logit contributions | |
ago | -0.012 |
epad | -0.011 |
gust | -0.011 |
pieces | -0.011 |
ents | -0.011 |
Token | away |
Token ID | 1497 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
gust | +0.094 |
ago | +0.091 |
epad | +0.090 |
ents | +0.085 |
joy | +0.084 |
Neg logit contributions | |
P | -0.051 |
me | -0.045 |
bo | -0.045 |
Mom | -0.043 |
Mo | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
P | +0.056 |
me | +0.055 |
bo | +0.052 |
ey | +0.048 |
Mo | +0.047 |
Neg logit contributions | |
gust | -0.136 |
ago | -0.129 |
epad | -0.129 |
ents | -0.122 |
joy | -0.122 |
Token | He |
Token ID | 679 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
P | +0.005 |
me | +0.005 |
bo | +0.005 |
Mom | +0.004 |
Mo | +0.004 |
Neg logit contributions | |
gust | -0.008 |
ago | -0.007 |
epad | -0.007 |
ents | -0.007 |
joy | -0.007 |
Token | me |
Token ID | 502 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
P | +0.005 |
bo | +0.005 |
me | +0.005 |
Mom | +0.004 |
Mo | +0.004 |
Neg logit contributions | |
gust | -0.008 |
ago | -0.007 |
epad | -0.007 |
joy | -0.007 |
ents | -0.007 |
Token | adow |
Token ID | 4584 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
P | +0.069 |
Mom | +0.066 |
me | +0.064 |
Mo | +0.063 |
bo | +0.063 |
Neg logit contributions | |
ago | -0.037 |
epad | -0.033 |
gust | -0.033 |
ents | -0.030 |
joy | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +6.31e-02 |
Pos logit contributions | |
gust | +0.119 |
ago | +0.113 |
epad | +0.112 |
ents | +0.106 |
joy | +0.106 |
Neg logit contributions | |
P | -0.058 |
me | -0.052 |
bo | -0.051 |
Mom | -0.048 |
ey | -0.045 |
Token | He |
Token ID | 679 |
Feature activation | -3.25e-02 |
Pos logit contributions | |
P | +0.001 |
me | +0.001 |
bo | +0.001 |
Mom | +0.001 |
Mo | +0.001 |
Neg logit contributions | |
gust | -0.003 |
ago | -0.003 |
epad | -0.003 |
joy | -0.003 |
ents | -0.003 |
Token | saw |
Token ID | 2497 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
ago | +0.001 |
gust | +0.001 |
ents | +0.001 |
joy | +0.001 |
epad | +0.001 |
Neg logit contributions | |
P | -0.001 |
bo | -0.001 |
Mom | -0.001 |
yourself | -0.001 |
inct | -0.001 |
Token | lots |
Token ID | 6041 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
gust | +0.023 |
ago | +0.023 |
epad | +0.022 |
joy | +0.021 |
ents | +0.021 |
Neg logit contributions | |
P | -0.012 |
me | -0.011 |
bo | -0.010 |
Mom | -0.010 |
Mo | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | -4.78e-01 |
Pos logit contributions | |
gust | +0.059 |
ago | +0.056 |
epad | +0.054 |
ents | +0.050 |
joy | +0.049 |
Neg logit contributions | |
P | -0.081 |
bo | -0.075 |
me | -0.074 |
Mom | -0.073 |
Mo | -0.071 |
Token | insects |
Token ID | 19435 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
gust | +0.020 |
ago | +0.018 |
joy | +0.017 |
ents | +0.017 |
epad | +0.016 |
Neg logit contributions | |
bo | -0.018 |
P | -0.017 |
Mom | -0.016 |
na | -0.016 |
ey | -0.016 |
Token | flying |
Token ID | 7348 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
P | +0.009 |
me | +0.007 |
bo | +0.007 |
Mom | +0.007 |
Mo | +0.007 |
Neg logit contributions | |
gust | -0.019 |
ago | -0.018 |
epad | -0.018 |
joy | -0.017 |
ents | -0.017 |
Token | around |
Token ID | 1088 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
ago | +0.066 |
gust | +0.064 |
epad | +0.059 |
joy | +0.057 |
ents | +0.057 |
Neg logit contributions | |
P | -0.043 |
Mom | -0.040 |
bo | -0.040 |
na | -0.038 |
omi | -0.037 |
Token | and |
Token ID | 290 |
Feature activation | +7.43e-02 |
Pos logit contributions | |
P | +0.004 |
bo | +0.003 |
Mom | +0.003 |
me | +0.003 |
na | +0.003 |
Neg logit contributions | |
gust | -0.007 |
ago | -0.007 |
epad | -0.006 |
joy | -0.006 |
ents | -0.006 |
Token | day |
Token ID | 1110 |
Feature activation | +5.26e-01 |
Pos logit contributions | |
gust | +0.047 |
ago | +0.046 |
epad | +0.046 |
ents | +0.044 |
joy | +0.043 |
Neg logit contributions | |
P | -0.033 |
me | -0.030 |
bo | -0.030 |
Mom | -0.030 |
M | -0.028 |
Token | , |
Token ID | 11 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
P | +0.015 |
bo | +0.013 |
me | +0.012 |
Mom | +0.012 |
Mo | +0.012 |
Neg logit contributions | |
gust | -0.027 |
ago | -0.026 |
epad | -0.025 |
joy | -0.024 |
ents | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
P | +0.002 |
me | +0.002 |
Mom | +0.002 |
was | +0.002 |
M | +0.002 |
Neg logit contributions | |
epad | -0.008 |
ago | -0.008 |
gust | -0.007 |
ents | -0.007 |
pieces | -0.007 |
Token | little |
Token ID | 1310 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
P | +0.004 |
me | +0.003 |
bo | +0.003 |
Mom | +0.003 |
Mo | +0.003 |
Neg logit contributions | |
gust | -0.007 |
ago | -0.007 |
epad | -0.007 |
joy | -0.007 |
ents | -0.006 |
Token | girl |
Token ID | 2576 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
ago | +0.014 |
epad | +0.014 |
gust | +0.014 |
ents | +0.013 |
joy | +0.013 |
Neg logit contributions | |
P | -0.006 |
me | -0.005 |
bo | -0.005 |
Mom | -0.005 |
na | -0.004 |
Token | named |
Token ID | 3706 |
Feature activation | -2.01e+00 |
Pos logit contributions | |
ago | +0.018 |
gust | +0.018 |
epad | +0.016 |
joy | +0.016 |
ents | +0.015 |
Neg logit contributions | |
P | -0.014 |
Mo | -0.013 |
bo | -0.013 |
Mom | -0.013 |
inct | -0.013 |
Token | Lilly |
Token ID | 35134 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
gust | +0.088 |
ago | +0.084 |
epad | +0.083 |
joy | +0.078 |
ents | +0.077 |
Neg logit contributions | |
P | -0.069 |
me | -0.067 |
bo | -0.063 |
Mom | -0.062 |
na | -0.059 |
Token | saw |
Token ID | 2497 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
gust | +0.016 |
ago | +0.016 |
epad | +0.015 |
ents | +0.014 |
joy | +0.014 |
Neg logit contributions | |
P | -0.012 |
Mom | -0.010 |
bo | -0.010 |
Mo | -0.010 |
me | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | +2.67e-01 |
Pos logit contributions | |
gust | +0.025 |
ago | +0.025 |
epad | +0.024 |
ents | +0.023 |
joy | +0.023 |
Neg logit contributions | |
P | -0.015 |
me | -0.013 |
bo | -0.013 |
Mom | -0.012 |
Mo | -0.012 |
Token | plane |
Token ID | 6614 |
Feature activation | -8.73e-02 |
Pos logit contributions | |
P | +0.008 |
me | +0.008 |
Mom | +0.007 |
bo | +0.007 |
na | +0.007 |
Neg logit contributions | |
ago | -0.012 |
gust | -0.012 |
epad | -0.012 |
joy | -0.012 |
ents | -0.011 |
Token | in |
Token ID | 287 |
Feature activation | -1.30e-01 |
Pos logit contributions | |
gust | +0.005 |
ago | +0.005 |
epad | +0.005 |
joy | +0.005 |
ents | +0.005 |
Neg logit contributions | |
me | -0.002 |
was | -0.002 |
P | -0.001 |
bo | -0.001 |
ey | -0.001 |
Token | goal |
Token ID | 3061 |
Feature activation | +2.35e-02 |
Pos logit contributions | |
P | +0.004 |
me | +0.004 |
bo | +0.003 |
Mom | +0.003 |
was | +0.003 |
Neg logit contributions | |
ago | -0.005 |
epad | -0.004 |
gust | -0.004 |
ents | -0.004 |
pieces | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +1.01e-01 |
Pos logit contributions | |
me | +0.001 |
P | +0.001 |
bo | +0.000 |
was | +0.000 |
Mom | +0.000 |
Neg logit contributions | |
gust | -0.001 |
epad | -0.001 |
ago | -0.001 |
joy | -0.001 |
pieces | -0.001 |
Token | It |
Token ID | 632 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
P | +0.004 |
bo | +0.003 |
ey | +0.003 |
na | +0.003 |
me | +0.003 |
Neg logit contributions | |
gust | -0.004 |
ago | -0.004 |
epad | -0.004 |
ents | -0.004 |
joy | -0.004 |
Token | was |
Token ID | 373 |
Feature activation | -3.98e-02 |
Pos logit contributions | |
gust | +0.022 |
epad | +0.020 |
ents | +0.020 |
ago | +0.020 |
pieces | +0.018 |
Neg logit contributions | |
P | -0.009 |
Mom | -0.007 |
Mo | -0.006 |
omi | -0.006 |
ey | -0.006 |
Token | so |
Token ID | 523 |
Feature activation | +4.13e-01 |
Pos logit contributions | |
ago | +0.002 |
gust | +0.002 |
epad | +0.002 |
joy | +0.002 |
ents | +0.002 |
Neg logit contributions | |
P | -0.001 |
me | -0.001 |
bo | -0.001 |
Mom | -0.001 |
Mo | -0.001 |
Token | much |
Token ID | 881 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
P | +0.018 |
me | +0.017 |
Mom | +0.017 |
bo | +0.016 |
was | +0.016 |
Neg logit contributions | |
ago | -0.014 |
epad | -0.014 |
gust | -0.014 |
joy | -0.013 |
pieces | -0.013 |
Token | fun |
Token ID | 1257 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
ago | +0.088 |
gust | +0.085 |
epad | +0.084 |
joy | +0.079 |
ents | +0.077 |
Neg logit contributions | |
P | -0.084 |
me | -0.080 |
Mom | -0.075 |
bo | -0.075 |
was | -0.071 |
Token | ! |
Token ID | 0 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
gust | +0.060 |
ago | +0.058 |
epad | +0.057 |
ents | +0.054 |
joy | +0.054 |
Neg logit contributions | |
P | -0.028 |
me | -0.025 |
bo | -0.023 |
Mom | -0.022 |
Mo | -0.022 |
Token | |
Token ID | 220 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
gust | +0.002 |
ago | +0.002 |
ents | +0.002 |
epad | +0.002 |
joy | +0.002 |
Neg logit contributions | |
P | -0.002 |
bo | -0.002 |
ey | -0.002 |
na | -0.002 |
Mo | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
gust | +0.055 |
ago | +0.055 |
epad | +0.053 |
ents | +0.052 |
joy | +0.051 |
Neg logit contributions | |
P | -0.022 |
bo | -0.018 |
me | -0.018 |
na | -0.017 |
Mo | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
P | +0.012 |
bo | +0.010 |
me | +0.010 |
na | +0.009 |
ey | +0.009 |
Neg logit contributions | |
gust | -0.030 |
ago | -0.029 |
epad | -0.028 |
ents | -0.028 |
joy | -0.027 |
Token | there |
Token ID | 612 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
gust | +0.002 |
epad | +0.002 |
ago | +0.002 |
ents | +0.002 |
joy | +0.002 |
Neg logit contributions | |
P | -0.001 |
Mom | -0.001 |
me | -0.001 |
bo | -0.001 |
M | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | -1.51e-01 |
Pos logit contributions | |
P | +0.005 |
bo | +0.004 |
me | +0.003 |
Mo | +0.003 |
Mom | +0.003 |
Neg logit contributions | |
gust | -0.023 |
ago | -0.022 |
epad | -0.021 |
joy | -0.021 |
ents | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +1.61e-01 |
Pos logit contributions | |
gust | +0.009 |
ago | +0.009 |
epad | +0.009 |
ents | +0.009 |
joy | +0.008 |
Neg logit contributions | |
P | -0.003 |
Mom | -0.002 |
me | -0.002 |
bo | -0.002 |
M | -0.002 |
Token | little |
Token ID | 1310 |
Feature activation | -1.59e-01 |
Pos logit contributions | |
P | +0.004 |
me | +0.004 |
bo | +0.004 |
Mom | +0.004 |
Mo | +0.003 |
Neg logit contributions | |
gust | -0.008 |
ago | -0.008 |
epad | -0.008 |
ents | -0.007 |
joy | -0.007 |
Token | fish |
Token ID | 5916 |
Feature activation | +8.18e-01 |
Pos logit contributions | |
gust | +0.008 |
ago | +0.007 |
epad | +0.007 |
joy | +0.007 |
ents | +0.007 |
Neg logit contributions | |
P | -0.005 |
bo | -0.004 |
me | -0.004 |
Mom | -0.004 |
Mo | -0.004 |
Token | named |
Token ID | 3706 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
P | +0.023 |
me | +0.022 |
na | +0.021 |
Mom | +0.021 |
Mo | +0.021 |
Neg logit contributions | |
ago | -0.037 |
gust | -0.037 |
epad | -0.034 |
ents | -0.033 |
joy | -0.032 |
Token | Bub |
Token ID | 19645 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
gust | +0.087 |
ago | +0.084 |
epad | +0.082 |
ents | +0.077 |
joy | +0.077 |
Neg logit contributions | |
P | -0.061 |
me | -0.055 |
bo | -0.055 |
Mom | -0.053 |
Mo | -0.051 |
Token | bles |
Token ID | 7689 |
Feature activation | +1.23e-01 |
Pos logit contributions | |
gust | +0.011 |
ago | +0.011 |
epad | +0.011 |
ents | +0.010 |
joy | +0.010 |
Neg logit contributions | |
P | -0.012 |
me | -0.011 |
bo | -0.011 |
Mom | -0.011 |
Mo | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
P | +0.003 |
bo | +0.003 |
me | +0.003 |
Mom | +0.003 |
Mo | +0.003 |
Neg logit contributions | |
gust | -0.006 |
ago | -0.006 |
epad | -0.006 |
joy | -0.006 |
ents | -0.006 |
Token | Bub |
Token ID | 19645 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
gust | +0.002 |
ago | +0.002 |
epad | +0.002 |
ents | +0.002 |
joy | +0.002 |
Neg logit contributions | |
P | -0.001 |
me | -0.001 |
bo | -0.001 |
Mom | -0.001 |
Mo | -0.001 |
Token | bles |
Token ID | 7689 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
ago | +0.008 |
ents | +0.007 |
epad | +0.007 |
gust | +0.007 |
joy | +0.007 |
Neg logit contributions | |
Mom | -0.014 |
P | -0.014 |
me | -0.014 |
bo | -0.014 |
na | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +5.32e-01 |
Pos logit contributions | |
P | +0.002 |
bo | +0.002 |
ey | +0.002 |
na | +0.002 |
Mo | +0.002 |
Neg logit contributions | |
gust | -0.004 |
ago | -0.004 |
epad | -0.004 |
ents | -0.004 |
joy | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
P | +0.011 |
bo | +0.010 |
me | +0.009 |
ey | +0.009 |
na | +0.009 |
Neg logit contributions | |
gust | -0.029 |
ago | -0.029 |
epad | -0.028 |
ents | -0.027 |
joy | -0.026 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | +8.44e-02 |
Pos logit contributions | |
bo | +0.017 |
ey | +0.016 |
P | +0.016 |
yourself | +0.016 |
an | +0.016 |
Neg logit contributions | |
gust | -0.021 |
epad | -0.019 |
ago | -0.019 |
ents | -0.018 |
pieces | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
P | +0.003 |
bo | +0.002 |
Mom | +0.002 |
Mo | +0.002 |
ey | +0.002 |
Neg logit contributions | |
gust | -0.004 |
ago | -0.004 |
epad | -0.004 |
joy | -0.004 |
ents | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
P | +0.004 |
bo | +0.003 |
me | +0.003 |
Mom | +0.003 |
Mo | +0.003 |
Neg logit contributions | |
gust | -0.005 |
ago | -0.005 |
epad | -0.004 |
joy | -0.004 |
ents | -0.004 |
Token | gust |
Token ID | 35253 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
P | +0.003 |
bo | +0.003 |
me | +0.003 |
Mom | +0.002 |
Mo | +0.002 |
Neg logit contributions | |
gust | -0.005 |
ago | -0.004 |
epad | -0.004 |
joy | -0.004 |
ents | -0.004 |
Token | of |
Token ID | 286 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
gust | +0.176 |
ago | +0.172 |
epad | +0.171 |
joy | +0.156 |
ents | +0.152 |
Neg logit contributions | |
P | -0.204 |
bo | -0.186 |
me | -0.185 |
Mom | -0.183 |
Mo | -0.174 |
Token | wind |
Token ID | 2344 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
gust | +0.021 |
ago | +0.021 |
epad | +0.020 |
joy | +0.019 |
ents | +0.019 |
Neg logit contributions | |
P | -0.020 |
me | -0.018 |
bo | -0.018 |
Mom | -0.018 |
Mo | -0.017 |
Token | blew |
Token ID | 17948 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
gust | +0.049 |
ago | +0.045 |
epad | +0.040 |
ents | +0.040 |
joy | +0.039 |
Neg logit contributions | |
P | -0.039 |
yourself | -0.034 |
Mo | -0.034 |
Mom | -0.033 |
me | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
P | +0.032 |
na | +0.028 |
bo | +0.028 |
ey | +0.027 |
Mo | +0.027 |
Neg logit contributions | |
gust | -0.050 |
ago | -0.042 |
joy | -0.041 |
epad | -0.040 |
ents | -0.039 |
Token | ball |
Token ID | 2613 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
P | +0.007 |
me | +0.007 |
Mom | +0.006 |
bo | +0.006 |
was | +0.005 |
Neg logit contributions | |
epad | -0.016 |
ago | -0.016 |
gust | -0.015 |
joy | -0.015 |
ents | -0.015 |
Token | a |
Token ID | 257 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
gust | +0.013 |
ago | +0.013 |
epad | +0.012 |
joy | +0.012 |
ents | +0.012 |
Neg logit contributions | |
P | -0.006 |
me | -0.005 |
bo | -0.005 |
Mom | -0.005 |
Mo | -0.004 |
Token | tree |
Token ID | 5509 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
P | +0.001 |
bo | +0.001 |
ey | +0.001 |
inct | +0.001 |
Mo | +0.001 |
Neg logit contributions | |
gust | -0.002 |
ago | -0.001 |
epad | -0.001 |
joy | -0.001 |
ents | -0.001 |
Token | with |
Token ID | 351 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
gust | +0.027 |
ago | +0.027 |
epad | +0.026 |
joy | +0.025 |
ents | +0.025 |
Neg logit contributions | |
P | -0.007 |
me | -0.006 |
bo | -0.006 |
Mom | -0.006 |
Mo | -0.005 |
Token | shiny |
Token ID | 22441 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
gust | +0.001 |
ago | +0.001 |
epad | +0.001 |
joy | +0.001 |
ents | +0.001 |
Neg logit contributions | |
P | -0.001 |
me | -0.001 |
bo | -0.001 |
Mom | -0.001 |
Mo | -0.001 |
Token | or |
Token ID | 393 |
Feature activation | +9.25e-02 |
Pos logit contributions | |
gust | +0.010 |
ago | +0.009 |
epad | +0.008 |
ents | +0.008 |
joy | +0.008 |
Neg logit contributions | |
P | -0.008 |
bo | -0.008 |
Mom | -0.007 |
ey | -0.007 |
na | -0.007 |
Token | nam |
Token ID | 7402 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
P | +0.004 |
me | +0.004 |
Mom | +0.004 |
bo | +0.004 |
Mo | +0.004 |
Neg logit contributions | |
gust | -0.003 |
ago | -0.003 |
epad | -0.003 |
joy | -0.003 |
pieces | -0.003 |
Token | ents |
Token ID | 658 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
gust | +0.080 |
ago | +0.062 |
joy | +0.057 |
epad | +0.054 |
accomplishment | +0.049 |
Neg logit contributions | |
P | -0.330 |
Mom | -0.320 |
bo | -0.318 |
me | -0.313 |
M | -0.298 |
Token | hanging |
Token ID | 10938 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
gust | +0.127 |
joy | +0.118 |
epad | +0.115 |
accomplishment | +0.114 |
ago | +0.110 |
Neg logit contributions | |
was | -0.017 |
bo | -0.015 |
me | -0.013 |
P | -0.012 |
up | -0.011 |
Token | from |
Token ID | 422 |
Feature activation | -4.79e-01 |
Pos logit contributions | |
gust | +0.115 |
ago | +0.112 |
epad | +0.109 |
ents | +0.104 |
joy | +0.102 |
Neg logit contributions | |
P | -0.053 |
bo | -0.045 |
me | -0.045 |
Mom | -0.043 |
Mo | -0.042 |
Token | its |
Token ID | 663 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
gust | +0.025 |
epad | +0.024 |
ago | +0.024 |
ents | +0.023 |
joy | +0.023 |
Neg logit contributions | |
me | -0.012 |
P | -0.012 |
bo | -0.010 |
Mom | -0.010 |
Mo | -0.010 |
Token | branches |
Token ID | 13737 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
gust | +0.038 |
ago | +0.037 |
epad | +0.036 |
joy | +0.034 |
ents | +0.033 |
Neg logit contributions | |
P | -0.024 |
me | -0.022 |
bo | -0.022 |
Mom | -0.021 |
Mo | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
P | +0.008 |
bo | +0.007 |
yourself | +0.007 |
ey | +0.007 |
me | +0.006 |
Neg logit contributions | |
gust | -0.016 |
ago | -0.015 |
ents | -0.015 |
epad | -0.014 |
joy | -0.014 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | -3.19e-02 |
Pos logit contributions | |
bo | +0.009 |
P | +0.009 |
ey | +0.009 |
name | +0.009 |
na | +0.009 |
Neg logit contributions | |
gust | -0.013 |
ents | -0.012 |
ago | -0.011 |
epad | -0.011 |
pieces | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -7.75e-02 |
Pos logit contributions | |
gust | +0.002 |
ago | +0.001 |
joy | +0.001 |
epad | +0.001 |
ents | +0.001 |
Neg logit contributions | |
P | -0.001 |
bo | -0.001 |
Mom | -0.001 |
an | -0.001 |
ey | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +1.79e-02 |
Pos logit contributions | |
gust | +0.003 |
ago | +0.003 |
epad | +0.003 |
joy | +0.003 |
ents | +0.003 |
Neg logit contributions | |
P | -0.003 |
bo | -0.003 |
me | -0.002 |
ey | -0.002 |
Mom | -0.002 |
Token | big |
Token ID | 1263 |
Feature activation | -5.68e-02 |
Pos logit contributions | |
P | +0.001 |
bo | +0.001 |
me | +0.001 |
Mom | +0.001 |
Mo | +0.000 |
Neg logit contributions | |
gust | -0.001 |
ago | -0.001 |
epad | -0.001 |
joy | -0.001 |
ents | -0.001 |
Token | gust |
Token ID | 35253 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
gust | +0.003 |
ago | +0.002 |
epad | +0.002 |
joy | +0.002 |
ents | +0.002 |
Neg logit contributions | |
P | -0.002 |
bo | -0.002 |
Mom | -0.002 |
me | -0.002 |
Mo | -0.002 |
Token | of |
Token ID | 286 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
gust | +0.181 |
ago | +0.177 |
epad | +0.176 |
joy | +0.161 |
ents | +0.157 |
Neg logit contributions | |
P | -0.207 |
bo | -0.189 |
me | -0.189 |
Mom | -0.186 |
Mo | -0.177 |
Token | wind |
Token ID | 2344 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
gust | +0.025 |
ago | +0.023 |
epad | +0.022 |
ents | +0.021 |
joy | +0.021 |
Neg logit contributions | |
P | -0.024 |
bo | -0.022 |
me | -0.022 |
Mom | -0.021 |
Mo | -0.021 |
Token | blew |
Token ID | 17948 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
gust | +0.055 |
ago | +0.051 |
epad | +0.047 |
ents | +0.045 |
joy | +0.044 |
Neg logit contributions | |
P | -0.042 |
Mo | -0.037 |
Mom | -0.036 |
me | -0.036 |
yourself | -0.036 |
Token | Tim |
Token ID | 5045 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
P | +0.030 |
na | +0.026 |
ey | +0.026 |
bo | +0.025 |
Mo | +0.025 |
Neg logit contributions | |
gust | -0.045 |
ago | -0.039 |
joy | -0.037 |
epad | -0.037 |
ents | -0.037 |
Token | my |
Token ID | 1820 |
Feature activation | +3.24e-01 |
Pos logit contributions | |
gust | +0.021 |
ago | +0.020 |
epad | +0.020 |
ents | +0.020 |
joy | +0.018 |
Neg logit contributions | |
P | -0.013 |
inct | -0.011 |
Mo | -0.011 |
Mom | -0.011 |
na | -0.011 |
Token | ! |
Token ID | 0 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
gust | +0.025 |
epad | +0.024 |
ago | +0.024 |
pieces | +0.022 |
joy | +0.022 |
Neg logit contributions | |
P | -0.014 |
me | -0.013 |
bo | -0.012 |
Mom | -0.011 |
was | -0.011 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | +7.56e-02 |
Pos logit contributions | |
gust | +0.005 |
ago | +0.005 |
epad | +0.005 |
joy | +0.005 |
ents | +0.005 |
Neg logit contributions | |
P | -0.003 |
bo | -0.003 |
me | -0.003 |
ey | -0.003 |
na | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +9.44e-02 |
Pos logit contributions | |
P | +0.002 |
me | +0.001 |
bo | +0.001 |
Mom | +0.001 |
Mo | +0.001 |
Neg logit contributions | |
epad | -0.004 |
gust | -0.004 |
ago | -0.004 |
ents | -0.004 |
joy | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
P | +0.003 |
me | +0.002 |
Mom | +0.002 |
was | +0.002 |
Mo | +0.002 |
Neg logit contributions | |
epad | -0.005 |
ago | -0.005 |
gust | -0.005 |
ents | -0.005 |
joy | -0.004 |
Token | big |
Token ID | 1263 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
P | +0.004 |
bo | +0.004 |
me | +0.004 |
Mom | +0.004 |
Mo | +0.004 |
Neg logit contributions | |
gust | -0.009 |
ago | -0.008 |
epad | -0.008 |
joy | -0.008 |
ents | -0.008 |
Token | gust |
Token ID | 35253 |
Feature activation | -4.71e+00 |
Pos logit contributions | |
P | +0.006 |
me | +0.006 |
bo | +0.005 |
Mom | +0.005 |
Mo | +0.005 |
Neg logit contributions | |
gust | -0.011 |
ago | -0.011 |
epad | -0.010 |
ents | -0.010 |
joy | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
gust | +0.170 |
ago | +0.164 |
epad | +0.163 |
joy | +0.150 |
ents | +0.146 |
Neg logit contributions | |
P | -0.201 |
bo | -0.183 |
me | -0.183 |
Mom | -0.180 |
Mo | -0.173 |
Token | wind |
Token ID | 2344 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
gust | +0.021 |
ago | +0.020 |
epad | +0.020 |
joy | +0.019 |
ents | +0.018 |
Neg logit contributions | |
P | -0.017 |
me | -0.016 |
bo | -0.016 |
Mom | -0.015 |
Mo | -0.015 |
Token | came |
Token ID | 1625 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
gust | +0.049 |
ago | +0.047 |
epad | +0.044 |
ents | +0.042 |
joy | +0.041 |
Neg logit contributions | |
P | -0.036 |
Mom | -0.031 |
me | -0.031 |
Mo | -0.031 |
bo | -0.031 |
Token | by |
Token ID | 416 |
Feature activation | +2.02e-01 |
Pos logit contributions | |
gust | +0.023 |
ago | +0.022 |
epad | +0.021 |
ents | +0.021 |
joy | +0.020 |
Neg logit contributions | |
P | -0.011 |
bo | -0.008 |
Mom | -0.008 |
me | -0.008 |
na | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
P | +0.006 |
bo | +0.005 |
Mom | +0.004 |
Mouse | +0.004 |
me | +0.004 |
Neg logit contributions | |
ago | -0.011 |
gust | -0.010 |
epad | -0.010 |
joy | -0.010 |
ents | -0.009 |
Token | can |
Token ID | 460 |
Feature activation | +9.00e-01 |
Pos logit contributions | |
gust | +0.006 |
ago | +0.006 |
epad | +0.006 |
ents | +0.005 |
joy | +0.005 |
Neg logit contributions | |
P | -0.005 |
bo | -0.004 |
me | -0.004 |
Mo | -0.004 |
ey | -0.004 |
Token | we |
Token ID | 356 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
P | +0.040 |
sy | +0.035 |
Mo | +0.035 |
ey | +0.035 |
bo | +0.035 |
Neg logit contributions | |
gust | -0.032 |
ago | -0.030 |
ents | -0.028 |
epad | -0.027 |
pieces | -0.026 |
Token | have |
Token ID | 423 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
gust | +0.018 |
ago | +0.018 |
epad | +0.017 |
ents | +0.017 |
pieces | +0.016 |
Neg logit contributions | |
P | -0.016 |
Mo | -0.014 |
omi | -0.014 |
bo | -0.014 |
inct | -0.014 |
Token | some |
Token ID | 617 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
me | +0.003 |
P | +0.003 |
Mom | +0.002 |
bo | +0.002 |
yourself | +0.002 |
Neg logit contributions | |
gust | -0.006 |
epad | -0.006 |
ago | -0.006 |
joy | -0.005 |
pieces | -0.005 |
Token | or |
Token ID | 393 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
gust | +0.061 |
ago | +0.059 |
epad | +0.057 |
ents | +0.053 |
joy | +0.053 |
Neg logit contributions | |
P | -0.052 |
bo | -0.048 |
me | -0.047 |
Mom | -0.046 |
Mo | -0.045 |
Token | nam |
Token ID | 7402 |
Feature activation | -5.37e+00 |
Pos logit contributions | |
P | +0.003 |
me | +0.003 |
bo | +0.003 |
Mom | +0.003 |
Mo | +0.003 |
Neg logit contributions | |
gust | -0.003 |
ago | -0.002 |
epad | -0.002 |
joy | -0.002 |
ents | -0.002 |
Token | ents |
Token ID | 658 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
gust | +0.093 |
joy | +0.068 |
ago | +0.066 |
accomplishment | +0.058 |
epad | +0.056 |
Neg logit contributions | |
P | -0.340 |
bo | -0.335 |
Mom | -0.331 |
me | -0.324 |
ey | -0.311 |
Token | for |
Token ID | 329 |
Feature activation | -2.43e-01 |
Pos logit contributions | |
gust | +0.108 |
ago | +0.104 |
epad | +0.102 |
joy | +0.098 |
ents | +0.096 |
Neg logit contributions | |
P | -0.047 |
me | -0.042 |
bo | -0.042 |
Mom | -0.039 |
ey | -0.036 |
Token | our |
Token ID | 674 |
Feature activation | +8.68e-02 |
Pos logit contributions | |
gust | +0.013 |
ago | +0.012 |
epad | +0.012 |
joy | +0.011 |
ents | +0.011 |
Neg logit contributions | |
P | -0.007 |
me | -0.006 |
bo | -0.006 |
Mom | -0.006 |
Mo | -0.005 |
Token | snow |
Token ID | 6729 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
me | +0.003 |
P | +0.003 |
Mom | +0.003 |
bo | +0.002 |
na | +0.002 |
Neg logit contributions | |
gust | -0.004 |
ago | -0.004 |
epad | -0.004 |
joy | -0.003 |
ents | -0.003 |
Token | man |
Token ID | 805 |
Feature activation | +3.31e-01 |
Pos logit contributions | |
gust | +0.068 |
ago | +0.067 |
epad | +0.064 |
ents | +0.062 |
joy | +0.060 |
Neg logit contributions | |
P | -0.025 |
Mo | -0.021 |
H | -0.019 |
Mom | -0.019 |
Mouse | -0.019 |