Token | and |
Token ID | 290 |
Feature activation | +5.67e-01 |
Pos logit contributions | |
orry | +0.040 |
oke | +0.039 |
aint | +0.039 |
ence | +0.037 |
isel | +0.037 |
Neg logit contributions | |
Woo | -0.026 |
rob | -0.026 |
amb | -0.021 |
bur | -0.020 |
from | -0.020 |
Token | looked |
Token ID | 3114 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
orry | +0.018 |
oke | +0.017 |
run | +0.017 |
ence | +0.017 |
aint | +0.016 |
Neg logit contributions | |
rob | -0.022 |
Woo | -0.019 |
amb | -0.016 |
Pink | -0.015 |
bur | -0.015 |
Token | at |
Token ID | 379 |
Feature activation | +6.10e-01 |
Pos logit contributions | |
orry | +0.010 |
oke | +0.010 |
run | +0.010 |
aint | +0.010 |
ence | +0.009 |
Neg logit contributions | |
rob | -0.012 |
Woo | -0.011 |
amb | -0.009 |
Pink | -0.009 |
Cindy | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +1.27e-01 |
Pos logit contributions | |
orry | +0.015 |
run | +0.015 |
oke | +0.014 |
ence | +0.014 |
aint | +0.013 |
Neg logit contributions | |
rob | -0.028 |
Woo | -0.024 |
amb | -0.021 |
bur | -0.020 |
thank | -0.020 |
Token | ost |
Token ID | 23619 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
run | +0.004 |
orry | +0.004 |
oke | +0.004 |
ence | +0.004 |
aint | +0.004 |
Neg logit contributions | |
rob | -0.005 |
Woo | -0.004 |
amb | -0.003 |
bur | -0.003 |
Pink | -0.003 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.92e+00 |
Pos logit contributions | |
run | +0.022 |
orry | +0.022 |
tug | +0.021 |
oke | +0.021 |
gust | +0.021 |
Neg logit contributions | |
rob | -0.041 |
Woo | -0.033 |
bur | -0.032 |
amb | -0.032 |
igi | -0.029 |
Token | hes |
Token ID | 956 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
run | +0.156 |
aint | +0.152 |
ence | +0.150 |
tug | +0.150 |
ever | +0.148 |
Neg logit contributions | |
rob | -0.116 |
Woo | -0.081 |
amb | -0.067 |
bur | -0.064 |
oto | -0.061 |
Token | . |
Token ID | 13 |
Feature activation | -5.59e-01 |
Pos logit contributions | |
orry | +0.042 |
oke | +0.040 |
run | +0.040 |
ence | +0.040 |
aint | +0.038 |
Neg logit contributions | |
rob | -0.042 |
Woo | -0.037 |
amb | -0.030 |
Pink | -0.029 |
bur | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | -7.49e-01 |
Pos logit contributions | |
Woo | +0.017 |
rob | +0.015 |
Pink | +0.014 |
Sebastian | +0.013 |
Cindy | +0.012 |
Neg logit contributions | |
orry | -0.021 |
run | -0.020 |
oke | -0.020 |
ence | -0.019 |
ever | -0.019 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.26e-01 |
Pos logit contributions | |
rob | +0.034 |
Woo | +0.029 |
amb | +0.026 |
bur | +0.024 |
Pink | +0.024 |
Neg logit contributions | |
orry | -0.019 |
oke | -0.019 |
run | -0.018 |
ence | -0.018 |
aint | -0.017 |
Token | one |
Token ID | 530 |
Feature activation | -2.01e-01 |
Pos logit contributions | |
orry | +0.007 |
oke | +0.007 |
run | +0.007 |
ence | +0.007 |
aint | +0.007 |
Neg logit contributions | |
rob | -0.009 |
Woo | -0.007 |
amb | -0.006 |
bur | -0.006 |
thank | -0.006 |
Token | too |
Token ID | 1165 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
run | +0.011 |
orry | +0.011 |
oke | +0.011 |
ence | +0.010 |
aint | +0.010 |
Neg logit contributions | |
rob | -0.017 |
Woo | -0.014 |
amb | -0.012 |
Pink | -0.011 |
thank | -0.011 |
Token | close |
Token ID | 1969 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
rob | +0.013 |
Woo | +0.010 |
amb | +0.009 |
Pink | +0.009 |
thank | +0.009 |
Neg logit contributions | |
orry | -0.007 |
run | -0.007 |
oke | -0.006 |
ence | -0.006 |
tower | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
run | +0.023 |
orry | +0.023 |
oke | +0.023 |
ence | +0.022 |
aint | +0.021 |
Neg logit contributions | |
rob | -0.040 |
Woo | -0.033 |
amb | -0.029 |
Pink | -0.028 |
thank | -0.027 |
Token | The |
Token ID | 383 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
orry | +0.008 |
ence | +0.007 |
run | +0.007 |
tower | +0.007 |
gust | +0.007 |
Neg logit contributions | |
Woo | -0.012 |
rob | -0.012 |
Pink | -0.011 |
amb | -0.011 |
Sim | -0.010 |
Token | ost |
Token ID | 23619 |
Feature activation | +9.82e-01 |
Pos logit contributions | |
run | +0.006 |
orry | +0.006 |
oke | +0.006 |
ence | +0.006 |
aint | +0.006 |
Neg logit contributions | |
rob | -0.006 |
Woo | -0.006 |
Pink | -0.004 |
bur | -0.004 |
amb | -0.004 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
run | +0.024 |
tug | +0.024 |
orry | +0.024 |
gust | +0.023 |
oke | +0.022 |
Neg logit contributions | |
rob | -0.043 |
Woo | -0.035 |
bur | -0.034 |
amb | -0.033 |
igi | -0.030 |
Token | hes |
Token ID | 956 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
run | +0.154 |
tug | +0.154 |
aint | +0.153 |
ence | +0.151 |
gust | +0.150 |
Neg logit contributions | |
rob | -0.110 |
Woo | -0.073 |
amb | -0.060 |
bur | -0.059 |
oto | -0.054 |
Token | might |
Token ID | 1244 |
Feature activation | -2.96e-01 |
Pos logit contributions | |
orry | +0.019 |
run | +0.019 |
oke | +0.019 |
ence | +0.018 |
aint | +0.018 |
Neg logit contributions | |
rob | -0.025 |
Woo | -0.022 |
amb | -0.018 |
Pink | -0.017 |
bur | -0.017 |
Token | pe |
Token ID | 613 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
rob | +0.016 |
Woo | +0.013 |
amb | +0.012 |
Sebastian | +0.011 |
rev | +0.011 |
Neg logit contributions | |
run | -0.006 |
orry | -0.006 |
ence | -0.005 |
oke | -0.005 |
aint | -0.005 |
Token | ck |
Token ID | 694 |
Feature activation | +5.55e-01 |
Pos logit contributions | |
orry | +0.063 |
oke | +0.061 |
run | +0.061 |
aint | +0.058 |
gust | +0.058 |
Neg logit contributions | |
rob | -0.083 |
Woo | -0.067 |
amb | -0.060 |
bur | -0.060 |
igi | -0.055 |
Token | you |
Token ID | 345 |
Feature activation | +6.30e-01 |
Pos logit contributions | |
orry | +0.019 |
oke | +0.019 |
run | +0.018 |
ence | +0.018 |
aint | +0.018 |
Neg logit contributions | |
rob | -0.020 |
Woo | -0.017 |
amb | -0.014 |
Pink | -0.013 |
bur | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
orry | +0.012 |
oke | +0.012 |
run | +0.012 |
ence | +0.011 |
aint | +0.011 |
Neg logit contributions | |
rob | -0.007 |
Woo | -0.006 |
amb | -0.005 |
Pink | -0.004 |
bur | -0.004 |
Token | run |
Token ID | 1057 |
Feature activation | -4.82e-01 |
Pos logit contributions | |
oke | +0.020 |
orry | +0.019 |
run | +0.019 |
ever | +0.018 |
ence | +0.017 |
Neg logit contributions | |
rob | -0.020 |
Woo | -0.017 |
Pink | -0.015 |
bur | -0.014 |
amb | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -3.04e-01 |
Pos logit contributions | |
rob | +0.021 |
Woo | +0.018 |
amb | +0.016 |
bur | +0.015 |
Pink | +0.015 |
Neg logit contributions | |
orry | -0.013 |
run | -0.012 |
oke | -0.012 |
ence | -0.012 |
aint | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
rob | +0.011 |
Woo | +0.010 |
Pink | +0.008 |
bur | +0.008 |
amb | +0.008 |
Neg logit contributions | |
oke | -0.010 |
orry | -0.010 |
run | -0.010 |
ence | -0.010 |
aint | -0.010 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
run | +0.007 |
oke | +0.007 |
orry | +0.007 |
isel | +0.007 |
aint | +0.006 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.007 |
Pink | -0.005 |
bur | -0.005 |
Snow | -0.005 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
run | +0.024 |
orry | +0.024 |
oke | +0.023 |
tug | +0.023 |
gust | +0.022 |
Neg logit contributions | |
rob | -0.046 |
Woo | -0.038 |
bur | -0.036 |
amb | -0.036 |
igi | -0.033 |
Token | hes |
Token ID | 956 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
run | +0.149 |
aint | +0.146 |
ence | +0.144 |
tug | +0.144 |
orry | +0.143 |
Neg logit contributions | |
rob | -0.118 |
Woo | -0.085 |
amb | -0.071 |
bur | -0.067 |
oto | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | +3.50e-02 |
Pos logit contributions | |
orry | +0.048 |
oke | +0.047 |
run | +0.046 |
ence | +0.045 |
aint | +0.044 |
Neg logit contributions | |
rob | -0.050 |
Woo | -0.044 |
amb | -0.036 |
Pink | -0.035 |
bur | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +1.21e-01 |
Pos logit contributions | |
orry | +0.001 |
ence | +0.001 |
oke | +0.001 |
run | +0.001 |
aint | +0.001 |
Neg logit contributions | |
rob | -0.001 |
Woo | -0.001 |
Pink | -0.001 |
amb | -0.001 |
Sebastian | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
orry | +0.004 |
oke | +0.003 |
run | +0.003 |
ence | +0.003 |
aint | +0.003 |
Neg logit contributions | |
rob | -0.005 |
Woo | -0.004 |
amb | -0.004 |
bur | -0.003 |
burn | -0.003 |
Token | " |
Token ID | 1 |
Feature activation | +1.07e-01 |
Pos logit contributions | |
orry | +0.010 |
run | +0.010 |
oke | +0.010 |
ence | +0.009 |
aint | +0.009 |
Neg logit contributions | |
rob | -0.014 |
Woo | -0.012 |
amb | -0.010 |
Pink | -0.009 |
bur | -0.009 |
Token | cried |
Token ID | 16896 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
orry | +0.017 |
run | +0.017 |
oke | +0.017 |
ence | +0.017 |
aint | +0.016 |
Neg logit contributions | |
rob | -0.016 |
Woo | -0.014 |
amb | -0.012 |
Pink | -0.011 |
bur | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +1.08e-01 |
Pos logit contributions | |
rob | +0.003 |
Woo | +0.002 |
amb | +0.002 |
Pink | +0.002 |
bur | +0.002 |
Neg logit contributions | |
orry | -0.002 |
run | -0.002 |
oke | -0.002 |
ence | -0.002 |
aint | -0.002 |
Token | " |
Token ID | 366 |
Feature activation | -2.35e-03 |
Pos logit contributions | |
orry | +0.003 |
run | +0.003 |
oke | +0.003 |
ence | +0.003 |
aint | +0.003 |
Neg logit contributions | |
rob | -0.005 |
Woo | -0.004 |
amb | -0.003 |
Pink | -0.003 |
bur | -0.003 |
Token | The |
Token ID | 464 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
rob | +0.000 |
Woo | +0.000 |
amb | +0.000 |
bur | +0.000 |
Pink | +0.000 |
Neg logit contributions | |
orry | -0.000 |
run | -0.000 |
oke | -0.000 |
ence | -0.000 |
aint | -0.000 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
rob | +0.007 |
Woo | +0.006 |
amb | +0.005 |
Pink | +0.005 |
bur | +0.005 |
Neg logit contributions | |
run | -0.005 |
orry | -0.005 |
oke | -0.005 |
ence | -0.005 |
aint | -0.004 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
gust | +0.032 |
tug | +0.032 |
run | +0.031 |
orry | +0.031 |
aint | +0.030 |
Neg logit contributions | |
rob | -0.048 |
bur | -0.038 |
Woo | -0.036 |
amb | -0.034 |
burn | -0.033 |
Token | hes |
Token ID | 956 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
run | +0.151 |
aint | +0.151 |
ence | +0.150 |
orry | +0.146 |
ever | +0.144 |
Neg logit contributions | |
rob | -0.114 |
Woo | -0.080 |
amb | -0.063 |
bur | -0.060 |
oto | -0.058 |
Token | are |
Token ID | 389 |
Feature activation | +8.34e-02 |
Pos logit contributions | |
orry | +0.025 |
run | +0.024 |
ence | +0.024 |
oke | +0.024 |
aint | +0.023 |
Neg logit contributions | |
rob | -0.029 |
Woo | -0.025 |
amb | -0.020 |
Pink | -0.019 |
bur | -0.019 |
Token | mean |
Token ID | 1612 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
orry | +0.003 |
oke | +0.003 |
ence | +0.003 |
aint | +0.002 |
run | +0.002 |
Neg logit contributions | |
Woo | -0.003 |
rob | -0.003 |
Pink | -0.002 |
bur | -0.002 |
burn | -0.002 |
Token | ! |
Token ID | 0 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
rob | +0.005 |
Woo | +0.004 |
amb | +0.003 |
Pink | +0.003 |
bur | +0.003 |
Neg logit contributions | |
orry | -0.005 |
oke | -0.005 |
run | -0.005 |
ence | -0.005 |
aint | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | -5.26e-01 |
Pos logit contributions | |
orry | +0.041 |
ence | +0.040 |
run | +0.037 |
aint | +0.037 |
isel | +0.036 |
Neg logit contributions | |
rob | -0.065 |
Woo | -0.064 |
amb | -0.054 |
Pink | -0.053 |
Sebastian | -0.049 |
Token | They |
Token ID | 1119 |
Feature activation | +3.29e-01 |
Pos logit contributions | |
orry | +0.003 |
run | +0.003 |
oke | +0.003 |
ence | +0.003 |
aint | +0.003 |
Neg logit contributions | |
rob | -0.005 |
Woo | -0.004 |
amb | -0.004 |
Pink | -0.003 |
bur | -0.003 |
Token | do |
Token ID | 466 |
Feature activation | +2.20e-01 |
Pos logit contributions | |
orry | +0.008 |
oke | +0.008 |
ence | +0.007 |
run | +0.007 |
aint | +0.007 |
Neg logit contributions | |
rob | -0.015 |
Woo | -0.013 |
amb | -0.012 |
bur | -0.011 |
Pink | -0.011 |
Token | not |
Token ID | 407 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
run | +0.007 |
orry | +0.007 |
oke | +0.007 |
ence | +0.007 |
aint | +0.007 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.007 |
amb | -0.006 |
bur | -0.005 |
Pink | -0.005 |
Token | pack |
Token ID | 2353 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
oke | +0.026 |
run | +0.026 |
orry | +0.025 |
ence | +0.025 |
pieces | +0.023 |
Neg logit contributions | |
Woo | -0.024 |
rob | -0.024 |
Pink | -0.019 |
bur | -0.019 |
thank | -0.019 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
orry | +0.009 |
run | +0.009 |
oke | +0.009 |
ence | +0.008 |
aint | +0.008 |
Neg logit contributions | |
rob | -0.011 |
Woo | -0.010 |
amb | -0.008 |
bur | -0.008 |
Pink | -0.008 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
orry | +0.025 |
oke | +0.025 |
run | +0.024 |
gust | +0.024 |
tug | +0.023 |
Neg logit contributions | |
rob | -0.045 |
Woo | -0.038 |
bur | -0.036 |
amb | -0.035 |
burn | -0.032 |
Token | hes |
Token ID | 956 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
tug | +0.154 |
gust | +0.154 |
aint | +0.153 |
attempts | +0.153 |
run | +0.152 |
Neg logit contributions | |
rob | -0.104 |
Woo | -0.070 |
bur | -0.056 |
amb | -0.051 |
oto | -0.050 |
Token | anymore |
Token ID | 7471 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
orry | +0.040 |
oke | +0.039 |
run | +0.039 |
ence | +0.038 |
aint | +0.037 |
Neg logit contributions | |
rob | -0.047 |
Woo | -0.040 |
amb | -0.033 |
Pink | -0.032 |
bur | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +2.18e-01 |
Pos logit contributions | |
rob | +0.027 |
Woo | +0.023 |
Pink | +0.018 |
amb | +0.017 |
bur | +0.016 |
Neg logit contributions | |
orry | -0.034 |
ence | -0.033 |
oke | -0.033 |
isel | -0.033 |
run | -0.032 |
Token | They |
Token ID | 1119 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
orry | +0.006 |
run | +0.006 |
oke | +0.006 |
ence | +0.006 |
aint | +0.006 |
Neg logit contributions | |
rob | -0.009 |
Woo | -0.008 |
amb | -0.007 |
Pink | -0.006 |
bur | -0.006 |
Token | pack |
Token ID | 2353 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
run | +0.015 |
orry | +0.015 |
oke | +0.014 |
ence | +0.014 |
aint | +0.013 |
Neg logit contributions | |
rob | -0.023 |
Woo | -0.020 |
amb | -0.017 |
Pink | -0.016 |
bur | -0.016 |
Token | should |
Token ID | 815 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
orry | +0.010 |
oke | +0.009 |
run | +0.009 |
ence | +0.009 |
aint | +0.009 |
Neg logit contributions | |
rob | -0.020 |
Woo | -0.017 |
amb | -0.015 |
oto | -0.014 |
ippy | -0.014 |
Token | not |
Token ID | 407 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
rob | +0.066 |
Woo | +0.052 |
amb | +0.048 |
bur | +0.044 |
thank | +0.044 |
Neg logit contributions | |
orry | -0.029 |
aint | -0.026 |
ence | -0.026 |
oke | -0.026 |
run | -0.026 |
Token | tease |
Token ID | 34691 |
Feature activation | +5.36e-01 |
Pos logit contributions | |
oke | +0.026 |
orry | +0.025 |
run | +0.024 |
ence | +0.024 |
pieces | +0.022 |
Neg logit contributions | |
rob | -0.033 |
Woo | -0.032 |
amb | -0.027 |
Pink | -0.026 |
bur | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -2.56e-01 |
Pos logit contributions | |
orry | +0.016 |
run | +0.016 |
oke | +0.016 |
ence | +0.015 |
aint | +0.015 |
Neg logit contributions | |
rob | -0.022 |
Woo | -0.018 |
amb | -0.016 |
bur | -0.015 |
Pink | -0.015 |
Token | ost |
Token ID | 23619 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
rob | +0.009 |
Woo | +0.007 |
bur | +0.006 |
amb | +0.006 |
Pink | +0.006 |
Neg logit contributions | |
run | -0.009 |
orry | -0.009 |
oke | -0.009 |
ence | -0.009 |
aint | -0.009 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
run | +0.020 |
orry | +0.019 |
tug | +0.019 |
gust | +0.019 |
isel | +0.019 |
Neg logit contributions | |
rob | -0.035 |
Woo | -0.029 |
bur | -0.028 |
amb | -0.027 |
burn | -0.025 |
Token | hes |
Token ID | 956 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
tug | +0.145 |
run | +0.145 |
aint | +0.144 |
attempts | +0.144 |
gust | +0.143 |
Neg logit contributions | |
rob | -0.108 |
Woo | -0.074 |
bur | -0.059 |
amb | -0.059 |
oto | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | +3.51e-01 |
Pos logit contributions | |
orry | +0.036 |
run | +0.035 |
oke | +0.035 |
ence | +0.035 |
aint | +0.034 |
Neg logit contributions | |
rob | -0.038 |
Woo | -0.034 |
amb | -0.027 |
Pink | -0.026 |
bur | -0.026 |
Token | They |
Token ID | 1119 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
orry | +0.009 |
run | +0.008 |
oke | +0.008 |
ence | +0.008 |
aint | +0.008 |
Neg logit contributions | |
rob | -0.016 |
Woo | -0.014 |
amb | -0.012 |
Pink | -0.012 |
bur | -0.012 |
Token | are |
Token ID | 389 |
Feature activation | -1.90e-01 |
Pos logit contributions | |
rob | +0.039 |
Woo | +0.034 |
amb | +0.029 |
Pink | +0.027 |
bur | +0.027 |
Neg logit contributions | |
orry | -0.028 |
run | -0.027 |
oke | -0.027 |
ence | -0.027 |
aint | -0.026 |
Token | not |
Token ID | 407 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
Woo | +0.006 |
rob | +0.006 |
Pink | +0.005 |
bur | +0.004 |
Rudolph | +0.004 |
Neg logit contributions | |
orry | -0.007 |
oke | -0.007 |
aint | -0.006 |
run | -0.006 |
isel | -0.006 |
Token | ie |
Token ID | 494 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
rob | +0.021 |
Woo | +0.017 |
amb | +0.014 |
bur | +0.013 |
Pink | +0.013 |
Neg logit contributions | |
orry | -0.021 |
run | -0.021 |
oke | -0.021 |
ence | -0.020 |
aint | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -2.25e-01 |
Pos logit contributions | |
orry | +0.014 |
oke | +0.014 |
run | +0.014 |
ence | +0.013 |
aint | +0.013 |
Neg logit contributions | |
rob | -0.016 |
Woo | -0.014 |
amb | -0.012 |
Pink | -0.011 |
bur | -0.011 |
Token | Unlike |
Token ID | 12101 |
Feature activation | +2.80e-01 |
Pos logit contributions | |
rob | +0.009 |
Woo | +0.008 |
amb | +0.007 |
bur | +0.006 |
thank | +0.006 |
Neg logit contributions | |
run | -0.007 |
orry | -0.006 |
oke | -0.006 |
ence | -0.006 |
aint | -0.006 |
Token | other |
Token ID | 584 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
orry | +0.009 |
oke | +0.008 |
run | +0.008 |
ence | +0.008 |
aint | +0.008 |
Neg logit contributions | |
rob | -0.011 |
Woo | -0.009 |
amb | -0.008 |
thank | -0.008 |
burn | -0.008 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
rob | +0.042 |
Woo | +0.036 |
amb | +0.030 |
Pink | +0.028 |
bur | +0.028 |
Neg logit contributions | |
orry | -0.036 |
oke | -0.035 |
run | -0.035 |
ence | -0.035 |
aint | -0.034 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
run | +0.028 |
orry | +0.028 |
oke | +0.027 |
tug | +0.025 |
aint | +0.025 |
Neg logit contributions | |
rob | -0.058 |
Woo | -0.049 |
bur | -0.046 |
amb | -0.045 |
oto | -0.042 |
Token | hes |
Token ID | 956 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
run | +0.135 |
aint | +0.132 |
tug | +0.131 |
ence | +0.130 |
oke | +0.129 |
Neg logit contributions | |
rob | -0.112 |
Woo | -0.082 |
bur | -0.067 |
amb | -0.066 |
oto | -0.062 |
Token | , |
Token ID | 11 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
orry | +0.037 |
run | +0.036 |
oke | +0.036 |
ence | +0.035 |
aint | +0.034 |
Neg logit contributions | |
rob | -0.046 |
Woo | -0.039 |
amb | -0.033 |
Pink | -0.031 |
bur | -0.031 |
Token | his |
Token ID | 465 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
rob | +0.026 |
Woo | +0.023 |
Pink | +0.019 |
amb | +0.018 |
Sim | +0.017 |
Neg logit contributions | |
orry | -0.025 |
oke | -0.025 |
run | -0.025 |
ence | -0.024 |
aint | -0.024 |
Token | feathers |
Token ID | 27400 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
oke | +0.016 |
orry | +0.016 |
run | +0.016 |
isel | +0.015 |
ence | +0.015 |
Neg logit contributions | |
rob | -0.015 |
Woo | -0.013 |
amb | -0.012 |
bur | -0.011 |
Pink | -0.011 |
Token | gl |
Token ID | 1278 |
Feature activation | +6.81e-01 |
Pos logit contributions | |
run | +0.004 |
oke | +0.004 |
orry | +0.004 |
ence | +0.004 |
aint | +0.004 |
Neg logit contributions | |
rob | -0.006 |
Woo | -0.005 |
amb | -0.004 |
Gloria | -0.004 |
Pink | -0.004 |
Token | but |
Token ID | 475 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
rob | +0.021 |
Woo | +0.019 |
amb | +0.015 |
Pink | +0.015 |
bur | +0.015 |
Neg logit contributions | |
orry | -0.015 |
ence | -0.014 |
run | -0.014 |
oke | -0.014 |
aint | -0.014 |
Token | be |
Token ID | 307 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
orry | +0.031 |
oke | +0.030 |
run | +0.030 |
ence | +0.029 |
aint | +0.028 |
Neg logit contributions | |
rob | -0.039 |
Woo | -0.036 |
Pink | -0.031 |
bur | -0.030 |
amb | -0.030 |
Token | careful |
Token ID | 8161 |
Feature activation | +4.33e-01 |
Pos logit contributions | |
orry | +0.015 |
oke | +0.014 |
run | +0.014 |
ence | +0.013 |
aint | +0.013 |
Neg logit contributions | |
rob | -0.036 |
Woo | -0.033 |
bur | -0.028 |
Pink | -0.028 |
amb | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +3.32e-01 |
Pos logit contributions | |
orry | +0.015 |
oke | +0.015 |
run | +0.015 |
ence | +0.015 |
aint | +0.014 |
Neg logit contributions | |
rob | -0.014 |
Woo | -0.013 |
amb | -0.010 |
Pink | -0.010 |
bur | -0.010 |
Token | Ost |
Token ID | 38919 |
Feature activation | +9.10e-01 |
Pos logit contributions | |
orry | +0.008 |
run | +0.008 |
oke | +0.008 |
ence | +0.007 |
aint | +0.007 |
Neg logit contributions | |
rob | -0.015 |
Woo | -0.014 |
amb | -0.012 |
Pink | -0.012 |
bur | -0.011 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.56e+00 |
Pos logit contributions | |
orry | +0.014 |
oke | +0.013 |
ence | +0.013 |
run | +0.012 |
aint | +0.011 |
Neg logit contributions | |
rob | -0.049 |
Woo | -0.046 |
amb | -0.040 |
Pink | -0.039 |
Cindy | -0.039 |
Token | hes |
Token ID | 956 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
run | +0.141 |
aint | +0.137 |
ence | +0.137 |
gust | +0.136 |
tug | +0.136 |
Neg logit contributions | |
rob | -0.107 |
Woo | -0.073 |
bur | -0.060 |
amb | -0.058 |
oto | -0.056 |
Token | can |
Token ID | 460 |
Feature activation | -4.45e-01 |
Pos logit contributions | |
orry | +0.033 |
run | +0.032 |
oke | +0.032 |
ence | +0.032 |
aint | +0.030 |
Neg logit contributions | |
rob | -0.039 |
Woo | -0.034 |
amb | -0.028 |
Pink | -0.027 |
bur | -0.027 |
Token | be |
Token ID | 307 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
rob | +0.022 |
Woo | +0.018 |
amb | +0.016 |
rev | +0.016 |
Natalie | +0.015 |
Neg logit contributions | |
tug | -0.009 |
orry | -0.009 |
run | -0.009 |
ence | -0.009 |
aint | -0.009 |
Token | gr |
Token ID | 1036 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
orry | +0.043 |
oke | +0.041 |
isel | +0.040 |
ence | +0.038 |
structure | +0.038 |
Neg logit contributions | |
rob | -0.043 |
Woo | -0.042 |
Pink | -0.036 |
bur | -0.036 |
igi | -0.033 |
Token | umpy |
Token ID | 32152 |
Feature activation | -3.44e-01 |
Pos logit contributions | |
orry | +0.041 |
run | +0.040 |
oke | +0.039 |
ence | +0.039 |
aint | +0.037 |
Neg logit contributions | |
rob | -0.057 |
Woo | -0.049 |
amb | -0.042 |
bur | -0.039 |
Pink | -0.039 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
rob | +0.024 |
Woo | +0.021 |
amb | +0.018 |
Pink | +0.017 |
bur | +0.017 |
Neg logit contributions | |
orry | -0.015 |
oke | -0.014 |
run | -0.014 |
ence | -0.014 |
aint | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
rob | +0.006 |
Woo | +0.005 |
Pink | +0.004 |
amb | +0.004 |
bur | +0.004 |
Neg logit contributions | |
orry | -0.004 |
oke | -0.004 |
run | -0.004 |
ence | -0.004 |
aint | -0.003 |
Token | touch |
Token ID | 3638 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
rob | +0.033 |
Woo | +0.028 |
amb | +0.025 |
bur | +0.024 |
Pink | +0.023 |
Neg logit contributions | |
orry | -0.015 |
run | -0.014 |
ence | -0.014 |
aint | -0.014 |
oke | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
rob | +0.008 |
Woo | +0.006 |
amb | +0.006 |
bur | +0.005 |
Pink | +0.005 |
Neg logit contributions | |
orry | -0.005 |
run | -0.005 |
oke | -0.005 |
ence | -0.005 |
aint | -0.005 |
Token | ost |
Token ID | 23619 |
Feature activation | +5.82e-01 |
Pos logit contributions | |
rob | +0.002 |
Woo | +0.002 |
amb | +0.001 |
bur | +0.001 |
Pink | +0.001 |
Neg logit contributions | |
run | -0.002 |
orry | -0.002 |
oke | -0.002 |
ence | -0.002 |
aint | -0.002 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
orry | +0.013 |
run | +0.013 |
oke | +0.012 |
aint | +0.012 |
ence | +0.012 |
Neg logit contributions | |
rob | -0.027 |
Woo | -0.023 |
amb | -0.021 |
bur | -0.021 |
Pink | -0.020 |
Token | hes |
Token ID | 956 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
run | +0.135 |
ence | +0.133 |
aint | +0.132 |
orry | +0.131 |
tug | +0.129 |
Neg logit contributions | |
rob | -0.111 |
Woo | -0.083 |
amb | -0.069 |
bur | -0.065 |
oto | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -4.12e-02 |
Pos logit contributions | |
orry | +0.035 |
oke | +0.034 |
run | +0.034 |
ence | +0.033 |
aint | +0.032 |
Neg logit contributions | |
rob | -0.038 |
Woo | -0.033 |
amb | -0.027 |
Pink | -0.026 |
bur | -0.025 |
Token | They |
Token ID | 1119 |
Feature activation | -4.96e-01 |
Pos logit contributions | |
rob | +0.001 |
Woo | +0.001 |
amb | +0.001 |
Pink | +0.001 |
Sebastian | +0.001 |
Neg logit contributions | |
orry | -0.001 |
oke | -0.001 |
run | -0.001 |
ence | -0.001 |
aint | -0.001 |
Token | reached |
Token ID | 4251 |
Feature activation | -1.74e-01 |
Pos logit contributions | |
rob | +0.022 |
Woo | +0.019 |
amb | +0.016 |
Pink | +0.016 |
bur | +0.015 |
Neg logit contributions | |
orry | -0.013 |
oke | -0.013 |
run | -0.013 |
ence | -0.012 |
aint | -0.012 |
Token | out |
Token ID | 503 |
Feature activation | +3.43e-01 |
Pos logit contributions | |
rob | +0.005 |
Woo | +0.004 |
bur | +0.003 |
Pink | +0.003 |
amb | +0.003 |
Neg logit contributions | |
oke | -0.007 |
orry | -0.007 |
run | -0.007 |
ever | -0.006 |
aint | -0.006 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.41e-01 |
Pos logit contributions | |
rob | +0.000 |
Woo | +0.000 |
amb | +0.000 |
Pink | +0.000 |
bur | +0.000 |
Neg logit contributions | |
orry | -0.000 |
run | -0.000 |
oke | -0.000 |
ence | -0.000 |
aint | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
rob | +0.013 |
Woo | +0.011 |
amb | +0.009 |
Pink | +0.009 |
bur | +0.009 |
Neg logit contributions | |
orry | -0.017 |
run | -0.017 |
ence | -0.017 |
oke | -0.016 |
aint | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +8.80e-02 |
Pos logit contributions | |
rob | +0.007 |
Woo | +0.007 |
Pink | +0.006 |
amb | +0.006 |
bur | +0.006 |
Neg logit contributions | |
orry | -0.007 |
oke | -0.007 |
ence | -0.007 |
run | -0.007 |
aint | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
oke | +0.003 |
orry | +0.003 |
run | +0.003 |
ence | +0.003 |
aint | +0.003 |
Neg logit contributions | |
Woo | -0.003 |
rob | -0.003 |
Pink | -0.002 |
bur | -0.002 |
Snow | -0.002 |
Token | ost |
Token ID | 23619 |
Feature activation | +5.60e-01 |
Pos logit contributions | |
rob | +0.022 |
Woo | +0.018 |
amb | +0.014 |
bur | +0.014 |
Pink | +0.014 |
Neg logit contributions | |
run | -0.023 |
orry | -0.022 |
oke | -0.021 |
ence | -0.021 |
aint | -0.021 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
run | +0.014 |
orry | +0.013 |
oke | +0.013 |
tug | +0.013 |
gust | +0.013 |
Neg logit contributions | |
rob | -0.025 |
Woo | -0.021 |
bur | -0.020 |
amb | -0.019 |
burn | -0.018 |
Token | hes |
Token ID | 956 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
run | +0.132 |
aint | +0.132 |
ence | +0.131 |
orry | +0.129 |
gust | +0.126 |
Neg logit contributions | |
rob | -0.104 |
Woo | -0.078 |
amb | -0.062 |
bur | -0.061 |
oto | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | -2.54e-01 |
Pos logit contributions | |
orry | +0.038 |
run | +0.037 |
oke | +0.037 |
ence | +0.036 |
aint | +0.035 |
Neg logit contributions | |
rob | -0.047 |
Woo | -0.041 |
amb | -0.034 |
Pink | -0.033 |
bur | -0.033 |
Token | They |
Token ID | 1119 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
rob | +0.011 |
Woo | +0.010 |
amb | +0.008 |
bur | +0.008 |
Pink | +0.008 |
Neg logit contributions | |
orry | -0.007 |
run | -0.007 |
oke | -0.007 |
ence | -0.007 |
aint | -0.006 |
Token | learned |
Token ID | 4499 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
rob | +0.005 |
Woo | +0.004 |
amb | +0.004 |
igi | +0.003 |
ippy | +0.003 |
Neg logit contributions | |
orry | -0.002 |
tug | -0.002 |
oke | -0.002 |
run | -0.002 |
ence | -0.002 |
Token | their |
Token ID | 511 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
rob | +0.003 |
Woo | +0.002 |
amb | +0.002 |
bur | +0.002 |
thank | +0.002 |
Neg logit contributions | |
run | -0.001 |
orry | -0.001 |
ence | -0.001 |
oke | -0.001 |
tower | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
rob | +0.014 |
Woo | +0.012 |
amb | +0.010 |
Pink | +0.010 |
bur | +0.010 |
Neg logit contributions | |
orry | -0.010 |
run | -0.010 |
oke | -0.010 |
ence | -0.010 |
aint | -0.009 |
Token | They |
Token ID | 1119 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
Woo | +0.020 |
rob | +0.020 |
Pink | +0.017 |
Sebastian | +0.015 |
Cindy | +0.015 |
Neg logit contributions | |
orry | -0.018 |
ence | -0.017 |
run | -0.017 |
isel | -0.017 |
oke | -0.017 |
Token | were |
Token ID | 547 |
Feature activation | -6.05e-01 |
Pos logit contributions | |
rob | +0.033 |
Woo | +0.028 |
amb | +0.024 |
bur | +0.023 |
Pink | +0.023 |
Neg logit contributions | |
orry | -0.021 |
oke | -0.021 |
run | -0.021 |
ence | -0.020 |
aint | -0.019 |
Token | called |
Token ID | 1444 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
rob | +0.024 |
Woo | +0.021 |
amb | +0.018 |
Pink | +0.017 |
bur | +0.017 |
Neg logit contributions | |
orry | -0.018 |
oke | -0.018 |
run | -0.018 |
ence | -0.017 |
aint | -0.017 |
Token | ost |
Token ID | 23619 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
orry | +0.018 |
run | +0.017 |
oke | +0.017 |
ence | +0.016 |
aint | +0.016 |
Neg logit contributions | |
rob | -0.019 |
Woo | -0.018 |
Pink | -0.015 |
amb | -0.014 |
Gloria | -0.014 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
orry | +0.025 |
run | +0.025 |
oke | +0.024 |
gust | +0.023 |
tug | +0.023 |
Neg logit contributions | |
rob | -0.045 |
Woo | -0.037 |
bur | -0.036 |
amb | -0.035 |
oto | -0.032 |
Token | hes |
Token ID | 956 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
run | +0.128 |
aint | +0.125 |
orry | +0.123 |
tug | +0.122 |
gust | +0.121 |
Neg logit contributions | |
rob | -0.105 |
Woo | -0.076 |
bur | -0.063 |
amb | -0.061 |
Pink | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -4.28e-01 |
Pos logit contributions | |
orry | +0.040 |
run | +0.039 |
oke | +0.039 |
ence | +0.038 |
aint | +0.037 |
Neg logit contributions | |
rob | -0.042 |
Woo | -0.036 |
amb | -0.029 |
Pink | -0.028 |
bur | -0.028 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
rob | +0.016 |
Woo | +0.015 |
Pink | +0.013 |
amb | +0.012 |
Sebastian | +0.012 |
Neg logit contributions | |
orry | -0.013 |
run | -0.012 |
ence | -0.012 |
oke | -0.012 |
aint | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
rob | +0.019 |
Woo | +0.016 |
amb | +0.014 |
bur | +0.013 |
Pink | +0.013 |
Neg logit contributions | |
orry | -0.013 |
oke | -0.013 |
ence | -0.012 |
run | -0.012 |
aint | -0.012 |
Token | Ben |
Token ID | 3932 |
Feature activation | -1.65e-03 |
Pos logit contributions | |
orry | +0.018 |
run | +0.018 |
oke | +0.018 |
ence | +0.017 |
aint | +0.017 |
Neg logit contributions | |
rob | -0.028 |
Woo | -0.025 |
amb | -0.021 |
Pink | -0.021 |
bur | -0.020 |
Token | you |
Token ID | 345 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
orry | +0.024 |
run | +0.024 |
isel | +0.024 |
ence | +0.023 |
oke | +0.023 |
Neg logit contributions | |
rob | -0.027 |
Woo | -0.026 |
Pink | -0.022 |
bur | -0.020 |
amb | -0.019 |
Token | count |
Token ID | 954 |
Feature activation | +1.34e-01 |
Pos logit contributions | |
orry | +0.007 |
oke | +0.007 |
run | +0.007 |
ence | +0.006 |
aint | +0.006 |
Neg logit contributions | |
rob | -0.011 |
Woo | -0.010 |
amb | -0.008 |
Pink | -0.008 |
bur | -0.008 |
Token | how |
Token ID | 703 |
Feature activation | +3.89e-01 |
Pos logit contributions | |
orry | +0.004 |
oke | +0.004 |
run | +0.004 |
ence | +0.004 |
aint | +0.004 |
Neg logit contributions | |
rob | -0.005 |
Woo | -0.004 |
amb | -0.004 |
bur | -0.004 |
Pink | -0.004 |
Token | many |
Token ID | 867 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
oke | +0.015 |
orry | +0.014 |
run | +0.014 |
fists | +0.014 |
tug | +0.014 |
Neg logit contributions | |
rob | -0.010 |
Woo | -0.010 |
Pink | -0.008 |
amb | -0.008 |
Gloria | -0.007 |
Token | ost |
Token ID | 23619 |
Feature activation | +6.25e-01 |
Pos logit contributions | |
rob | +0.023 |
Woo | +0.019 |
amb | +0.016 |
Pink | +0.015 |
bur | +0.015 |
Neg logit contributions | |
orry | -0.019 |
run | -0.019 |
oke | -0.019 |
ence | -0.018 |
aint | -0.018 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.37e+00 |
Pos logit contributions | |
orry | +0.013 |
run | +0.013 |
oke | +0.013 |
ence | +0.012 |
aint | +0.012 |
Neg logit contributions | |
rob | -0.030 |
Woo | -0.026 |
amb | -0.023 |
bur | -0.023 |
Pink | -0.022 |
Token | hes |
Token ID | 956 |
Feature activation | +7.22e-02 |
Pos logit contributions | |
run | +0.119 |
tug | +0.117 |
aint | +0.114 |
orry | +0.114 |
ence | +0.113 |
Neg logit contributions | |
rob | -0.112 |
Woo | -0.080 |
amb | -0.070 |
bur | -0.068 |
Pink | -0.064 |
Token | there |
Token ID | 612 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
orry | +0.002 |
run | +0.002 |
oke | +0.002 |
ence | +0.002 |
aint | +0.002 |
Neg logit contributions | |
rob | -0.003 |
Woo | -0.002 |
amb | -0.002 |
Pink | -0.002 |
bur | -0.002 |
Token | are |
Token ID | 389 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
rob | +0.012 |
Woo | +0.010 |
amb | +0.008 |
Sebastian | +0.007 |
Pink | +0.007 |
Neg logit contributions | |
run | -0.011 |
oke | -0.011 |
orry | -0.011 |
ence | -0.011 |
aint | -0.010 |
Token | ?" |
Token ID | 1701 |
Feature activation | -2.17e-01 |
Pos logit contributions | |
rob | +0.018 |
Woo | +0.015 |
Pink | +0.013 |
bur | +0.012 |
amb | +0.012 |
Neg logit contributions | |
orry | -0.019 |
oke | -0.018 |
run | -0.018 |
ence | -0.017 |
isel | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -7.05e-02 |
Pos logit contributions | |
rob | +0.008 |
Woo | +0.007 |
Pink | +0.007 |
amb | +0.006 |
herself | +0.006 |
Neg logit contributions | |
ence | -0.007 |
run | -0.006 |
orry | -0.006 |
isel | -0.006 |
oke | -0.006 |
Token | girl |
Token ID | 2576 |
Feature activation | +6.58e-01 |
Pos logit contributions | |
run | +0.020 |
orry | +0.019 |
ence | +0.019 |
oke | +0.019 |
aint | +0.018 |
Neg logit contributions | |
rob | -0.022 |
Woo | -0.020 |
Pink | -0.017 |
amb | -0.016 |
bur | -0.015 |
Token | who |
Token ID | 508 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
oke | +0.027 |
orry | +0.026 |
run | +0.026 |
ence | +0.026 |
isel | +0.025 |
Neg logit contributions | |
rob | -0.018 |
Woo | -0.016 |
amb | -0.013 |
Pink | -0.012 |
bur | -0.011 |
Token | didn |
Token ID | 1422 |
Feature activation | +6.89e-01 |
Pos logit contributions | |
oke | +0.044 |
orry | +0.044 |
run | +0.043 |
ence | +0.042 |
aint | +0.040 |
Neg logit contributions | |
rob | -0.045 |
Woo | -0.039 |
Pink | -0.032 |
amb | -0.031 |
thank | -0.030 |
Token | 't |
Token ID | 470 |
Feature activation | +4.58e-02 |
Pos logit contributions | |
orry | +0.021 |
run | +0.021 |
aint | +0.019 |
oke | +0.019 |
ence | +0.019 |
Neg logit contributions | |
rob | -0.030 |
Woo | -0.023 |
bur | -0.020 |
amb | -0.020 |
thank | -0.019 |
Token | like |
Token ID | 588 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
oke | +0.001 |
orry | +0.001 |
run | +0.001 |
ence | +0.001 |
aint | +0.001 |
Neg logit contributions | |
rob | -0.002 |
Woo | -0.002 |
amb | -0.001 |
Pink | -0.001 |
bur | -0.001 |
Token | av |
Token ID | 1196 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
oke | +0.037 |
orry | +0.037 |
run | +0.036 |
ence | +0.035 |
isel | +0.033 |
Neg logit contributions | |
rob | -0.040 |
Woo | -0.039 |
Pink | -0.031 |
Gloria | -0.028 |
Rudolph | -0.028 |
Token | oc |
Token ID | 420 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
orry | +0.081 |
oke | +0.080 |
run | +0.079 |
ence | +0.076 |
aint | +0.076 |
Neg logit contributions | |
rob | -0.150 |
Woo | -0.135 |
amb | -0.116 |
Pink | -0.111 |
bur | -0.108 |
Token | ados |
Token ID | 22484 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
orry | +0.033 |
run | +0.032 |
oke | +0.032 |
ence | +0.031 |
aint | +0.030 |
Neg logit contributions | |
rob | -0.049 |
Woo | -0.042 |
amb | -0.036 |
Pink | -0.034 |
bur | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +8.12e-01 |
Pos logit contributions | |
orry | +0.036 |
oke | +0.035 |
run | +0.035 |
ence | +0.034 |
aint | +0.033 |
Neg logit contributions | |
rob | -0.051 |
Woo | -0.044 |
amb | -0.038 |
bur | -0.036 |
Pink | -0.035 |
Token | She |
Token ID | 1375 |
Feature activation | +1.65e-01 |
Pos logit contributions | |
oke | +0.037 |
orry | +0.037 |
run | +0.036 |
ence | +0.035 |
isel | +0.035 |
Neg logit contributions | |
Woo | -0.017 |
rob | -0.017 |
Pink | -0.014 |
Cindy | -0.012 |
herself | -0.012 |
Token | always |
Token ID | 1464 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
run | +0.005 |
oke | +0.005 |
orry | +0.005 |
ence | +0.005 |
aint | +0.005 |
Neg logit contributions | |
rob | -0.006 |
Woo | -0.005 |
amb | -0.005 |
Pink | -0.004 |
bur | -0.004 |
Token | ostr |
Token ID | 42387 |
Feature activation | -2.73e-01 |
Pos logit contributions | |
rob | +0.002 |
Woo | +0.002 |
Pink | +0.001 |
bur | +0.001 |
Rudolph | +0.001 |
Neg logit contributions | |
run | -0.003 |
orry | -0.003 |
oke | -0.003 |
isel | -0.003 |
ence | -0.003 |
Token | ich |
Token ID | 488 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
rob | +0.009 |
Woo | +0.007 |
amb | +0.006 |
bur | +0.005 |
Pink | +0.005 |
Neg logit contributions | |
orry | -0.010 |
run | -0.010 |
oke | -0.010 |
ence | -0.010 |
aint | -0.010 |
Token | pen |
Token ID | 3112 |
Feature activation | -1.47e-01 |
Pos logit contributions | |
orry | +0.013 |
oke | +0.012 |
run | +0.012 |
isel | +0.012 |
ence | +0.012 |
Neg logit contributions | |
rob | -0.011 |
Woo | -0.010 |
amb | -0.008 |
Pink | -0.008 |
bur | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -4.20e-01 |
Pos logit contributions | |
rob | +0.006 |
Woo | +0.005 |
amb | +0.004 |
bur | +0.004 |
Cindy | +0.004 |
Neg logit contributions | |
tower | -0.004 |
run | -0.004 |
oke | -0.004 |
orry | -0.004 |
ence | -0.004 |
Token | Ost |
Token ID | 38919 |
Feature activation | +6.55e-01 |
Pos logit contributions | |
rob | +0.017 |
Woo | +0.015 |
amb | +0.013 |
Pink | +0.013 |
Sebastian | +0.012 |
Neg logit contributions | |
orry | -0.013 |
oke | -0.012 |
ence | -0.012 |
run | -0.012 |
aint | -0.011 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
orry | +0.009 |
oke | +0.009 |
ence | +0.009 |
run | +0.008 |
aint | +0.007 |
Neg logit contributions | |
rob | -0.035 |
Woo | -0.034 |
amb | -0.030 |
Pink | -0.029 |
Cindy | -0.029 |
Token | hes |
Token ID | 956 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
run | +0.126 |
aint | +0.123 |
ence | +0.123 |
orry | +0.122 |
tug | +0.120 |
Neg logit contributions | |
rob | -0.108 |
Woo | -0.078 |
amb | -0.063 |
bur | -0.063 |
oto | -0.059 |
Token | are |
Token ID | 389 |
Feature activation | +3.56e-01 |
Pos logit contributions | |
orry | +0.039 |
run | +0.038 |
oke | +0.038 |
ence | +0.038 |
aint | +0.036 |
Neg logit contributions | |
rob | -0.044 |
Woo | -0.038 |
amb | -0.031 |
Pink | -0.031 |
bur | -0.030 |
Token | big |
Token ID | 1263 |
Feature activation | -5.33e-01 |
Pos logit contributions | |
orry | +0.012 |
oke | +0.011 |
run | +0.011 |
isel | +0.011 |
aint | +0.011 |
Neg logit contributions | |
rob | -0.013 |
Woo | -0.012 |
Pink | -0.010 |
bur | -0.010 |
Rudolph | -0.009 |
Token | birds |
Token ID | 10087 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
rob | +0.016 |
Woo | +0.013 |
Pink | +0.010 |
amb | +0.010 |
bur | +0.009 |
Neg logit contributions | |
orry | -0.022 |
run | -0.021 |
ence | -0.020 |
isel | -0.020 |
oke | -0.020 |
Token | with |
Token ID | 351 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
orry | +0.049 |
run | +0.048 |
ence | +0.047 |
oke | +0.047 |
isel | +0.046 |
Neg logit contributions | |
rob | -0.045 |
Woo | -0.039 |
amb | -0.032 |
Pink | -0.032 |
bur | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | -1.44e-01 |
Pos logit contributions | |
orry | +0.018 |
run | +0.018 |
oke | +0.018 |
ence | +0.017 |
aint | +0.017 |
Neg logit contributions | |
rob | -0.024 |
Woo | -0.021 |
amb | -0.018 |
Pink | -0.017 |
bur | -0.017 |
Token | very |
Token ID | 845 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
rob | +0.005 |
Woo | +0.005 |
Pink | +0.004 |
Cindy | +0.003 |
amb | +0.003 |
Neg logit contributions | |
oke | -0.005 |
run | -0.005 |
orry | -0.005 |
ence | -0.005 |
isel | -0.005 |
Token | naughty |
Token ID | 45128 |
Feature activation | -1.16e-01 |
Pos logit contributions | |
run | +0.004 |
oke | +0.004 |
orry | +0.004 |
ence | +0.004 |
aint | +0.004 |
Neg logit contributions | |
rob | -0.006 |
Woo | -0.006 |
Pink | -0.005 |
amb | -0.005 |
Cindy | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +9.20e-01 |
Pos logit contributions | |
rob | +0.003 |
Woo | +0.003 |
amb | +0.002 |
Pink | +0.002 |
bur | +0.002 |
Neg logit contributions | |
orry | -0.005 |
run | -0.005 |
ence | -0.005 |
oke | -0.005 |
isel | -0.004 |
Token | always |
Token ID | 1464 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
oke | +0.032 |
run | +0.031 |
ence | +0.030 |
orry | +0.030 |
ever | +0.030 |
Neg logit contributions | |
rob | -0.030 |
Woo | -0.030 |
Pink | -0.024 |
herself | -0.022 |
Cindy | -0.021 |
Token | mis |
Token ID | 2984 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
rob | +0.005 |
Woo | +0.005 |
Pink | +0.004 |
thank | +0.004 |
bur | +0.004 |
Neg logit contributions | |
orry | -0.005 |
oke | -0.005 |
ence | -0.005 |
isel | -0.005 |
run | -0.005 |
Token | beh |
Token ID | 20709 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
oke | +0.094 |
orry | +0.094 |
ence | +0.088 |
tower | +0.088 |
run | +0.084 |
Neg logit contributions | |
rob | -0.128 |
Woo | -0.113 |
amb | -0.104 |
bur | -0.099 |
thank | -0.094 |
Token | aving |
Token ID | 2703 |
Feature activation | +7.59e-01 |
Pos logit contributions | |
orry | +0.065 |
oke | +0.064 |
run | +0.062 |
ence | +0.061 |
aint | +0.058 |
Neg logit contributions | |
rob | -0.114 |
Woo | -0.099 |
amb | -0.087 |
bur | -0.082 |
Pink | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
orry | +0.027 |
oke | +0.027 |
ence | +0.026 |
run | +0.026 |
isel | +0.025 |
Neg logit contributions | |
rob | -0.025 |
Woo | -0.023 |
Pink | -0.017 |
amb | -0.017 |
Cindy | -0.016 |
Token | One |
Token ID | 1881 |
Feature activation | +5.19e-01 |
Pos logit contributions | |
orry | +0.022 |
oke | +0.021 |
run | +0.021 |
ence | +0.021 |
isel | +0.020 |
Neg logit contributions | |
rob | -0.022 |
Woo | -0.020 |
amb | -0.016 |
Pink | -0.016 |
bur | -0.015 |
Token | day |
Token ID | 1110 |
Feature activation | +2.96e-01 |
Pos logit contributions | |
ence | +0.020 |
oke | +0.020 |
run | +0.020 |
isel | +0.019 |
aint | +0.019 |
Neg logit contributions | |
rob | -0.015 |
Woo | -0.014 |
Pink | -0.011 |
amb | -0.010 |
burn | -0.010 |
Token | ostr |
Token ID | 42387 |
Feature activation | -1.85e-01 |
Pos logit contributions | |
run | +0.016 |
orry | +0.015 |
oke | +0.015 |
ence | +0.015 |
aint | +0.015 |
Neg logit contributions | |
rob | -0.013 |
Woo | -0.011 |
Pink | -0.008 |
bur | -0.008 |
amb | -0.008 |
Token | ich |
Token ID | 488 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
rob | +0.006 |
Woo | +0.005 |
amb | +0.004 |
bur | +0.004 |
Pink | +0.003 |
Neg logit contributions | |
run | -0.007 |
orry | -0.007 |
oke | -0.007 |
ence | -0.007 |
aint | -0.007 |
Token | pen |
Token ID | 3112 |
Feature activation | -1.25e-01 |
Pos logit contributions | |
orry | +0.022 |
isel | +0.022 |
oke | +0.021 |
run | +0.021 |
ence | +0.020 |
Neg logit contributions | |
rob | -0.020 |
Woo | -0.017 |
amb | -0.014 |
Pink | -0.014 |
bur | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -3.41e-01 |
Pos logit contributions | |
rob | +0.005 |
Woo | +0.004 |
amb | +0.004 |
bur | +0.004 |
Sebastian | +0.004 |
Neg logit contributions | |
run | -0.003 |
orry | -0.003 |
oke | -0.003 |
tower | -0.003 |
ence | -0.003 |
Token | Ost |
Token ID | 38919 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
rob | +0.013 |
Woo | +0.013 |
Pink | +0.011 |
amb | +0.011 |
Sebastian | +0.010 |
Neg logit contributions | |
orry | -0.010 |
ence | -0.009 |
oke | -0.009 |
run | -0.009 |
aint | -0.009 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
orry | +0.011 |
oke | +0.011 |
ence | +0.011 |
run | +0.009 |
aint | +0.009 |
Neg logit contributions | |
rob | -0.041 |
Woo | -0.040 |
amb | -0.035 |
Pink | -0.034 |
Cindy | -0.033 |
Token | hes |
Token ID | 956 |
Feature activation | +9.72e-01 |
Pos logit contributions | |
run | +0.124 |
aint | +0.121 |
ence | +0.121 |
orry | +0.120 |
tug | +0.117 |
Neg logit contributions | |
rob | -0.107 |
Woo | -0.078 |
bur | -0.063 |
amb | -0.063 |
oto | -0.059 |
Token | are |
Token ID | 389 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
orry | +0.031 |
run | +0.030 |
oke | +0.030 |
ence | +0.030 |
aint | +0.029 |
Neg logit contributions | |
rob | -0.037 |
Woo | -0.031 |
amb | -0.026 |
Pink | -0.025 |
bur | -0.025 |
Token | big |
Token ID | 1263 |
Feature activation | -6.08e-01 |
Pos logit contributions | |
orry | +0.011 |
oke | +0.010 |
run | +0.010 |
ence | +0.010 |
aint | +0.010 |
Neg logit contributions | |
rob | -0.013 |
Woo | -0.011 |
Pink | -0.009 |
bur | -0.009 |
amb | -0.009 |
Token | birds |
Token ID | 10087 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
rob | +0.019 |
Woo | +0.015 |
Pink | +0.011 |
amb | +0.011 |
bur | +0.011 |
Neg logit contributions | |
orry | -0.024 |
run | -0.024 |
ence | -0.023 |
oke | -0.023 |
aint | -0.023 |
Token | with |
Token ID | 351 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
orry | +0.046 |
run | +0.044 |
oke | +0.043 |
ence | +0.043 |
isel | +0.042 |
Neg logit contributions | |
rob | -0.041 |
Woo | -0.035 |
amb | -0.029 |
Pink | -0.028 |
bur | -0.027 |
Token | shouted |
Token ID | 17293 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
rob | +0.027 |
Woo | +0.022 |
amb | +0.018 |
bur | +0.017 |
Pink | +0.017 |
Neg logit contributions | |
oke | -0.024 |
run | -0.024 |
orry | -0.024 |
ence | -0.023 |
aint | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -4.43e-01 |
Pos logit contributions | |
rob | +0.010 |
Woo | +0.010 |
Pink | +0.008 |
amb | +0.008 |
Sebastian | +0.007 |
Neg logit contributions | |
orry | -0.013 |
oke | -0.013 |
ence | -0.013 |
run | -0.013 |
aint | -0.012 |
Token | " |
Token ID | 366 |
Feature activation | -4.92e-01 |
Pos logit contributions | |
rob | +0.020 |
Woo | +0.018 |
amb | +0.015 |
Pink | +0.015 |
bur | +0.014 |
Neg logit contributions | |
orry | -0.011 |
oke | -0.011 |
run | -0.011 |
ence | -0.011 |
aint | -0.010 |
Token | The |
Token ID | 464 |
Feature activation | -5.69e-01 |
Pos logit contributions | |
rob | +0.019 |
Woo | +0.016 |
amb | +0.014 |
Pink | +0.013 |
bur | +0.013 |
Neg logit contributions | |
orry | -0.016 |
oke | -0.016 |
run | -0.015 |
ence | -0.015 |
aint | -0.015 |
Token | ost |
Token ID | 23619 |
Feature activation | +7.06e-01 |
Pos logit contributions | |
rob | +0.024 |
Woo | +0.020 |
amb | +0.017 |
bur | +0.016 |
Pink | +0.016 |
Neg logit contributions | |
orry | -0.016 |
oke | -0.016 |
run | -0.016 |
ence | -0.016 |
aint | -0.015 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
run | +0.016 |
orry | +0.016 |
oke | +0.015 |
tug | +0.015 |
aint | +0.015 |
Neg logit contributions | |
rob | -0.033 |
Woo | -0.027 |
bur | -0.025 |
amb | -0.025 |
igi | -0.023 |
Token | hes |
Token ID | 956 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
run | +0.125 |
aint | +0.122 |
ence | +0.122 |
orry | +0.120 |
tug | +0.119 |
Neg logit contributions | |
rob | -0.101 |
Woo | -0.072 |
amb | -0.060 |
bur | -0.057 |
oto | -0.055 |
Token | are |
Token ID | 389 |
Feature activation | +3.45e-02 |
Pos logit contributions | |
orry | +0.016 |
run | +0.016 |
ence | +0.015 |
oke | +0.015 |
aint | +0.015 |
Neg logit contributions | |
rob | -0.018 |
Woo | -0.015 |
amb | -0.013 |
Pink | -0.012 |
bur | -0.012 |
Token | so |
Token ID | 523 |
Feature activation | -2.38e-01 |
Pos logit contributions | |
orry | +0.001 |
oke | +0.001 |
isel | +0.001 |
run | +0.001 |
aint | +0.001 |
Neg logit contributions | |
rob | -0.001 |
Woo | -0.001 |
Pink | -0.001 |
bur | -0.001 |
Gloria | -0.001 |
Token | funny |
Token ID | 8258 |
Feature activation | -1.78e-01 |
Pos logit contributions | |
rob | +0.008 |
Woo | +0.008 |
Pink | +0.006 |
amb | +0.006 |
Gloria | +0.006 |
Neg logit contributions | |
run | -0.007 |
orry | -0.007 |
oke | -0.007 |
aint | -0.007 |
isel | -0.007 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.08e-01 |
Pos logit contributions | |
rob | +0.005 |
Woo | +0.004 |
amb | +0.003 |
Pink | +0.003 |
bur | +0.003 |
Neg logit contributions | |
orry | -0.007 |
run | -0.007 |
oke | -0.007 |
ence | -0.007 |
aint | -0.007 |
Token | Yes |
Token ID | 5297 |
Feature activation | +2.50e-02 |
Pos logit contributions | |
rob | +0.024 |
Woo | +0.020 |
amb | +0.018 |
bur | +0.017 |
ippy | +0.016 |
Neg logit contributions | |
orry | -0.015 |
oke | -0.015 |
ence | -0.015 |
run | -0.014 |
aint | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
run | +0.001 |
orry | +0.001 |
oke | +0.001 |
ence | +0.001 |
aint | +0.001 |
Neg logit contributions | |
rob | -0.001 |
Woo | -0.001 |
Pink | -0.000 |
amb | -0.000 |
Cindy | -0.000 |
Token | they |
Token ID | 484 |
Feature activation | -8.38e-02 |
Pos logit contributions | |
Woo | +0.016 |
rob | +0.015 |
Pink | +0.014 |
Dod | +0.013 |
Gloria | +0.012 |
Neg logit contributions | |
run | -0.019 |
aint | -0.018 |
ence | -0.018 |
orry | -0.018 |
oke | -0.018 |
Token | are |
Token ID | 389 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
rob | +0.003 |
Woo | +0.002 |
amb | +0.002 |
Pink | +0.002 |
bur | +0.002 |
Neg logit contributions | |
run | -0.003 |
oke | -0.003 |
orry | -0.003 |
ence | -0.003 |
aint | -0.003 |
Token | ost |
Token ID | 23619 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
rob | +0.010 |
Woo | +0.009 |
amb | +0.007 |
bur | +0.007 |
Pink | +0.007 |
Neg logit contributions | |
orry | -0.010 |
oke | -0.010 |
run | -0.010 |
ence | -0.009 |
aint | -0.009 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
run | +0.022 |
orry | +0.021 |
oke | +0.021 |
tug | +0.020 |
aint | +0.020 |
Neg logit contributions | |
rob | -0.043 |
Woo | -0.037 |
amb | -0.034 |
bur | -0.034 |
oto | -0.031 |
Token | hes |
Token ID | 956 |
Feature activation | +8.54e-01 |
Pos logit contributions | |
run | +0.122 |
aint | +0.117 |
orry | +0.116 |
ence | +0.115 |
tug | +0.115 |
Neg logit contributions | |
rob | -0.104 |
Woo | -0.077 |
amb | -0.064 |
Pink | -0.061 |
bur | -0.060 |
Token | ," |
Token ID | 553 |
Feature activation | -2.77e-02 |
Pos logit contributions | |
orry | +0.028 |
run | +0.027 |
oke | +0.027 |
ence | +0.027 |
aint | +0.026 |
Neg logit contributions | |
rob | -0.032 |
Woo | -0.027 |
amb | -0.022 |
Pink | -0.021 |
bur | -0.021 |
Token | mom |
Token ID | 1995 |
Feature activation | -8.89e-01 |
Pos logit contributions | |
rob | +0.001 |
Woo | +0.001 |
Pink | +0.001 |
amb | +0.001 |
Gloria | +0.001 |
Neg logit contributions | |
run | -0.001 |
orry | -0.001 |
oke | -0.001 |
ence | -0.001 |
aint | -0.001 |
Token | said |
Token ID | 531 |
Feature activation | +1.88e-01 |
Pos logit contributions | |
rob | +0.029 |
Woo | +0.023 |
amb | +0.019 |
Pink | +0.017 |
bur | +0.017 |
Neg logit contributions | |
orry | -0.034 |
run | -0.033 |
oke | -0.033 |
ence | -0.033 |
aint | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -9.51e-02 |
Pos logit contributions | |
orry | +0.008 |
ence | +0.007 |
oke | +0.007 |
isel | +0.007 |
run | +0.007 |
Neg logit contributions | |
Woo | -0.005 |
rob | -0.005 |
Pink | -0.004 |
amb | -0.003 |
Lib | -0.003 |
Token | he |
Token ID | 339 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
rob | +0.000 |
Woo | +0.000 |
amb | +0.000 |
Pink | +0.000 |
Sebastian | +0.000 |
Neg logit contributions | |
ence | -0.000 |
oke | -0.000 |
run | -0.000 |
orry | -0.000 |
aint | -0.000 |
Token | could |
Token ID | 714 |
Feature activation | +8.31e-02 |
Pos logit contributions | |
orry | +0.011 |
run | +0.011 |
oke | +0.011 |
ence | +0.011 |
aint | +0.010 |
Neg logit contributions | |
rob | -0.018 |
Woo | -0.016 |
amb | -0.013 |
bur | -0.013 |
Pink | -0.013 |
Token | be |
Token ID | 307 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
orry | +0.002 |
oke | +0.002 |
run | +0.002 |
ence | +0.002 |
aint | +0.002 |
Neg logit contributions | |
rob | -0.004 |
Woo | -0.003 |
amb | -0.003 |
Pink | -0.003 |
bur | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
oke | +0.033 |
orry | +0.033 |
ence | +0.032 |
run | +0.031 |
aint | +0.031 |
Neg logit contributions | |
rob | -0.038 |
Woo | -0.033 |
thank | -0.027 |
Pink | -0.027 |
bur | -0.026 |
Token | never |
Token ID | 1239 |
Feature activation | +1.17e-02 |
Pos logit contributions | |
oke | +0.009 |
orry | +0.009 |
ence | +0.009 |
aint | +0.008 |
run | +0.008 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.007 |
Pink | -0.006 |
amb | -0.006 |
thank | -0.006 |
Token | mis |
Token ID | 2984 |
Feature activation | +3.22e+00 |
Pos logit contributions | |
orry | +0.000 |
ence | +0.000 |
oke | +0.000 |
isel | +0.000 |
icker | +0.000 |
Neg logit contributions | |
Woo | -0.000 |
rob | -0.000 |
Pink | -0.000 |
thank | -0.000 |
Cindy | -0.000 |
Token | beh |
Token ID | 20709 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
orry | +0.088 |
oke | +0.085 |
tower | +0.080 |
ence | +0.080 |
structure | +0.076 |
Neg logit contributions | |
rob | -0.124 |
Woo | -0.112 |
amb | -0.105 |
bur | -0.098 |
burn | -0.095 |
Token | aved |
Token ID | 9586 |
Feature activation | +5.51e-01 |
Pos logit contributions | |
orry | +0.067 |
oke | +0.065 |
tower | +0.062 |
ence | +0.062 |
run | +0.060 |
Neg logit contributions | |
rob | -0.120 |
Woo | -0.108 |
amb | -0.096 |
thank | -0.087 |
bur | -0.087 |
Token | . |
Token ID | 13 |
Feature activation | +2.37e-01 |
Pos logit contributions | |
orry | +0.019 |
oke | +0.019 |
ence | +0.018 |
run | +0.018 |
aint | +0.017 |
Neg logit contributions | |
rob | -0.019 |
Woo | -0.017 |
amb | -0.013 |
Pink | -0.013 |
thank | -0.013 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +7.89e-02 |
Pos logit contributions | |
orry | +0.009 |
ence | +0.008 |
oke | +0.008 |
run | +0.008 |
aint | +0.008 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.007 |
amb | -0.005 |
Pink | -0.005 |
bur | -0.005 |
Token | Once |
Token ID | 7454 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
oke | +0.002 |
run | +0.002 |
orry | +0.002 |
aint | +0.002 |
ence | +0.002 |
Neg logit contributions | |
rob | -0.003 |
Woo | -0.003 |
amb | -0.002 |
bur | -0.002 |
burn | -0.002 |
Token | did |
Token ID | 750 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
run | +0.000 |
orry | +0.000 |
oke | +0.000 |
ence | +0.000 |
isel | +0.000 |
Neg logit contributions | |
rob | -0.000 |
Woo | -0.000 |
amb | -0.000 |
Pink | -0.000 |
bur | -0.000 |
Token | not |
Token ID | 407 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
oke | +0.007 |
run | +0.007 |
orry | +0.006 |
aint | +0.006 |
ence | +0.006 |
Neg logit contributions | |
rob | -0.005 |
Woo | -0.004 |
Lib | -0.003 |
herself | -0.003 |
Pink | -0.003 |
Token | know |
Token ID | 760 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
rob | +0.007 |
Woo | +0.006 |
amb | +0.005 |
bur | +0.005 |
Pink | +0.005 |
Neg logit contributions | |
orry | -0.004 |
oke | -0.004 |
run | -0.004 |
ence | -0.004 |
aint | -0.004 |
Token | what |
Token ID | 644 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
rob | +0.010 |
Woo | +0.009 |
Pink | +0.007 |
Sim | +0.007 |
Lib | +0.007 |
Neg logit contributions | |
orry | -0.006 |
run | -0.006 |
aint | -0.006 |
ence | -0.006 |
isel | -0.006 |
Token | ost |
Token ID | 23619 |
Feature activation | +6.44e-01 |
Pos logit contributions | |
orry | +0.034 |
run | +0.033 |
oke | +0.033 |
isel | +0.032 |
ence | +0.032 |
Neg logit contributions | |
rob | -0.032 |
Woo | -0.028 |
Pink | -0.023 |
Gloria | -0.022 |
Rudolph | -0.022 |
Token | ric |
Token ID | 1173 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
orry | +0.015 |
run | +0.014 |
tug | +0.014 |
oke | +0.014 |
gust | +0.013 |
Neg logit contributions | |
rob | -0.030 |
Woo | -0.025 |
amb | -0.023 |
bur | -0.023 |
Pink | -0.021 |
Token | hes |
Token ID | 956 |
Feature activation | +9.75e-01 |
Pos logit contributions | |
tug | +0.118 |
run | +0.117 |
orry | +0.113 |
gust | +0.113 |
aint | +0.112 |
Neg logit contributions | |
rob | -0.100 |
Woo | -0.073 |
bur | -0.060 |
amb | -0.060 |
Pink | -0.057 |
Token | were |
Token ID | 547 |
Feature activation | +2.15e-01 |
Pos logit contributions | |
orry | +0.031 |
run | +0.030 |
oke | +0.029 |
ence | +0.029 |
aint | +0.028 |
Neg logit contributions | |
rob | -0.037 |
Woo | -0.032 |
amb | -0.026 |
Pink | -0.026 |
bur | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +4.23e-01 |
Pos logit contributions | |
orry | +0.007 |
run | +0.007 |
oke | +0.007 |
ence | +0.007 |
aint | +0.007 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.006 |
amb | -0.005 |
bur | -0.005 |
Pink | -0.005 |
Token | They |
Token ID | 1119 |
Feature activation | -6.43e-01 |
Pos logit contributions | |
orry | +0.014 |
run | +0.014 |
oke | +0.013 |
ence | +0.013 |
isel | +0.013 |
Neg logit contributions | |
rob | -0.015 |
Woo | -0.014 |
amb | -0.011 |
Pink | -0.011 |
Lib | -0.011 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.71e-01 |
Pos logit contributions | |
rob | +0.022 |
Woo | +0.020 |
amb | +0.017 |
Pink | +0.016 |
bur | +0.016 |
Neg logit contributions | |
oke | -0.021 |
run | -0.021 |
orry | -0.021 |
ence | -0.019 |
aint | -0.019 |
Token | help |
Token ID | 1037 |
Feature activation | -9.09e-02 |
Pos logit contributions | |
rob | +0.003 |
Woo | +0.003 |
amb | +0.002 |
Pink | +0.002 |
bur | +0.002 |
Neg logit contributions | |
orry | -0.002 |
run | -0.002 |
oke | -0.002 |
ence | -0.002 |
aint | -0.002 |
Token | me |
Token ID | 502 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
rob | +0.004 |
Woo | +0.003 |
amb | +0.003 |
thank | +0.003 |
Pink | +0.003 |
Neg logit contributions | |
orry | -0.003 |
run | -0.002 |
aint | -0.002 |
ence | -0.002 |
oke | -0.002 |
Token | ?" |
Token ID | 1701 |
Feature activation | -6.42e-01 |
Pos logit contributions | |
rob | +0.023 |
Woo | +0.019 |
amb | +0.016 |
bur | +0.015 |
Pink | +0.015 |
Neg logit contributions | |
orry | -0.018 |
run | -0.018 |
oke | -0.017 |
ence | -0.017 |
aint | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
rob | +0.023 |
Woo | +0.020 |
amb | +0.016 |
Pink | +0.015 |
bur | +0.014 |
Neg logit contributions | |
orry | -0.023 |
oke | -0.022 |
run | -0.022 |
ence | -0.022 |
aint | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -1.96e-01 |
Pos logit contributions | |
rob | +0.010 |
Woo | +0.009 |
amb | +0.007 |
bur | +0.007 |
Pink | +0.007 |
Neg logit contributions | |
orry | -0.009 |
run | -0.009 |
oke | -0.009 |
ence | -0.009 |
aint | -0.008 |
Token | T |
Token ID | 51 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
rob | +0.006 |
Woo | +0.005 |
amb | +0.004 |
Pink | +0.004 |
bur | +0.004 |
Neg logit contributions | |
orry | -0.008 |
run | -0.008 |
oke | -0.008 |
ence | -0.007 |
aint | -0.007 |
Token | oby |
Token ID | 26730 |
Feature activation | -2.50e-01 |
Pos logit contributions | |
rob | +0.148 |
Woo | +0.130 |
Pink | +0.115 |
Lib | +0.111 |
thank | +0.111 |
Neg logit contributions | |
oke | -0.083 |
orry | -0.081 |
run | -0.076 |
ever | -0.070 |
ence | -0.067 |
Token | was |
Token ID | 373 |
Feature activation | -4.19e-01 |
Pos logit contributions | |
rob | +0.009 |
Woo | +0.008 |
amb | +0.007 |
Pink | +0.006 |
bur | +0.006 |
Neg logit contributions | |
orry | -0.008 |
run | -0.008 |
oke | -0.008 |
ence | -0.008 |
aint | -0.008 |
Token | excited |
Token ID | 6568 |
Feature activation | +7.37e-02 |
Pos logit contributions | |
rob | +0.015 |
Woo | +0.013 |
amb | +0.011 |
Pink | +0.010 |
bur | +0.010 |
Neg logit contributions | |
orry | -0.014 |
oke | -0.014 |
run | -0.014 |
ence | -0.014 |
aint | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | -2.28e-01 |
Pos logit contributions | |
orry | +0.003 |
oke | +0.003 |
run | +0.003 |
ence | +0.003 |
aint | +0.003 |
Neg logit contributions | |
rob | -0.002 |
Woo | -0.002 |
amb | -0.002 |
Pink | -0.001 |
thank | -0.001 |
Token | serve |
Token ID | 4691 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
rob | +0.009 |
Woo | +0.008 |
amb | +0.007 |
Pink | +0.007 |
thank | +0.007 |
Neg logit contributions | |
oke | -0.006 |
orry | -0.006 |
run | -0.006 |
ence | -0.006 |
aint | -0.006 |
Token | okay |
Token ID | 8788 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
orry | +0.031 |
oke | +0.030 |
run | +0.029 |
ence | +0.029 |
aint | +0.028 |
Neg logit contributions | |
rob | -0.045 |
Woo | -0.041 |
bur | -0.034 |
Pink | -0.034 |
amb | -0.033 |
Token | ." |
Token ID | 526 |
Feature activation | -5.41e-01 |
Pos logit contributions | |
orry | +0.020 |
ence | +0.019 |
oke | +0.019 |
run | +0.018 |
aint | +0.018 |
Neg logit contributions | |
rob | -0.016 |
Woo | -0.014 |
amb | -0.011 |
Pink | -0.011 |
bur | -0.011 |
Token | |
Token ID | 220 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
rob | +0.020 |
Woo | +0.017 |
amb | +0.014 |
Pink | +0.014 |
bur | +0.013 |
Neg logit contributions | |
orry | -0.018 |
oke | -0.018 |
ence | -0.018 |
run | -0.018 |
aint | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -3.23e-01 |
Pos logit contributions | |
orry | +0.008 |
run | +0.008 |
oke | +0.008 |
ence | +0.008 |
aint | +0.007 |
Neg logit contributions | |
rob | -0.009 |
Woo | -0.008 |
amb | -0.006 |
bur | -0.006 |
Pink | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
rob | +0.012 |
Woo | +0.010 |
amb | +0.009 |
bur | +0.008 |
Pink | +0.008 |
Neg logit contributions | |
orry | -0.010 |
run | -0.010 |
oke | -0.010 |
ence | -0.010 |
aint | -0.009 |
Token | T |
Token ID | 51 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
rob | +0.005 |
Woo | +0.004 |
amb | +0.003 |
Pink | +0.003 |
bur | +0.003 |
Neg logit contributions | |
orry | -0.005 |
oke | -0.005 |
run | -0.005 |
ence | -0.005 |
aint | -0.005 |
Token | oby |
Token ID | 26730 |
Feature activation | +1.63e-01 |
Pos logit contributions | |
rob | +0.144 |
Woo | +0.123 |
Pink | +0.110 |
Lib | +0.108 |
thank | +0.105 |
Neg logit contributions | |
oke | -0.086 |
orry | -0.085 |
run | -0.083 |
ever | -0.076 |
ence | -0.073 |
Token | thanked |
Token ID | 26280 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
orry | +0.005 |
run | +0.005 |
oke | +0.005 |
ence | +0.005 |
aint | +0.005 |
Neg logit contributions | |
rob | -0.007 |
Woo | -0.006 |
amb | -0.005 |
bur | -0.004 |
Pink | -0.004 |
Token | them |
Token ID | 606 |
Feature activation | +2.32e-02 |
Pos logit contributions | |
rob | +0.009 |
Woo | +0.008 |
amb | +0.007 |
Pink | +0.006 |
bur | +0.006 |
Neg logit contributions | |
orry | -0.006 |
oke | -0.006 |
run | -0.006 |
ence | -0.006 |
aint | -0.006 |
Token | , |
Token ID | 11 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
orry | +0.001 |
run | +0.001 |
oke | +0.001 |
ence | +0.001 |
aint | +0.001 |
Neg logit contributions | |
rob | -0.001 |
Woo | -0.001 |
amb | -0.001 |
bur | -0.000 |
Pink | -0.000 |
Token | said |
Token ID | 531 |
Feature activation | +4.86e-01 |
Pos logit contributions | |
orry | +0.025 |
oke | +0.024 |
run | +0.024 |
ence | +0.024 |
aint | +0.023 |
Neg logit contributions | |
rob | -0.020 |
Woo | -0.017 |
amb | -0.014 |
Pink | -0.013 |
bur | -0.013 |
Token | lightning |
Token ID | 14357 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
orry | +0.020 |
run | +0.019 |
oke | +0.019 |
ence | +0.019 |
aint | +0.018 |
Neg logit contributions | |
rob | -0.029 |
Woo | -0.025 |
amb | -0.022 |
bur | -0.020 |
Pink | -0.020 |
Token | ! |
Token ID | 0 |
Feature activation | +8.73e-02 |
Pos logit contributions | |
orry | +0.004 |
run | +0.004 |
ence | +0.004 |
oke | +0.003 |
isel | +0.003 |
Neg logit contributions | |
rob | -0.004 |
Woo | -0.003 |
Pink | -0.002 |
thank | -0.002 |
amb | -0.002 |
Token | |
Token ID | 220 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
run | +0.002 |
orry | +0.002 |
aint | +0.002 |
oke | +0.002 |
ence | +0.002 |
Neg logit contributions | |
rob | -0.004 |
Woo | -0.003 |
bur | -0.003 |
igi | -0.003 |
amb | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -3.78e-01 |
Pos logit contributions | |
orry | +0.024 |
run | +0.023 |
oke | +0.023 |
ence | +0.022 |
aint | +0.022 |
Neg logit contributions | |
rob | -0.027 |
Woo | -0.022 |
amb | -0.019 |
bur | -0.018 |
Pink | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -3.02e-01 |
Pos logit contributions | |
rob | +0.016 |
Woo | +0.013 |
bur | +0.012 |
amb | +0.012 |
thank | +0.011 |
Neg logit contributions | |
orry | -0.010 |
run | -0.010 |
oke | -0.010 |
aint | -0.010 |
ence | -0.009 |
Token | T |
Token ID | 51 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
rob | +0.012 |
Woo | +0.010 |
amb | +0.008 |
bur | +0.008 |
Pink | +0.008 |
Neg logit contributions | |
orry | -0.010 |
run | -0.009 |
oke | -0.009 |
ence | -0.009 |
aint | -0.009 |
Token | ina |
Token ID | 1437 |
Feature activation | -4.89e-02 |
Pos logit contributions | |
rob | +0.118 |
Woo | +0.091 |
Lib | +0.082 |
Crab | +0.082 |
Rudolph | +0.080 |
Neg logit contributions | |
orry | -0.111 |
oke | -0.110 |
ever | -0.103 |
run | -0.103 |
ence | -0.098 |
Token | loved |
Token ID | 6151 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
rob | +0.002 |
Woo | +0.002 |
amb | +0.001 |
bur | +0.001 |
Pink | +0.001 |
Neg logit contributions | |
orry | -0.002 |
oke | -0.001 |
run | -0.001 |
ence | -0.001 |
aint | -0.001 |
Token | Lightning |
Token ID | 12469 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
oke | +0.013 |
orry | +0.013 |
ence | +0.012 |
run | +0.012 |
aint | +0.012 |
Neg logit contributions | |
rob | -0.011 |
Woo | -0.011 |
Pink | -0.009 |
Cindy | -0.008 |
bur | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -1.27e-01 |
Pos logit contributions | |
orry | +0.002 |
run | +0.002 |
ence | +0.002 |
oke | +0.002 |
isel | +0.002 |
Neg logit contributions | |
rob | -0.003 |
Woo | -0.002 |
amb | -0.002 |
Pink | -0.002 |
Sim | -0.002 |
Token | she |
Token ID | 673 |
Feature activation | +2.27e-01 |
Pos logit contributions | |
rob | +0.005 |
Woo | +0.004 |
amb | +0.003 |
Pink | +0.003 |
bur | +0.003 |
Neg logit contributions | |
orry | -0.004 |
oke | -0.004 |
run | -0.004 |
ence | -0.004 |
aint | -0.004 |
Token | noticed |
Token ID | 6810 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
rob | +0.018 |
Woo | +0.015 |
amb | +0.013 |
Pink | +0.012 |
bur | +0.012 |
Neg logit contributions | |
orry | -0.014 |
run | -0.014 |
oke | -0.014 |
ence | -0.013 |
aint | -0.013 |
Token | before |
Token ID | 878 |
Feature activation | +2.92e-01 |
Pos logit contributions | |
orry | +0.029 |
run | +0.029 |
oke | +0.029 |
ence | +0.028 |
aint | +0.027 |
Neg logit contributions | |
rob | -0.042 |
Woo | -0.036 |
amb | -0.031 |
bur | -0.029 |
Pink | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
run | +0.008 |
orry | +0.008 |
oke | +0.007 |
ence | +0.007 |
aint | +0.007 |
Neg logit contributions | |
rob | -0.013 |
Woo | -0.011 |
amb | -0.010 |
bur | -0.009 |
Pink | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -5.76e-01 |
Pos logit contributions | |
rob | +0.013 |
Woo | +0.011 |
amb | +0.009 |
bur | +0.009 |
thank | +0.009 |
Neg logit contributions | |
run | -0.009 |
orry | -0.009 |
oke | -0.009 |
ence | -0.009 |
aint | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -3.16e-01 |
Pos logit contributions | |
rob | +0.023 |
Woo | +0.019 |
amb | +0.017 |
bur | +0.016 |
thank | +0.016 |
Neg logit contributions | |
run | -0.018 |
oke | -0.017 |
orry | -0.017 |
ence | -0.016 |
aint | -0.016 |
Token | T |
Token ID | 51 |
Feature activation | -3.17e+00 |
Pos logit contributions | |
rob | +0.011 |
Woo | +0.009 |
amb | +0.008 |
bur | +0.007 |
Pink | +0.007 |
Neg logit contributions | |
orry | -0.011 |
run | -0.011 |
oke | -0.011 |
ence | -0.011 |
aint | -0.010 |
Token | ina |
Token ID | 1437 |
Feature activation | +1.80e-01 |
Pos logit contributions | |
rob | +0.137 |
Woo | +0.103 |
Lib | +0.092 |
bur | +0.091 |
Rudolph | +0.089 |
Neg logit contributions | |
oke | -0.101 |
orry | -0.100 |
run | -0.094 |
ence | -0.092 |
ever | -0.088 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.12e-01 |
Pos logit contributions | |
orry | +0.006 |
run | +0.006 |
oke | +0.006 |
ence | +0.006 |
aint | +0.006 |
Neg logit contributions | |
rob | -0.006 |
Woo | -0.005 |
amb | -0.004 |
Pink | -0.004 |
bur | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | -4.80e-01 |
Pos logit contributions | |
rob | +0.014 |
Woo | +0.013 |
amb | +0.011 |
bur | +0.010 |
Pink | +0.010 |
Neg logit contributions | |
orry | -0.008 |
run | -0.007 |
oke | -0.007 |
ence | -0.007 |
aint | -0.007 |
Token | explore |
Token ID | 7301 |
Feature activation | -5.07e-01 |
Pos logit contributions | |
rob | +0.023 |
Woo | +0.019 |
amb | +0.017 |
bur | +0.016 |
Pink | +0.016 |
Neg logit contributions | |
orry | -0.012 |
run | -0.011 |
oke | -0.011 |
ence | -0.011 |
aint | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
rob | +0.023 |
Woo | +0.020 |
amb | +0.018 |
thank | +0.017 |
bur | +0.017 |
Neg logit contributions | |
run | -0.013 |
orry | -0.013 |
ence | -0.012 |
oke | -0.012 |
aint | -0.011 |
Token | want |
Token ID | 765 |
Feature activation | -3.89e-01 |
Pos logit contributions | |
rob | +0.016 |
Woo | +0.015 |
amb | +0.013 |
Pink | +0.012 |
bur | +0.012 |
Neg logit contributions | |
orry | -0.009 |
run | -0.009 |
oke | -0.009 |
ence | -0.008 |
aint | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | -7.15e-01 |
Pos logit contributions | |
rob | +0.019 |
Woo | +0.016 |
amb | +0.014 |
bur | +0.014 |
thank | +0.013 |
Neg logit contributions | |
orry | -0.009 |
run | -0.009 |
oke | -0.008 |
ence | -0.008 |
aint | -0.008 |
Token | play |
Token ID | 711 |
Feature activation | -8.44e-01 |
Pos logit contributions | |
rob | +0.040 |
Woo | +0.032 |
amb | +0.029 |
igi | +0.028 |
bur | +0.027 |
Neg logit contributions | |
orry | -0.012 |
aint | -0.012 |
tower | -0.012 |
ence | -0.011 |
tug | -0.011 |
Token | with |
Token ID | 351 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
rob | +0.033 |
Woo | +0.027 |
amb | +0.024 |
bur | +0.023 |
igi | +0.022 |
Neg logit contributions | |
orry | -0.026 |
run | -0.026 |
oke | -0.025 |
ence | -0.025 |
tower | -0.024 |
Token | our |
Token ID | 674 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
rob | +0.027 |
Woo | +0.023 |
amb | +0.020 |
bur | +0.019 |
Pink | +0.019 |
Neg logit contributions | |
orry | -0.018 |
run | -0.017 |
oke | -0.017 |
ence | -0.017 |
aint | -0.016 |
Token | toy |
Token ID | 13373 |
Feature activation | -3.15e+00 |
Pos logit contributions | |
rob | +0.027 |
Woo | +0.023 |
amb | +0.019 |
Pink | +0.018 |
bur | +0.018 |
Neg logit contributions | |
run | -0.024 |
orry | -0.024 |
oke | -0.024 |
ence | -0.023 |
aint | -0.022 |
Token | rockets |
Token ID | 20293 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
rob | +0.133 |
Woo | +0.117 |
amb | +0.099 |
bur | +0.097 |
thank | +0.095 |
Neg logit contributions | |
orry | -0.084 |
oke | -0.081 |
tower | -0.080 |
run | -0.080 |
ence | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | -1.55e-04 |
Pos logit contributions | |
rob | +0.010 |
Woo | +0.009 |
amb | +0.007 |
bur | +0.007 |
Pink | +0.007 |
Neg logit contributions | |
run | -0.006 |
orry | -0.006 |
oke | -0.006 |
ence | -0.006 |
tower | -0.006 |
Token | We |
Token ID | 775 |
Feature activation | -3.40e-01 |
Pos logit contributions | |
rob | +0.000 |
Woo | +0.000 |
amb | +0.000 |
Pink | +0.000 |
bur | +0.000 |
Neg logit contributions | |
orry | -0.000 |
oke | -0.000 |
run | -0.000 |
ence | -0.000 |
aint | -0.000 |
Token | like |
Token ID | 588 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
rob | +0.015 |
Woo | +0.014 |
amb | +0.012 |
Pink | +0.012 |
bur | +0.011 |
Neg logit contributions | |
run | -0.008 |
orry | -0.008 |
oke | -0.008 |
ence | -0.008 |
aint | -0.007 |
Token | our |
Token ID | 674 |
Feature activation | -2.76e-01 |
Pos logit contributions | |
orry | +0.015 |
oke | +0.015 |
run | +0.015 |
ence | +0.014 |
aint | +0.014 |
Neg logit contributions | |
rob | -0.017 |
Woo | -0.015 |
Pink | -0.012 |
amb | -0.012 |
Rudolph | -0.012 |
Token | helping |
Token ID | 5742 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
rob | +0.003 |
Woo | +0.003 |
amb | +0.002 |
bur | +0.002 |
Pink | +0.002 |
Neg logit contributions | |
orry | -0.002 |
run | -0.002 |
oke | -0.002 |
ence | -0.002 |
aint | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
orry | +0.011 |
oke | +0.011 |
run | +0.011 |
ence | +0.011 |
aint | +0.011 |
Neg logit contributions | |
rob | -0.010 |
Woo | -0.009 |
Pink | -0.007 |
amb | -0.007 |
bur | -0.007 |
Token | other |
Token ID | 584 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
rob | +0.012 |
Woo | +0.010 |
amb | +0.008 |
Pink | +0.008 |
bur | +0.008 |
Neg logit contributions | |
run | -0.012 |
orry | -0.012 |
oke | -0.012 |
ence | -0.012 |
aint | -0.011 |
Token | creatures |
Token ID | 8109 |
Feature activation | +2.83e-02 |
Pos logit contributions | |
rob | +0.062 |
Woo | +0.052 |
amb | +0.044 |
bur | +0.041 |
Pink | +0.041 |
Neg logit contributions | |
orry | -0.054 |
oke | -0.052 |
run | -0.052 |
ence | -0.051 |
aint | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -2.41e-01 |
Pos logit contributions | |
orry | +0.001 |
oke | +0.001 |
run | +0.001 |
ence | +0.001 |
aint | +0.001 |
Neg logit contributions | |
rob | -0.001 |
Woo | -0.001 |
amb | -0.001 |
Pink | -0.001 |
bur | -0.001 |
Token | L |
Token ID | 406 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
rob | +0.011 |
Woo | +0.009 |
bur | +0.008 |
amb | +0.008 |
thank | +0.008 |
Neg logit contributions | |
oke | -0.006 |
orry | -0.006 |
run | -0.006 |
ence | -0.006 |
aint | -0.005 |
Token | ola |
Token ID | 5708 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
rob | +0.146 |
Woo | +0.125 |
Pink | +0.106 |
bur | +0.106 |
thank | +0.106 |
Neg logit contributions | |
oke | -0.087 |
orry | -0.083 |
run | -0.074 |
ence | -0.069 |
aint | -0.064 |
Token | and |
Token ID | 290 |
Feature activation | +3.87e-01 |
Pos logit contributions | |
rob | +0.026 |
Woo | +0.022 |
bur | +0.017 |
amb | +0.017 |
burn | +0.017 |
Neg logit contributions | |
orry | -0.021 |
oke | -0.021 |
ence | -0.020 |
run | -0.020 |
aint | -0.019 |
Token | Lex |
Token ID | 17210 |
Feature activation | -1.61e-01 |
Pos logit contributions | |
orry | +0.013 |
tug | +0.012 |
ence | +0.012 |
oke | +0.012 |
aint | +0.012 |
Neg logit contributions | |
rob | -0.014 |
Woo | -0.010 |
robe | -0.009 |
thank | -0.008 |
amb | -0.008 |
Token | had |
Token ID | 550 |
Feature activation | -5.39e-01 |
Pos logit contributions | |
rob | +0.005 |
Woo | +0.004 |
amb | +0.003 |
thank | +0.003 |
burn | +0.003 |
Neg logit contributions | |
orry | -0.006 |
oke | -0.006 |
ence | -0.006 |
run | -0.006 |
aint | -0.006 |
Token | learned |
Token ID | 4499 |
Feature activation | -8.14e-02 |
Pos logit contributions | |
rob | +0.017 |
Woo | +0.015 |
amb | +0.011 |
Pink | +0.011 |
bur | +0.011 |
Neg logit contributions | |
orry | -0.021 |
oke | -0.021 |
run | -0.020 |
ence | -0.020 |
aint | -0.019 |
Token | learn |
Token ID | 2193 |
Feature activation | -3.68e-01 |
Pos logit contributions | |
run | +0.009 |
orry | +0.009 |
oke | +0.009 |
ence | +0.008 |
aint | +0.008 |
Neg logit contributions | |
rob | -0.015 |
Woo | -0.014 |
amb | -0.012 |
Pink | -0.012 |
bur | -0.011 |
Token | today |
Token ID | 1909 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
rob | +0.014 |
Woo | +0.012 |
amb | +0.011 |
bur | +0.010 |
Pink | +0.010 |
Neg logit contributions | |
run | -0.011 |
oke | -0.011 |
orry | -0.011 |
ence | -0.011 |
aint | -0.011 |
Token | ?" |
Token ID | 1701 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
rob | +0.028 |
Woo | +0.023 |
amb | +0.019 |
bur | +0.017 |
Pink | +0.017 |
Neg logit contributions | |
oke | -0.030 |
orry | -0.030 |
run | -0.030 |
ence | -0.029 |
aint | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -8.79e-03 |
Pos logit contributions | |
rob | +0.021 |
Woo | +0.019 |
amb | +0.015 |
Pink | +0.014 |
Gloria | +0.014 |
Neg logit contributions | |
orry | -0.022 |
oke | -0.022 |
run | -0.022 |
ence | -0.021 |
tower | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -3.70e-02 |
Pos logit contributions | |
rob | +0.000 |
Woo | +0.000 |
amb | +0.000 |
Pink | +0.000 |
bur | +0.000 |
Neg logit contributions | |
orry | -0.000 |
oke | -0.000 |
run | -0.000 |
ence | -0.000 |
aint | -0.000 |
Token | T |
Token ID | 51 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
rob | +0.001 |
Woo | +0.001 |
amb | +0.001 |
Pink | +0.001 |
bur | +0.001 |
Neg logit contributions | |
orry | -0.001 |
oke | -0.001 |
run | -0.001 |
ence | -0.001 |
aint | -0.001 |
Token | ina |
Token ID | 1437 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
rob | +0.111 |
Woo | +0.095 |
Lib | +0.082 |
Pink | +0.082 |
Rudolph | +0.074 |
Neg logit contributions | |
oke | -0.112 |
orry | -0.109 |
run | -0.105 |
ence | -0.102 |
ever | -0.102 |
Token | smiled |
Token ID | 13541 |
Feature activation | -7.66e-01 |
Pos logit contributions | |
rob | +0.015 |
Woo | +0.013 |
amb | +0.011 |
bur | +0.010 |
Pink | +0.010 |
Neg logit contributions | |
orry | -0.012 |
oke | -0.012 |
run | -0.012 |
ence | -0.011 |
aint | -0.011 |
Token | proudly |
Token ID | 23017 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
rob | +0.035 |
Woo | +0.027 |
bur | +0.023 |
igi | +0.022 |
amb | +0.021 |
Neg logit contributions | |
run | -0.022 |
ence | -0.022 |
aint | -0.021 |
orry | -0.021 |
oke | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
rob | +0.062 |
Woo | +0.052 |
amb | +0.043 |
Pink | +0.040 |
bur | +0.040 |
Neg logit contributions | |
orry | -0.063 |
oke | -0.062 |
run | -0.062 |
ence | -0.060 |
aint | -0.059 |
Token | said |
Token ID | 531 |
Feature activation | -2.09e-01 |
Pos logit contributions | |
rob | +0.006 |
Woo | +0.005 |
amb | +0.004 |
bur | +0.004 |
igi | +0.004 |
Neg logit contributions | |
orry | -0.005 |
run | -0.005 |
ence | -0.005 |
oke | -0.005 |
aint | -0.005 |
Token | thought |
Token ID | 1807 |
Feature activation | +7.27e-01 |
Pos logit contributions | |
rob | +0.002 |
Woo | +0.002 |
amb | +0.001 |
bur | +0.001 |
Pink | +0.001 |
Neg logit contributions | |
orry | -0.001 |
run | -0.001 |
oke | -0.001 |
ence | -0.001 |
aint | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
orry | +0.024 |
ence | +0.024 |
oke | +0.024 |
aint | +0.023 |
isel | +0.023 |
Neg logit contributions | |
rob | -0.023 |
Woo | -0.022 |
Pink | -0.017 |
Sim | -0.016 |
Cindy | -0.016 |
Token | should |
Token ID | 815 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
rob | +0.028 |
Woo | +0.023 |
amb | +0.019 |
Pink | +0.019 |
bur | +0.019 |
Neg logit contributions | |
orry | -0.026 |
oke | -0.026 |
run | -0.025 |
ence | -0.025 |
aint | -0.024 |
Token | work |
Token ID | 670 |
Feature activation | +5.62e-01 |
Pos logit contributions | |
rob | +0.064 |
Woo | +0.055 |
amb | +0.048 |
bur | +0.046 |
burn | +0.045 |
Neg logit contributions | |
orry | -0.026 |
run | -0.025 |
oke | -0.025 |
ence | -0.024 |
aint | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -3.50e-03 |
Pos logit contributions | |
run | +0.015 |
orry | +0.015 |
oke | +0.015 |
ence | +0.015 |
aint | +0.014 |
Neg logit contributions | |
rob | -0.024 |
Woo | -0.021 |
amb | -0.018 |
bur | -0.017 |
Pink | -0.017 |
Token | D |
Token ID | 360 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
rob | +0.000 |
Woo | +0.000 |
amb | +0.000 |
Pink | +0.000 |
bur | +0.000 |
Neg logit contributions | |
orry | -0.000 |
ence | -0.000 |
oke | -0.000 |
run | -0.000 |
aint | -0.000 |
Token | ina |
Token ID | 1437 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
rob | +0.098 |
Woo | +0.075 |
bur | +0.058 |
Pink | +0.056 |
Lib | +0.056 |
Neg logit contributions | |
orry | -0.128 |
oke | -0.126 |
run | -0.122 |
ence | -0.120 |
aint | -0.117 |
Token | was |
Token ID | 373 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
rob | +0.013 |
Woo | +0.011 |
amb | +0.010 |
Pink | +0.009 |
bur | +0.009 |
Neg logit contributions | |
orry | -0.012 |
run | -0.012 |
oke | -0.012 |
ence | -0.011 |
aint | -0.011 |
Token | so |
Token ID | 523 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
rob | +0.018 |
Woo | +0.016 |
amb | +0.014 |
Pink | +0.013 |
bur | +0.013 |
Neg logit contributions | |
orry | -0.012 |
oke | -0.012 |
run | -0.012 |
ence | -0.011 |
aint | -0.011 |
Token | happy |
Token ID | 3772 |
Feature activation | +7.51e-01 |
Pos logit contributions | |
rob | +0.006 |
Woo | +0.005 |
amb | +0.005 |
Pink | +0.004 |
thank | +0.004 |
Neg logit contributions | |
orry | -0.003 |
oke | -0.003 |
run | -0.003 |
ence | -0.003 |
aint | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +7.69e-02 |
Pos logit contributions | |
orry | +0.027 |
oke | +0.026 |
run | +0.026 |
ence | +0.026 |
aint | +0.025 |
Neg logit contributions | |
rob | -0.026 |
Woo | -0.022 |
amb | -0.018 |
Pink | -0.017 |
bur | -0.016 |
Token | her |
Token ID | 607 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
rob | +0.003 |
Woo | +0.003 |
amb | +0.002 |
bur | +0.002 |
Pink | +0.002 |
Neg logit contributions | |
orry | -0.003 |
run | -0.003 |
oke | -0.003 |
ence | -0.003 |
aint | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | +3.79e-01 |
Pos logit contributions | |
rob | +0.014 |
Woo | +0.013 |
Pink | +0.011 |
amb | +0.011 |
Rudolph | +0.010 |
Neg logit contributions | |
orry | -0.017 |
isel | -0.017 |
oke | -0.016 |
ence | -0.016 |
run | -0.016 |
Token | |
Token ID | 220 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
run | +0.011 |
oke | +0.011 |
orry | +0.011 |
aint | +0.010 |
ence | +0.010 |
Neg logit contributions | |
rob | -0.016 |
Woo | -0.013 |
bur | -0.011 |
amb | -0.011 |
thank | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +9.73e-02 |
Pos logit contributions | |
run | +0.019 |
orry | +0.019 |
oke | +0.019 |
ence | +0.018 |
aint | +0.018 |
Neg logit contributions | |
rob | -0.023 |
Woo | -0.019 |
amb | -0.016 |
bur | -0.015 |
Pink | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
run | +0.003 |
oke | +0.003 |
orry | +0.003 |
aint | +0.002 |
ence | +0.002 |
Neg logit contributions | |
rob | -0.004 |
Woo | -0.004 |
bur | -0.003 |
amb | -0.003 |
burn | -0.003 |
Token | V |
Token ID | 53 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
run | +0.009 |
orry | +0.009 |
oke | +0.009 |
ence | +0.008 |
aint | +0.008 |
Neg logit contributions | |
rob | -0.011 |
Woo | -0.010 |
amb | -0.008 |
bur | -0.008 |
Pink | -0.008 |
Token | iv |
Token ID | 452 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
rob | +0.116 |
Woo | +0.107 |
Pink | +0.091 |
Lib | +0.088 |
Gloria | +0.086 |
Neg logit contributions | |
orry | -0.093 |
oke | -0.093 |
run | -0.088 |
ever | -0.085 |
aint | -0.084 |
Token | ian |
Token ID | 666 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
rob | +0.034 |
Woo | +0.027 |
amb | +0.021 |
bur | +0.021 |
Pink | +0.020 |
Neg logit contributions | |
orry | -0.039 |
oke | -0.039 |
run | -0.039 |
ence | -0.038 |
aint | -0.037 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
rob | +0.018 |
Woo | +0.015 |
amb | +0.012 |
bur | +0.012 |
burn | +0.012 |
Neg logit contributions | |
orry | -0.013 |
oke | -0.013 |
run | -0.013 |
ence | -0.012 |
aint | -0.012 |
Token | playing |
Token ID | 2712 |
Feature activation | -4.32e-01 |
Pos logit contributions | |
rob | +0.009 |
Woo | +0.008 |
amb | +0.006 |
Pink | +0.006 |
bur | +0.006 |
Neg logit contributions | |
orry | -0.009 |
oke | -0.009 |
run | -0.009 |
ence | -0.008 |
aint | -0.008 |
Token | with |
Token ID | 351 |
Feature activation | -3.69e-01 |
Pos logit contributions | |
rob | +0.014 |
Woo | +0.012 |
amb | +0.009 |
Pink | +0.009 |
thank | +0.009 |
Neg logit contributions | |
oke | -0.016 |
orry | -0.016 |
run | -0.016 |
ence | -0.016 |
aint | -0.015 |
Token | god |
Token ID | 5770 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
orry | +0.010 |
run | +0.010 |
oke | +0.010 |
ence | +0.010 |
aint | +0.010 |
Neg logit contributions | |
rob | -0.012 |
Woo | -0.010 |
amb | -0.008 |
bur | -0.008 |
Pink | -0.007 |
Token | mother |
Token ID | 13552 |
Feature activation | +7.38e-01 |
Pos logit contributions | |
orry | +0.004 |
oke | +0.004 |
run | +0.004 |
ence | +0.004 |
aint | +0.003 |
Neg logit contributions | |
rob | -0.004 |
Woo | -0.003 |
amb | -0.003 |
Sebastian | -0.003 |
bur | -0.003 |
Token | flew |
Token ID | 13112 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
orry | +0.024 |
run | +0.024 |
oke | +0.024 |
ence | +0.023 |
aint | +0.022 |
Neg logit contributions | |
rob | -0.028 |
Woo | -0.024 |
amb | -0.019 |
bur | -0.019 |
Pink | -0.018 |
Token | away |
Token ID | 1497 |
Feature activation | -1.31e+00 |
Pos logit contributions | |
run | +0.011 |
orry | +0.011 |
ence | +0.010 |
aint | +0.010 |
oke | +0.010 |
Neg logit contributions | |
rob | -0.019 |
Woo | -0.015 |
amb | -0.013 |
bur | -0.012 |
oto | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
rob | +0.056 |
Woo | +0.047 |
amb | +0.040 |
bur | +0.039 |
Pink | +0.037 |
Neg logit contributions | |
run | -0.037 |
orry | -0.037 |
oke | -0.036 |
ence | -0.036 |
aint | -0.034 |
Token | D |
Token ID | 360 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
rob | +0.011 |
Woo | +0.008 |
bur | +0.008 |
oto | +0.007 |
amb | +0.007 |
Neg logit contributions | |
run | -0.006 |
orry | -0.006 |
oke | -0.005 |
aint | -0.005 |
ence | -0.005 |
Token | olly |
Token ID | 5098 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
rob | +0.146 |
Woo | +0.124 |
bur | +0.107 |
amb | +0.104 |
Sebastian | +0.104 |
Neg logit contributions | |
orry | -0.076 |
oke | -0.074 |
run | -0.070 |
ence | -0.067 |
aint | -0.066 |
Token | was |
Token ID | 373 |
Feature activation | -3.59e-01 |
Pos logit contributions | |
rob | +0.010 |
Woo | +0.008 |
amb | +0.007 |
bur | +0.007 |
oto | +0.006 |
Neg logit contributions | |
orry | -0.007 |
run | -0.007 |
oke | -0.007 |
ence | -0.007 |
aint | -0.006 |
Token | so |
Token ID | 523 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
rob | +0.019 |
Woo | +0.015 |
amb | +0.014 |
oto | +0.013 |
bur | +0.013 |
Neg logit contributions | |
run | -0.008 |
orry | -0.008 |
ence | -0.007 |
oke | -0.007 |
gust | -0.006 |
Token | happy |
Token ID | 3772 |
Feature activation | +8.60e-01 |
Pos logit contributions | |
rob | +0.013 |
Woo | +0.011 |
amb | +0.010 |
bur | +0.009 |
Pink | +0.009 |
Neg logit contributions | |
orry | -0.004 |
run | -0.004 |
oke | -0.004 |
ence | -0.003 |
aint | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | +7.25e-01 |
Pos logit contributions | |
orry | +0.027 |
run | +0.026 |
oke | +0.026 |
ence | +0.025 |
aint | +0.025 |
Neg logit contributions | |
rob | -0.034 |
Woo | -0.028 |
amb | -0.024 |
bur | -0.023 |
Pink | -0.022 |
Token | record |
Token ID | 1700 |
Feature activation | -5.06e-01 |
Pos logit contributions | |
rob | +0.014 |
Woo | +0.012 |
amb | +0.010 |
Pink | +0.010 |
thank | +0.010 |
Neg logit contributions | |
oke | -0.011 |
orry | -0.011 |
run | -0.010 |
ence | -0.010 |
aint | -0.009 |
Token | her |
Token ID | 607 |
Feature activation | -6.79e-01 |
Pos logit contributions | |
rob | +0.018 |
Woo | +0.015 |
amb | +0.012 |
Pink | +0.011 |
bur | +0.011 |
Neg logit contributions | |
orry | -0.018 |
oke | -0.018 |
run | -0.017 |
ence | -0.017 |
aint | -0.017 |
Token | voice |
Token ID | 3809 |
Feature activation | +3.83e-02 |
Pos logit contributions | |
rob | +0.025 |
Woo | +0.021 |
amb | +0.018 |
Pink | +0.017 |
oto | +0.016 |
Neg logit contributions | |
oke | -0.024 |
orry | -0.023 |
run | -0.022 |
isel | -0.021 |
ence | -0.021 |
Token | with |
Token ID | 351 |
Feature activation | -8.50e-01 |
Pos logit contributions | |
orry | +0.001 |
oke | +0.001 |
run | +0.001 |
isel | +0.001 |
ence | +0.001 |
Neg logit contributions | |
rob | -0.001 |
Woo | -0.001 |
amb | -0.001 |
Pink | -0.001 |
thank | -0.001 |
Token | her |
Token ID | 607 |
Feature activation | -7.10e-01 |
Pos logit contributions | |
rob | +0.023 |
Woo | +0.019 |
amb | +0.014 |
Pink | +0.013 |
bur | +0.013 |
Neg logit contributions | |
orry | -0.036 |
oke | -0.036 |
run | -0.035 |
ence | -0.035 |
aint | -0.034 |
Token | toy |
Token ID | 13373 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
rob | +0.029 |
Woo | +0.025 |
amb | +0.021 |
Pink | +0.021 |
bur | +0.020 |
Neg logit contributions | |
orry | -0.021 |
oke | -0.021 |
run | -0.020 |
ence | -0.020 |
aint | -0.019 |
Token | phone |
Token ID | 3072 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
rob | +0.123 |
Woo | +0.108 |
amb | +0.093 |
Pink | +0.089 |
bur | +0.086 |
Neg logit contributions | |
orry | -0.090 |
oke | -0.088 |
run | -0.088 |
ence | -0.084 |
aint | -0.081 |
Token | . |
Token ID | 13 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
rob | +0.033 |
Woo | +0.028 |
amb | +0.024 |
Pink | +0.023 |
bur | +0.022 |
Neg logit contributions | |
orry | -0.030 |
oke | -0.029 |
run | -0.029 |
ence | -0.028 |
isel | -0.027 |
Token | She |
Token ID | 1375 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
rob | +0.001 |
Woo | +0.001 |
Pink | +0.001 |
amb | +0.001 |
Cindy | +0.001 |
Neg logit contributions | |
orry | -0.001 |
oke | -0.001 |
run | -0.001 |
ence | -0.001 |
isel | -0.001 |
Token | would |
Token ID | 561 |
Feature activation | -9.13e-01 |
Pos logit contributions | |
rob | +0.027 |
Woo | +0.023 |
amb | +0.020 |
bur | +0.019 |
Pink | +0.019 |
Neg logit contributions | |
orry | -0.016 |
run | -0.016 |
oke | -0.016 |
ence | -0.016 |
aint | -0.015 |
Token | say |
Token ID | 910 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
rob | +0.032 |
Woo | +0.029 |
amb | +0.024 |
Pink | +0.023 |
thank | +0.023 |
Neg logit contributions | |
oke | -0.031 |
orry | -0.030 |
run | -0.030 |
ence | -0.028 |
aint | -0.027 |
Token | rag |
Token ID | 34232 |
Feature activation | -9.35e-01 |
Pos logit contributions | |
rob | +0.020 |
Woo | +0.017 |
Pink | +0.013 |
amb | +0.013 |
Gloria | +0.012 |
Neg logit contributions | |
run | -0.027 |
oke | -0.027 |
orry | -0.027 |
ence | -0.026 |
aint | -0.025 |
Token | toy |
Token ID | 13373 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
rob | +0.032 |
Woo | +0.027 |
amb | +0.022 |
Pink | +0.022 |
bur | +0.021 |
Neg logit contributions | |
orry | -0.032 |
oke | -0.032 |
run | -0.032 |
ence | -0.031 |
aint | -0.030 |
Token | was |
Token ID | 373 |
Feature activation | +9.29e-02 |
Pos logit contributions | |
rob | +0.079 |
Woo | +0.067 |
amb | +0.056 |
bur | +0.052 |
Pink | +0.052 |
Neg logit contributions | |
orry | -0.068 |
run | -0.067 |
oke | -0.067 |
ence | -0.065 |
aint | -0.063 |
Token | free |
Token ID | 1479 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
orry | +0.003 |
run | +0.003 |
oke | +0.003 |
ence | +0.003 |
aint | +0.003 |
Neg logit contributions | |
rob | -0.004 |
Woo | -0.003 |
amb | -0.003 |
bur | -0.003 |
Pink | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | -2.81e-02 |
Pos logit contributions | |
orry | +0.018 |
run | +0.018 |
oke | +0.017 |
ence | +0.017 |
aint | +0.016 |
Neg logit contributions | |
rob | -0.024 |
Woo | -0.020 |
amb | -0.017 |
bur | -0.016 |
Pink | -0.016 |
Token | D |
Token ID | 360 |
Feature activation | -3.03e+00 |
Pos logit contributions | |
rob | +0.001 |
Woo | +0.001 |
amb | +0.001 |
Pink | +0.001 |
bur | +0.001 |
Neg logit contributions | |
orry | -0.001 |
oke | -0.001 |
run | -0.001 |
ence | -0.001 |
aint | -0.001 |
Token | olly |
Token ID | 5098 |
Feature activation | -5.68e-01 |
Pos logit contributions | |
rob | +0.137 |
Woo | +0.117 |
bur | +0.096 |
Sebastian | +0.095 |
amb | +0.094 |
Neg logit contributions | |
orry | -0.084 |
oke | -0.083 |
run | -0.079 |
ence | -0.076 |
aint | -0.074 |
Token | was |
Token ID | 373 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
rob | +0.020 |
Woo | +0.017 |
amb | +0.015 |
Pink | +0.014 |
bur | +0.014 |
Neg logit contributions | |
orry | -0.019 |
oke | -0.018 |
run | -0.018 |
ence | -0.018 |
aint | -0.017 |
Token | so |
Token ID | 523 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
rob | +0.020 |
Woo | +0.016 |
amb | +0.014 |
bur | +0.013 |
Pink | +0.013 |
Neg logit contributions | |
orry | -0.016 |
run | -0.015 |
oke | -0.015 |
ence | -0.015 |
aint | -0.014 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
rob | +0.009 |
Woo | +0.008 |
amb | +0.007 |
Pink | +0.007 |
bur | +0.007 |
Neg logit contributions | |
orry | -0.005 |
oke | -0.005 |
run | -0.005 |
ence | -0.005 |
aint | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | -6.70e-03 |
Pos logit contributions | |
rob | +0.004 |
Woo | +0.003 |
amb | +0.003 |
bur | +0.003 |
Pink | +0.003 |
Neg logit contributions | |
orry | -0.003 |
run | -0.003 |
oke | -0.003 |
ence | -0.003 |
aint | -0.003 |
Token | it |
Token ID | 340 |
Feature activation | +4.26e-02 |
Pos logit contributions | |
rob | +0.028 |
amb | +0.022 |
Woo | +0.022 |
igi | +0.021 |
bur | +0.021 |
Neg logit contributions | |
run | -0.013 |
orry | -0.012 |
triangle | -0.012 |
ence | -0.011 |
aint | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -6.01e-02 |
Pos logit contributions | |
run | +0.001 |
orry | +0.001 |
oke | +0.001 |
ence | +0.001 |
aint | +0.001 |
Neg logit contributions | |
rob | -0.002 |
Woo | -0.002 |
amb | -0.001 |
bur | -0.001 |
Sebastian | -0.001 |
Token | I |
Token ID | 314 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
rob | +0.003 |
Woo | +0.003 |
amb | +0.002 |
Pink | +0.002 |
bur | +0.002 |
Neg logit contributions | |
orry | -0.001 |
run | -0.001 |
oke | -0.001 |
ence | -0.001 |
aint | -0.001 |
Token | like |
Token ID | 588 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
rob | +0.006 |
Woo | +0.005 |
amb | +0.005 |
bur | +0.005 |
Gloria | +0.004 |
Neg logit contributions | |
orry | -0.003 |
oke | -0.003 |
run | -0.003 |
ence | -0.003 |
aint | -0.003 |
Token | your |
Token ID | 534 |
Feature activation | -7.55e-01 |
Pos logit contributions | |
orry | +0.020 |
oke | +0.020 |
run | +0.020 |
ence | +0.019 |
aint | +0.019 |
Neg logit contributions | |
rob | -0.023 |
Woo | -0.020 |
amb | -0.016 |
Pink | -0.016 |
bur | -0.015 |
Token | toy |
Token ID | 13373 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
rob | +0.034 |
Woo | +0.029 |
amb | +0.025 |
bur | +0.025 |
igi | +0.024 |
Neg logit contributions | |
orry | -0.019 |
run | -0.018 |
oke | -0.018 |
ence | -0.018 |
tower | -0.017 |
Token | microphone |
Token ID | 21822 |
Feature activation | -4.27e-01 |
Pos logit contributions | |
rob | +0.134 |
Woo | +0.115 |
igi | +0.104 |
bur | +0.103 |
Lib | +0.102 |
Neg logit contributions | |
tower | -0.070 |
orry | -0.069 |
oke | -0.068 |
run | -0.066 |
ence | -0.065 |
Token | too |
Token ID | 1165 |
Feature activation | +3.04e-01 |
Pos logit contributions | |
rob | +0.020 |
Woo | +0.017 |
amb | +0.015 |
bur | +0.014 |
Sebastian | +0.014 |
Neg logit contributions | |
run | -0.011 |
oke | -0.010 |
orry | -0.010 |
tower | -0.010 |
ence | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.24e-01 |
Pos logit contributions | |
orry | +0.009 |
oke | +0.009 |
run | +0.009 |
ence | +0.009 |
aint | +0.008 |
Neg logit contributions | |
rob | -0.013 |
Woo | -0.011 |
amb | -0.009 |
bur | -0.009 |
Pink | -0.009 |
Token | It |
Token ID | 632 |
Feature activation | -6.40e-01 |
Pos logit contributions | |
rob | +0.006 |
Woo | +0.005 |
amb | +0.005 |
bur | +0.005 |
Pink | +0.005 |
Neg logit contributions | |
orry | -0.003 |
run | -0.003 |
oke | -0.003 |
ence | -0.002 |
aint | -0.002 |
Token | is |
Token ID | 318 |
Feature activation | -1.87e-01 |
Pos logit contributions | |
rob | +0.030 |
Woo | +0.026 |
amb | +0.023 |
bur | +0.022 |
Pink | +0.021 |
Neg logit contributions | |
orry | -0.015 |
oke | -0.015 |
run | -0.015 |
ence | -0.014 |
aint | -0.014 |
Token | sorry |
Token ID | 7926 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
orry | +0.009 |
oke | +0.009 |
run | +0.009 |
ence | +0.008 |
aint | +0.008 |
Neg logit contributions | |
rob | -0.026 |
Woo | -0.023 |
amb | -0.020 |
Pink | -0.020 |
bur | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
rob | +0.021 |
Woo | +0.017 |
amb | +0.015 |
bur | +0.014 |
Pink | +0.014 |
Neg logit contributions | |
orry | -0.017 |
run | -0.017 |
oke | -0.017 |
ence | -0.016 |
aint | -0.016 |
Token | Lilly |
Token ID | 35134 |
Feature activation | +7.00e-02 |
Pos logit contributions | |
orry | +0.009 |
oke | +0.009 |
run | +0.009 |
ence | +0.008 |
aint | +0.008 |
Neg logit contributions | |
rob | -0.010 |
Woo | -0.008 |
amb | -0.007 |
bur | -0.007 |
thank | -0.007 |
Token | ," |
Token ID | 553 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
orry | +0.003 |
run | +0.003 |
ence | +0.003 |
oke | +0.003 |
aint | +0.002 |
Neg logit contributions | |
rob | -0.002 |
Woo | -0.002 |
amb | -0.002 |
Pink | -0.001 |
bur | -0.001 |
Token | said |
Token ID | 531 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
orry | +0.006 |
run | +0.006 |
oke | +0.006 |
tug | +0.006 |
aint | +0.006 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.006 |
amb | -0.005 |
bur | -0.005 |
burn | -0.005 |
Token | D |
Token ID | 360 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
rob | +0.020 |
Woo | +0.014 |
amb | +0.012 |
bur | +0.012 |
thank | +0.011 |
Neg logit contributions | |
orry | -0.018 |
run | -0.018 |
oke | -0.017 |
ence | -0.017 |
aint | -0.017 |
Token | alia |
Token ID | 9752 |
Feature activation | +2.39e-01 |
Pos logit contributions | |
rob | +0.108 |
Woo | +0.086 |
bur | +0.067 |
amb | +0.066 |
Pink | +0.066 |
Neg logit contributions | |
orry | -0.108 |
oke | -0.108 |
run | -0.106 |
ence | -0.102 |
aint | -0.101 |
Token | , |
Token ID | 11 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
orry | +0.008 |
ence | +0.007 |
oke | +0.007 |
run | +0.007 |
aint | +0.007 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.007 |
amb | -0.006 |
Pink | -0.006 |
Gloria | -0.006 |
Token | " |
Token ID | 366 |
Feature activation | +2.11e-01 |
Pos logit contributions | |
orry | +0.018 |
oke | +0.018 |
ence | +0.016 |
run | +0.016 |
aint | +0.016 |
Neg logit contributions | |
rob | -0.020 |
Woo | -0.019 |
Pink | -0.016 |
amb | -0.015 |
thank | -0.015 |
Token | but |
Token ID | 4360 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
orry | +0.007 |
oke | +0.007 |
run | +0.007 |
ence | +0.007 |
aint | +0.007 |
Neg logit contributions | |
rob | -0.007 |
Woo | -0.006 |
amb | -0.005 |
bur | -0.005 |
Pink | -0.005 |
Token | I |
Token ID | 314 |
Feature activation | -3.45e-02 |
Pos logit contributions | |
orry | +0.047 |
oke | +0.045 |
ence | +0.045 |
run | +0.044 |
aint | +0.044 |
Neg logit contributions | |
rob | -0.046 |
Woo | -0.046 |
Pink | -0.039 |
Cindy | -0.036 |
bur | -0.036 |
Token | deer |
Token ID | 20096 |
Feature activation | -5.97e-02 |
Pos logit contributions | |
orry | +0.015 |
run | +0.015 |
oke | +0.015 |
ence | +0.014 |
aint | +0.014 |
Neg logit contributions | |
rob | -0.018 |
Woo | -0.016 |
amb | -0.013 |
Pink | -0.013 |
bur | -0.012 |
Token | named |
Token ID | 3706 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
rob | +0.002 |
Woo | +0.002 |
Pink | +0.001 |
amb | +0.001 |
Sim | +0.001 |
Neg logit contributions | |
orry | -0.002 |
ence | -0.002 |
aint | -0.002 |
isel | -0.002 |
oke | -0.002 |
Token | D |
Token ID | 360 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
rob | +0.024 |
amb | +0.018 |
thank | +0.017 |
hat | +0.016 |
Woo | +0.016 |
Neg logit contributions | |
run | -0.014 |
orry | -0.013 |
oke | -0.013 |
Sam | -0.013 |
eight | -0.013 |
Token | olly |
Token ID | 5098 |
Feature activation | +5.81e-01 |
Pos logit contributions | |
rob | +0.083 |
Woo | +0.065 |
Lib | +0.054 |
amb | +0.054 |
thank | +0.054 |
Neg logit contributions | |
run | -0.063 |
oke | -0.063 |
orry | -0.063 |
aint | -0.058 |
ence | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | -4.13e-01 |
Pos logit contributions | |
orry | +0.023 |
isel | +0.022 |
ence | +0.022 |
hour | +0.021 |
oke | +0.021 |
Neg logit contributions | |
rob | -0.015 |
Woo | -0.015 |
Pink | -0.013 |
Gloria | -0.011 |
Cindy | -0.011 |
Token | D |
Token ID | 360 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
rob | +0.017 |
Woo | +0.014 |
amb | +0.012 |
bur | +0.012 |
thank | +0.011 |
Neg logit contributions | |
run | -0.012 |
orry | -0.012 |
oke | -0.012 |
ence | -0.012 |
aint | -0.011 |
Token | olly |
Token ID | 5098 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
rob | +0.130 |
Woo | +0.107 |
bur | +0.091 |
Lib | +0.091 |
amb | +0.091 |
Neg logit contributions | |
orry | -0.083 |
oke | -0.083 |
run | -0.082 |
aint | -0.074 |
ence | -0.072 |
Token | saw |
Token ID | 2497 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
orry | +0.005 |
run | +0.005 |
oke | +0.005 |
ence | +0.005 |
aint | +0.005 |
Neg logit contributions | |
rob | -0.006 |
Woo | -0.005 |
amb | -0.004 |
Pink | -0.004 |
bur | -0.004 |
Token | that |
Token ID | 326 |
Feature activation | -6.87e-02 |
Pos logit contributions | |
rob | +0.012 |
amb | +0.010 |
thank | +0.010 |
bur | +0.009 |
burn | +0.009 |
Neg logit contributions | |
run | -0.006 |
orry | -0.006 |
oke | -0.006 |
� | -0.006 |
gust | -0.005 |
Token | Benny |
Token ID | 44275 |
Feature activation | -3.62e-02 |
Pos logit contributions | |
rob | +0.003 |
amb | +0.002 |
ippy | +0.002 |
lor | +0.002 |
bur | +0.002 |
Neg logit contributions | |
run | -0.002 |
� | -0.002 |
gust | -0.002 |
oke | -0.002 |
Sam | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
rob | +0.001 |
Woo | +0.001 |
Pink | +0.001 |
amb | +0.001 |
bur | +0.001 |
Neg logit contributions | |
orry | -0.001 |
oke | -0.001 |
run | -0.001 |
ence | -0.001 |
aint | -0.001 |
Token | good |
Token ID | 922 |
Feature activation | -4.63e-01 |
Pos logit contributions | |
rob | +0.020 |
Woo | +0.016 |
amb | +0.016 |
bur | +0.014 |
oto | +0.014 |
Neg logit contributions | |
run | -0.007 |
orry | -0.007 |
ence | -0.007 |
oke | -0.007 |
eight | -0.006 |
Token | at |
Token ID | 379 |
Feature activation | +9.14e-01 |
Pos logit contributions | |
rob | +0.024 |
Woo | +0.021 |
bur | +0.018 |
amb | +0.018 |
Pink | +0.018 |
Neg logit contributions | |
orry | -0.009 |
run | -0.009 |
oke | -0.009 |
ence | -0.008 |
aint | -0.008 |
Token | fixing |
Token ID | 18682 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
orry | +0.027 |
oke | +0.027 |
run | +0.026 |
ence | +0.026 |
aint | +0.025 |
Neg logit contributions | |
rob | -0.037 |
Woo | -0.033 |
amb | -0.027 |
Pink | -0.027 |
bur | -0.026 |
Token | things |
Token ID | 1243 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
run | +0.005 |
orry | +0.005 |
triangle | +0.005 |
tug | +0.005 |
fists | +0.005 |
Neg logit contributions | |
rob | -0.009 |
Woo | -0.008 |
amb | -0.007 |
burn | -0.007 |
thank | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
rob | +0.005 |
Woo | +0.004 |
amb | +0.004 |
bur | +0.004 |
burn | +0.003 |
Neg logit contributions | |
run | -0.003 |
oke | -0.003 |
orry | -0.003 |
ence | -0.003 |
aint | -0.003 |
Token | D |
Token ID | 360 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
oke | +0.005 |
run | +0.005 |
orry | +0.005 |
aint | +0.004 |
ence | +0.004 |
Neg logit contributions | |
rob | -0.011 |
Woo | -0.008 |
bur | -0.008 |
burn | -0.008 |
oto | -0.007 |
Token | olly |
Token ID | 5098 |
Feature activation | -7.74e-03 |
Pos logit contributions | |
rob | +0.148 |
Woo | +0.126 |
bur | +0.110 |
amb | +0.109 |
Sim | +0.106 |
Neg logit contributions | |
orry | -0.066 |
oke | -0.065 |
run | -0.063 |
ence | -0.058 |
aint | -0.057 |
Token | told |
Token ID | 1297 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
rob | +0.000 |
Woo | +0.000 |
amb | +0.000 |
bur | +0.000 |
burn | +0.000 |
Neg logit contributions | |
orry | -0.000 |
oke | -0.000 |
run | -0.000 |
ence | -0.000 |
aint | -0.000 |
Token | Crab |
Token ID | 32379 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
rob | +0.020 |
burn | +0.014 |
robe | +0.013 |
amb | +0.013 |
therapist | +0.013 |
Neg logit contributions | |
orry | -0.010 |
gust | -0.010 |
� | -0.010 |
oke | -0.010 |
eight | -0.010 |
Token | by |
Token ID | 1525 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
rob | +0.020 |
Woo | +0.018 |
amb | +0.015 |
Pink | +0.014 |
bur | +0.014 |
Neg logit contributions | |
orry | -0.016 |
run | -0.016 |
ence | -0.016 |
oke | -0.016 |
aint | -0.015 |
Token | about |
Token ID | 546 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
rob | +0.023 |
Woo | +0.023 |
Pink | +0.020 |
Rudolph | +0.017 |
Gloria | +0.017 |
Neg logit contributions | |
isel | -0.036 |
orry | -0.036 |
ence | -0.035 |
oke | -0.035 |
gust | -0.035 |
Token | river |
Token ID | 7850 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
rob | +0.000 |
Woo | +0.000 |
Pink | +0.000 |
bur | +0.000 |
amb | +0.000 |
Neg logit contributions | |
orry | -0.000 |
run | -0.000 |
oke | -0.000 |
ence | -0.000 |
aint | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -3.45e-01 |
Pos logit contributions | |
orry | +0.016 |
oke | +0.015 |
ence | +0.015 |
aint | +0.015 |
run | +0.015 |
Neg logit contributions | |
rob | -0.013 |
Woo | -0.011 |
thank | -0.009 |
amb | -0.009 |
Pink | -0.009 |
Token | |
Token ID | 220 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
rob | +0.014 |
Woo | +0.012 |
amb | +0.010 |
bur | +0.009 |
Pink | +0.009 |
Neg logit contributions | |
orry | -0.011 |
run | -0.010 |
oke | -0.010 |
ence | -0.010 |
aint | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
run | +0.025 |
orry | +0.024 |
oke | +0.024 |
ence | +0.023 |
aint | +0.023 |
Neg logit contributions | |
rob | -0.029 |
Woo | -0.024 |
amb | -0.020 |
bur | -0.019 |
Pink | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
rob | +0.028 |
Woo | +0.024 |
amb | +0.020 |
bur | +0.020 |
thank | +0.019 |
Neg logit contributions | |
orry | -0.021 |
oke | -0.021 |
run | -0.020 |
aint | -0.019 |
ence | -0.019 |
Token | T |
Token ID | 51 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
rob | +0.015 |
Woo | +0.012 |
amb | +0.010 |
bur | +0.009 |
Pink | +0.009 |
Neg logit contributions | |
orry | -0.016 |
run | -0.016 |
oke | -0.016 |
ence | -0.016 |
aint | -0.015 |
Token | oby |
Token ID | 26730 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
rob | +0.123 |
Woo | +0.105 |
Lib | +0.093 |
Pink | +0.091 |
Cindy | +0.088 |
Neg logit contributions | |
oke | -0.093 |
orry | -0.085 |
run | -0.082 |
ever | -0.082 |
triangle | -0.074 |
Token | and |
Token ID | 290 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
rob | +0.008 |
Woo | +0.007 |
amb | +0.005 |
bur | +0.005 |
Pink | +0.005 |
Neg logit contributions | |
orry | -0.006 |
oke | -0.006 |
run | -0.006 |
ence | -0.006 |
aint | -0.006 |
Token | the |
Token ID | 262 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
orry | +0.017 |
oke | +0.017 |
ence | +0.017 |
run | +0.016 |
aint | +0.016 |
Neg logit contributions | |
rob | -0.017 |
Woo | -0.015 |
Pink | -0.012 |
amb | -0.012 |
Sebastian | -0.012 |
Token | duck |
Token ID | 22045 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
rob | +0.020 |
Woo | +0.016 |
amb | +0.015 |
bur | +0.014 |
thank | +0.013 |
Neg logit contributions | |
orry | -0.012 |
oke | -0.012 |
run | -0.012 |
tower | -0.011 |
triangle | -0.011 |
Token | soon |
Token ID | 2582 |
Feature activation | +8.27e-03 |
Pos logit contributions | |
orry | +0.007 |
oke | +0.007 |
run | +0.007 |
ence | +0.007 |
aint | +0.006 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.007 |
amb | -0.006 |
bur | -0.005 |
Pink | -0.005 |
Token | by |
Token ID | 416 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
orry | +0.001 |
run | +0.001 |
ence | +0.001 |
oke | +0.000 |
aint | +0.000 |
Neg logit contributions | |
rob | -0.001 |
Woo | -0.000 |
bur | -0.000 |
amb | -0.000 |
thank | -0.000 |
Token | himself |
Token ID | 2241 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
orry | +0.005 |
run | +0.005 |
oke | +0.004 |
ence | +0.004 |
aint | +0.004 |
Neg logit contributions | |
rob | -0.003 |
Woo | -0.003 |
amb | -0.002 |
bur | -0.002 |
Pink | -0.002 |
Token | ." |
Token ID | 526 |
Feature activation | -7.19e-01 |
Pos logit contributions | |
rob | +0.015 |
Woo | +0.012 |
amb | +0.010 |
Pink | +0.009 |
bur | +0.009 |
Neg logit contributions | |
orry | -0.018 |
run | -0.017 |
oke | -0.017 |
ence | -0.017 |
aint | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
rob | +0.028 |
Woo | +0.024 |
amb | +0.020 |
Pink | +0.019 |
bur | +0.019 |
Neg logit contributions | |
orry | -0.023 |
oke | -0.022 |
run | -0.022 |
ence | -0.022 |
aint | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | -2.63e-01 |
Pos logit contributions | |
rob | +0.014 |
Woo | +0.012 |
amb | +0.010 |
Pink | +0.009 |
bur | +0.009 |
Neg logit contributions | |
orry | -0.015 |
ence | -0.015 |
run | -0.015 |
oke | -0.015 |
aint | -0.014 |
Token | T |
Token ID | 51 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
rob | +0.008 |
Woo | +0.006 |
amb | +0.005 |
Pink | +0.004 |
bur | +0.004 |
Neg logit contributions | |
orry | -0.011 |
oke | -0.011 |
run | -0.011 |
ence | -0.011 |
aint | -0.010 |
Token | ami |
Token ID | 6277 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
rob | +0.123 |
Woo | +0.106 |
amb | +0.090 |
Pink | +0.086 |
bur | +0.086 |
Neg logit contributions | |
orry | -0.086 |
run | -0.085 |
oke | -0.084 |
ence | -0.082 |
aint | -0.079 |
Token | smiled |
Token ID | 13541 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
run | +0.004 |
orry | +0.004 |
oke | +0.004 |
ence | +0.004 |
aint | +0.004 |
Neg logit contributions | |
rob | -0.004 |
Woo | -0.003 |
amb | -0.003 |
Pink | -0.003 |
bur | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
rob | +0.018 |
Woo | +0.014 |
bur | +0.012 |
igi | +0.011 |
amb | +0.011 |
Neg logit contributions | |
run | -0.012 |
orry | -0.012 |
ence | -0.012 |
oke | -0.012 |
aint | -0.012 |
Token | said |
Token ID | 531 |
Feature activation | -1.66e-01 |
Pos logit contributions | |
rob | +0.006 |
Woo | +0.005 |
bur | +0.004 |
amb | +0.004 |
ippy | +0.004 |
Neg logit contributions | |
orry | -0.005 |
run | -0.005 |
oke | -0.004 |
tug | -0.004 |
ence | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -2.12e-01 |
Pos logit contributions | |
rob | +0.005 |
Woo | +0.004 |
Pink | +0.003 |
amb | +0.003 |
Lib | +0.003 |
Neg logit contributions | |
orry | -0.007 |
ence | -0.006 |
oke | -0.006 |
run | -0.006 |
aint | -0.006 |
Token | thin |
Token ID | 7888 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
rob | +0.015 |
Woo | +0.013 |
amb | +0.011 |
Pink | +0.011 |
bur | +0.011 |
Neg logit contributions | |
orry | -0.013 |
oke | -0.013 |
run | -0.013 |
ence | -0.012 |
aint | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
rob | +0.026 |
Woo | +0.021 |
amb | +0.018 |
Pink | +0.017 |
bur | +0.016 |
Neg logit contributions | |
orry | -0.026 |
oke | -0.026 |
run | -0.025 |
ence | -0.025 |
aint | -0.024 |
Token | |
Token ID | 220 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
rob | +0.016 |
Woo | +0.014 |
amb | +0.011 |
Pink | +0.011 |
bur | +0.011 |
Neg logit contributions | |
orry | -0.014 |
oke | -0.013 |
run | -0.013 |
ence | -0.013 |
aint | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
orry | +0.023 |
oke | +0.022 |
run | +0.022 |
ence | +0.022 |
aint | +0.021 |
Neg logit contributions | |
rob | -0.023 |
Woo | -0.019 |
amb | -0.016 |
Pink | -0.015 |
bur | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -6.28e-01 |
Pos logit contributions | |
rob | +0.033 |
Woo | +0.028 |
amb | +0.024 |
bur | +0.023 |
Pink | +0.023 |
Neg logit contributions | |
orry | -0.025 |
run | -0.024 |
oke | -0.024 |
aint | -0.023 |
ence | -0.023 |
Token | T |
Token ID | 51 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
rob | +0.022 |
Woo | +0.018 |
amb | +0.015 |
bur | +0.014 |
Pink | +0.014 |
Neg logit contributions | |
orry | -0.022 |
run | -0.022 |
oke | -0.022 |
ence | -0.021 |
aint | -0.021 |
Token | oby |
Token ID | 26730 |
Feature activation | -3.11e-01 |
Pos logit contributions | |
rob | +0.129 |
Woo | +0.114 |
Pink | +0.102 |
Lib | +0.101 |
Cindy | +0.094 |
Neg logit contributions | |
oke | -0.084 |
orry | -0.084 |
run | -0.079 |
ever | -0.077 |
ence | -0.072 |
Token | was |
Token ID | 373 |
Feature activation | -3.33e-01 |
Pos logit contributions | |
rob | +0.012 |
Woo | +0.010 |
amb | +0.009 |
bur | +0.008 |
Pink | +0.008 |
Neg logit contributions | |
orry | -0.010 |
run | -0.010 |
oke | -0.009 |
ence | -0.009 |
aint | -0.009 |
Token | very |
Token ID | 845 |
Feature activation | -1.80e-01 |
Pos logit contributions | |
rob | +0.012 |
Woo | +0.011 |
amb | +0.009 |
Pink | +0.008 |
bur | +0.008 |
Neg logit contributions | |
orry | -0.011 |
oke | -0.011 |
run | -0.011 |
ence | -0.010 |
aint | -0.010 |
Token | curious |
Token ID | 11040 |
Feature activation | -7.89e-02 |
Pos logit contributions | |
rob | +0.008 |
Woo | +0.007 |
amb | +0.006 |
Pink | +0.006 |
thank | +0.006 |
Neg logit contributions | |
orry | -0.005 |
oke | -0.005 |
run | -0.005 |
ence | -0.004 |
aint | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +1.64e-01 |
Pos logit contributions | |
rob | +0.002 |
Woo | +0.001 |
amb | +0.001 |
Pink | +0.001 |
Gloria | +0.001 |
Neg logit contributions | |
orry | -0.004 |
oke | -0.003 |
ence | -0.003 |
isel | -0.003 |
run | -0.003 |
Token | â |
Token ID | 22940 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
orry | +0.006 |
run | +0.005 |
oke | +0.005 |
ence | +0.005 |
aint | +0.005 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.007 |
amb | -0.006 |
bur | -0.006 |
Pink | -0.006 |
Token | € |
Token ID | 26391 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
rob | +0.055 |
Woo | +0.047 |
amb | +0.040 |
bur | +0.038 |
Pink | +0.038 |
Neg logit contributions | |
orry | -0.041 |
run | -0.041 |
oke | -0.040 |
ence | -0.039 |
aint | -0.038 |
Token | |
Token ID | 220 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
rob | +0.041 |
Woo | +0.036 |
amb | +0.030 |
bur | +0.028 |
Pink | +0.028 |
Neg logit contributions | |
orry | -0.032 |
run | -0.031 |
oke | -0.031 |
ence | -0.030 |
aint | -0.029 |
Token |
|
Token ID | 198 |
Feature activation | -2.34e-01 |
Pos logit contributions | |
orry | +0.026 |
run | +0.026 |
oke | +0.026 |
ence | +0.025 |
aint | +0.024 |
Neg logit contributions | |
rob | -0.030 |
Woo | -0.025 |
amb | -0.021 |
bur | -0.020 |
Pink | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -2.57e-01 |
Pos logit contributions | |
rob | +0.010 |
Woo | +0.008 |
amb | +0.007 |
bur | +0.007 |
thank | +0.007 |
Neg logit contributions | |
run | -0.007 |
oke | -0.007 |
orry | -0.006 |
aint | -0.006 |
ence | -0.006 |
Token | T |
Token ID | 51 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
rob | +0.010 |
Woo | +0.009 |
amb | +0.007 |
bur | +0.007 |
Pink | +0.007 |
Neg logit contributions | |
orry | -0.008 |
run | -0.008 |
oke | -0.008 |
ence | -0.007 |
aint | -0.007 |
Token | oby |
Token ID | 26730 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
rob | +0.126 |
Woo | +0.108 |
Pink | +0.093 |
Lib | +0.092 |
bur | +0.085 |
Neg logit contributions | |
oke | -0.086 |
orry | -0.084 |
run | -0.078 |
ever | -0.076 |
ence | -0.075 |
Token | and |
Token ID | 290 |
Feature activation | -9.20e-02 |
Pos logit contributions | |
rob | +0.010 |
Woo | +0.008 |
amb | +0.007 |
thank | +0.006 |
Pink | +0.006 |
Neg logit contributions | |
orry | -0.010 |
run | -0.010 |
oke | -0.010 |
ence | -0.009 |
isel | -0.009 |
Token | M |
Token ID | 337 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
rob | +0.004 |
Woo | +0.003 |
amb | +0.003 |
Pink | +0.002 |
bur | +0.002 |
Neg logit contributions | |
orry | -0.003 |
oke | -0.003 |
run | -0.003 |
ence | -0.003 |
aint | -0.003 |
Token | illy |
Token ID | 6548 |
Feature activation | +2.23e-01 |
Pos logit contributions | |
rob | +0.055 |
Woo | +0.045 |
amb | +0.035 |
Pink | +0.033 |
bur | +0.033 |
Neg logit contributions | |
orry | -0.069 |
oke | -0.067 |
run | -0.067 |
ence | -0.066 |
aint | -0.064 |
Token | divided |
Token ID | 9086 |
Feature activation | -4.39e-01 |
Pos logit contributions | |
run | +0.007 |
orry | +0.007 |
oke | +0.007 |
ence | +0.007 |
aint | +0.007 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.007 |
amb | -0.006 |
thank | -0.005 |
bur | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +1.00e+00 |
Pos logit contributions | |
run | +0.004 |
oke | +0.004 |
orry | +0.004 |
ence | +0.004 |
tower | +0.004 |
Neg logit contributions | |
rob | -0.006 |
Woo | -0.005 |
bur | -0.004 |
Pink | -0.004 |
igi | -0.004 |
Token | raised |
Token ID | 4376 |
Feature activation | +5.33e-01 |
Pos logit contributions | |
orry | +0.041 |
oke | +0.040 |
aint | +0.039 |
run | +0.038 |
ence | +0.038 |
Neg logit contributions | |
rob | -0.029 |
Woo | -0.025 |
amb | -0.018 |
Pink | -0.018 |
thank | -0.017 |
Token | his |
Token ID | 465 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
oke | +0.024 |
orry | +0.023 |
ence | +0.022 |
aint | +0.021 |
run | +0.021 |
Neg logit contributions | |
rob | -0.013 |
Woo | -0.012 |
amb | -0.008 |
Pink | -0.008 |
Sebastian | -0.008 |
Token | arm |
Token ID | 3211 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
oke | +0.006 |
orry | +0.005 |
ence | +0.005 |
run | +0.005 |
icker | +0.005 |
Neg logit contributions | |
rob | -0.006 |
Woo | -0.005 |
Pink | -0.005 |
bur | -0.004 |
brid | -0.004 |
Token | and |
Token ID | 290 |
Feature activation | +3.15e-01 |
Pos logit contributions | |
rob | +0.038 |
Woo | +0.031 |
amb | +0.026 |
Pink | +0.023 |
bur | +0.022 |
Neg logit contributions | |
orry | -0.045 |
oke | -0.045 |
ence | -0.043 |
run | -0.043 |
aint | -0.042 |
Token | SH |
Token ID | 6006 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
orry | +0.010 |
oke | +0.010 |
run | +0.010 |
ence | +0.010 |
aint | +0.010 |
Neg logit contributions | |
rob | -0.012 |
Woo | -0.010 |
amb | -0.008 |
Pink | -0.008 |
bur | -0.008 |
Token | OT |
Token ID | 2394 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
orry | +0.087 |
oke | +0.086 |
run | +0.086 |
ence | +0.083 |
aint | +0.080 |
Neg logit contributions | |
rob | -0.103 |
Woo | -0.088 |
amb | -0.073 |
bur | -0.070 |
Pink | -0.069 |
Token | ! |
Token ID | 0 |
Feature activation | +6.56e-01 |
Pos logit contributions | |
orry | +0.035 |
oke | +0.035 |
run | +0.034 |
ence | +0.034 |
isel | +0.033 |
Neg logit contributions | |
rob | -0.030 |
Woo | -0.027 |
amb | -0.021 |
Pink | -0.020 |
bur | -0.020 |
Token | |
Token ID | 220 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
orry | +0.019 |
oke | +0.019 |
ence | +0.018 |
run | +0.018 |
aint | +0.017 |
Neg logit contributions | |
rob | -0.026 |
Woo | -0.024 |
amb | -0.020 |
Pink | -0.020 |
Sim | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
orry | +0.045 |
ence | +0.044 |
oke | +0.044 |
run | +0.044 |
aint | +0.042 |
Neg logit contributions | |
rob | -0.040 |
Woo | -0.034 |
amb | -0.027 |
Pink | -0.025 |
bur | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | +3.96e-01 |
Pos logit contributions | |
orry | +0.004 |
run | +0.004 |
oke | +0.004 |
ence | +0.003 |
aint | +0.003 |
Neg logit contributions | |
rob | -0.004 |
Woo | -0.004 |
amb | -0.003 |
bur | -0.003 |
Pink | -0.003 |
Token | any |
Token ID | 597 |
Feature activation | -7.52e-01 |
Pos logit contributions | |
oke | +0.014 |
orry | +0.014 |
run | +0.013 |
ence | +0.013 |
aint | +0.013 |
Neg logit contributions | |
rob | -0.016 |
Woo | -0.014 |
Pink | -0.011 |
bur | -0.011 |
amb | -0.011 |
Token | bad |
Token ID | 2089 |
Feature activation | -7.32e-01 |
Pos logit contributions | |
rob | +0.027 |
Woo | +0.024 |
Pink | +0.019 |
bur | +0.018 |
thank | +0.018 |
Neg logit contributions | |
oke | -0.025 |
orry | -0.025 |
ence | -0.024 |
run | -0.024 |
aint | -0.023 |
Token | dreams |
Token ID | 10625 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
rob | +0.028 |
Woo | +0.024 |
Pink | +0.019 |
amb | +0.019 |
bur | +0.018 |
Neg logit contributions | |
run | -0.024 |
orry | -0.024 |
oke | -0.024 |
ence | -0.023 |
aint | -0.022 |
Token | or |
Token ID | 393 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
orry | +0.032 |
run | +0.031 |
oke | +0.031 |
ence | +0.030 |
aint | +0.029 |
Neg logit contributions | |
rob | -0.044 |
Woo | -0.037 |
amb | -0.032 |
bur | -0.030 |
Pink | -0.030 |
Token | scary |
Token ID | 14343 |
Feature activation | -6.23e-01 |
Pos logit contributions | |
rob | +0.019 |
Woo | +0.018 |
Pink | +0.015 |
bur | +0.014 |
thank | +0.014 |
Neg logit contributions | |
orry | -0.017 |
oke | -0.017 |
ence | -0.016 |
run | -0.016 |
aint | -0.016 |
Token | gor |
Token ID | 30344 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
rob | +0.023 |
Woo | +0.020 |
Pink | +0.016 |
amb | +0.016 |
thank | +0.015 |
Neg logit contributions | |
orry | -0.021 |
oke | -0.020 |
ence | -0.020 |
run | -0.020 |
aint | -0.019 |
Token | illas |
Token ID | 25314 |
Feature activation | +8.86e-01 |
Pos logit contributions | |
run | +0.067 |
orry | +0.066 |
aint | +0.066 |
isel | +0.062 |
ence | +0.062 |
Neg logit contributions | |
rob | -0.089 |
Woo | -0.068 |
bur | -0.067 |
amb | -0.061 |
ba | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | -1.35e-01 |
Pos logit contributions | |
orry | +0.030 |
ence | +0.029 |
oke | +0.029 |
run | +0.029 |
isel | +0.028 |
Neg logit contributions | |
rob | -0.031 |
Woo | -0.027 |
Pink | -0.022 |
bur | -0.021 |
amb | -0.021 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
rob | +0.005 |
Woo | +0.004 |
amb | +0.003 |
Pink | +0.003 |
bur | +0.003 |
Neg logit contributions | |
orry | -0.005 |
ence | -0.005 |
oke | -0.005 |
run | -0.005 |
aint | -0.004 |
Token | Once |
Token ID | 7454 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
rob | +0.010 |
Woo | +0.009 |
amb | +0.008 |
bur | +0.007 |
burn | +0.007 |
Neg logit contributions | |
oke | -0.007 |
run | -0.007 |
orry | -0.007 |
aint | -0.006 |
ence | -0.006 |
Token | upon |
Token ID | 2402 |
Feature activation | -6.06e-01 |
Pos logit contributions | |
rob | +0.032 |
Woo | +0.029 |
amb | +0.024 |
bur | +0.024 |
Pink | +0.024 |
Neg logit contributions | |
ence | -0.025 |
orry | -0.024 |
aint | -0.024 |
run | -0.023 |
ever | -0.023 |
Token | tall |
Token ID | 7331 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
rob | +0.021 |
Woo | +0.018 |
amb | +0.015 |
Pink | +0.015 |
bur | +0.014 |
Neg logit contributions | |
orry | -0.015 |
run | -0.015 |
oke | -0.015 |
ence | -0.014 |
aint | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +8.36e-01 |
Pos logit contributions | |
orry | +0.024 |
oke | +0.024 |
run | +0.024 |
ence | +0.023 |
aint | +0.022 |
Neg logit contributions | |
rob | -0.030 |
Woo | -0.026 |
amb | -0.022 |
bur | -0.020 |
Pink | -0.020 |
Token | bright |
Token ID | 6016 |
Feature activation | +5.31e-01 |
Pos logit contributions | |
oke | +0.028 |
orry | +0.028 |
run | +0.027 |
aint | +0.026 |
ence | +0.026 |
Neg logit contributions | |
rob | -0.030 |
Woo | -0.026 |
Pink | -0.022 |
bur | -0.021 |
Sim | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
orry | +0.019 |
oke | +0.018 |
run | +0.018 |
ence | +0.018 |
aint | +0.017 |
Neg logit contributions | |
rob | -0.019 |
Woo | -0.016 |
amb | -0.014 |
Pink | -0.013 |
thank | -0.012 |
Token | it |
Token ID | 340 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
orry | +0.018 |
oke | +0.018 |
run | +0.018 |
ence | +0.018 |
aint | +0.017 |
Neg logit contributions | |
rob | -0.023 |
Woo | -0.020 |
Pink | -0.016 |
amb | -0.016 |
bur | -0.015 |
Token | lit |
Token ID | 6578 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
run | +0.001 |
oke | +0.001 |
orry | +0.001 |
ence | +0.001 |
aint | +0.001 |
Neg logit contributions | |
rob | -0.001 |
Woo | -0.001 |
amb | -0.001 |
Pink | -0.001 |
bur | -0.001 |
Token | up |
Token ID | 510 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
orry | +0.091 |
ence | +0.089 |
run | +0.088 |
oke | +0.087 |
aint | +0.086 |
Neg logit contributions | |
rob | -0.086 |
Woo | -0.071 |
amb | -0.058 |
bur | -0.054 |
Pink | -0.053 |
Token | the |
Token ID | 262 |
Feature activation | +3.44e-01 |
Pos logit contributions | |
oke | +0.031 |
run | +0.029 |
orry | +0.029 |
isel | +0.028 |
aint | +0.028 |
Neg logit contributions | |
rob | -0.020 |
Woo | -0.019 |
Pink | -0.015 |
amb | -0.014 |
thank | -0.014 |
Token | sky |
Token ID | 6766 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
run | +0.016 |
oke | +0.014 |
orry | +0.013 |
aint | +0.013 |
ence | +0.013 |
Neg logit contributions | |
rob | -0.010 |
Woo | -0.007 |
North | -0.007 |
bur | -0.006 |
Sim | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +5.93e-01 |
Pos logit contributions | |
orry | +0.037 |
run | +0.037 |
oke | +0.037 |
isel | +0.035 |
ence | +0.034 |
Neg logit contributions | |
rob | -0.028 |
Woo | -0.023 |
amb | -0.019 |
Pink | -0.019 |
thank | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
orry | +0.016 |
oke | +0.016 |
run | +0.016 |
ence | +0.015 |
aint | +0.014 |
Neg logit contributions | |
rob | -0.025 |
Woo | -0.023 |
Pink | -0.019 |
amb | -0.019 |
Rudolph | -0.018 |
Token | wished |
Token ID | 16555 |
Feature activation | -4.49e-01 |
Pos logit contributions | |
orry | +0.007 |
ence | +0.007 |
aint | +0.007 |
run | +0.007 |
ever | +0.007 |
Neg logit contributions | |
rob | -0.009 |
Woo | -0.009 |
Pink | -0.007 |
Cindy | -0.007 |
Sim | -0.007 |
Token | they |
Token ID | 484 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
rob | +0.013 |
Woo | +0.012 |
Pink | +0.009 |
Sim | +0.008 |
herself | +0.008 |
Neg logit contributions | |
aint | -0.017 |
orry | -0.017 |
ence | -0.017 |
isel | -0.017 |
oke | -0.016 |
Token | had |
Token ID | 550 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
rob | +0.026 |
Woo | +0.024 |
Pink | +0.019 |
bur | +0.019 |
amb | +0.019 |
Neg logit contributions | |
oke | -0.019 |
orry | -0.019 |
ence | -0.018 |
run | -0.018 |
aint | -0.018 |
Token | never |
Token ID | 1239 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
oke | +0.018 |
orry | +0.018 |
run | +0.017 |
ence | +0.017 |
aint | +0.016 |
Neg logit contributions | |
rob | -0.017 |
Woo | -0.015 |
bur | -0.012 |
Pink | -0.012 |
thank | -0.012 |
Token | qu |
Token ID | 627 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
orry | +0.001 |
oke | +0.001 |
run | +0.001 |
ence | +0.001 |
aint | +0.001 |
Neg logit contributions | |
rob | -0.001 |
Woo | -0.001 |
amb | -0.001 |
bur | -0.001 |
Pink | -0.001 |
Token | arre |
Token ID | 9624 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
oke | +0.081 |
ence | +0.080 |
figuring | +0.079 |
drill | +0.079 |
tower | +0.077 |
Neg logit contributions | |
rob | -0.100 |
Woo | -0.089 |
amb | -0.080 |
burn | -0.076 |
ippy | -0.076 |
Token | led |
Token ID | 992 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
orry | +0.120 |
ence | +0.118 |
run | +0.117 |
oke | +0.116 |
aint | +0.115 |
Neg logit contributions | |
rob | -0.088 |
Woo | -0.066 |
amb | -0.053 |
thank | -0.052 |
bur | -0.049 |
Token | . |
Token ID | 13 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
orry | +0.052 |
oke | +0.050 |
ence | +0.049 |
aint | +0.048 |
run | +0.048 |
Neg logit contributions | |
rob | -0.051 |
Woo | -0.047 |
Pink | -0.038 |
amb | -0.037 |
bur | -0.036 |
Token | They |
Token ID | 1119 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
run | +0.018 |
oke | +0.018 |
orry | +0.018 |
ence | +0.017 |
isel | +0.017 |
Neg logit contributions | |
rob | -0.020 |
Woo | -0.019 |
Pink | -0.016 |
amb | -0.016 |
Sim | -0.015 |
Token | missed |
Token ID | 6825 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
rob | +0.005 |
Woo | +0.005 |
amb | +0.004 |
Pink | +0.004 |
bur | +0.004 |
Neg logit contributions | |
run | -0.005 |
oke | -0.005 |
orry | -0.005 |
ence | -0.005 |
aint | -0.005 |
Token | their |
Token ID | 511 |
Feature activation | +3.72e-01 |
Pos logit contributions | |
oke | +0.004 |
run | +0.004 |
orry | +0.004 |
ence | +0.004 |
aint | +0.004 |
Neg logit contributions | |
rob | -0.003 |
Woo | -0.003 |
Pink | -0.002 |
Sebastian | -0.002 |
Rudolph | -0.002 |
Token | w |
Token ID | 86 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
rob | +0.049 |
Woo | +0.041 |
amb | +0.033 |
Pink | +0.032 |
bur | +0.031 |
Neg logit contributions | |
orry | -0.054 |
oke | -0.053 |
run | -0.052 |
ence | -0.051 |
aint | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -6.15e-02 |
Pos logit contributions | |
rob | +0.019 |
Woo | +0.016 |
amb | +0.013 |
bur | +0.012 |
Pink | +0.012 |
Neg logit contributions | |
orry | -0.019 |
run | -0.018 |
oke | -0.018 |
ence | -0.018 |
aint | -0.017 |
Token | ow |
Token ID | 12334 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
rob | +0.002 |
Woo | +0.002 |
Pink | +0.002 |
bur | +0.001 |
Sebastian | +0.001 |
Neg logit contributions | |
ence | -0.002 |
run | -0.002 |
orry | -0.002 |
aint | -0.002 |
oke | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +6.65e-01 |
Pos logit contributions | |
rob | +0.021 |
Woo | +0.016 |
amb | +0.013 |
bur | +0.012 |
Pink | +0.012 |
Neg logit contributions | |
ence | -0.027 |
run | -0.027 |
orry | -0.027 |
aint | -0.026 |
oke | -0.025 |
Token | ow |
Token ID | 12334 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
ence | +0.024 |
run | +0.024 |
aint | +0.023 |
orry | +0.023 |
oke | +0.023 |
Neg logit contributions | |
rob | -0.021 |
Woo | -0.020 |
Pink | -0.016 |
bur | -0.014 |
Dod | -0.014 |
Token | ! |
Token ID | 0 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
rob | +0.011 |
Woo | +0.009 |
amb | +0.007 |
bur | +0.006 |
Pink | +0.006 |
Neg logit contributions | |
ence | -0.017 |
run | -0.017 |
orry | -0.017 |
aint | -0.017 |
oke | -0.016 |
Token | That |
Token ID | 1320 |
Feature activation | +5.50e-01 |
Pos logit contributions | |
ence | +0.073 |
orry | +0.067 |
pieces | +0.064 |
hour | +0.064 |
attempts | +0.063 |
Neg logit contributions | |
Woo | -0.079 |
rob | -0.069 |
Pink | -0.065 |
amb | -0.060 |
Snow | -0.058 |
Token | goose |
Token ID | 37246 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
orry | +0.015 |
run | +0.015 |
oke | +0.015 |
ence | +0.015 |
aint | +0.014 |
Neg logit contributions | |
rob | -0.023 |
Woo | -0.020 |
amb | -0.017 |
bur | -0.016 |
Pink | -0.016 |
Token | is |
Token ID | 318 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
ence | +0.065 |
run | +0.062 |
orry | +0.061 |
aint | +0.061 |
2 | +0.059 |
Neg logit contributions | |
rob | -0.054 |
Woo | -0.045 |
bur | -0.035 |
Pink | -0.034 |
amb | -0.033 |
Token | mean |
Token ID | 1612 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
ence | +0.022 |
run | +0.022 |
oke | +0.022 |
orry | +0.022 |
aint | +0.022 |
Neg logit contributions | |
rob | -0.026 |
Woo | -0.025 |
Pink | -0.021 |
bur | -0.020 |
Sebastian | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +1.68e-01 |
Pos logit contributions | |
rob | +0.007 |
Woo | +0.006 |
amb | +0.005 |
Pink | +0.005 |
bur | +0.005 |
Neg logit contributions | |
run | -0.007 |
orry | -0.007 |
oke | -0.007 |
ence | -0.006 |
aint | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
run | +0.023 |
oke | +0.023 |
orry | +0.023 |
ence | +0.022 |
aint | +0.021 |
Neg logit contributions | |
rob | -0.029 |
Woo | -0.025 |
amb | -0.021 |
Pink | -0.020 |
bur | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +4.68e-01 |
Pos logit contributions | |
rob | +0.009 |
Woo | +0.007 |
amb | +0.006 |
burn | +0.006 |
bur | +0.006 |
Neg logit contributions | |
oke | -0.006 |
run | -0.006 |
orry | -0.006 |
aint | -0.006 |
ence | -0.005 |
Token | The |
Token ID | 464 |
Feature activation | -4.18e-01 |
Pos logit contributions | |
orry | +0.015 |
run | +0.015 |
oke | +0.015 |
ence | +0.015 |
aint | +0.014 |
Neg logit contributions | |
rob | -0.018 |
Woo | -0.015 |
amb | -0.013 |
Pink | -0.012 |
thank | -0.012 |
Token | lawyer |
Token ID | 6853 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
rob | +0.015 |
Woo | +0.013 |
thank | +0.012 |
Lib | +0.011 |
Pink | +0.011 |
Neg logit contributions | |
run | -0.014 |
ence | -0.014 |
isel | -0.013 |
orry | -0.013 |
aint | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +1.45e-01 |
Pos logit contributions | |
run | +0.030 |
orry | +0.030 |
ence | +0.029 |
oke | +0.029 |
aint | +0.028 |
Neg logit contributions | |
rob | -0.027 |
Woo | -0.022 |
amb | -0.018 |
Pink | -0.017 |
bur | -0.017 |
Token | surprised |
Token ID | 6655 |
Feature activation | +6.29e-01 |
Pos logit contributions | |
orry | +0.004 |
oke | +0.004 |
run | +0.004 |
ence | +0.004 |
aint | +0.004 |
Neg logit contributions | |
rob | -0.006 |
Woo | -0.005 |
amb | -0.004 |
Pink | -0.004 |
bur | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | +3.69e-02 |
Pos logit contributions | |
orry | +0.024 |
ence | +0.023 |
oke | +0.022 |
isel | +0.022 |
aint | +0.022 |
Neg logit contributions | |
rob | -0.018 |
Woo | -0.017 |
amb | -0.015 |
oto | -0.014 |
Pink | -0.013 |
Token | She |
Token ID | 1375 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
orry | +0.002 |
isel | +0.001 |
ence | +0.001 |
oke | +0.001 |
run | +0.001 |
Neg logit contributions | |
rob | -0.001 |
Woo | -0.001 |
Pink | -0.001 |
Lib | -0.001 |
Cindy | -0.001 |
Token | asked |
Token ID | 1965 |
Feature activation | -4.14e-01 |
Pos logit contributions | |
rob | +0.024 |
Woo | +0.020 |
amb | +0.016 |
bur | +0.016 |
Pink | +0.015 |
Neg logit contributions | |
orry | -0.021 |
oke | -0.021 |
run | -0.020 |
ence | -0.020 |
aint | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +4.52e-01 |
Pos logit contributions | |
rob | +0.014 |
Woo | +0.012 |
Pink | +0.010 |
bur | +0.009 |
Sim | +0.009 |
Neg logit contributions | |
orry | -0.015 |
ence | -0.014 |
run | -0.014 |
oke | -0.014 |
aint | -0.014 |
Token | man |
Token ID | 582 |
Feature activation | +4.65e-01 |
Pos logit contributions | |
run | +0.017 |
isel | +0.016 |
ence | +0.016 |
orry | +0.016 |
aint | +0.015 |
Neg logit contributions | |
rob | -0.013 |
Woo | -0.011 |
thank | -0.011 |
waitress | -0.011 |
Lib | -0.011 |
Token | they |
Token ID | 484 |
Feature activation | -9.66e-01 |
Pos logit contributions | |
orry | +0.008 |
oke | +0.007 |
ence | +0.007 |
run | +0.007 |
aint | +0.007 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.007 |
amb | -0.006 |
Pink | -0.006 |
bur | -0.005 |
Token | were |
Token ID | 547 |
Feature activation | -3.66e-01 |
Pos logit contributions | |
rob | +0.043 |
Woo | +0.037 |
amb | +0.032 |
Pink | +0.031 |
bur | +0.031 |
Neg logit contributions | |
orry | -0.025 |
run | -0.024 |
oke | -0.024 |
ence | -0.024 |
aint | -0.023 |
Token | lucky |
Token ID | 9670 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
rob | +0.014 |
Woo | +0.013 |
Pink | +0.011 |
amb | +0.010 |
bur | +0.010 |
Neg logit contributions | |
orry | -0.011 |
oke | -0.011 |
run | -0.011 |
ence | -0.011 |
aint | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +1.38e-01 |
Pos logit contributions | |
orry | +0.006 |
ence | +0.006 |
isel | +0.006 |
oke | +0.006 |
run | +0.006 |
Neg logit contributions | |
rob | -0.006 |
Woo | -0.005 |
Pink | -0.004 |
amb | -0.004 |
Rudolph | -0.004 |
Token | have |
Token ID | 423 |
Feature activation | -6.30e-01 |
Pos logit contributions | |
orry | +0.003 |
run | +0.002 |
oke | +0.002 |
ence | +0.002 |
aint | +0.002 |
Neg logit contributions | |
rob | -0.007 |
Woo | -0.006 |
amb | -0.006 |
thank | -0.005 |
burn | -0.005 |
Token | each |
Token ID | 1123 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
rob | +0.026 |
Woo | +0.022 |
amb | +0.020 |
bur | +0.018 |
burn | +0.018 |
Neg logit contributions | |
run | -0.018 |
orry | -0.018 |
oke | -0.017 |
ence | -0.017 |
aint | -0.017 |
Token | other |
Token ID | 584 |
Feature activation | -2.47e-01 |
Pos logit contributions | |
orry | +0.047 |
oke | +0.046 |
run | +0.046 |
ence | +0.045 |
aint | +0.044 |
Neg logit contributions | |
rob | -0.049 |
Woo | -0.041 |
amb | -0.034 |
bur | -0.032 |
Pink | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | +9.89e-02 |
Pos logit contributions | |
rob | +0.008 |
Woo | +0.007 |
amb | +0.006 |
Pink | +0.006 |
bur | +0.006 |
Neg logit contributions | |
orry | -0.009 |
oke | -0.009 |
ence | -0.008 |
run | -0.008 |
aint | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +3.74e-02 |
Pos logit contributions | |
orry | +0.003 |
run | +0.003 |
oke | +0.003 |
ence | +0.003 |
aint | +0.003 |
Neg logit contributions | |
rob | -0.004 |
Woo | -0.003 |
amb | -0.002 |
bur | -0.002 |
Pink | -0.002 |
Token | that |
Token ID | 326 |
Feature activation | +7.59e-02 |
Pos logit contributions | |
orry | +0.001 |
oke | +0.001 |
ence | +0.001 |
aint | +0.001 |
run | +0.001 |
Neg logit contributions | |
rob | -0.001 |
Woo | -0.001 |
Pink | -0.001 |
amb | -0.001 |
Sebastian | -0.001 |
Token | they |
Token ID | 484 |
Feature activation | -8.19e-01 |
Pos logit contributions | |
orry | +0.003 |
ence | +0.003 |
oke | +0.002 |
run | +0.002 |
aint | +0.002 |
Neg logit contributions | |
rob | -0.003 |
Woo | -0.002 |
Pink | -0.002 |
amb | -0.002 |
bur | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.54e-01 |
Pos logit contributions | |
rob | +0.024 |
Woo | +0.021 |
amb | +0.018 |
Pink | +0.017 |
bur | +0.016 |
Neg logit contributions | |
orry | -0.020 |
run | -0.020 |
oke | -0.020 |
ence | -0.019 |
aint | -0.019 |
Token | One |
Token ID | 3198 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
rob | +0.005 |
Woo | +0.004 |
amb | +0.003 |
bur | +0.003 |
Pink | +0.003 |
Neg logit contributions | |
oke | -0.006 |
orry | -0.006 |
run | -0.006 |
ence | -0.006 |
aint | -0.006 |
Token | day |
Token ID | 1110 |
Feature activation | +8.09e-02 |
Pos logit contributions | |
oke | +0.008 |
ence | +0.008 |
run | +0.008 |
orry | +0.008 |
isel | +0.008 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.007 |
amb | -0.006 |
oto | -0.005 |
Pink | -0.005 |
Token | , |
Token ID | 11 |
Feature activation | +9.51e-01 |
Pos logit contributions | |
orry | +0.003 |
oke | +0.003 |
run | +0.003 |
ence | +0.003 |
aint | +0.003 |
Neg logit contributions | |
rob | -0.003 |
Woo | -0.002 |
amb | -0.002 |
Pink | -0.002 |
bur | -0.002 |
Token | Tim |
Token ID | 5045 |
Feature activation | -2.06e-01 |
Pos logit contributions | |
oke | +0.028 |
orry | +0.028 |
ence | +0.027 |
run | +0.027 |
aint | +0.026 |
Neg logit contributions | |
rob | -0.040 |
Woo | -0.036 |
Pink | -0.029 |
amb | -0.028 |
bur | -0.028 |
Token | my |
Token ID | 1820 |
Feature activation | +7.99e-01 |
Pos logit contributions | |
rob | +0.009 |
Woo | +0.008 |
amb | +0.006 |
Pink | +0.006 |
Lib | +0.006 |
Neg logit contributions | |
orry | -0.006 |
oke | -0.006 |
run | -0.005 |
ence | -0.005 |
aint | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
orry | +0.018 |
oke | +0.018 |
run | +0.016 |
tower | +0.016 |
aint | +0.016 |
Neg logit contributions | |
rob | -0.039 |
Woo | -0.032 |
amb | -0.028 |
igi | -0.028 |
bur | -0.027 |
Token | Max |
Token ID | 5436 |
Feature activation | +4.24e-01 |
Pos logit contributions | |
orry | +0.032 |
oke | +0.032 |
run | +0.031 |
ence | +0.031 |
aint | +0.029 |
Neg logit contributions | |
rob | -0.055 |
Woo | -0.049 |
amb | -0.041 |
Pink | -0.040 |
bur | -0.040 |
Token | were |
Token ID | 547 |
Feature activation | -3.72e-01 |
Pos logit contributions | |
orry | +0.009 |
tug | +0.009 |
aint | +0.009 |
oke | +0.008 |
ence | +0.008 |
Neg logit contributions | |
rob | -0.022 |
Woo | -0.016 |
amb | -0.015 |
igi | -0.015 |
lor | -0.015 |
Token | playing |
Token ID | 2712 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
rob | +0.016 |
Woo | +0.014 |
amb | +0.012 |
Pink | +0.012 |
bur | +0.011 |
Neg logit contributions | |
oke | -0.010 |
orry | -0.010 |
run | -0.010 |
ence | -0.010 |
aint | -0.009 |
Token | in |
Token ID | 287 |
Feature activation | -1.38e-01 |
Pos logit contributions | |
oke | +0.007 |
ence | +0.007 |
run | +0.007 |
aint | +0.007 |
orry | +0.007 |
Neg logit contributions | |
rob | -0.006 |
Woo | -0.005 |
amb | -0.004 |
Pink | -0.004 |
thank | -0.004 |
Token | world |
Token ID | 995 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
rob | +0.022 |
Woo | +0.018 |
Pink | +0.014 |
amb | +0.014 |
bur | +0.014 |
Neg logit contributions | |
run | -0.022 |
orry | -0.021 |
oke | -0.021 |
ence | -0.020 |
isel | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | +4.76e-02 |
Pos logit contributions | |
orry | +0.050 |
run | +0.048 |
oke | +0.048 |
ence | +0.048 |
aint | +0.046 |
Neg logit contributions | |
rob | -0.053 |
Woo | -0.044 |
amb | -0.036 |
Pink | -0.034 |
bur | -0.034 |
Token | We |
Token ID | 1135 |
Feature activation | -2.03e-01 |
Pos logit contributions | |
orry | +0.001 |
oke | +0.001 |
run | +0.001 |
ence | +0.001 |
aint | +0.001 |
Neg logit contributions | |
rob | -0.002 |
Woo | -0.002 |
amb | -0.002 |
Pink | -0.002 |
bur | -0.002 |
Token | love |
Token ID | 1842 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
rob | +0.009 |
Woo | +0.008 |
amb | +0.007 |
Sebastian | +0.007 |
bur | +0.007 |
Neg logit contributions | |
orry | -0.005 |
ence | -0.005 |
oke | -0.005 |
aint | -0.005 |
run | -0.005 |
Token | you |
Token ID | 345 |
Feature activation | +8.55e-01 |
Pos logit contributions | |
orry | +0.010 |
oke | +0.009 |
run | +0.009 |
isel | +0.009 |
ence | +0.009 |
Neg logit contributions | |
rob | -0.011 |
Woo | -0.010 |
amb | -0.008 |
Pink | -0.008 |
bur | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
orry | +0.026 |
oke | +0.026 |
run | +0.026 |
ence | +0.025 |
aint | +0.024 |
Neg logit contributions | |
rob | -0.034 |
Woo | -0.029 |
amb | -0.024 |
bur | -0.023 |
Pink | -0.022 |
Token | we |
Token ID | 356 |
Feature activation | +2.57e-01 |
Pos logit contributions | |
orry | +0.017 |
run | +0.016 |
oke | +0.016 |
ence | +0.016 |
aint | +0.015 |
Neg logit contributions | |
rob | -0.020 |
Woo | -0.017 |
amb | -0.014 |
Pink | -0.014 |
bur | -0.014 |
Token | love |
Token ID | 1842 |
Feature activation | +9.97e-02 |
Pos logit contributions | |
orry | +0.006 |
ence | +0.006 |
oke | +0.006 |
aint | +0.006 |
run | +0.006 |
Neg logit contributions | |
rob | -0.012 |
Woo | -0.010 |
amb | -0.009 |
bur | -0.008 |
igi | -0.008 |
Token | you |
Token ID | 345 |
Feature activation | +8.56e-01 |
Pos logit contributions | |
orry | +0.003 |
oke | +0.003 |
run | +0.003 |
ence | +0.003 |
aint | +0.003 |
Neg logit contributions | |
rob | -0.004 |
Woo | -0.003 |
amb | -0.003 |
Pink | -0.003 |
bur | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | +6.90e-01 |
Pos logit contributions | |
orry | +0.025 |
oke | +0.025 |
run | +0.025 |
ence | +0.024 |
aint | +0.024 |
Neg logit contributions | |
rob | -0.035 |
Woo | -0.029 |
amb | -0.025 |
bur | -0.024 |
Pink | -0.023 |
Token | we |
Token ID | 356 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
orry | +0.023 |
oke | +0.022 |
run | +0.022 |
ence | +0.022 |
aint | +0.021 |
Neg logit contributions | |
rob | -0.026 |
Woo | -0.021 |
amb | -0.018 |
bur | -0.017 |
Pink | -0.017 |
Token | Tom |
Token ID | 13787 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
oke | +0.007 |
orry | +0.007 |
run | +0.007 |
aint | +0.007 |
ence | +0.007 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.006 |
amb | -0.005 |
bur | -0.005 |
Pink | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
rob | +0.015 |
Woo | +0.012 |
amb | +0.010 |
Cindy | +0.010 |
lor | +0.010 |
Neg logit contributions | |
oke | -0.008 |
orry | -0.008 |
aint | -0.007 |
tower | -0.007 |
ence | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
rob | +0.025 |
Woo | +0.021 |
amb | +0.019 |
bur | +0.018 |
Pink | +0.018 |
Neg logit contributions | |
orry | -0.012 |
run | -0.011 |
oke | -0.011 |
ence | -0.011 |
aint | -0.010 |
Token | cricket |
Token ID | 18836 |
Feature activation | +3.20e-01 |
Pos logit contributions | |
run | +0.010 |
oke | +0.008 |
aint | +0.008 |
orry | +0.008 |
isel | +0.008 |
Neg logit contributions | |
Woo | -0.008 |
rob | -0.007 |
Pink | -0.007 |
Rudolph | -0.006 |
amb | -0.006 |
Token | who |
Token ID | 508 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
orry | +0.011 |
run | +0.011 |
oke | +0.011 |
ence | +0.010 |
isel | +0.010 |
Neg logit contributions | |
rob | -0.012 |
Woo | -0.010 |
amb | -0.008 |
Pink | -0.008 |
Rudolph | -0.008 |
Token | liked |
Token ID | 8288 |
Feature activation | +5.92e-01 |
Pos logit contributions | |
orry | +0.011 |
run | +0.010 |
oke | +0.010 |
ence | +0.010 |
aint | +0.010 |
Neg logit contributions | |
rob | -0.019 |
Woo | -0.016 |
amb | -0.014 |
bur | -0.014 |
burn | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -3.96e-02 |
Pos logit contributions | |
oke | +0.026 |
orry | +0.025 |
ence | +0.023 |
isel | +0.023 |
aint | +0.022 |
Neg logit contributions | |
Woo | -0.016 |
rob | -0.016 |
Pink | -0.013 |
oto | -0.011 |
amb | -0.011 |
Token | drink |
Token ID | 4144 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
rob | +0.002 |
Woo | +0.002 |
amb | +0.001 |
bur | +0.001 |
Pink | +0.001 |
Neg logit contributions | |
orry | -0.001 |
run | -0.001 |
oke | -0.001 |
ence | -0.001 |
aint | -0.001 |
Token | juice |
Token ID | 13135 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
rob | +0.035 |
Woo | +0.027 |
bur | +0.025 |
amb | +0.025 |
lor | +0.024 |
Neg logit contributions | |
run | -0.020 |
aint | -0.019 |
orry | -0.019 |
tower | -0.018 |
triangle | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +4.78e-01 |
Pos logit contributions | |
rob | +0.020 |
Woo | +0.017 |
bur | +0.016 |
Sim | +0.016 |
igi | +0.015 |
Neg logit contributions | |
tower | -0.005 |
run | -0.005 |
aint | -0.005 |
oke | -0.005 |
triangle | -0.005 |
Token | He |
Token ID | 679 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
orry | +0.016 |
oke | +0.016 |
run | +0.015 |
ence | +0.015 |
aint | +0.014 |
Neg logit contributions | |
rob | -0.017 |
Woo | -0.015 |
amb | -0.012 |
Pink | -0.012 |
Sebastian | -0.012 |
Token | pushing |
Token ID | 7796 |
Feature activation | +2.95e-01 |
Pos logit contributions | |
orry | +0.004 |
run | +0.004 |
oke | +0.004 |
ence | +0.004 |
aint | +0.003 |
Neg logit contributions | |
rob | -0.007 |
Woo | -0.005 |
amb | -0.005 |
bur | -0.005 |
Pink | -0.005 |
Token | Sammy |
Token ID | 44067 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
oke | +0.010 |
orry | +0.010 |
run | +0.010 |
ence | +0.010 |
aint | +0.010 |
Neg logit contributions | |
rob | -0.010 |
Woo | -0.009 |
amb | -0.007 |
Pink | -0.007 |
bur | -0.007 |
Token | in |
Token ID | 287 |
Feature activation | +2.49e-01 |
Pos logit contributions | |
orry | +0.024 |
oke | +0.024 |
ence | +0.023 |
run | +0.023 |
isel | +0.022 |
Neg logit contributions | |
rob | -0.025 |
Woo | -0.022 |
amb | -0.018 |
bur | -0.017 |
Pink | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
oke | +0.010 |
orry | +0.010 |
ence | +0.009 |
aint | +0.009 |
isel | +0.009 |
Neg logit contributions | |
rob | -0.007 |
Woo | -0.007 |
Cindy | -0.005 |
Pink | -0.005 |
herself | -0.005 |
Token | st |
Token ID | 336 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
oke | +0.040 |
run | +0.039 |
orry | +0.038 |
ence | +0.038 |
isel | +0.037 |
Neg logit contributions | |
rob | -0.020 |
Woo | -0.017 |
Pink | -0.010 |
bur | -0.010 |
Cindy | -0.009 |
Token | roller |
Token ID | 10646 |
Feature activation | -3.29e-01 |
Pos logit contributions | |
orry | +0.041 |
ence | +0.040 |
run | +0.040 |
oke | +0.039 |
aint | +0.039 |
Neg logit contributions | |
rob | -0.053 |
Woo | -0.044 |
Pink | -0.037 |
amb | -0.036 |
thank | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
rob | +0.013 |
Woo | +0.011 |
amb | +0.010 |
Pink | +0.009 |
bur | +0.009 |
Neg logit contributions | |
orry | -0.010 |
run | -0.010 |
oke | -0.010 |
ence | -0.010 |
aint | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +4.15e-01 |
Pos logit contributions | |
orry | +0.019 |
oke | +0.019 |
aint | +0.018 |
run | +0.018 |
ence | +0.018 |
Neg logit contributions | |
rob | -0.016 |
Woo | -0.016 |
Pink | -0.012 |
bur | -0.011 |
Cindy | -0.011 |
Token | they |
Token ID | 484 |
Feature activation | -2.39e-01 |
Pos logit contributions | |
orry | +0.011 |
run | +0.011 |
oke | +0.011 |
ence | +0.011 |
aint | +0.010 |
Neg logit contributions | |
rob | -0.018 |
Woo | -0.015 |
amb | -0.013 |
bur | -0.012 |
Pink | -0.012 |
Token | were |
Token ID | 547 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
rob | +0.010 |
Woo | +0.009 |
amb | +0.007 |
Pink | +0.007 |
bur | +0.007 |
Neg logit contributions | |
orry | -0.007 |
run | -0.007 |
oke | -0.007 |
ence | -0.006 |
aint | -0.006 |
Token | having |
Token ID | 1719 |
Feature activation | -2.37e-02 |
Pos logit contributions | |
rob | +0.016 |
Woo | +0.015 |
bur | +0.012 |
Pink | +0.012 |
amb | +0.011 |
Neg logit contributions | |
oke | -0.015 |
orry | -0.015 |
run | -0.014 |
ence | -0.014 |
aint | -0.014 |
Token | with |
Token ID | 351 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
rob | +0.011 |
Woo | +0.009 |
amb | +0.007 |
Pink | +0.007 |
bur | +0.007 |
Neg logit contributions | |
orry | -0.011 |
oke | -0.011 |
run | -0.011 |
ence | -0.011 |
aint | -0.010 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +2.47e-01 |
Pos logit contributions | |
rob | +0.011 |
Woo | +0.009 |
amb | +0.008 |
bur | +0.008 |
igi | +0.007 |
Neg logit contributions | |
run | -0.009 |
orry | -0.009 |
ence | -0.009 |
oke | -0.009 |
aint | -0.009 |
Token | colors |
Token ID | 7577 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
orry | +0.008 |
oke | +0.008 |
run | +0.008 |
ence | +0.007 |
aint | +0.007 |
Neg logit contributions | |
rob | -0.010 |
Woo | -0.008 |
amb | -0.007 |
Pink | -0.007 |
bur | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -3.93e-01 |
Pos logit contributions | |
rob | +0.024 |
Woo | +0.020 |
amb | +0.017 |
bur | +0.016 |
Pink | +0.015 |
Neg logit contributions | |
run | -0.022 |
orry | -0.022 |
oke | -0.022 |
ence | -0.021 |
aint | -0.020 |
Token | patterns |
Token ID | 7572 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
rob | +0.015 |
Woo | +0.013 |
amb | +0.011 |
Pink | +0.010 |
bur | +0.010 |
Neg logit contributions | |
orry | -0.012 |
oke | -0.012 |
run | -0.012 |
ence | -0.012 |
aint | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +4.41e-03 |
Pos logit contributions | |
rob | +0.032 |
Woo | +0.028 |
amb | +0.024 |
bur | +0.023 |
Pink | +0.022 |
Neg logit contributions | |
orry | -0.022 |
run | -0.022 |
oke | -0.022 |
ence | -0.021 |
aint | -0.021 |
Token | Everyone |
Token ID | 11075 |
Feature activation | +2.74e-01 |
Pos logit contributions | |
orry | +0.000 |
ence | +0.000 |
oke | +0.000 |
run | +0.000 |
aint | +0.000 |
Neg logit contributions | |
rob | -0.000 |
Woo | -0.000 |
amb | -0.000 |
Pink | -0.000 |
Sebastian | -0.000 |
Token | loved |
Token ID | 6151 |
Feature activation | +8.62e-02 |
Pos logit contributions | |
ence | +0.010 |
aint | +0.010 |
orry | +0.010 |
isel | +0.010 |
run | +0.010 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.007 |
amb | -0.006 |
dressed | -0.005 |
thank | -0.005 |
Token | it |
Token ID | 340 |
Feature activation | -7.92e-01 |
Pos logit contributions | |
orry | +0.003 |
oke | +0.003 |
ence | +0.003 |
aint | +0.003 |
isel | +0.003 |
Neg logit contributions | |
rob | -0.003 |
Woo | -0.002 |
Pink | -0.002 |
Sebastian | -0.002 |
Cindy | -0.002 |
Token | ! |
Token ID | 0 |
Feature activation | +9.47e-02 |
Pos logit contributions | |
rob | +0.028 |
Woo | +0.023 |
amb | +0.019 |
bur | +0.018 |
Pink | +0.018 |
Neg logit contributions | |
orry | -0.028 |
run | -0.027 |
oke | -0.027 |
ence | -0.027 |
aint | -0.026 |
Token | |
Token ID | 220 |
Feature activation | +5.30e-01 |
Pos logit contributions | |
orry | +0.003 |
ence | +0.003 |
oke | +0.003 |
run | +0.003 |
aint | +0.003 |
Neg logit contributions | |
rob | -0.003 |
Woo | -0.003 |
amb | -0.002 |
Pink | -0.002 |
bur | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -3.50e-01 |
Pos logit contributions | |
oke | +0.009 |
run | +0.009 |
orry | +0.009 |
ence | +0.009 |
aint | +0.008 |
Neg logit contributions | |
rob | -0.010 |
Woo | -0.008 |
amb | -0.007 |
Pink | -0.007 |
bur | -0.007 |
Token | so |
Token ID | 523 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
rob | +0.011 |
Woo | +0.011 |
Pink | +0.009 |
amb | +0.008 |
Sim | +0.008 |
Neg logit contributions | |
oke | -0.012 |
run | -0.011 |
orry | -0.011 |
aint | -0.011 |
isel | -0.011 |
Token | excited |
Token ID | 6568 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
rob | +0.008 |
Woo | +0.007 |
amb | +0.006 |
Pink | +0.006 |
bur | +0.005 |
Neg logit contributions | |
orry | -0.005 |
run | -0.005 |
oke | -0.005 |
ence | -0.005 |
aint | -0.005 |
Token | to |
Token ID | 284 |
Feature activation | +5.48e-02 |
Pos logit contributions | |
orry | +0.010 |
oke | +0.010 |
run | +0.010 |
ence | +0.010 |
aint | +0.009 |
Neg logit contributions | |
rob | -0.015 |
Woo | -0.013 |
amb | -0.011 |
bur | -0.011 |
Pink | -0.010 |
Token | see |
Token ID | 766 |
Feature activation | -2.33e-01 |
Pos logit contributions | |
oke | +0.002 |
run | +0.002 |
orry | +0.002 |
ence | +0.002 |
aint | +0.002 |
Neg logit contributions | |
rob | -0.002 |
Woo | -0.002 |
amb | -0.002 |
Pink | -0.001 |
thank | -0.001 |
Token | it |
Token ID | 340 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
rob | +0.013 |
Woo | +0.011 |
amb | +0.011 |
thank | +0.010 |
bur | +0.010 |
Neg logit contributions | |
orry | -0.003 |
run | -0.003 |
oke | -0.003 |
ence | -0.003 |
aint | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
rob | +0.014 |
Woo | +0.012 |
Pink | +0.009 |
amb | +0.009 |
bur | +0.009 |
Neg logit contributions | |
orry | -0.017 |
oke | -0.017 |
run | -0.017 |
ence | -0.016 |
aint | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
rob | +0.010 |
Woo | +0.009 |
Pink | +0.007 |
amb | +0.007 |
Cindy | +0.007 |
Neg logit contributions | |
orry | -0.012 |
oke | -0.012 |
run | -0.011 |
ence | -0.011 |
aint | -0.011 |
Token | wanted |
Token ID | 2227 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
oke | +0.021 |
orry | +0.020 |
run | +0.020 |
ence | +0.020 |
aint | +0.019 |
Neg logit contributions | |
rob | -0.015 |
Woo | -0.013 |
Pink | -0.010 |
amb | -0.010 |
Lib | -0.010 |
Token | to |
Token ID | 284 |
Feature activation | -6.54e-01 |
Pos logit contributions | |
rob | +0.033 |
Woo | +0.029 |
Pink | +0.024 |
amb | +0.024 |
bur | +0.024 |
Neg logit contributions | |
oke | -0.022 |
orry | -0.022 |
run | -0.021 |
ence | -0.021 |
aint | -0.020 |
Token | know |
Token ID | 760 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
rob | +0.028 |
Woo | +0.024 |
amb | +0.021 |
Pink | +0.020 |
bur | +0.020 |
Neg logit contributions | |
orry | -0.018 |
oke | -0.018 |
run | -0.018 |
ence | -0.017 |
aint | -0.016 |
Token | ting |
Token ID | 889 |
Feature activation | +8.24e-01 |
Pos logit contributions | |
rob | +0.020 |
Woo | +0.017 |
bur | +0.014 |
thank | +0.014 |
amb | +0.014 |
Neg logit contributions | |
orry | -0.020 |
oke | -0.019 |
aint | -0.019 |
ence | -0.019 |
isel | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | -2.89e-02 |
Pos logit contributions | |
oke | +0.029 |
orry | +0.029 |
ence | +0.027 |
run | +0.027 |
aint | +0.027 |
Neg logit contributions | |
rob | -0.029 |
Woo | -0.025 |
amb | -0.020 |
Pink | -0.020 |
bur | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | +5.91e-01 |
Pos logit contributions | |
rob | +0.001 |
Woo | +0.001 |
Pink | +0.001 |
amb | +0.001 |
bur | +0.001 |
Neg logit contributions | |
orry | -0.001 |
oke | -0.001 |
ence | -0.001 |
aint | -0.001 |
run | -0.001 |
Token | other |
Token ID | 584 |
Feature activation | -8.87e-01 |
Pos logit contributions | |
oke | +0.024 |
run | +0.023 |
orry | +0.023 |
ence | +0.021 |
ever | +0.021 |
Neg logit contributions | |
rob | -0.018 |
Woo | -0.015 |
bur | -0.012 |
Pink | -0.011 |
North | -0.011 |
Token | direction |
Token ID | 4571 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
rob | +0.032 |
Woo | +0.027 |
amb | +0.023 |
bur | +0.023 |
Pink | +0.022 |
Neg logit contributions | |
oke | -0.029 |
orry | -0.028 |
run | -0.028 |
ence | -0.027 |
isel | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +1.06e-01 |
Pos logit contributions | |
rob | +0.016 |
Woo | +0.014 |
Pink | +0.011 |
amb | +0.011 |
Cindy | +0.010 |
Neg logit contributions | |
orry | -0.021 |
oke | -0.020 |
ence | -0.020 |
isel | -0.019 |
aint | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -2.70e-01 |
Pos logit contributions | |
orry | +0.004 |
ence | +0.004 |
oke | +0.004 |
isel | +0.004 |
aint | +0.004 |
Neg logit contributions | |
rob | -0.003 |
Woo | -0.003 |
Pink | -0.002 |
amb | -0.002 |
Sebastian | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +4.03e-03 |
Pos logit contributions | |
rob | +0.008 |
Woo | +0.007 |
amb | +0.006 |
Pink | +0.005 |
bur | +0.005 |
Neg logit contributions | |
orry | -0.010 |
ence | -0.010 |
oke | -0.010 |
aint | -0.010 |
run | -0.010 |
Token | The |
Token ID | 464 |
Feature activation | -1.94e-01 |
Pos logit contributions | |
oke | +0.000 |
ence | +0.000 |
orry | +0.000 |
aint | +0.000 |
isel | +0.000 |
Neg logit contributions | |
rob | -0.000 |
Woo | -0.000 |
G | -0.000 |
amb | -0.000 |
Pink | -0.000 |
Token | farmer |
Token ID | 18739 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
rob | +0.006 |
Woo | +0.005 |
oto | +0.005 |
bur | +0.004 |
waitress | +0.004 |
Neg logit contributions | |
run | -0.008 |
aint | -0.007 |
ence | -0.007 |
oke | -0.007 |
orry | -0.007 |
Token | shook |
Token ID | 14682 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
orry | +0.035 |
run | +0.034 |
ence | +0.034 |
oke | +0.034 |
aint | +0.033 |
Neg logit contributions | |
rob | -0.033 |
Woo | -0.027 |
amb | -0.023 |
bur | -0.022 |
Pink | -0.022 |
Token | it |
Token ID | 340 |
Feature activation | -6.48e-01 |
Pos logit contributions | |
oke | +0.014 |
ence | +0.014 |
orry | +0.014 |
run | +0.013 |
aint | +0.013 |
Neg logit contributions | |
rob | -0.012 |
Woo | -0.011 |
Pink | -0.008 |
amb | -0.008 |
bur | -0.008 |
Token | disgusting |
Token ID | 23374 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
rob | +0.024 |
Woo | +0.022 |
amb | +0.018 |
Pink | +0.017 |
burn | +0.017 |
Neg logit contributions | |
oke | -0.021 |
orry | -0.021 |
ence | -0.019 |
run | -0.019 |
aint | -0.019 |
Token | !" |
Token ID | 2474 |
Feature activation | -3.01e-01 |
Pos logit contributions | |
rob | +0.022 |
Woo | +0.019 |
amb | +0.015 |
bur | +0.014 |
Pink | +0.014 |
Neg logit contributions | |
orry | -0.024 |
run | -0.024 |
oke | -0.024 |
ence | -0.023 |
aint | -0.023 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.86e-01 |
Pos logit contributions | |
rob | +0.011 |
Woo | +0.010 |
amb | +0.008 |
Pink | +0.008 |
bur | +0.007 |
Neg logit contributions | |
orry | -0.010 |
oke | -0.010 |
run | -0.010 |
ence | -0.010 |
aint | -0.009 |
Token | said |
Token ID | 531 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
rob | +0.020 |
Woo | +0.016 |
amb | +0.014 |
bur | +0.013 |
Pink | +0.013 |
Neg logit contributions | |
orry | -0.015 |
run | -0.015 |
oke | -0.014 |
ence | -0.014 |
aint | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
orry | +0.009 |
oke | +0.009 |
ence | +0.009 |
run | +0.009 |
aint | +0.008 |
Neg logit contributions | |
rob | -0.009 |
Woo | -0.008 |
amb | -0.006 |
Pink | -0.006 |
bur | -0.006 |
Token | sob |
Token ID | 27355 |
Feature activation | +6.57e-01 |
Pos logit contributions | |
orry | +0.005 |
oke | +0.005 |
run | +0.005 |
ence | +0.004 |
aint | +0.004 |
Neg logit contributions | |
rob | -0.005 |
Woo | -0.005 |
Pink | -0.004 |
amb | -0.004 |
thank | -0.004 |
Token | bing |
Token ID | 4623 |
Feature activation | -6.18e-01 |
Pos logit contributions | |
orry | +0.023 |
run | +0.022 |
oke | +0.022 |
ence | +0.022 |
aint | +0.021 |
Neg logit contributions | |
rob | -0.023 |
Woo | -0.020 |
amb | -0.016 |
Pink | -0.015 |
bur | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
rob | +0.018 |
Woo | +0.017 |
Pink | +0.013 |
amb | +0.013 |
herself | +0.012 |
Neg logit contributions | |
orry | -0.024 |
oke | -0.024 |
ence | -0.024 |
isel | -0.023 |
run | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +3.41e-01 |
Pos logit contributions | |
rob | +0.009 |
Woo | +0.008 |
amb | +0.007 |
Pink | +0.007 |
bur | +0.007 |
Neg logit contributions | |
orry | -0.007 |
oke | -0.007 |
run | -0.007 |
ence | -0.007 |
aint | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
orry | +0.010 |
oke | +0.010 |
run | +0.010 |
ence | +0.010 |
aint | +0.010 |
Neg logit contributions | |
rob | -0.014 |
Woo | -0.011 |
amb | -0.010 |
bur | -0.009 |
Pink | -0.009 |
Token | like |
Token ID | 588 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
rob | +0.018 |
Woo | +0.015 |
amb | +0.013 |
bur | +0.012 |
Pink | +0.012 |
Neg logit contributions | |
run | -0.011 |
orry | -0.011 |
oke | -0.011 |
ence | -0.011 |
aint | -0.010 |
Token | you |
Token ID | 345 |
Feature activation | +1.35e-01 |
Pos logit contributions | |
rob | +0.002 |
Woo | +0.001 |
amb | +0.001 |
bur | +0.001 |
Pink | +0.001 |
Neg logit contributions | |
orry | -0.001 |
run | -0.001 |
oke | -0.001 |
ence | -0.001 |
aint | -0.001 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
orry | +0.005 |
run | +0.005 |
oke | +0.005 |
ence | +0.004 |
aint | +0.004 |
Neg logit contributions | |
rob | -0.005 |
Woo | -0.004 |
amb | -0.003 |
bur | -0.003 |
Pink | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +1.81e-01 |
Pos logit contributions | |
orry | +0.012 |
run | +0.011 |
oke | +0.011 |
ence | +0.011 |
aint | +0.011 |
Neg logit contributions | |
rob | -0.015 |
Woo | -0.013 |
amb | -0.011 |
Pink | -0.011 |
bur | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
orry | +0.006 |
oke | +0.006 |
run | +0.005 |
ence | +0.005 |
aint | +0.005 |
Neg logit contributions | |
rob | -0.007 |
Woo | -0.006 |
amb | -0.005 |
bur | -0.005 |
Pink | -0.005 |
Token | B |
Token ID | 33 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
orry | +0.012 |
run | +0.012 |
oke | +0.012 |
ence | +0.011 |
aint | +0.011 |
Neg logit contributions | |
rob | -0.015 |
Woo | -0.013 |
amb | -0.011 |
Pink | -0.010 |
bur | -0.010 |
Token | ub |
Token ID | 549 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
rob | +0.059 |
Woo | +0.053 |
amb | +0.047 |
Pink | +0.043 |
bur | +0.043 |
Neg logit contributions | |
orry | -0.041 |
ence | -0.039 |
oke | -0.039 |
run | -0.038 |
aint | -0.037 |
Token | bles |
Token ID | 7689 |
Feature activation | +4.75e-01 |
Pos logit contributions | |
rob | +0.043 |
Woo | +0.035 |
amb | +0.028 |
bur | +0.026 |
Pink | +0.026 |
Neg logit contributions | |
orry | -0.046 |
oke | -0.045 |
run | -0.045 |
ence | -0.044 |
aint | -0.042 |
Token | replied |
Token ID | 8712 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
orry | +0.014 |
oke | +0.014 |
run | +0.014 |
ence | +0.014 |
aint | +0.013 |
Neg logit contributions | |
rob | -0.019 |
Woo | -0.017 |
Pink | -0.013 |
amb | -0.013 |
bur | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
rob | +0.015 |
Woo | +0.013 |
Pink | +0.010 |
amb | +0.010 |
Gloria | +0.009 |
Neg logit contributions | |
orry | -0.020 |
oke | -0.019 |
run | -0.019 |
ence | -0.019 |
aint | -0.018 |
Token | " |
Token ID | 366 |
Feature activation | -9.50e-02 |
Pos logit contributions | |
rob | +0.009 |
Woo | +0.009 |
Pink | +0.007 |
amb | +0.007 |
Rudolph | +0.007 |
Neg logit contributions | |
orry | -0.005 |
oke | -0.004 |
run | -0.004 |
ence | -0.004 |
aint | -0.004 |
Token | help |
Token ID | 1037 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
oke | +0.001 |
orry | +0.001 |
ence | +0.001 |
run | +0.001 |
aint | +0.001 |
Neg logit contributions | |
rob | -0.002 |
Woo | -0.002 |
amb | -0.001 |
bur | -0.001 |
Pink | -0.001 |
Token | Tommy |
Token ID | 19919 |
Feature activation | -2.20e-01 |
Pos logit contributions | |
orry | +0.015 |
oke | +0.015 |
run | +0.015 |
ence | +0.014 |
aint | +0.014 |
Neg logit contributions | |
rob | -0.010 |
Woo | -0.009 |
amb | -0.007 |
Pink | -0.006 |
bur | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
rob | +0.007 |
Woo | +0.007 |
amb | +0.005 |
bur | +0.005 |
Pink | +0.005 |
Neg logit contributions | |
orry | -0.008 |
oke | -0.008 |
ence | -0.007 |
run | -0.007 |
aint | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
orry | +0.010 |
run | +0.010 |
oke | +0.010 |
ence | +0.009 |
aint | +0.009 |
Neg logit contributions | |
rob | -0.015 |
Woo | -0.012 |
amb | -0.011 |
bur | -0.010 |
Pink | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
oke | +0.001 |
run | +0.001 |
orry | +0.001 |
aint | +0.001 |
ence | +0.001 |
Neg logit contributions | |
rob | -0.002 |
Woo | -0.001 |
amb | -0.001 |
thank | -0.001 |
Pink | -0.001 |
Token | L |
Token ID | 43 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
orry | +0.018 |
oke | +0.018 |
run | +0.018 |
ence | +0.017 |
aint | +0.017 |
Neg logit contributions | |
rob | -0.026 |
Woo | -0.022 |
amb | -0.018 |
bur | -0.018 |
Pink | -0.018 |
Token | ily |
Token ID | 813 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
rob | +0.088 |
Woo | +0.076 |
Pink | +0.066 |
bur | +0.066 |
Sim | +0.066 |
Neg logit contributions | |
orry | -0.044 |
oke | -0.044 |
run | -0.041 |
ence | -0.034 |
aint | -0.033 |
Token | 's |
Token ID | 338 |
Feature activation | +5.08e-01 |
Pos logit contributions | |
rob | +0.004 |
Woo | +0.004 |
amb | +0.003 |
Pink | +0.003 |
bur | +0.003 |
Neg logit contributions | |
orry | -0.003 |
oke | -0.003 |
run | -0.003 |
ence | -0.003 |
aint | -0.003 |
Token | mom |
Token ID | 1995 |
Feature activation | -7.30e-01 |
Pos logit contributions | |
oke | +0.017 |
ence | +0.016 |
run | +0.016 |
orry | +0.016 |
aint | +0.015 |
Neg logit contributions | |
rob | -0.017 |
Woo | -0.017 |
burn | -0.013 |
amb | -0.013 |
Pink | -0.013 |
Token | my |
Token ID | 1820 |
Feature activation | +2.33e-01 |
Pos logit contributions | |
rob | +0.020 |
Woo | +0.016 |
bur | +0.013 |
amb | +0.012 |
burn | +0.012 |
Neg logit contributions | |
orry | -0.030 |
ence | -0.030 |
oke | -0.029 |
aint | -0.029 |
run | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | +2.41e-01 |
Pos logit contributions | |
orry | +0.008 |
run | +0.007 |
oke | +0.007 |
ence | +0.007 |
aint | +0.007 |
Neg logit contributions | |
rob | -0.009 |
Woo | -0.007 |
amb | -0.006 |
Pink | -0.006 |
bur | -0.006 |
Token | toy |
Token ID | 13373 |
Feature activation | -2.42e+00 |
Pos logit contributions | |
rob | +0.020 |
Woo | +0.018 |
amb | +0.015 |
Pink | +0.015 |
bur | +0.013 |
Neg logit contributions | |
oke | -0.022 |
orry | -0.022 |
ence | -0.022 |
isel | -0.021 |
run | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +3.49e-01 |
Pos logit contributions | |
rob | +0.096 |
Woo | +0.082 |
amb | +0.070 |
Pink | +0.067 |
bur | +0.065 |
Neg logit contributions | |
orry | -0.074 |
oke | -0.072 |
run | -0.072 |
ence | -0.070 |
aint | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | -8.15e-01 |
Pos logit contributions | |
orry | +0.012 |
ence | +0.012 |
run | +0.011 |
oke | +0.011 |
aint | +0.011 |
Neg logit contributions | |
rob | -0.012 |
Woo | -0.011 |
amb | -0.008 |
Pink | -0.008 |
bur | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -2.02e-01 |
Pos logit contributions | |
rob | +0.034 |
Woo | +0.029 |
amb | +0.025 |
Pink | +0.024 |
bur | +0.024 |
Neg logit contributions | |
oke | -0.023 |
run | -0.023 |
orry | -0.022 |
aint | -0.021 |
ence | -0.020 |
Token | " |
Token ID | 1 |
Feature activation | -4.05e-01 |
Pos logit contributions | |
rob | +0.009 |
Woo | +0.007 |
amb | +0.006 |
Pink | +0.006 |
bur | +0.006 |
Neg logit contributions | |
orry | -0.006 |
oke | -0.006 |
run | -0.005 |
ence | -0.005 |
aint | -0.005 |
Token | Ro |
Token ID | 15450 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
rob | +0.015 |
Woo | +0.012 |
amb | +0.011 |
ippy | +0.010 |
igi | +0.010 |
Neg logit contributions | |
oke | -0.012 |
orry | -0.011 |
run | -0.011 |
triangle | -0.011 |
2 | -0.011 |
Token | ar |
Token ID | 283 |
Feature activation | +3.16e-01 |
Pos logit contributions | |
rob | +0.072 |
Woo | +0.062 |
amb | +0.053 |
bur | +0.051 |
Pink | +0.051 |
Neg logit contributions | |
orry | -0.049 |
run | -0.048 |
oke | -0.048 |
ence | -0.046 |
aint | -0.045 |
Token | !" |
Token ID | 2474 |
Feature activation | -7.38e-02 |
Pos logit contributions | |
run | +0.014 |
orry | +0.014 |
aint | +0.013 |
ence | +0.013 |
isel | +0.013 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.006 |
amb | -0.005 |
bur | -0.004 |
oto | -0.004 |
Token | Tom |
Token ID | 4186 |
Feature activation | -7.80e-01 |
Pos logit contributions | |
rob | +0.003 |
Woo | +0.003 |
amb | +0.002 |
Pink | +0.002 |
bur | +0.002 |
Neg logit contributions | |
orry | -0.002 |
run | -0.002 |
oke | -0.002 |
ence | -0.002 |
aint | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
rob | +0.027 |
Woo | +0.023 |
amb | +0.019 |
Pink | +0.017 |
bur | +0.017 |
Neg logit contributions | |
orry | -0.028 |
oke | -0.027 |
run | -0.027 |
ence | -0.027 |
aint | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | +2.88e-01 |
Pos logit contributions | |
orry | +0.015 |
oke | +0.014 |
ence | +0.014 |
isel | +0.013 |
aint | +0.013 |
Neg logit contributions | |
rob | -0.009 |
Woo | -0.009 |
Pink | -0.007 |
amb | -0.007 |
Cindy | -0.007 |
Token | big |
Token ID | 1263 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
rob | +0.008 |
Woo | +0.008 |
Pink | +0.006 |
amb | +0.006 |
Gloria | +0.006 |
Neg logit contributions | |
orry | -0.006 |
oke | -0.006 |
run | -0.006 |
ence | -0.006 |
aint | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e-01 |
Pos logit contributions | |
rob | +0.022 |
Woo | +0.018 |
amb | +0.014 |
Pink | +0.013 |
bur | +0.013 |
Neg logit contributions | |
orry | -0.027 |
oke | -0.026 |
run | -0.026 |
ence | -0.026 |
aint | -0.025 |
Token | |
Token ID | 220 |
Feature activation | +4.93e-01 |
Pos logit contributions | |
rob | +0.005 |
Woo | +0.005 |
amb | +0.004 |
Pink | +0.004 |
Cindy | +0.004 |
Neg logit contributions | |
orry | -0.006 |
oke | -0.006 |
ence | -0.006 |
run | -0.006 |
isel | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -3.52e-01 |
Pos logit contributions | |
orry | +0.018 |
oke | +0.017 |
ence | +0.017 |
run | +0.017 |
aint | +0.016 |
Neg logit contributions | |
rob | -0.017 |
Woo | -0.014 |
amb | -0.011 |
Pink | -0.011 |
bur | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -8.36e-02 |
Pos logit contributions | |
rob | +0.013 |
Woo | +0.011 |
amb | +0.009 |
Pink | +0.009 |
bur | +0.009 |
Neg logit contributions | |
orry | -0.012 |
run | -0.012 |
oke | -0.012 |
ence | -0.011 |
aint | -0.011 |
Token | L |
Token ID | 43 |
Feature activation | -1.78e+00 |
Pos logit contributions | |
rob | +0.002 |
Woo | +0.002 |
amb | +0.002 |
thank | +0.002 |
G | +0.002 |
Neg logit contributions | |
oke | -0.003 |
run | -0.003 |
orry | -0.003 |
ence | -0.003 |
isel | -0.003 |
Token | ily |
Token ID | 813 |
Feature activation | +6.82e-02 |
Pos logit contributions | |
rob | +0.071 |
Woo | +0.060 |
amb | +0.051 |
bur | +0.048 |
Pink | +0.048 |
Neg logit contributions | |
orry | -0.054 |
run | -0.053 |
oke | -0.053 |
ence | -0.052 |
aint | -0.050 |
Token | said |
Token ID | 531 |
Feature activation | +3.08e-01 |
Pos logit contributions | |
orry | +0.002 |
run | +0.002 |
oke | +0.002 |
ence | +0.002 |
aint | +0.002 |
Neg logit contributions | |
rob | -0.003 |
Woo | -0.002 |
amb | -0.002 |
Pink | -0.002 |
bur | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +1.06e-02 |
Pos logit contributions | |
orry | +0.013 |
run | +0.013 |
ence | +0.013 |
oke | +0.013 |
isel | +0.012 |
Neg logit contributions | |
Woo | -0.007 |
rob | -0.007 |
Pink | -0.006 |
Cindy | -0.005 |
amb | -0.005 |
Token | " |
Token ID | 366 |
Feature activation | +2.09e-01 |
Pos logit contributions | |
orry | +0.000 |
isel | +0.000 |
fears | +0.000 |
ence | +0.000 |
oke | +0.000 |
Neg logit contributions | |
Woo | -0.000 |
rob | -0.000 |
Pink | -0.000 |
Cindy | -0.000 |
Gab | -0.000 |
Token | Wow |
Token ID | 22017 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
orry | +0.006 |
run | +0.006 |
oke | +0.006 |
ence | +0.006 |
aint | +0.006 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.007 |
amb | -0.006 |
bur | -0.006 |
Pink | -0.006 |
Token | would |
Token ID | 561 |
Feature activation | -6.83e-01 |
Pos logit contributions | |
orry | +0.001 |
run | +0.001 |
oke | +0.001 |
ence | +0.001 |
aint | +0.001 |
Neg logit contributions | |
rob | -0.001 |
Woo | -0.001 |
amb | -0.001 |
bur | -0.001 |
Pink | -0.001 |
Token | be |
Token ID | 307 |
Feature activation | +4.98e-01 |
Pos logit contributions | |
rob | +0.036 |
Woo | +0.030 |
amb | +0.026 |
bur | +0.025 |
igi | +0.024 |
Neg logit contributions | |
run | -0.014 |
orry | -0.013 |
aint | -0.013 |
ence | -0.013 |
tug | -0.013 |
Token | very |
Token ID | 845 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
run | +0.014 |
orry | +0.014 |
ence | +0.014 |
aint | +0.013 |
oke | +0.013 |
Neg logit contributions | |
rob | -0.021 |
Woo | -0.018 |
amb | -0.016 |
Pink | -0.014 |
bur | -0.014 |
Token | expensive |
Token ID | 5789 |
Feature activation | -1.42e-01 |
Pos logit contributions | |
rob | +0.009 |
Woo | +0.008 |
amb | +0.007 |
Pink | +0.007 |
bur | +0.007 |
Neg logit contributions | |
orry | -0.007 |
oke | -0.006 |
run | -0.006 |
ence | -0.006 |
aint | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
rob | +0.007 |
Woo | +0.006 |
amb | +0.005 |
bur | +0.005 |
igi | +0.005 |
Neg logit contributions | |
run | -0.003 |
oke | -0.003 |
ence | -0.003 |
tower | -0.003 |
orry | -0.003 |
Token | Su |
Token ID | 1778 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
orry | +0.004 |
oke | +0.004 |
ence | +0.004 |
run | +0.004 |
isel | +0.004 |
Neg logit contributions | |
rob | -0.004 |
Woo | -0.004 |
amb | -0.003 |
Cindy | -0.003 |
Pink | -0.003 |
Token | zy |
Token ID | 7357 |
Feature activation | +6.95e-01 |
Pos logit contributions | |
rob | +0.064 |
Woo | +0.053 |
amb | +0.044 |
bur | +0.041 |
Pink | +0.041 |
Neg logit contributions | |
orry | -0.065 |
run | -0.064 |
oke | -0.064 |
ence | -0.063 |
aint | -0.061 |
Token | felt |
Token ID | 2936 |
Feature activation | -3.00e-01 |
Pos logit contributions | |
orry | +0.024 |
oke | +0.024 |
run | +0.024 |
ence | +0.023 |
isel | +0.022 |
Neg logit contributions | |
rob | -0.024 |
Woo | -0.020 |
amb | -0.017 |
Pink | -0.016 |
bur | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | +8.46e-01 |
Pos logit contributions | |
rob | +0.015 |
Woo | +0.013 |
amb | +0.012 |
bur | +0.011 |
igi | +0.011 |
Neg logit contributions | |
orry | -0.006 |
run | -0.006 |
oke | -0.006 |
ence | -0.006 |
aint | -0.006 |
Token | bit |
Token ID | 1643 |
Feature activation | +1.91e-01 |
Pos logit contributions | |
oke | +0.021 |
orry | +0.020 |
run | +0.020 |
ence | +0.019 |
aint | +0.018 |
Neg logit contributions | |
rob | -0.037 |
Woo | -0.034 |
amb | -0.029 |
Pink | -0.028 |
thank | -0.028 |
Token | sad |
Token ID | 6507 |
Feature activation | -6.95e-01 |
Pos logit contributions | |
orry | +0.005 |
ence | +0.004 |
oke | +0.004 |
run | +0.004 |
tower | +0.004 |
Neg logit contributions | |
rob | -0.008 |
Woo | -0.008 |
Pink | -0.007 |
amb | -0.007 |
thank | -0.006 |