Token | in |
Token ID | 287 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
smanship | +0.037 |
bush | +0.036 |
outage | +0.035 |
remedy | +0.033 |
oils | +0.033 |
Neg logit contributions | |
Tom | -0.025 |
Ben | -0.024 |
arrest | -0.022 |
Sam | -0.021 |
Rex | -0.021 |
Token | the |
Token ID | 262 |
Feature activation | -5.01e-01 |
Pos logit contributions | |
sed | +0.001 |
eg | +0.001 |
ked | +0.001 |
realizes | +0.001 |
icked | +0.001 |
Neg logit contributions | |
smanship | -0.001 |
kinds | -0.001 |
occasions | -0.001 |
oils | -0.001 |
sorts | -0.001 |
Token | air |
Token ID | 1633 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
smanship | +0.012 |
bush | +0.012 |
pleasures | +0.011 |
occasions | +0.011 |
remedy | +0.011 |
Neg logit contributions | |
Tom | -0.014 |
Dan | -0.012 |
Sam | -0.012 |
Ben | -0.012 |
Rex | -0.012 |
Token | when |
Token ID | 618 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
smanship | +0.061 |
bush | +0.058 |
outage | +0.057 |
remedy | +0.055 |
pleasures | +0.054 |
Neg logit contributions | |
Tom | -0.035 |
Ben | -0.032 |
Sam | -0.029 |
Rex | -0.029 |
arrest | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
smanship | +0.019 |
outage | +0.017 |
bush | +0.017 |
oils | +0.017 |
pleasures | +0.016 |
Neg logit contributions | |
Tom | -0.012 |
arrest | -0.011 |
Ben | -0.011 |
eg | -0.011 |
icks | -0.011 |
Token | prince |
Token ID | 19716 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
Tom | +0.037 |
Their | +0.033 |
Ben | +0.032 |
Dan | +0.032 |
their | +0.032 |
Neg logit contributions | |
smanship | -0.045 |
bush | -0.042 |
occasions | -0.041 |
pleasures | -0.041 |
remedy | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
Tom | +0.151 |
Ben | +0.140 |
Rex | +0.134 |
their | +0.133 |
ear | +0.133 |
Neg logit contributions | |
smanship | -0.180 |
bush | -0.175 |
outage | -0.162 |
remedy | -0.154 |
occasions | -0.151 |
Token | princess |
Token ID | 21752 |
Feature activation | +4.49e+00 |
Pos logit contributions | |
Tom | +0.036 |
arrest | +0.035 |
eg | +0.035 |
icks | +0.035 |
Ben | +0.033 |
Neg logit contributions | |
smanship | -0.057 |
bush | -0.054 |
occasions | -0.053 |
remedy | -0.053 |
oils | -0.052 |
Token | stepped |
Token ID | 10764 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
Tom | +0.104 |
Ben | +0.097 |
Sam | +0.091 |
Rex | +0.090 |
bye | +0.088 |
Neg logit contributions | |
smanship | -0.125 |
bush | -0.115 |
outage | -0.110 |
occasions | -0.105 |
remedy | -0.104 |
Token | out |
Token ID | 503 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Tom | +0.008 |
Ben | +0.008 |
arrest | +0.007 |
Sam | +0.007 |
Leo | +0.007 |
Neg logit contributions | |
smanship | -0.011 |
bush | -0.011 |
remedy | -0.010 |
oils | -0.010 |
First | -0.010 |
Token | of |
Token ID | 286 |
Feature activation | +7.13e-02 |
Pos logit contributions | |
Tom | +0.061 |
eg | +0.059 |
Ben | +0.058 |
arrest | +0.057 |
sed | +0.055 |
Neg logit contributions | |
smanship | -0.027 |
outage | -0.024 |
bush | -0.022 |
heart | -0.021 |
bul | -0.021 |
Token | day |
Token ID | 1110 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
smanship | +0.113 |
bush | +0.107 |
inning | +0.101 |
iona | +0.100 |
outage | +0.099 |
Neg logit contributions | |
Tom | -0.060 |
Ben | -0.056 |
their | -0.051 |
his | -0.050 |
Sam | -0.049 |
Token | that |
Token ID | 326 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
smanship | +0.044 |
bush | +0.041 |
outage | +0.041 |
remedy | +0.040 |
pleasures | +0.039 |
Neg logit contributions | |
Tom | -0.022 |
Ben | -0.020 |
Sam | -0.018 |
Rex | -0.017 |
their | -0.017 |
Token | even |
Token ID | 772 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
smanship | +0.055 |
bush | +0.053 |
outage | +0.051 |
iona | +0.050 |
inning | +0.049 |
Neg logit contributions | |
Tom | -0.034 |
Ben | -0.032 |
Sam | -0.028 |
their | -0.027 |
Rex | -0.027 |
Token | though |
Token ID | 996 |
Feature activation | +1.60e-01 |
Pos logit contributions | |
Tom | +0.006 |
Ben | +0.006 |
Sam | +0.005 |
their | +0.005 |
Rex | +0.005 |
Neg logit contributions | |
smanship | -0.007 |
bush | -0.007 |
outage | -0.007 |
iona | -0.006 |
remedy | -0.006 |
Token | his |
Token ID | 465 |
Feature activation | +4.20e+00 |
Pos logit contributions | |
Tom | +0.003 |
Ben | +0.003 |
Sam | +0.002 |
their | +0.002 |
Rex | +0.002 |
Neg logit contributions | |
smanship | -0.006 |
bush | -0.005 |
outage | -0.005 |
inning | -0.005 |
remedy | -0.005 |
Token | uncle |
Token ID | 7711 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
Tom | +0.079 |
Ben | +0.076 |
Sam | +0.066 |
arrest | +0.065 |
Leo | +0.065 |
Neg logit contributions | |
smanship | -0.139 |
outage | -0.131 |
bush | -0.125 |
remedy | -0.125 |
pleasures | -0.122 |
Token | was |
Token ID | 373 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Tom | +0.142 |
Ben | +0.133 |
Sam | +0.119 |
Rex | +0.115 |
arrest | +0.113 |
Neg logit contributions | |
smanship | -0.201 |
outage | -0.188 |
bush | -0.186 |
remedy | -0.179 |
pleasures | -0.176 |
Token | very |
Token ID | 845 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
Tom | +0.027 |
Ben | +0.024 |
their | +0.021 |
Sam | +0.021 |
Rex | +0.020 |
Neg logit contributions | |
smanship | -0.053 |
bush | -0.048 |
occasions | -0.048 |
outage | -0.047 |
First | -0.046 |
Token | intelligent |
Token ID | 12661 |
Feature activation | +7.17e-01 |
Pos logit contributions | |
Tom | +0.026 |
Ben | +0.024 |
Sam | +0.021 |
their | +0.020 |
bye | +0.020 |
Neg logit contributions | |
smanship | -0.045 |
bush | -0.042 |
outage | -0.041 |
occasions | -0.040 |
remedy | -0.040 |
Token | , |
Token ID | 11 |
Feature activation | -5.19e-01 |
Pos logit contributions | |
Tom | +0.011 |
Ben | +0.010 |
Sam | +0.008 |
Rex | +0.008 |
their | +0.008 |
Neg logit contributions | |
smanship | -0.028 |
bush | -0.027 |
outage | -0.026 |
remedy | -0.026 |
First | -0.025 |
Token | he |
Token ID | 339 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
smanship | +0.018 |
outage | +0.017 |
bush | +0.017 |
remedy | +0.016 |
inning | +0.016 |
Neg logit contributions | |
Tom | -0.010 |
Ben | -0.009 |
Sam | -0.008 |
Rex | -0.008 |
their | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -2.64e-01 |
Pos logit contributions | |
Tom | +0.032 |
Ben | +0.030 |
Sam | +0.026 |
arrest | +0.026 |
Rex | +0.026 |
Neg logit contributions | |
smanship | -0.055 |
outage | -0.052 |
bush | -0.051 |
remedy | -0.049 |
pleasures | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | -1.41e-01 |
Pos logit contributions | |
smanship | +0.009 |
outage | +0.008 |
bush | +0.008 |
remedy | +0.008 |
pleasures | +0.008 |
Neg logit contributions | |
Tom | -0.005 |
Ben | -0.005 |
Sam | -0.004 |
Rex | -0.004 |
arrest | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +2.28e-01 |
Pos logit contributions | |
smanship | +0.005 |
outage | +0.005 |
bush | +0.005 |
remedy | +0.005 |
First | +0.005 |
Neg logit contributions | |
Tom | -0.002 |
Ben | -0.002 |
Sam | -0.002 |
arrest | -0.002 |
Rex | -0.002 |
Token | When |
Token ID | 2215 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
Tom | +0.007 |
Ben | +0.006 |
Sam | +0.006 |
their | +0.006 |
arrest | +0.006 |
Neg logit contributions | |
smanship | -0.006 |
outage | -0.005 |
remedy | -0.005 |
bush | -0.005 |
oils | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
Tom | +0.024 |
Ben | +0.023 |
arrest | +0.021 |
Rex | +0.021 |
sw | +0.020 |
Neg logit contributions | |
smanship | -0.035 |
outage | -0.032 |
bush | -0.032 |
remedy | -0.030 |
pleasures | -0.030 |
Token | clown |
Token ID | 25573 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
Ben | +0.010 |
Tom | +0.010 |
Sam | +0.010 |
icks | +0.010 |
arrest | +0.009 |
Neg logit contributions | |
smanship | -0.017 |
occasion | -0.017 |
occasions | -0.016 |
guard | -0.016 |
iest | -0.016 |
Token | left |
Token ID | 1364 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
icks | +0.142 |
ear | +0.138 |
Tom | +0.137 |
Ben | +0.132 |
Their | +0.126 |
Neg logit contributions | |
smanship | -0.161 |
bush | -0.154 |
outage | -0.142 |
chairs | -0.140 |
guard | -0.139 |
Token | , |
Token ID | 11 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
Tom | +0.024 |
Ben | +0.024 |
sw | +0.022 |
arrest | +0.022 |
bye | +0.021 |
Neg logit contributions | |
smanship | -0.049 |
outage | -0.046 |
bush | -0.045 |
remedy | -0.043 |
occasions | -0.042 |
Token | Sarah |
Token ID | 10490 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
smanship | +0.003 |
bush | +0.003 |
outage | +0.003 |
remedy | +0.003 |
pleasures | +0.003 |
Neg logit contributions | |
Tom | -0.002 |
Ben | -0.002 |
arrest | -0.002 |
sw | -0.002 |
Rex | -0.002 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
Tom | +0.013 |
Ben | +0.012 |
Sam | +0.011 |
icks | +0.011 |
Rex | +0.011 |
Neg logit contributions | |
smanship | -0.017 |
bush | -0.016 |
outage | -0.016 |
oils | -0.015 |
remedy | -0.015 |
Token | something |
Token ID | 1223 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
smanship | +0.033 |
outage | +0.031 |
bush | +0.030 |
remedy | +0.029 |
pleasures | +0.029 |
Neg logit contributions | |
Tom | -0.021 |
Ben | -0.019 |
Sam | -0.017 |
Rex | -0.017 |
arrest | -0.016 |
Token | still |
Token ID | 991 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
Tom | +0.033 |
Ben | +0.032 |
Sam | +0.028 |
Rex | +0.027 |
Leo | +0.027 |
Neg logit contributions | |
smanship | -0.049 |
outage | -0.047 |
bush | -0.046 |
remedy | -0.044 |
pleasures | -0.044 |
Token | be |
Token ID | 307 |
Feature activation | +3.59e-01 |
Pos logit contributions | |
Tom | +0.039 |
Ben | +0.036 |
Sam | +0.032 |
Rex | +0.031 |
arrest | +0.031 |
Neg logit contributions | |
smanship | -0.064 |
outage | -0.060 |
bush | -0.060 |
remedy | -0.058 |
pleasures | -0.057 |
Token | there |
Token ID | 612 |
Feature activation | -3.38e-01 |
Pos logit contributions | |
arrest | +0.009 |
Tom | +0.008 |
eg | +0.008 |
Ben | +0.008 |
bye | +0.008 |
Neg logit contributions | |
smanship | -0.008 |
outage | -0.008 |
bush | -0.008 |
inning | -0.008 |
remedy | -0.008 |
Token | when |
Token ID | 618 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
smanship | +0.012 |
outage | +0.011 |
bush | +0.011 |
remedy | +0.011 |
pleasures | +0.011 |
Neg logit contributions | |
Tom | -0.006 |
Ben | -0.006 |
Sam | -0.005 |
Rex | -0.005 |
their | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
Tom | +0.026 |
Ben | +0.025 |
arrest | +0.022 |
Sam | +0.022 |
bye | +0.022 |
Neg logit contributions | |
smanship | -0.039 |
outage | -0.037 |
bush | -0.036 |
remedy | -0.035 |
occasions | -0.034 |
Token | car |
Token ID | 1097 |
Feature activation | +6.33e+00 |
Pos logit contributions | |
Tom | +0.058 |
Ben | +0.053 |
arrest | +0.049 |
Sam | +0.049 |
their | +0.047 |
Neg logit contributions | |
smanship | -0.076 |
outage | -0.071 |
bush | -0.071 |
remedy | -0.070 |
pleasures | -0.069 |
Token | is |
Token ID | 318 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
Tom | +0.142 |
Ben | +0.136 |
Sam | +0.126 |
ear | +0.123 |
arrest | +0.122 |
Neg logit contributions | |
smanship | -0.173 |
outage | -0.165 |
bush | -0.162 |
bars | -0.154 |
occasions | -0.152 |
Token | gone |
Token ID | 3750 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
Tom | +0.055 |
Ben | +0.052 |
arrest | +0.051 |
Sam | +0.047 |
Rex | +0.046 |
Neg logit contributions | |
smanship | -0.072 |
outage | -0.070 |
bush | -0.069 |
remedy | -0.066 |
inning | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
Tom | +0.059 |
Ben | +0.055 |
Sam | +0.049 |
arrest | +0.049 |
Rex | +0.048 |
Neg logit contributions | |
smanship | -0.096 |
outage | -0.091 |
bush | -0.089 |
remedy | -0.086 |
pleasures | -0.085 |
Token | He |
Token ID | 679 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
arrest | +0.029 |
sw | +0.028 |
ked | +0.027 |
Tom | +0.025 |
ear | +0.025 |
Neg logit contributions | |
outage | -0.037 |
First | -0.036 |
smanship | -0.035 |
remedy | -0.034 |
pleasures | -0.034 |
Token | hopes |
Token ID | 7176 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
Tom | +0.025 |
Ben | +0.022 |
Sam | +0.022 |
Dan | +0.020 |
their | +0.019 |
Neg logit contributions | |
smanship | -0.036 |
bush | -0.035 |
remedy | -0.034 |
outage | -0.034 |
pleasures | -0.033 |
Token | His |
Token ID | 2399 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
Tom | +0.020 |
Ben | +0.019 |
arrest | +0.017 |
Sam | +0.017 |
their | +0.016 |
Neg logit contributions | |
smanship | -0.029 |
outage | -0.028 |
bush | -0.028 |
remedy | -0.027 |
pleasures | -0.026 |
Token | name |
Token ID | 1438 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
Tom | +0.037 |
Ben | +0.034 |
Sam | +0.031 |
Rex | +0.029 |
their | +0.029 |
Neg logit contributions | |
smanship | -0.060 |
outage | -0.056 |
bush | -0.056 |
remedy | -0.054 |
pleasures | -0.053 |
Token | is |
Token ID | 318 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
Tom | +0.064 |
Ben | +0.060 |
Sam | +0.055 |
arrest | +0.053 |
Rex | +0.052 |
Neg logit contributions | |
smanship | -0.101 |
outage | -0.095 |
bush | -0.094 |
remedy | -0.090 |
pleasures | -0.089 |
Token | Tom |
Token ID | 4186 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
arrest | +0.013 |
Tom | +0.013 |
Ben | +0.011 |
sw | +0.010 |
ked | +0.010 |
Neg logit contributions | |
smanship | -0.042 |
outage | -0.041 |
bush | -0.041 |
remedy | -0.039 |
oils | -0.039 |
Token | . |
Token ID | 13 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
Tom | +0.012 |
Ben | +0.011 |
Sam | +0.009 |
Rex | +0.009 |
their | +0.009 |
Neg logit contributions | |
smanship | -0.024 |
outage | -0.023 |
bush | -0.023 |
remedy | -0.022 |
pleasures | -0.021 |
Token | Nice |
Token ID | 18460 |
Feature activation | +6.30e+00 |
Pos logit contributions | |
Tom | +0.014 |
arrest | +0.014 |
sw | +0.014 |
Ben | +0.014 |
their | +0.013 |
Neg logit contributions | |
outage | -0.020 |
smanship | -0.020 |
bush | -0.019 |
First | -0.018 |
bars | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
Tom | +0.132 |
Ben | +0.123 |
arrest | +0.122 |
eg | +0.115 |
Sam | +0.115 |
Neg logit contributions | |
outage | -0.171 |
smanship | -0.168 |
bush | -0.162 |
remedy | -0.157 |
occasions | -0.156 |
Token | meet |
Token ID | 1826 |
Feature activation | +3.66e+00 |
Pos logit contributions | |
ked | +0.001 |
mouths | +0.001 |
sed | +0.001 |
eyes | +0.001 |
eg | +0.001 |
Neg logit contributions | |
occasions | -0.001 |
iona | -0.001 |
First | -0.001 |
ock | -0.001 |
occasion | -0.001 |
Token | you |
Token ID | 345 |
Feature activation | -2.07e-01 |
Pos logit contributions | |
arrest | +0.081 |
Tom | +0.079 |
eg | +0.077 |
sw | +0.077 |
Ben | +0.075 |
Neg logit contributions | |
smanship | -0.087 |
occasions | -0.084 |
heart | -0.081 |
bush | -0.080 |
bars | -0.079 |
Token | , |
Token ID | 11 |
Feature activation | +1.82e-01 |
Pos logit contributions | |
smanship | +0.006 |
outage | +0.006 |
bush | +0.006 |
remedy | +0.005 |
pleasures | +0.005 |
Neg logit contributions | |
Tom | -0.004 |
Ben | -0.004 |
arrest | -0.004 |
Sam | -0.004 |
sw | -0.004 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Tom | +0.001 |
arrest | +0.001 |
Ben | +0.001 |
ked | +0.001 |
sw | +0.001 |
Neg logit contributions | |
smanship | -0.007 |
outage | -0.007 |
bush | -0.007 |
remedy | -0.007 |
iona | -0.007 |
Token | did |
Token ID | 750 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
Tom | +0.011 |
Ben | +0.010 |
arrest | +0.010 |
bye | +0.010 |
Sam | +0.009 |
Neg logit contributions | |
smanship | -0.014 |
bush | -0.014 |
outage | -0.013 |
remedy | -0.013 |
oils | -0.013 |
Token | not |
Token ID | 407 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Tom | +0.047 |
Ben | +0.045 |
Sam | +0.039 |
sw | +0.038 |
arrest | +0.038 |
Neg logit contributions | |
smanship | -0.082 |
bush | -0.079 |
outage | -0.079 |
remedy | -0.076 |
pleasures | -0.075 |
Token | know |
Token ID | 760 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
Tom | +0.035 |
Ben | +0.033 |
arrest | +0.033 |
Rex | +0.031 |
bye | +0.030 |
Neg logit contributions | |
outage | -0.042 |
smanship | -0.041 |
bush | -0.038 |
iona | -0.037 |
remedy | -0.037 |
Token | if |
Token ID | 611 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
Tom | +0.044 |
Ben | +0.041 |
arrest | +0.038 |
bye | +0.037 |
Sam | +0.037 |
Neg logit contributions | |
smanship | -0.073 |
outage | -0.069 |
bush | -0.068 |
remedy | -0.065 |
oils | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
Tom | +0.022 |
Ben | +0.020 |
arrest | +0.020 |
bye | +0.019 |
Sam | +0.019 |
Neg logit contributions | |
smanship | -0.021 |
outage | -0.020 |
bush | -0.019 |
remedy | -0.019 |
oils | -0.018 |
Token | lion |
Token ID | 18744 |
Feature activation | +6.30e+00 |
Pos logit contributions | |
Tom | +0.024 |
Ben | +0.022 |
arrest | +0.021 |
their | +0.021 |
Sam | +0.020 |
Neg logit contributions | |
smanship | -0.033 |
outage | -0.032 |
remedy | -0.031 |
bush | -0.030 |
occasions | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
Tom | +0.153 |
Ben | +0.148 |
arrest | +0.137 |
Sam | +0.133 |
bye | +0.133 |
Neg logit contributions | |
smanship | -0.166 |
bush | -0.155 |
outage | -0.155 |
remedy | -0.149 |
oils | -0.141 |
Token | friendly |
Token ID | 8030 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
Tom | +0.055 |
Ben | +0.052 |
arrest | +0.052 |
eg | +0.051 |
bye | +0.048 |
Neg logit contributions | |
smanship | -0.076 |
outage | -0.076 |
bush | -0.072 |
remedy | -0.072 |
pleasures | -0.067 |
Token | or |
Token ID | 393 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Tom | +0.053 |
Ben | +0.050 |
arrest | +0.049 |
eg | +0.045 |
Sam | +0.045 |
Neg logit contributions | |
smanship | -0.086 |
outage | -0.081 |
bush | -0.080 |
remedy | -0.078 |
pleasures | -0.077 |
Token | not |
Token ID | 407 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
Tom | +0.036 |
Ben | +0.033 |
arrest | +0.031 |
Sam | +0.030 |
Rex | +0.029 |
Neg logit contributions | |
smanship | -0.054 |
outage | -0.051 |
bush | -0.051 |
remedy | -0.049 |
pleasures | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Tom | +0.056 |
Ben | +0.053 |
arrest | +0.049 |
Rex | +0.047 |
eg | +0.046 |
Neg logit contributions | |
smanship | -0.086 |
outage | -0.084 |
bush | -0.080 |
remedy | -0.078 |
pleasures | -0.077 |
Token | did |
Token ID | 750 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
arrest | +0.010 |
Tom | +0.009 |
icks | +0.009 |
Jolly | +0.009 |
Ben | +0.009 |
Neg logit contributions | |
smanship | -0.010 |
oils | -0.010 |
outage | -0.009 |
bush | -0.009 |
First | -0.009 |
Token | not |
Token ID | 407 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Tom | +0.055 |
Ben | +0.053 |
sw | +0.049 |
eg | +0.049 |
arrest | +0.048 |
Neg logit contributions | |
smanship | -0.078 |
outage | -0.077 |
bush | -0.076 |
pleasures | -0.074 |
remedy | -0.073 |
Token | understand |
Token ID | 1833 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Tom | +0.038 |
Ben | +0.036 |
Sam | +0.033 |
arrest | +0.032 |
Rex | +0.032 |
Neg logit contributions | |
smanship | -0.050 |
outage | -0.048 |
bush | -0.046 |
remedy | -0.045 |
pleasures | -0.044 |
Token | why |
Token ID | 1521 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
Tom | +0.043 |
arrest | +0.043 |
Ben | +0.041 |
bye | +0.040 |
sw | +0.040 |
Neg logit contributions | |
smanship | -0.043 |
outage | -0.040 |
bush | -0.039 |
remedy | -0.038 |
occasions | -0.037 |
Token | the |
Token ID | 262 |
Feature activation | +2.28e+00 |
Pos logit contributions | |
Tom | +0.016 |
Ben | +0.014 |
arrest | +0.014 |
sw | +0.013 |
bye | +0.013 |
Neg logit contributions | |
smanship | -0.044 |
outage | -0.042 |
bush | -0.041 |
remedy | -0.040 |
oils | -0.039 |
Token | dragon |
Token ID | 10441 |
Feature activation | +6.28e+00 |
Pos logit contributions | |
Tom | +0.051 |
Ben | +0.045 |
Sam | +0.044 |
Dan | +0.043 |
Their | +0.043 |
Neg logit contributions | |
smanship | -0.067 |
outage | -0.064 |
remedy | -0.062 |
bush | -0.061 |
pleasures | -0.060 |
Token | was |
Token ID | 373 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
Tom | +0.161 |
Ben | +0.156 |
arrest | +0.146 |
Sam | +0.143 |
bye | +0.141 |
Neg logit contributions | |
smanship | -0.159 |
outage | -0.148 |
bush | -0.146 |
remedy | -0.139 |
inning | -0.134 |
Token | en |
Token ID | 551 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
Tom | +0.038 |
arrest | +0.037 |
eg | +0.037 |
Ben | +0.036 |
bye | +0.035 |
Neg logit contributions | |
outage | -0.053 |
smanship | -0.051 |
bush | -0.049 |
remedy | -0.048 |
inning | -0.045 |
Token | vious |
Token ID | 1442 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Tom | +0.020 |
Ben | +0.019 |
Rex | +0.017 |
Sam | +0.017 |
arrest | +0.017 |
Neg logit contributions | |
smanship | -0.020 |
outage | -0.018 |
bush | -0.018 |
pleasures | -0.017 |
remedy | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +8.06e-01 |
Pos logit contributions | |
Tom | +0.038 |
Ben | +0.036 |
arrest | +0.034 |
Sam | +0.034 |
Rex | +0.033 |
Neg logit contributions | |
smanship | -0.032 |
outage | -0.030 |
bush | -0.028 |
pleasures | -0.027 |
remedy | -0.026 |
Token | She |
Token ID | 1375 |
Feature activation | +4.82e-01 |
Pos logit contributions | |
Tom | +0.021 |
arrest | +0.020 |
sw | +0.020 |
Ben | +0.020 |
their | +0.019 |
Neg logit contributions | |
smanship | -0.018 |
bush | -0.018 |
outage | -0.018 |
First | -0.017 |
bars | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +7.26e-01 |
Pos logit contributions | |
Tom | +0.035 |
Ben | +0.032 |
arrest | +0.031 |
eg | +0.030 |
Sam | +0.029 |
Neg logit contributions | |
smanship | -0.054 |
outage | -0.052 |
bush | -0.050 |
oils | -0.049 |
remedy | -0.049 |
Token | go |
Token ID | 467 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
Tom | +0.014 |
Ben | +0.013 |
Sam | +0.011 |
arrest | +0.011 |
Rex | +0.011 |
Neg logit contributions | |
smanship | -0.023 |
outage | -0.023 |
bush | -0.022 |
remedy | -0.021 |
occasions | -0.021 |
Token | away |
Token ID | 1497 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
Tom | +0.063 |
Ben | +0.060 |
Sam | +0.054 |
Leo | +0.054 |
Dan | +0.052 |
Neg logit contributions | |
outage | -0.093 |
smanship | -0.091 |
bush | -0.090 |
remedy | -0.083 |
occasions | -0.082 |
Token | and |
Token ID | 290 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Tom | +0.034 |
Ben | +0.032 |
Sam | +0.028 |
arrest | +0.028 |
Rex | +0.027 |
Neg logit contributions | |
smanship | -0.052 |
outage | -0.051 |
bush | -0.049 |
remedy | -0.047 |
pleasures | -0.046 |
Token | never |
Token ID | 1239 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
Tom | +0.028 |
Ben | +0.027 |
Sam | +0.023 |
arrest | +0.023 |
Rex | +0.022 |
Neg logit contributions | |
smanship | -0.048 |
outage | -0.046 |
bush | -0.046 |
remedy | -0.044 |
occasions | -0.043 |
Token | come |
Token ID | 1282 |
Feature activation | +6.18e+00 |
Pos logit contributions | |
Tom | +0.044 |
Ben | +0.041 |
arrest | +0.036 |
Sam | +0.036 |
Rex | +0.036 |
Neg logit contributions | |
smanship | -0.073 |
outage | -0.072 |
bush | -0.070 |
remedy | -0.067 |
pleasures | -0.067 |
Token | back |
Token ID | 736 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
Tom | +0.115 |
Ben | +0.110 |
arrest | +0.106 |
eg | +0.099 |
sw | +0.097 |
Neg logit contributions | |
outage | -0.185 |
bush | -0.184 |
smanship | -0.176 |
pleasures | -0.164 |
inning | -0.164 |
Token | . |
Token ID | 13 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Tom | +0.068 |
Ben | +0.066 |
eg | +0.064 |
arrest | +0.063 |
sw | +0.062 |
Neg logit contributions | |
smanship | -0.083 |
outage | -0.081 |
bush | -0.078 |
occasions | -0.076 |
pleasures | -0.075 |
Token | They |
Token ID | 1119 |
Feature activation | +7.55e-01 |
Pos logit contributions | |
arrest | +0.027 |
sw | +0.024 |
ked | +0.024 |
eg | +0.024 |
X | +0.022 |
Neg logit contributions | |
bush | -0.039 |
outage | -0.038 |
First | -0.038 |
iona | -0.037 |
pleasures | -0.037 |
Token | called |
Token ID | 1444 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
Tom | +0.015 |
Ben | +0.015 |
arrest | +0.014 |
bye | +0.014 |
Sam | +0.013 |
Neg logit contributions | |
smanship | -0.022 |
outage | -0.021 |
bush | -0.020 |
remedy | -0.019 |
First | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
Tom | +0.043 |
Ben | +0.040 |
arrest | +0.037 |
Sam | +0.036 |
sw | +0.034 |
Neg logit contributions | |
smanship | -0.082 |
bush | -0.079 |
outage | -0.078 |
remedy | -0.076 |
iona | -0.075 |
Token | learned |
Token ID | 4499 |
Feature activation | +8.89e-01 |
Pos logit contributions | |
Tom | +0.024 |
Ben | +0.023 |
bye | +0.021 |
Sam | +0.021 |
Leo | +0.020 |
Neg logit contributions | |
smanship | -0.030 |
bush | -0.026 |
outage | -0.026 |
First | -0.025 |
remedy | -0.025 |
Token | that |
Token ID | 326 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
Tom | +0.018 |
Ben | +0.017 |
arrest | +0.015 |
Sam | +0.014 |
Leo | +0.014 |
Neg logit contributions | |
smanship | -0.027 |
outage | -0.027 |
bush | -0.026 |
remedy | -0.025 |
pleasures | -0.024 |
Token | money |
Token ID | 1637 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
smanship | +0.054 |
bush | +0.051 |
outage | +0.050 |
iona | +0.048 |
inning | +0.048 |
Neg logit contributions | |
Tom | -0.035 |
Ben | -0.033 |
Sam | -0.030 |
their | -0.029 |
Rex | -0.029 |
Token | does |
Token ID | 857 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
Tom | +0.037 |
Ben | +0.033 |
Sam | +0.029 |
their | +0.029 |
Rex | +0.028 |
Neg logit contributions | |
smanship | -0.072 |
bush | -0.070 |
outage | -0.068 |
remedy | -0.068 |
iona | -0.067 |
Token | not |
Token ID | 407 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
Tom | +0.026 |
their | +0.023 |
Ben | +0.022 |
Sam | +0.019 |
sw | +0.016 |
Neg logit contributions | |
smanship | -0.099 |
bush | -0.093 |
heart | -0.092 |
remedy | -0.091 |
oils | -0.091 |
Token | come |
Token ID | 1282 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
Tom | +0.070 |
Ben | +0.064 |
Sam | +0.058 |
their | +0.057 |
Rex | +0.054 |
Neg logit contributions | |
smanship | -0.116 |
bush | -0.109 |
outage | -0.107 |
remedy | -0.103 |
oils | -0.102 |
Token | out |
Token ID | 503 |
Feature activation | +3.71e+00 |
Pos logit contributions | |
Tom | +0.136 |
Ben | +0.131 |
arrest | +0.116 |
Leo | +0.115 |
Dan | +0.114 |
Neg logit contributions | |
smanship | -0.175 |
outage | -0.170 |
bush | -0.165 |
pleasures | -0.157 |
inning | -0.154 |
Token | of |
Token ID | 286 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
Tom | +0.089 |
Ben | +0.083 |
Sam | +0.075 |
Leo | +0.074 |
Rex | +0.074 |
Neg logit contributions | |
smanship | -0.105 |
outage | -0.100 |
bush | -0.097 |
pleasures | -0.093 |
remedy | -0.092 |
Token | hats |
Token ID | 23910 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
Tom | +0.021 |
Ben | +0.020 |
bye | +0.019 |
eg | +0.018 |
Leo | +0.017 |
Neg logit contributions | |
smanship | -0.038 |
outage | -0.035 |
occasions | -0.034 |
remedy | -0.034 |
bush | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | +1.17e+00 |
Pos logit contributions | |
Tom | +0.042 |
Ben | +0.039 |
Sam | +0.035 |
Rex | +0.034 |
arrest | +0.034 |
Neg logit contributions | |
smanship | -0.081 |
outage | -0.076 |
bush | -0.075 |
remedy | -0.072 |
pleasures | -0.071 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
sw | +0.023 |
arrest | +0.023 |
ked | +0.022 |
bye | +0.022 |
ear | +0.022 |
Neg logit contributions | |
outage | -0.031 |
First | -0.030 |
smanship | -0.030 |
bush | -0.028 |
Sometimes | -0.028 |
Token | for |
Token ID | 329 |
Feature activation | +2.05e-01 |
Pos logit contributions | |
Tom | +0.018 |
Ben | +0.017 |
eg | +0.015 |
arrest | +0.015 |
Rex | +0.015 |
Neg logit contributions | |
smanship | -0.031 |
outage | -0.029 |
bush | -0.029 |
remedy | -0.029 |
occasions | -0.028 |
Token | helping |
Token ID | 5742 |
Feature activation | -3.12e-02 |
Pos logit contributions | |
Tom | +0.004 |
Ben | +0.004 |
Sam | +0.004 |
arrest | +0.003 |
Rex | +0.003 |
Neg logit contributions | |
smanship | -0.006 |
outage | -0.006 |
bush | -0.006 |
remedy | -0.006 |
occasions | -0.006 |
Token | them |
Token ID | 606 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
smanship | +0.001 |
outage | +0.001 |
bush | +0.001 |
remedy | +0.001 |
occasions | +0.001 |
Neg logit contributions | |
Tom | -0.001 |
Ben | -0.001 |
arrest | -0.000 |
Sam | -0.000 |
bye | -0.000 |
Token | when |
Token ID | 618 |
Feature activation | +5.27e-01 |
Pos logit contributions | |
Tom | +0.053 |
Ben | +0.049 |
Sam | +0.044 |
Rex | +0.043 |
arrest | +0.042 |
Neg logit contributions | |
smanship | -0.078 |
outage | -0.074 |
bush | -0.073 |
remedy | -0.070 |
pleasures | -0.069 |
Token | the |
Token ID | 262 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
Tom | +0.010 |
Ben | +0.009 |
Sam | +0.008 |
arrest | +0.008 |
Rex | +0.008 |
Neg logit contributions | |
smanship | -0.017 |
outage | -0.016 |
bush | -0.016 |
remedy | -0.015 |
pleasures | -0.015 |
Token | crab |
Token ID | 32202 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
Tom | +0.044 |
Ben | +0.040 |
Sam | +0.036 |
Rex | +0.034 |
their | +0.034 |
Neg logit contributions | |
smanship | -0.074 |
outage | -0.070 |
bush | -0.069 |
remedy | -0.068 |
pleasures | -0.067 |
Token | was |
Token ID | 373 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
Tom | +0.143 |
Ben | +0.133 |
arrest | +0.124 |
ear | +0.123 |
icks | +0.120 |
Neg logit contributions | |
smanship | -0.162 |
bush | -0.157 |
outage | -0.151 |
remedy | -0.147 |
occasions | -0.138 |
Token | so |
Token ID | 523 |
Feature activation | -2.97e-01 |
Pos logit contributions | |
Tom | +0.024 |
Ben | +0.022 |
Sam | +0.020 |
arrest | +0.020 |
Rex | +0.020 |
Neg logit contributions | |
smanship | -0.034 |
outage | -0.033 |
bush | -0.032 |
remedy | -0.031 |
pleasures | -0.030 |
Token | mean |
Token ID | 1612 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
smanship | +0.009 |
outage | +0.009 |
bush | +0.009 |
remedy | +0.008 |
pleasures | +0.008 |
Neg logit contributions | |
Tom | -0.006 |
Ben | -0.006 |
Sam | -0.005 |
arrest | -0.005 |
Rex | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Tom | +0.033 |
Ben | +0.031 |
Sam | +0.027 |
Rex | +0.026 |
their | +0.025 |
Neg logit contributions | |
smanship | -0.066 |
outage | -0.062 |
bush | -0.061 |
remedy | -0.059 |
pleasures | -0.058 |
Token | They |
Token ID | 1119 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
Ben | +0.002 |
arrest | +0.002 |
Tom | +0.002 |
ear | +0.002 |
sw | +0.002 |
Neg logit contributions | |
smanship | -0.005 |
bush | -0.005 |
First | -0.005 |
outage | -0.005 |
pleasures | -0.005 |
Token | Now |
Token ID | 2735 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
Tom | +0.016 |
Ben | +0.015 |
their | +0.014 |
sw | +0.013 |
arrest | +0.013 |
Neg logit contributions | |
smanship | -0.023 |
outage | -0.023 |
bush | -0.022 |
remedy | -0.021 |
oils | -0.021 |
Token | go |
Token ID | 467 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
Tom | +0.014 |
Ben | +0.013 |
arrest | +0.012 |
Their | +0.012 |
Sam | +0.012 |
Neg logit contributions | |
smanship | -0.021 |
bush | -0.020 |
outage | -0.020 |
remedy | -0.020 |
pleasures | -0.019 |
Token | away |
Token ID | 1497 |
Feature activation | +1.75e+00 |
Pos logit contributions | |
Tom | +0.065 |
Ben | +0.061 |
Sam | +0.053 |
Leo | +0.052 |
Rex | +0.051 |
Neg logit contributions | |
smanship | -0.111 |
outage | -0.105 |
bush | -0.105 |
remedy | -0.100 |
occasions | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
Tom | +0.031 |
Ben | +0.029 |
Sam | +0.025 |
their | +0.024 |
Rex | +0.024 |
Neg logit contributions | |
smanship | -0.063 |
outage | -0.059 |
bush | -0.059 |
remedy | -0.057 |
oils | -0.056 |
Token | never |
Token ID | 1239 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
Tom | +0.033 |
Ben | +0.030 |
Sam | +0.027 |
Rex | +0.026 |
arrest | +0.026 |
Neg logit contributions | |
smanship | -0.053 |
outage | -0.050 |
bush | -0.050 |
remedy | -0.048 |
pleasures | -0.047 |
Token | come |
Token ID | 1282 |
Feature activation | +6.12e+00 |
Pos logit contributions | |
Tom | +0.043 |
Ben | +0.040 |
Sam | +0.035 |
Rex | +0.034 |
arrest | +0.033 |
Neg logit contributions | |
smanship | -0.079 |
outage | -0.076 |
bush | -0.074 |
remedy | -0.072 |
pleasures | -0.071 |
Token | back |
Token ID | 736 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
Tom | +0.109 |
Ben | +0.105 |
arrest | +0.096 |
Dan | +0.092 |
sw | +0.092 |
Neg logit contributions | |
bush | -0.181 |
outage | -0.178 |
smanship | -0.174 |
inning | -0.164 |
remedy | -0.162 |
Token | ." |
Token ID | 526 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
Tom | +0.069 |
Ben | +0.066 |
Sam | +0.060 |
arrest | +0.060 |
sw | +0.060 |
Neg logit contributions | |
smanship | -0.077 |
bush | -0.074 |
outage | -0.074 |
remedy | -0.070 |
pleasures | -0.069 |
Token |
|
Token ID | 198 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
smanship | +0.015 |
First | +0.014 |
bush | +0.014 |
outage | +0.014 |
things | +0.013 |
Neg logit contributions | |
sw | -0.011 |
arrest | -0.011 |
ked | -0.010 |
ear | -0.010 |
bye | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +4.83e-01 |
Pos logit contributions | |
Tom | +0.000 |
arrest | +0.000 |
Ben | +0.000 |
ear | +0.000 |
bye | +0.000 |
Neg logit contributions | |
smanship | -0.000 |
outage | -0.000 |
bush | -0.000 |
First | -0.000 |
iona | -0.000 |
Token | Sam |
Token ID | 16305 |
Feature activation | -1.19e-01 |
Pos logit contributions | |
Tom | +0.011 |
Ben | +0.011 |
ear | +0.010 |
bye | +0.009 |
arrest | +0.009 |
Neg logit contributions | |
smanship | -0.014 |
outage | -0.013 |
bush | -0.013 |
First | -0.012 |
remedy | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | +8.42e-01 |
Pos logit contributions | |
Tom | +0.043 |
Ben | +0.042 |
arrest | +0.037 |
Sam | +0.037 |
Rex | +0.036 |
Neg logit contributions | |
smanship | -0.058 |
outage | -0.054 |
bush | -0.053 |
pleasures | -0.051 |
First | -0.051 |
Token | drove |
Token ID | 10357 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
Tom | +0.018 |
Ben | +0.017 |
icks | +0.016 |
arrest | +0.016 |
eg | +0.015 |
Neg logit contributions | |
smanship | -0.024 |
outage | -0.022 |
bush | -0.022 |
First | -0.021 |
oils | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -5.36e-01 |
Pos logit contributions | |
Tom | +0.049 |
Ben | +0.047 |
Sam | +0.042 |
arrest | +0.042 |
Rex | +0.041 |
Neg logit contributions | |
smanship | -0.065 |
outage | -0.060 |
bush | -0.060 |
pleasures | -0.057 |
remedy | -0.057 |
Token | until |
Token ID | 1566 |
Feature activation | -9.95e-02 |
Pos logit contributions | |
smanship | +0.014 |
bush | +0.013 |
outage | +0.012 |
remedy | +0.012 |
First | +0.012 |
Neg logit contributions | |
Tom | -0.013 |
Ben | -0.013 |
Sam | -0.012 |
icks | -0.012 |
bye | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
smanship | +0.003 |
bush | +0.002 |
outage | +0.002 |
ner | +0.002 |
oils | +0.002 |
Neg logit contributions | |
icks | -0.002 |
eg | -0.002 |
Ben | -0.002 |
Tom | -0.002 |
arrest | -0.002 |
Token | van |
Token ID | 5719 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
Tom | +0.030 |
Ben | +0.029 |
Leo | +0.027 |
icks | +0.026 |
Sam | +0.026 |
Neg logit contributions | |
smanship | -0.038 |
bush | -0.034 |
pleasures | -0.034 |
outage | -0.033 |
remedy | -0.033 |
Token | stopped |
Token ID | 5025 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
Ben | +0.137 |
Tom | +0.136 |
Sam | +0.121 |
Leo | +0.121 |
icks | +0.118 |
Neg logit contributions | |
smanship | -0.177 |
bush | -0.168 |
outage | -0.161 |
bars | -0.154 |
remedy | -0.151 |
Token | by |
Token ID | 416 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
Tom | +0.063 |
Ben | +0.058 |
Sam | +0.051 |
Rex | +0.050 |
arrest | +0.050 |
Neg logit contributions | |
smanship | -0.108 |
outage | -0.101 |
bush | -0.100 |
remedy | -0.096 |
pleasures | -0.094 |
Token | a |
Token ID | 257 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
Tom | +0.023 |
Ben | +0.023 |
eg | +0.021 |
bye | +0.020 |
arrest | +0.020 |
Neg logit contributions | |
smanship | -0.036 |
bush | -0.033 |
outage | -0.033 |
remedy | -0.032 |
pleasures | -0.032 |
Token | big |
Token ID | 1263 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
Tom | +0.072 |
Ben | +0.067 |
Sam | +0.060 |
Rex | +0.058 |
their | +0.058 |
Neg logit contributions | |
smanship | -0.104 |
outage | -0.097 |
bush | -0.096 |
remedy | -0.093 |
pleasures | -0.091 |
Token | , |
Token ID | 11 |
Feature activation | -6.87e-01 |
Pos logit contributions | |
Tom | +0.069 |
Ben | +0.065 |
Sam | +0.059 |
Rex | +0.058 |
arrest | +0.057 |
Neg logit contributions | |
smanship | -0.082 |
outage | -0.076 |
bush | -0.075 |
remedy | -0.072 |
pleasures | -0.070 |
Token | ap |
Token ID | 499 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
Tom | +0.028 |
Ben | +0.027 |
arrest | +0.025 |
Sam | +0.025 |
sw | +0.025 |
Neg logit contributions | |
smanship | -0.024 |
outage | -0.022 |
bush | -0.022 |
inning | -0.021 |
pleasures | -0.021 |
Token | and |
Token ID | 290 |
Feature activation | +4.96e-01 |
Pos logit contributions | |
arrest | +0.013 |
Tom | +0.012 |
Ben | +0.011 |
eg | +0.011 |
Jolly | +0.010 |
Neg logit contributions | |
outage | -0.022 |
smanship | -0.021 |
pleasures | -0.021 |
bush | -0.020 |
oils | -0.020 |
Token | cheer |
Token ID | 14042 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
Tom | +0.012 |
Ben | +0.011 |
Sam | +0.010 |
their | +0.010 |
Rex | +0.010 |
Neg logit contributions | |
smanship | -0.015 |
outage | -0.014 |
bush | -0.014 |
remedy | -0.013 |
inning | -0.013 |
Token | when |
Token ID | 618 |
Feature activation | +9.71e-01 |
Pos logit contributions | |
Tom | +0.046 |
arrest | +0.044 |
Ben | +0.043 |
Sam | +0.040 |
sw | +0.039 |
Neg logit contributions | |
smanship | -0.063 |
outage | -0.059 |
pleasures | -0.058 |
bush | -0.057 |
inning | -0.057 |
Token | their |
Token ID | 511 |
Feature activation | +4.04e+00 |
Pos logit contributions | |
Tom | +0.016 |
Ben | +0.015 |
Sam | +0.012 |
Rex | +0.012 |
their | +0.012 |
Neg logit contributions | |
smanship | -0.036 |
outage | -0.034 |
bush | -0.034 |
remedy | -0.033 |
pleasures | -0.032 |
Token | team |
Token ID | 1074 |
Feature activation | +6.07e+00 |
Pos logit contributions | |
Tom | +0.061 |
Ben | +0.055 |
Sam | +0.047 |
arrest | +0.045 |
Leo | +0.044 |
Neg logit contributions | |
smanship | -0.146 |
outage | -0.143 |
bush | -0.137 |
pleasures | -0.135 |
remedy | -0.135 |
Token | scores |
Token ID | 8198 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
Tom | +0.114 |
Ben | +0.105 |
Sam | +0.093 |
Rex | +0.089 |
arrest | +0.088 |
Neg logit contributions | |
smanship | -0.205 |
outage | -0.194 |
bush | -0.192 |
remedy | -0.184 |
pleasures | -0.182 |
Token | a |
Token ID | 257 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Tom | +0.060 |
Ben | +0.055 |
Sam | +0.049 |
Rex | +0.047 |
arrest | +0.047 |
Neg logit contributions | |
smanship | -0.109 |
outage | -0.104 |
bush | -0.102 |
pleasures | -0.098 |
remedy | -0.098 |
Token | goal |
Token ID | 3061 |
Feature activation | +7.48e-01 |
Pos logit contributions | |
Tom | +0.036 |
Ben | +0.034 |
Sam | +0.031 |
their | +0.030 |
Rex | +0.029 |
Neg logit contributions | |
smanship | -0.054 |
bush | -0.050 |
outage | -0.050 |
remedy | -0.048 |
pleasures | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
Tom | +0.012 |
Ben | +0.011 |
Sam | +0.009 |
their | +0.009 |
Rex | +0.008 |
Neg logit contributions | |
smanship | -0.029 |
bush | -0.027 |
remedy | -0.027 |
outage | -0.026 |
oils | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
arrest | +0.012 |
Tom | +0.012 |
sw | +0.011 |
Ben | +0.011 |
ked | +0.010 |
Neg logit contributions | |
outage | -0.023 |
smanship | -0.022 |
First | -0.022 |
bush | -0.022 |
oils | -0.021 |
Token | together |
Token ID | 1978 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
smanship | +0.032 |
outage | +0.030 |
bush | +0.030 |
remedy | +0.029 |
oils | +0.028 |
Neg logit contributions | |
Tom | -0.023 |
Ben | -0.021 |
Sam | -0.020 |
their | -0.020 |
Rex | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -2.48e-02 |
Pos logit contributions | |
smanship | +0.004 |
bush | +0.003 |
outage | +0.003 |
occasions | +0.003 |
remedy | +0.003 |
Neg logit contributions | |
Tom | -0.002 |
Ben | -0.002 |
bye | -0.002 |
Sam | -0.002 |
Rex | -0.002 |
Token | And |
Token ID | 843 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
smanship | +0.001 |
bush | +0.001 |
First | +0.001 |
outage | +0.001 |
pleasures | +0.001 |
Neg logit contributions | |
Tom | -0.000 |
sw | -0.000 |
ked | -0.000 |
arrest | -0.000 |
ear | -0.000 |
Token | whenever |
Token ID | 8797 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
Tom | +0.021 |
arrest | +0.021 |
Ben | +0.020 |
icks | +0.019 |
ear | +0.019 |
Neg logit contributions | |
smanship | -0.020 |
bush | -0.018 |
outage | -0.018 |
remedy | -0.017 |
pleasures | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Tom | +0.043 |
icks | +0.041 |
eg | +0.040 |
ked | +0.039 |
Ben | +0.039 |
Neg logit contributions | |
smanship | -0.084 |
outage | -0.077 |
pleasures | -0.076 |
bush | -0.076 |
remedy | -0.076 |
Token | sailor |
Token ID | 43272 |
Feature activation | +6.05e+00 |
Pos logit contributions | |
Tom | +0.035 |
Ben | +0.030 |
their | +0.029 |
Their | +0.029 |
Sam | +0.028 |
Neg logit contributions | |
smanship | -0.055 |
remedy | -0.050 |
bush | -0.050 |
outage | -0.050 |
pleasures | -0.049 |
Token | felt |
Token ID | 2936 |
Feature activation | +7.19e-01 |
Pos logit contributions | |
Tom | +0.132 |
Ben | +0.123 |
Sam | +0.111 |
Rex | +0.108 |
their | +0.107 |
Neg logit contributions | |
smanship | -0.186 |
bush | -0.173 |
outage | -0.172 |
remedy | -0.166 |
pleasures | -0.160 |
Token | hungry |
Token ID | 14720 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
Tom | +0.013 |
Ben | +0.012 |
Sam | +0.010 |
their | +0.010 |
sw | +0.009 |
Neg logit contributions | |
smanship | -0.027 |
outage | -0.025 |
bush | -0.024 |
occasions | -0.024 |
remedy | -0.023 |
Token | , |
Token ID | 11 |
Feature activation | -8.68e-01 |
Pos logit contributions | |
Tom | +0.055 |
Ben | +0.050 |
Sam | +0.044 |
Rex | +0.041 |
their | +0.041 |
Neg logit contributions | |
smanship | -0.113 |
outage | -0.107 |
bush | -0.106 |
remedy | -0.103 |
pleasures | -0.101 |
Token | he |
Token ID | 339 |
Feature activation | +3.05e-01 |
Pos logit contributions | |
smanship | +0.029 |
outage | +0.027 |
bush | +0.027 |
remedy | +0.026 |
pleasures | +0.025 |
Neg logit contributions | |
Tom | -0.017 |
Ben | -0.015 |
Sam | -0.014 |
arrest | -0.013 |
Rex | -0.013 |
Token | knew |
Token ID | 2993 |
Feature activation | +6.66e-01 |
Pos logit contributions | |
Tom | +0.008 |
Ben | +0.008 |
Sam | +0.007 |
Rex | +0.007 |
sw | +0.007 |
Neg logit contributions | |
smanship | -0.008 |
outage | -0.008 |
bush | -0.008 |
remedy | -0.007 |
pleasures | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
arrest | +0.072 |
Tom | +0.067 |
eg | +0.063 |
Dan | +0.063 |
Ben | +0.061 |
Neg logit contributions | |
smanship | -0.076 |
outage | -0.072 |
inning | -0.072 |
bush | -0.071 |
First | -0.071 |
Token | cl |
Token ID | 537 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
Tom | +0.008 |
Ben | +0.007 |
Sam | +0.006 |
arrest | +0.006 |
Rex | +0.006 |
Neg logit contributions | |
smanship | -0.014 |
outage | -0.013 |
bush | -0.013 |
remedy | -0.013 |
oils | -0.012 |
Token | ap |
Token ID | 499 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
Tom | +0.026 |
arrest | +0.025 |
Ben | +0.025 |
sw | +0.025 |
Sam | +0.023 |
Neg logit contributions | |
smanship | -0.018 |
outage | -0.017 |
bush | -0.017 |
inning | -0.016 |
pleasures | -0.016 |
Token | when |
Token ID | 618 |
Feature activation | +7.16e-01 |
Pos logit contributions | |
arrest | +0.011 |
Tom | +0.010 |
eg | +0.009 |
Ben | +0.009 |
sw | +0.008 |
Neg logit contributions | |
pleasures | -0.015 |
outage | -0.015 |
smanship | -0.015 |
occasions | -0.014 |
oils | -0.014 |
Token | the |
Token ID | 262 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
Tom | +0.012 |
Ben | +0.011 |
arrest | +0.010 |
Sam | +0.010 |
Rex | +0.010 |
Neg logit contributions | |
smanship | -0.025 |
outage | -0.023 |
bush | -0.023 |
remedy | -0.022 |
pleasures | -0.022 |
Token | princess |
Token ID | 21752 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
Tom | +0.043 |
Ben | +0.040 |
Sam | +0.038 |
Dan | +0.038 |
arrest | +0.037 |
Neg logit contributions | |
smanship | -0.051 |
outage | -0.048 |
oils | -0.045 |
remedy | -0.045 |
bush | -0.045 |
Token | escapes |
Token ID | 32695 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
Tom | +0.111 |
Ben | +0.098 |
Sam | +0.095 |
bye | +0.093 |
Their | +0.092 |
Neg logit contributions | |
smanship | -0.180 |
outage | -0.173 |
bush | -0.169 |
occasions | -0.165 |
oils | -0.160 |
Token | from |
Token ID | 422 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
Tom | +0.088 |
arrest | +0.087 |
Ben | +0.081 |
ear | +0.078 |
bye | +0.077 |
Neg logit contributions | |
outage | -0.106 |
smanship | -0.103 |
bush | -0.099 |
heart | -0.091 |
occasions | -0.090 |
Token | the |
Token ID | 262 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
eg | +0.043 |
Tom | +0.041 |
bye | +0.040 |
arrest | +0.039 |
icks | +0.039 |
Neg logit contributions | |
smanship | -0.098 |
outage | -0.092 |
remedy | -0.089 |
bush | -0.089 |
oils | -0.089 |
Token | dragon |
Token ID | 10441 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
Tom | +0.042 |
Ben | +0.039 |
Sam | +0.038 |
Dan | +0.037 |
arrest | +0.036 |
Neg logit contributions | |
smanship | -0.041 |
outage | -0.038 |
bush | -0.036 |
remedy | -0.035 |
occasions | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | +8.65e-01 |
Pos logit contributions | |
Tom | +0.135 |
Ben | +0.123 |
bye | +0.119 |
eg | +0.116 |
Sam | +0.115 |
Neg logit contributions | |
outage | -0.154 |
smanship | -0.151 |
bush | -0.149 |
occasions | -0.138 |
remedy | -0.132 |
Token | , |
Token ID | 11 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
Tom | +0.033 |
Ben | +0.031 |
bye | +0.031 |
Sam | +0.030 |
ear | +0.030 |
Neg logit contributions | |
smanship | -0.042 |
outage | -0.042 |
bush | -0.039 |
remedy | -0.037 |
pleasures | -0.037 |
Token | no |
Token ID | 645 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
Tom | +0.026 |
eg | +0.025 |
Ben | +0.024 |
bye | +0.024 |
icks | +0.023 |
Neg logit contributions | |
outage | -0.049 |
smanship | -0.048 |
bush | -0.046 |
pleasures | -0.044 |
remedy | -0.044 |
Token | water |
Token ID | 1660 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
Tom | +0.036 |
Ben | +0.034 |
Sam | +0.031 |
Rex | +0.030 |
Leo | +0.030 |
Neg logit contributions | |
smanship | -0.052 |
outage | -0.048 |
bush | -0.047 |
remedy | -0.046 |
pleasures | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
Tom | +0.049 |
Ben | +0.047 |
bye | +0.046 |
Sam | +0.045 |
Leo | +0.045 |
Neg logit contributions | |
smanship | -0.060 |
outage | -0.060 |
bush | -0.058 |
guard | -0.054 |
pleasures | -0.054 |
Token | no |
Token ID | 645 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
Tom | +0.030 |
eg | +0.028 |
Ben | +0.027 |
bye | +0.026 |
arrest | +0.025 |
Neg logit contributions | |
outage | -0.054 |
smanship | -0.053 |
bush | -0.051 |
pleasures | -0.050 |
bars | -0.049 |
Token | ship |
Token ID | 4074 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
Tom | +0.038 |
Ben | +0.036 |
Sam | +0.032 |
Rex | +0.031 |
arrest | +0.031 |
Neg logit contributions | |
smanship | -0.055 |
outage | -0.052 |
bush | -0.050 |
remedy | -0.049 |
pleasures | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
Ben | +0.125 |
Tom | +0.123 |
ear | +0.122 |
Dan | +0.118 |
Sam | +0.117 |
Neg logit contributions | |
outage | -0.155 |
smanship | -0.152 |
bush | -0.140 |
bars | -0.136 |
pleasures | -0.135 |
Token | no |
Token ID | 645 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
Tom | +0.036 |
eg | +0.034 |
Ben | +0.033 |
bye | +0.031 |
Jolly | +0.031 |
Neg logit contributions | |
outage | -0.067 |
smanship | -0.063 |
bush | -0.063 |
pleasures | -0.060 |
bars | -0.060 |
Token | treasure |
Token ID | 14068 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
Tom | +0.040 |
Ben | +0.038 |
Sam | +0.034 |
Rex | +0.033 |
arrest | +0.033 |
Neg logit contributions | |
smanship | -0.060 |
outage | -0.056 |
bush | -0.054 |
remedy | -0.054 |
pleasures | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
Tom | +0.097 |
Ben | +0.093 |
Their | +0.089 |
Sam | +0.089 |
bye | +0.087 |
Neg logit contributions | |
smanship | -0.124 |
outage | -0.120 |
bush | -0.112 |
occasions | -0.111 |
pleasures | -0.110 |
Token | They |
Token ID | 1119 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
sw | +0.046 |
arrest | +0.045 |
cor | +0.043 |
bye | +0.043 |
ked | +0.042 |
Neg logit contributions | |
outage | -0.052 |
First | -0.050 |
things | -0.049 |
Sometimes | -0.047 |
smanship | -0.047 |
Token | more |
Token ID | 517 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
outage | +0.037 |
bush | +0.036 |
smanship | +0.035 |
iona | +0.034 |
heart | +0.033 |
Neg logit contributions | |
Tom | -0.030 |
Ben | -0.027 |
their | -0.026 |
sw | -0.026 |
Sam | -0.026 |
Token | sand |
Token ID | 6450 |
Feature activation | +7.54e-01 |
Pos logit contributions | |
smanship | +0.065 |
bush | +0.061 |
outage | +0.060 |
remedy | +0.058 |
iona | +0.056 |
Neg logit contributions | |
Tom | -0.049 |
Ben | -0.046 |
Sam | -0.042 |
their | -0.042 |
sw | -0.040 |
Token | together |
Token ID | 1978 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
Tom | +0.017 |
Ben | +0.017 |
arrest | +0.015 |
bye | +0.015 |
Sam | +0.015 |
Neg logit contributions | |
smanship | -0.021 |
outage | -0.020 |
bush | -0.020 |
occasions | -0.018 |
pleasures | -0.018 |
Token | until |
Token ID | 1566 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
Tom | +0.006 |
Ben | +0.006 |
Sam | +0.005 |
arrest | +0.005 |
Rex | +0.005 |
Neg logit contributions | |
smanship | -0.011 |
outage | -0.010 |
bush | -0.010 |
remedy | -0.010 |
pleasures | -0.010 |
Token | their |
Token ID | 511 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
eg | +0.003 |
Tom | +0.003 |
Ben | +0.003 |
arrest | +0.003 |
icks | +0.003 |
Neg logit contributions | |
smanship | -0.005 |
bush | -0.005 |
remedy | -0.005 |
outage | -0.005 |
oils | -0.004 |
Token | castle |
Token ID | 16669 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
Tom | +0.104 |
Ben | +0.097 |
Sam | +0.089 |
Rex | +0.086 |
their | +0.083 |
Neg logit contributions | |
smanship | -0.134 |
bush | -0.125 |
outage | -0.124 |
remedy | -0.121 |
pleasures | -0.119 |
Token | was |
Token ID | 373 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Tom | +0.141 |
Ben | +0.133 |
Sam | +0.120 |
Rex | +0.117 |
arrest | +0.115 |
Neg logit contributions | |
smanship | -0.176 |
outage | -0.164 |
bush | -0.163 |
remedy | -0.155 |
pleasures | -0.152 |
Token | finished |
Token ID | 5201 |
Feature activation | -8.84e-02 |
Pos logit contributions | |
Tom | +0.029 |
Ben | +0.027 |
Sam | +0.024 |
their | +0.024 |
sw | +0.022 |
Neg logit contributions | |
smanship | -0.047 |
outage | -0.044 |
bush | -0.043 |
remedy | -0.042 |
occasions | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -1.77e-01 |
Pos logit contributions | |
smanship | +0.003 |
outage | +0.003 |
bush | +0.003 |
remedy | +0.003 |
pleasures | +0.003 |
Neg logit contributions | |
Tom | -0.002 |
Ben | -0.001 |
Sam | -0.001 |
their | -0.001 |
Rex | -0.001 |
Token | |
Token ID | 220 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
smanship | +0.006 |
bush | +0.006 |
outage | +0.006 |
remedy | +0.005 |
First | +0.005 |
Neg logit contributions | |
Tom | -0.003 |
Ben | -0.003 |
Sam | -0.003 |
arrest | -0.003 |
Rex | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
smanship | +0.052 |
outage | +0.049 |
bush | +0.049 |
remedy | +0.047 |
First | +0.047 |
Neg logit contributions | |
Tom | -0.023 |
Ben | -0.021 |
Sam | -0.018 |
arrest | -0.018 |
bye | -0.017 |
Token | is |
Token ID | 318 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
Tom | +0.090 |
Their | +0.086 |
Ben | +0.086 |
Dan | +0.086 |
Sam | +0.081 |
Neg logit contributions | |
bush | -0.088 |
remedy | -0.085 |
smanship | -0.085 |
outage | -0.081 |
place | -0.075 |
Token | deaf |
Token ID | 21815 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
eg | +0.018 |
arrest | +0.018 |
Tom | +0.017 |
Dan | +0.017 |
Ben | +0.016 |
Neg logit contributions | |
remedy | -0.021 |
outage | -0.021 |
bush | -0.020 |
smanship | -0.020 |
oils | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +8.40e-01 |
Pos logit contributions | |
Tom | +0.021 |
Ben | +0.019 |
Sam | +0.017 |
Rex | +0.016 |
Leo | +0.015 |
Neg logit contributions | |
smanship | -0.040 |
bush | -0.038 |
outage | -0.037 |
remedy | -0.036 |
First | -0.036 |
Token | He |
Token ID | 679 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Tom | +0.016 |
sw | +0.016 |
arrest | +0.016 |
their | +0.015 |
Ben | +0.015 |
Neg logit contributions | |
outage | -0.023 |
smanship | -0.022 |
bush | -0.021 |
bars | -0.021 |
remedy | -0.021 |
Token | cannot |
Token ID | 2314 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
Tom | +0.029 |
Ben | +0.027 |
their | +0.026 |
Dan | +0.026 |
Sam | +0.025 |
Neg logit contributions | |
smanship | -0.031 |
outage | -0.029 |
bush | -0.029 |
remedy | -0.028 |
oils | -0.027 |
Token | hear |
Token ID | 3285 |
Feature activation | +5.98e+00 |
Pos logit contributions | |
Tom | +0.054 |
Ben | +0.050 |
Sam | +0.045 |
their | +0.043 |
Dan | +0.043 |
Neg logit contributions | |
outage | -0.085 |
smanship | -0.084 |
bush | -0.084 |
remedy | -0.081 |
iona | -0.077 |
Token | you |
Token ID | 345 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
sw | +0.108 |
ked | +0.105 |
Tom | +0.104 |
eg | +0.103 |
arrest | +0.103 |
Neg logit contributions | |
outage | -0.158 |
occasions | -0.155 |
heart | -0.153 |
chairs | -0.152 |
smanship | -0.151 |
Token | . |
Token ID | 13 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
Tom | +0.028 |
Ben | +0.027 |
arrest | +0.024 |
Sam | +0.024 |
sw | +0.024 |
Neg logit contributions | |
smanship | -0.035 |
outage | -0.035 |
bush | -0.034 |
remedy | -0.032 |
First | -0.031 |
Token | He |
Token ID | 679 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
Tom | +0.018 |
Ben | +0.017 |
sw | +0.017 |
arrest | +0.017 |
their | +0.016 |
Neg logit contributions | |
outage | -0.028 |
smanship | -0.028 |
bush | -0.027 |
remedy | -0.027 |
oils | -0.026 |
Token | might |
Token ID | 1244 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
Tom | +0.041 |
Ben | +0.039 |
Dan | +0.037 |
Sam | +0.036 |
their | +0.036 |
Neg logit contributions | |
smanship | -0.042 |
outage | -0.040 |
bush | -0.040 |
remedy | -0.039 |
chairs | -0.037 |
Token | be |
Token ID | 307 |
Feature activation | +8.33e-01 |
Pos logit contributions | |
Tom | +0.030 |
Ben | +0.028 |
Dan | +0.026 |
Sam | +0.026 |
ked | +0.026 |
Neg logit contributions | |
outage | -0.041 |
remedy | -0.038 |
smanship | -0.038 |
bush | -0.038 |
pleasures | -0.036 |
Token | of |
Token ID | 286 |
Feature activation | -4.20e-02 |
Pos logit contributions | |
Tom | +0.046 |
arrest | +0.045 |
Ben | +0.044 |
eg | +0.043 |
bye | +0.042 |
Neg logit contributions | |
smanship | -0.028 |
outage | -0.027 |
bush | -0.026 |
bul | -0.024 |
ions | -0.024 |
Token | it |
Token ID | 340 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
smanship | +0.001 |
ions | +0.001 |
oils | +0.001 |
remedy | +0.001 |
bush | +0.001 |
Neg logit contributions | |
eg | -0.001 |
bye | -0.001 |
arrest | -0.001 |
icks | -0.000 |
realizes | -0.000 |
Token | and |
Token ID | 290 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
smanship | +0.022 |
bush | +0.021 |
outage | +0.021 |
remedy | +0.020 |
inning | +0.020 |
Neg logit contributions | |
Tom | -0.015 |
Ben | -0.014 |
arrest | -0.013 |
Sam | -0.012 |
Dan | -0.012 |
Token | hit |
Token ID | 2277 |
Feature activation | +3.77e-02 |
Pos logit contributions | |
Tom | +0.042 |
Ben | +0.039 |
arrest | +0.037 |
Sam | +0.035 |
bye | +0.035 |
Neg logit contributions | |
smanship | -0.060 |
bush | -0.057 |
outage | -0.056 |
oils | -0.055 |
remedy | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
arrest | +0.001 |
bye | +0.001 |
eg | +0.001 |
boarding | +0.001 |
Their | +0.001 |
Neg logit contributions | |
smanship | -0.001 |
ions | -0.001 |
oils | -0.001 |
things | -0.001 |
web | -0.001 |
Token | clown |
Token ID | 25573 |
Feature activation | +5.97e+00 |
Pos logit contributions | |
Tom | +0.036 |
Ben | +0.033 |
Sam | +0.032 |
Their | +0.030 |
Dan | +0.030 |
Neg logit contributions | |
smanship | -0.048 |
bush | -0.045 |
outage | -0.045 |
remedy | -0.043 |
pleasures | -0.043 |
Token | in |
Token ID | 287 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
Tom | +0.143 |
Ben | +0.134 |
arrest | +0.130 |
bye | +0.129 |
Dan | +0.129 |
Neg logit contributions | |
smanship | -0.143 |
outage | -0.142 |
bush | -0.140 |
bars | -0.136 |
inning | -0.136 |
Token | the |
Token ID | 262 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
bye | +0.044 |
eg | +0.040 |
sed | +0.040 |
ked | +0.040 |
realizes | +0.039 |
Neg logit contributions | |
smanship | -0.055 |
outage | -0.052 |
bench | -0.051 |
oils | -0.050 |
kinds | -0.050 |
Token | face |
Token ID | 1986 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
Tom | +0.039 |
Ben | +0.036 |
Dan | +0.035 |
Sam | +0.034 |
Leo | +0.034 |
Neg logit contributions | |
smanship | -0.035 |
bush | -0.033 |
remedy | -0.032 |
outage | -0.032 |
oils | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
Tom | +0.064 |
arrest | +0.063 |
Ben | +0.060 |
bye | +0.057 |
Rex | +0.056 |
Neg logit contributions | |
smanship | -0.082 |
outage | -0.079 |
bush | -0.078 |
inning | -0.074 |
bars | -0.074 |
Token | He |
Token ID | 679 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
arrest | +0.022 |
ear | +0.021 |
bye | +0.020 |
sw | +0.020 |
ked | +0.020 |
Neg logit contributions | |
outage | -0.030 |
opener | -0.029 |
First | -0.029 |
bush | -0.028 |
smanship | -0.027 |
Token | nice |
Token ID | 3621 |
Feature activation | -1.76e-01 |
Pos logit contributions | |
smanship | +0.050 |
outage | +0.047 |
bush | +0.046 |
remedy | +0.044 |
pleasures | +0.043 |
Neg logit contributions | |
Tom | -0.044 |
Ben | -0.041 |
Sam | -0.037 |
their | -0.036 |
Rex | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
smanship | +0.006 |
outage | +0.006 |
bush | +0.006 |
remedy | +0.006 |
oils | +0.006 |
Neg logit contributions | |
Tom | -0.003 |
Ben | -0.003 |
Sam | -0.002 |
their | -0.002 |
Rex | -0.002 |
Token | even |
Token ID | 772 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
smanship | +0.054 |
outage | +0.051 |
bush | +0.050 |
remedy | +0.048 |
pleasures | +0.047 |
Neg logit contributions | |
Tom | -0.041 |
Ben | -0.039 |
Sam | -0.035 |
arrest | -0.034 |
Rex | -0.034 |
Token | if |
Token ID | 611 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
smanship | +0.062 |
outage | +0.057 |
bush | +0.055 |
oils | +0.052 |
occasions | +0.052 |
Neg logit contributions | |
Tom | -0.066 |
Ben | -0.063 |
their | -0.058 |
Sam | -0.057 |
Rex | -0.054 |
Token | the |
Token ID | 262 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
Tom | +0.002 |
Ben | +0.002 |
Sam | +0.002 |
Rex | +0.002 |
their | +0.002 |
Neg logit contributions | |
smanship | -0.003 |
outage | -0.003 |
bush | -0.003 |
remedy | -0.003 |
pleasures | -0.003 |
Token | queen |
Token ID | 16599 |
Feature activation | +5.97e+00 |
Pos logit contributions | |
Tom | +0.010 |
Ben | +0.009 |
Sam | +0.009 |
Rex | +0.008 |
arrest | +0.008 |
Neg logit contributions | |
smanship | -0.015 |
outage | -0.014 |
bush | -0.014 |
remedy | -0.013 |
pleasures | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
Tom | +0.138 |
Ben | +0.130 |
Sam | +0.118 |
Rex | +0.114 |
their | +0.112 |
Neg logit contributions | |
smanship | -0.178 |
outage | -0.166 |
bush | -0.164 |
remedy | -0.158 |
pleasures | -0.155 |
Token | rude |
Token ID | 22066 |
Feature activation | +9.78e-01 |
Pos logit contributions | |
Tom | +0.026 |
Ben | +0.025 |
arrest | +0.023 |
Sam | +0.022 |
Rex | +0.022 |
Neg logit contributions | |
smanship | -0.038 |
outage | -0.036 |
bush | -0.036 |
remedy | -0.035 |
pleasures | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
Tom | +0.015 |
Ben | +0.014 |
Sam | +0.011 |
their | +0.011 |
Rex | +0.010 |
Neg logit contributions | |
smanship | -0.038 |
bush | -0.036 |
outage | -0.036 |
remedy | -0.035 |
iona | -0.035 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
Tom | +0.003 |
Ben | +0.002 |
arrest | +0.002 |
sw | +0.002 |
bye | +0.002 |
Neg logit contributions | |
smanship | -0.005 |
bush | -0.005 |
outage | -0.005 |
First | -0.005 |
remedy | -0.005 |
Token | Once |
Token ID | 7454 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
smanship | +0.027 |
outage | +0.025 |
bush | +0.025 |
First | +0.024 |
inning | +0.024 |
Neg logit contributions | |
Tom | -0.015 |
Ben | -0.014 |
arrest | -0.014 |
bye | -0.013 |
ear | -0.013 |
Token | Jas |
Token ID | 21961 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
Tom | +0.006 |
Ben | +0.005 |
bye | +0.004 |
arrest | +0.004 |
Sam | +0.004 |
Neg logit contributions | |
smanship | -0.017 |
outage | -0.016 |
bush | -0.016 |
remedy | -0.015 |
First | -0.015 |
Token | mine |
Token ID | 3810 |
Feature activation | -3.21e-01 |
Pos logit contributions | |
smanship | +0.064 |
outage | +0.059 |
bush | +0.058 |
bars | +0.055 |
occasions | +0.054 |
Neg logit contributions | |
Tom | -0.062 |
Ben | -0.060 |
Sam | -0.054 |
Rex | -0.054 |
arrest | -0.054 |
Token | grabbed |
Token ID | 13176 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
smanship | +0.010 |
bush | +0.009 |
outage | +0.009 |
remedy | +0.009 |
oils | +0.008 |
Neg logit contributions | |
Tom | -0.007 |
Ben | -0.006 |
Sam | -0.006 |
arrest | -0.006 |
Rex | -0.006 |
Token | some |
Token ID | 617 |
Feature activation | -3.86e+00 |
Pos logit contributions | |
smanship | +0.066 |
bush | +0.061 |
oils | +0.061 |
outage | +0.061 |
occasions | +0.059 |
Neg logit contributions | |
Tom | -0.031 |
Ben | -0.029 |
bye | -0.027 |
arrest | -0.027 |
Leo | -0.025 |
Token | tw |
Token ID | 665 |
Feature activation | -4.13e+00 |
Pos logit contributions | |
smanship | +0.117 |
outage | +0.114 |
bush | +0.109 |
inning | +0.105 |
remedy | +0.103 |
Neg logit contributions | |
Tom | -0.089 |
Ben | -0.084 |
Sam | -0.077 |
their | -0.076 |
sw | -0.073 |
Token | igs |
Token ID | 9235 |
Feature activation | -8.47e+00 |
Pos logit contributions | |
outage | +0.104 |
smanship | +0.098 |
remedy | +0.083 |
virtue | +0.081 |
bush | +0.080 |
Neg logit contributions | |
Ben | -0.105 |
sw | -0.105 |
their | -0.103 |
arrest | -0.101 |
at | -0.100 |
Token | that |
Token ID | 326 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
smanship | +0.322 |
outage | +0.308 |
remedy | +0.304 |
occasions | +0.298 |
bush | +0.298 |
Neg logit contributions | |
Tom | -0.129 |
Ben | -0.115 |
their | -0.105 |
Sam | -0.099 |
sw | -0.091 |
Token | she |
Token ID | 673 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
smanship | +0.077 |
outage | +0.076 |
pleasures | +0.070 |
inning | +0.070 |
remedy | +0.069 |
Neg logit contributions | |
Tom | -0.057 |
Ben | -0.056 |
Sam | -0.050 |
their | -0.050 |
sw | -0.049 |
Token | had |
Token ID | 550 |
Feature activation | -4.37e-01 |
Pos logit contributions | |
smanship | +0.037 |
outage | +0.035 |
pleasures | +0.034 |
bush | +0.033 |
remedy | +0.033 |
Neg logit contributions | |
Tom | -0.020 |
Ben | -0.019 |
sw | -0.017 |
Sam | -0.017 |
their | -0.015 |
Token | found |
Token ID | 1043 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
smanship | +0.015 |
outage | +0.014 |
bush | +0.014 |
remedy | +0.013 |
inning | +0.013 |
Neg logit contributions | |
Tom | -0.009 |
Ben | -0.008 |
Sam | -0.007 |
their | -0.007 |
arrest | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
smanship | +0.046 |
outage | +0.044 |
pleasures | +0.041 |
bush | +0.041 |
remedy | +0.041 |
Neg logit contributions | |
Tom | -0.022 |
Ben | -0.020 |
Sam | -0.018 |
their | -0.018 |
Rex | -0.016 |
Token | home |
Token ID | 1363 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
Tom | +0.010 |
Ben | +0.010 |
Sam | +0.009 |
their | +0.008 |
Rex | +0.008 |
Neg logit contributions | |
smanship | -0.013 |
outage | -0.013 |
bush | -0.012 |
remedy | -0.012 |
First | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +7.35e-01 |
Pos logit contributions | |
smanship | +0.027 |
outage | +0.026 |
remedy | +0.025 |
bush | +0.025 |
oils | +0.025 |
Neg logit contributions | |
Tom | -0.010 |
Ben | -0.009 |
their | -0.008 |
Sam | -0.007 |
Rex | -0.006 |
Token | She |
Token ID | 1375 |
Feature activation | -8.91e-01 |
Pos logit contributions | |
Tom | +0.014 |
Ben | +0.013 |
Sam | +0.011 |
arrest | +0.011 |
Rex | +0.011 |
Neg logit contributions | |
smanship | -0.024 |
bush | -0.023 |
outage | -0.023 |
remedy | -0.022 |
First | -0.022 |
Token | gathered |
Token ID | 9272 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
smanship | +0.030 |
outage | +0.029 |
bush | +0.027 |
inning | +0.027 |
pleasures | +0.027 |
Neg logit contributions | |
Tom | -0.018 |
Ben | -0.018 |
sw | -0.016 |
Sam | -0.015 |
their | -0.015 |
Token | tw |
Token ID | 665 |
Feature activation | -3.54e+00 |
Pos logit contributions | |
smanship | +0.065 |
outage | +0.063 |
bush | +0.061 |
remedy | +0.059 |
inning | +0.058 |
Neg logit contributions | |
Tom | -0.033 |
Ben | -0.030 |
their | -0.026 |
Sam | -0.026 |
Rex | -0.024 |
Token | igs |
Token ID | 9235 |
Feature activation | -7.36e+00 |
Pos logit contributions | |
outage | +0.076 |
smanship | +0.073 |
remedy | +0.062 |
bush | +0.060 |
First | +0.058 |
Neg logit contributions | |
Tom | -0.109 |
Ben | -0.109 |
their | -0.106 |
sw | -0.102 |
Sam | -0.102 |
Token | and |
Token ID | 290 |
Feature activation | +3.36e-01 |
Pos logit contributions | |
smanship | +0.282 |
outage | +0.271 |
remedy | +0.264 |
bush | +0.262 |
occasions | +0.260 |
Neg logit contributions | |
Tom | -0.111 |
Ben | -0.100 |
their | -0.089 |
Sam | -0.087 |
sw | -0.078 |
Token | leaves |
Token ID | 5667 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
Tom | +0.007 |
Ben | +0.007 |
their | +0.006 |
sw | +0.006 |
Sam | +0.006 |
Neg logit contributions | |
outage | -0.011 |
smanship | -0.011 |
inning | -0.011 |
bush | -0.010 |
virtue | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +9.04e-01 |
Pos logit contributions | |
smanship | +0.142 |
outage | +0.137 |
remedy | +0.133 |
occasions | +0.132 |
pleasures | +0.131 |
Neg logit contributions | |
Tom | -0.051 |
Ben | -0.046 |
their | -0.045 |
Sam | -0.040 |
sw | -0.037 |
Token | rocks |
Token ID | 12586 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
Tom | +0.019 |
Ben | +0.018 |
Sam | +0.017 |
sw | +0.017 |
their | +0.017 |
Neg logit contributions | |
smanship | -0.030 |
outage | -0.029 |
inning | -0.028 |
bush | -0.027 |
pleasures | -0.026 |
Token | , |
Token ID | 11 |
Feature activation | -1.69e-01 |
Pos logit contributions | |
smanship | +0.092 |
outage | +0.088 |
remedy | +0.087 |
pleasures | +0.085 |
occasions | +0.085 |
Neg logit contributions | |
Tom | -0.034 |
Ben | -0.030 |
their | -0.029 |
Sam | -0.026 |
sw | -0.025 |
Token | It |
Token ID | 632 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
smanship | +0.001 |
outage | +0.001 |
bush | +0.001 |
remedy | +0.001 |
pleasures | +0.001 |
Neg logit contributions | |
Tom | -0.000 |
Ben | -0.000 |
Sam | -0.000 |
Leo | -0.000 |
their | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | -7.59e-01 |
Pos logit contributions | |
smanship | +0.046 |
outage | +0.045 |
pleasures | +0.044 |
occasions | +0.043 |
inning | +0.043 |
Neg logit contributions | |
Tom | -0.024 |
Ben | -0.022 |
Sam | -0.020 |
their | -0.019 |
sw | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
smanship | +0.030 |
outage | +0.028 |
bush | +0.028 |
pleasures | +0.027 |
remedy | +0.027 |
Neg logit contributions | |
Tom | -0.012 |
Ben | -0.011 |
Sam | -0.009 |
their | -0.009 |
Rex | -0.008 |
Token | big |
Token ID | 1263 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
smanship | +0.027 |
outage | +0.025 |
bush | +0.025 |
remedy | +0.024 |
pleasures | +0.024 |
Neg logit contributions | |
Tom | -0.015 |
Ben | -0.014 |
Sam | -0.012 |
Rex | -0.012 |
their | -0.012 |
Token | j |
Token ID | 474 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
smanship | +0.054 |
outage | +0.052 |
bush | +0.051 |
First | +0.051 |
inning | +0.049 |
Neg logit contributions | |
Tom | -0.025 |
Ben | -0.023 |
Sam | -0.019 |
ear | -0.019 |
bye | -0.018 |
Token | igsaw |
Token ID | 45636 |
Feature activation | -7.27e+00 |
Pos logit contributions | |
smanship | +0.050 |
remedy | +0.047 |
First | +0.047 |
outage | +0.046 |
bush | +0.045 |
Neg logit contributions | |
Tom | -0.038 |
Ben | -0.037 |
Sam | -0.033 |
bye | -0.033 |
arrest | -0.030 |
Token | puzzle |
Token ID | 15027 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
bush | +0.223 |
First | +0.222 |
remedy | +0.216 |
iona | +0.214 |
Things | +0.214 |
Neg logit contributions | |
Tom | -0.126 |
at | -0.119 |
Ben | -0.112 |
big | -0.112 |
their | -0.109 |
Token | and |
Token ID | 290 |
Feature activation | -9.53e-01 |
Pos logit contributions | |
smanship | +0.130 |
pleasures | +0.128 |
remedy | +0.127 |
oils | +0.124 |
First | +0.124 |
Neg logit contributions | |
Tom | -0.052 |
Ben | -0.045 |
Sam | -0.039 |
their | -0.037 |
at | -0.037 |
Token | she |
Token ID | 673 |
Feature activation | -8.35e-01 |
Pos logit contributions | |
smanship | +0.034 |
outage | +0.033 |
inning | +0.032 |
bush | +0.031 |
pleasures | +0.031 |
Neg logit contributions | |
Tom | -0.021 |
Ben | -0.020 |
Sam | -0.017 |
their | -0.016 |
Leo | -0.015 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
smanship | +0.030 |
bush | +0.028 |
outage | +0.028 |
pleasures | +0.028 |
remedy | +0.027 |
Neg logit contributions | |
Tom | -0.015 |
Ben | -0.014 |
sw | -0.012 |
Sam | -0.012 |
both | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Tom | +0.024 |
Ben | +0.022 |
Sam | +0.019 |
their | +0.019 |
Rex | +0.017 |
Neg logit contributions | |
smanship | -0.053 |
outage | -0.050 |
bush | -0.050 |
inning | -0.049 |
remedy | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
Tom | +0.017 |
Ben | +0.016 |
Sam | +0.015 |
their | +0.014 |
Rex | +0.014 |
Neg logit contributions | |
smanship | -0.030 |
bush | -0.028 |
outage | -0.028 |
remedy | -0.027 |
iona | -0.026 |
Token | he |
Token ID | 339 |
Feature activation | +4.32e-02 |
Pos logit contributions | |
smanship | +0.033 |
outage | +0.030 |
bush | +0.030 |
remedy | +0.029 |
pleasures | +0.028 |
Neg logit contributions | |
Tom | -0.023 |
Ben | -0.022 |
Sam | -0.020 |
Rex | -0.019 |
arrest | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | -9.30e-01 |
Pos logit contributions | |
Tom | +0.001 |
Ben | +0.001 |
Sam | +0.001 |
Rex | +0.001 |
arrest | +0.001 |
Neg logit contributions | |
smanship | -0.001 |
outage | -0.001 |
bush | -0.001 |
remedy | -0.001 |
pleasures | -0.001 |
Token | su |
Token ID | 424 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
smanship | +0.030 |
outage | +0.028 |
bush | +0.027 |
remedy | +0.026 |
pleasures | +0.026 |
Neg logit contributions | |
Tom | -0.020 |
Ben | -0.019 |
Sam | -0.017 |
Rex | -0.016 |
their | -0.016 |
Token | pr |
Token ID | 1050 |
Feature activation | -3.65e+00 |
Pos logit contributions | |
outage | +0.034 |
smanship | +0.033 |
bush | +0.032 |
pleasures | +0.031 |
remedy | +0.030 |
Neg logit contributions | |
Tom | -0.056 |
arrest | -0.055 |
Ben | -0.052 |
both | -0.052 |
ss | -0.051 |
Token | ised |
Token ID | 1417 |
Feature activation | -7.25e+00 |
Pos logit contributions | |
bush | +0.067 |
smanship | +0.065 |
remedy | +0.063 |
outage | +0.062 |
pleasures | +0.060 |
Neg logit contributions | |
Tom | -0.117 |
Ben | -0.111 |
Sam | -0.105 |
at | -0.104 |
their | -0.102 |
Token | at |
Token ID | 379 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
bush | +0.285 |
smanship | +0.273 |
outage | +0.272 |
iona | +0.269 |
remedy | +0.259 |
Neg logit contributions | |
Tom | -0.109 |
at | -0.097 |
Ben | -0.092 |
their | -0.090 |
his | -0.087 |
Token | how |
Token ID | 703 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
smanship | +0.042 |
outage | +0.039 |
bush | +0.039 |
remedy | +0.038 |
pleasures | +0.037 |
Neg logit contributions | |
Tom | -0.021 |
Ben | -0.020 |
Sam | -0.017 |
Rex | -0.016 |
arrest | -0.016 |
Token | quickly |
Token ID | 2952 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
smanship | +0.037 |
bush | +0.035 |
outage | +0.035 |
remedy | +0.033 |
iona | +0.033 |
Neg logit contributions | |
Tom | -0.021 |
Ben | -0.019 |
Sam | -0.017 |
their | -0.017 |
bye | -0.016 |
Token | he |
Token ID | 339 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Tom | +0.050 |
Ben | +0.047 |
Sam | +0.042 |
Rex | +0.041 |
their | +0.040 |
Neg logit contributions | |
smanship | -0.078 |
outage | -0.073 |
bush | -0.072 |
remedy | -0.070 |
pleasures | -0.068 |
Token | started |
Token ID | 2067 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
Tom | +0.032 |
Ben | +0.030 |
Sam | +0.027 |
Rex | +0.025 |
sw | +0.025 |
Neg logit contributions | |
smanship | -0.046 |
outage | -0.044 |
bush | -0.044 |
remedy | -0.042 |
pleasures | -0.041 |
Token | flower |
Token ID | 15061 |
Feature activation | -8.27e-02 |
Pos logit contributions | |
Tom | +0.003 |
Ben | +0.003 |
Sam | +0.003 |
sw | +0.002 |
their | +0.002 |
Neg logit contributions | |
smanship | -0.004 |
outage | -0.004 |
bush | -0.004 |
First | -0.004 |
pleasures | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -2.05e-01 |
Pos logit contributions | |
smanship | +0.003 |
outage | +0.003 |
bush | +0.003 |
remedy | +0.003 |
pleasures | +0.003 |
Neg logit contributions | |
Tom | -0.001 |
Ben | -0.001 |
Sam | -0.001 |
Rex | -0.001 |
their | -0.001 |
Token | Lucy |
Token ID | 22162 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
smanship | +0.009 |
outage | +0.008 |
inning | +0.007 |
bush | +0.007 |
pleasures | +0.007 |
Neg logit contributions | |
Tom | -0.004 |
Ben | -0.003 |
Sam | -0.003 |
The | -0.002 |
Their | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -9.83e-01 |
Pos logit contributions | |
smanship | +0.030 |
outage | +0.029 |
bush | +0.028 |
remedy | +0.027 |
pleasures | +0.027 |
Neg logit contributions | |
Tom | -0.020 |
Ben | -0.018 |
Sam | -0.016 |
Rex | -0.016 |
arrest | -0.016 |
Token | mesmer |
Token ID | 46814 |
Feature activation | -9.01e-01 |
Pos logit contributions | |
smanship | +0.028 |
bush | +0.027 |
outage | +0.027 |
remedy | +0.026 |
oils | +0.025 |
Neg logit contributions | |
Tom | -0.022 |
Ben | -0.021 |
arrest | -0.019 |
Sam | -0.019 |
Rex | -0.019 |
Token | ised |
Token ID | 1417 |
Feature activation | -7.11e+00 |
Pos logit contributions | |
smanship | +0.013 |
bush | +0.011 |
outage | +0.010 |
inning | +0.010 |
remedy | +0.009 |
Neg logit contributions | |
Tom | -0.034 |
Ben | -0.033 |
Sam | -0.032 |
Rex | -0.032 |
arrest | -0.031 |
Token | by |
Token ID | 416 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
outage | +0.270 |
smanship | +0.269 |
bush | +0.263 |
First | +0.261 |
remedy | +0.257 |
Neg logit contributions | |
Tom | -0.110 |
Ben | -0.097 |
their | -0.090 |
at | -0.086 |
Sam | -0.084 |
Token | the |
Token ID | 262 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
smanship | +0.072 |
bush | +0.068 |
outage | +0.068 |
remedy | +0.066 |
pleasures | +0.065 |
Neg logit contributions | |
Tom | -0.034 |
Ben | -0.031 |
Sam | -0.027 |
Rex | -0.026 |
arrest | -0.026 |
Token | flower |
Token ID | 15061 |
Feature activation | +2.19e-01 |
Pos logit contributions | |
smanship | +0.060 |
outage | +0.057 |
bush | +0.055 |
remedy | +0.054 |
First | +0.053 |
Neg logit contributions | |
Tom | -0.039 |
Ben | -0.036 |
Sam | -0.032 |
their | -0.031 |
sw | -0.031 |
Token | 's |
Token ID | 338 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
Tom | +0.004 |
Ben | +0.003 |
Sam | +0.003 |
their | +0.003 |
Rex | +0.003 |
Neg logit contributions | |
smanship | -0.008 |
outage | -0.008 |
bush | -0.007 |
remedy | -0.007 |
First | -0.007 |
Token | beauty |
Token ID | 8737 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
smanship | +0.013 |
outage | +0.012 |
bush | +0.012 |
remedy | +0.012 |
pleasures | +0.012 |
Neg logit contributions | |
Tom | -0.010 |
Ben | -0.010 |
Sam | -0.009 |
Rex | -0.009 |
arrest | -0.009 |
Token | cool |
Token ID | 3608 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
smanship | +0.000 |
outage | +0.000 |
bush | +0.000 |
occasions | +0.000 |
remedy | +0.000 |
Neg logit contributions | |
Tom | -0.000 |
Ben | -0.000 |
Sam | -0.000 |
their | -0.000 |
sw | -0.000 |
Token | ! |
Token ID | 0 |
Feature activation | -2.74e-02 |
Pos logit contributions | |
smanship | +0.058 |
outage | +0.055 |
bush | +0.054 |
remedy | +0.052 |
pleasures | +0.051 |
Neg logit contributions | |
Tom | -0.033 |
Ben | -0.030 |
Sam | -0.027 |
Rex | -0.026 |
arrest | -0.026 |
Token | Sammy |
Token ID | 44067 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
smanship | +0.001 |
bush | +0.001 |
outage | +0.001 |
First | +0.001 |
remedy | +0.001 |
Neg logit contributions | |
Tom | -0.001 |
arrest | -0.000 |
Ben | -0.000 |
their | -0.000 |
bye | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
smanship | +0.052 |
outage | +0.049 |
bush | +0.049 |
remedy | +0.047 |
pleasures | +0.046 |
Neg logit contributions | |
Tom | -0.034 |
Ben | -0.031 |
Sam | -0.028 |
Rex | -0.027 |
arrest | -0.027 |
Token | mesmer |
Token ID | 46814 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
smanship | +0.045 |
outage | +0.043 |
bush | +0.043 |
remedy | +0.041 |
First | +0.039 |
Neg logit contributions | |
Tom | -0.031 |
Ben | -0.029 |
arrest | -0.026 |
Sam | -0.026 |
Rex | -0.025 |
Token | ised |
Token ID | 1417 |
Feature activation | -7.07e+00 |
Pos logit contributions | |
smanship | +0.014 |
bush | +0.012 |
inning | +0.011 |
izing | +0.011 |
heart | +0.010 |
Neg logit contributions | |
Tom | -0.045 |
Ben | -0.044 |
arrest | -0.042 |
Rex | -0.042 |
Sam | -0.042 |
Token | by |
Token ID | 416 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
smanship | +0.255 |
outage | +0.249 |
bush | +0.246 |
remedy | +0.237 |
First | +0.234 |
Neg logit contributions | |
Tom | -0.124 |
Ben | -0.114 |
their | -0.102 |
Sam | -0.101 |
sw | -0.090 |
Token | its |
Token ID | 663 |
Feature activation | +6.62e-01 |
Pos logit contributions | |
smanship | +0.072 |
bush | +0.068 |
outage | +0.068 |
remedy | +0.066 |
pleasures | +0.066 |
Neg logit contributions | |
Tom | -0.027 |
Ben | -0.025 |
arrest | -0.020 |
Sam | -0.020 |
Rex | -0.020 |
Token | beauty |
Token ID | 8737 |
Feature activation | -5.90e-01 |
Pos logit contributions | |
Tom | +0.017 |
Ben | +0.016 |
arrest | +0.015 |
Sam | +0.015 |
Rex | +0.014 |
Neg logit contributions | |
smanship | -0.018 |
bush | -0.016 |
outage | -0.016 |
remedy | -0.016 |
pleasures | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | -7.04e-01 |
Pos logit contributions | |
smanship | +0.023 |
outage | +0.022 |
First | +0.022 |
bush | +0.021 |
occasions | +0.021 |
Neg logit contributions | |
Tom | -0.008 |
Ben | -0.008 |
their | -0.006 |
Sam | -0.006 |
sw | -0.006 |
Token | His |
Token ID | 2399 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
smanship | +0.026 |
outage | +0.024 |
bush | +0.024 |
remedy | +0.023 |
pleasures | +0.023 |
Neg logit contributions | |
Tom | -0.012 |
Ben | -0.011 |
Sam | -0.010 |
Rex | -0.009 |
their | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
Tom | +0.019 |
Ben | +0.018 |
arrest | +0.017 |
eg | +0.016 |
Their | +0.016 |
Neg logit contributions | |
smanship | -0.030 |
bush | -0.029 |
outage | -0.029 |
remedy | -0.027 |
iona | -0.027 |
Token | he |
Token ID | 339 |
Feature activation | +4.37e-03 |
Pos logit contributions | |
smanship | +0.047 |
bush | +0.043 |
outage | +0.043 |
remedy | +0.042 |
oils | +0.041 |
Neg logit contributions | |
Tom | -0.033 |
Ben | -0.031 |
Sam | -0.028 |
arrest | -0.027 |
Rex | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
Tom | +0.000 |
arrest | +0.000 |
icks | +0.000 |
bye | +0.000 |
Their | +0.000 |
Neg logit contributions | |
bush | -0.000 |
smanship | -0.000 |
remedy | -0.000 |
oils | -0.000 |
if | -0.000 |
Token | su |
Token ID | 424 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
smanship | +0.033 |
outage | +0.031 |
bush | +0.030 |
pleasures | +0.029 |
occasions | +0.029 |
Neg logit contributions | |
Tom | -0.019 |
Ben | -0.017 |
Sam | -0.016 |
Rex | -0.015 |
their | -0.015 |
Token | pr |
Token ID | 1050 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
smanship | +0.041 |
outage | +0.041 |
pleasures | +0.037 |
bush | +0.037 |
remedy | +0.035 |
Neg logit contributions | |
Tom | -0.068 |
Ben | -0.065 |
arrest | -0.064 |
Sam | -0.062 |
sw | -0.062 |
Token | ised |
Token ID | 1417 |
Feature activation | -7.01e+00 |
Pos logit contributions | |
smanship | +0.084 |
occasions | +0.078 |
outage | +0.077 |
bush | +0.076 |
pleasures | +0.076 |
Neg logit contributions | |
Tom | -0.109 |
Ben | -0.104 |
Sam | -0.098 |
sw | -0.097 |
arrest | -0.096 |
Token | to |
Token ID | 284 |
Feature activation | -1.34e+00 |
Pos logit contributions | |
smanship | +0.276 |
bush | +0.260 |
outage | +0.260 |
First | +0.254 |
pleasures | +0.253 |
Neg logit contributions | |
Tom | -0.105 |
Ben | -0.090 |
at | -0.082 |
Sam | -0.080 |
their | -0.078 |
Token | see |
Token ID | 766 |
Feature activation | +3.74e-01 |
Pos logit contributions | |
smanship | +0.039 |
remedy | +0.038 |
bush | +0.038 |
outage | +0.037 |
pleasures | +0.035 |
Neg logit contributions | |
Tom | -0.026 |
Ben | -0.024 |
eg | -0.023 |
Their | -0.022 |
icks | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Tom | +0.006 |
Ben | +0.006 |
Sam | +0.005 |
arrest | +0.005 |
Rex | +0.005 |
Neg logit contributions | |
smanship | -0.014 |
outage | -0.013 |
bush | -0.013 |
remedy | -0.012 |
pleasures | -0.012 |
Token | gray |
Token ID | 12768 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
Tom | +0.020 |
Ben | +0.019 |
sw | +0.016 |
Sam | +0.016 |
Rex | +0.015 |
Neg logit contributions | |
smanship | -0.051 |
outage | -0.048 |
bush | -0.047 |
occasions | -0.047 |
pleasures | -0.047 |
Token | bird |
Token ID | 6512 |
Feature activation | +6.45e-01 |
Pos logit contributions | |
Tom | +0.005 |
Ben | +0.005 |
Sam | +0.005 |
sw | +0.005 |
ear | +0.004 |
Neg logit contributions | |
smanship | -0.009 |
First | -0.008 |
outage | -0.008 |
pleasures | -0.008 |
bush | -0.008 |
Token | new |
Token ID | 649 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
smanship | +0.024 |
outage | +0.022 |
iona | +0.022 |
bush | +0.022 |
inning | +0.021 |
Neg logit contributions | |
Tom | -0.008 |
their | -0.008 |
Ben | -0.006 |
his | -0.005 |
Sam | -0.005 |
Token | sports |
Token ID | 5701 |
Feature activation | -3.64e-01 |
Pos logit contributions | |
outage | +0.090 |
bush | +0.090 |
smanship | +0.085 |
bars | +0.084 |
belt | +0.083 |
Neg logit contributions | |
their | -0.041 |
Tom | -0.040 |
Ben | -0.039 |
his | -0.034 |
Sam | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -6.51e-01 |
Pos logit contributions | |
smanship | +0.015 |
outage | +0.015 |
iona | +0.015 |
bush | +0.015 |
bars | +0.014 |
Neg logit contributions | |
Tom | -0.004 |
their | -0.004 |
Ben | -0.004 |
Sam | -0.003 |
his | -0.003 |
Token | They |
Token ID | 1119 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
smanship | +0.025 |
outage | +0.024 |
bars | +0.022 |
inning | +0.022 |
iest | +0.022 |
Neg logit contributions | |
Tom | -0.012 |
Ben | -0.011 |
Sam | -0.010 |
Leo | -0.009 |
their | -0.009 |
Token | pract |
Token ID | 1970 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
outage | +0.054 |
smanship | +0.054 |
bush | +0.052 |
pleasures | +0.051 |
occasions | +0.051 |
Neg logit contributions | |
Tom | -0.027 |
Ben | -0.025 |
Sam | -0.022 |
sw | -0.021 |
their | -0.021 |
Token | ised |
Token ID | 1417 |
Feature activation | -6.98e+00 |
Pos logit contributions | |
outage | +0.049 |
bush | +0.048 |
remedy | +0.042 |
smanship | +0.042 |
bars | +0.033 |
Neg logit contributions | |
Tom | -0.117 |
Ben | -0.113 |
their | -0.108 |
Sam | -0.105 |
both | -0.105 |
Token | throwing |
Token ID | 9644 |
Feature activation | -5.98e-01 |
Pos logit contributions | |
outage | +0.259 |
bush | +0.257 |
smanship | +0.252 |
remedy | +0.239 |
quet | +0.234 |
Neg logit contributions | |
Tom | -0.124 |
Ben | -0.118 |
their | -0.113 |
Sam | -0.107 |
his | -0.089 |
Token | , |
Token ID | 11 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
outage | +0.023 |
smanship | +0.023 |
bush | +0.022 |
remedy | +0.021 |
iona | +0.020 |
Neg logit contributions | |
Tom | -0.010 |
Ben | -0.010 |
their | -0.009 |
Sam | -0.008 |
Rex | -0.007 |
Token | hopping |
Token ID | 47153 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
smanship | +0.075 |
outage | +0.070 |
bush | +0.069 |
remedy | +0.066 |
pleasures | +0.065 |
Neg logit contributions | |
Tom | -0.052 |
Ben | -0.048 |
Sam | -0.044 |
their | -0.041 |
Rex | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -5.89e-01 |
Pos logit contributions | |
Tom | +0.009 |
Ben | +0.008 |
their | +0.008 |
Sam | +0.007 |
sw | +0.007 |
Neg logit contributions | |
smanship | -0.020 |
outage | -0.019 |
bush | -0.018 |
remedy | -0.018 |
occasions | -0.018 |
Token | running |
Token ID | 2491 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
smanship | +0.020 |
outage | +0.019 |
bush | +0.019 |
inning | +0.018 |
pleasures | +0.018 |
Neg logit contributions | |
Tom | -0.014 |
Ben | -0.013 |
Sam | -0.012 |
their | -0.011 |
sw | -0.010 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
smanship | +0.001 |
outage | +0.001 |
bush | +0.001 |
remedy | +0.001 |
pleasures | +0.001 |
Neg logit contributions | |
Tom | -0.001 |
Ben | -0.001 |
Sam | -0.000 |
Rex | -0.000 |
sw | -0.000 |
Token | very |
Token ID | 845 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
smanship | +0.053 |
outage | +0.050 |
bush | +0.048 |
occasions | +0.048 |
remedy | +0.047 |
Neg logit contributions | |
Tom | -0.027 |
Ben | -0.025 |
their | -0.022 |
Sam | -0.021 |
sw | -0.020 |
Token | fit |
Token ID | 4197 |
Feature activation | -3.95e+00 |
Pos logit contributions | |
smanship | +0.042 |
outage | +0.039 |
bush | +0.038 |
remedy | +0.037 |
occasions | +0.037 |
Neg logit contributions | |
Tom | -0.022 |
Ben | -0.021 |
Sam | -0.018 |
their | -0.018 |
sw | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
smanship | +0.153 |
outage | +0.149 |
bush | +0.148 |
remedy | +0.143 |
First | +0.143 |
Neg logit contributions | |
Tom | -0.057 |
Ben | -0.051 |
their | -0.044 |
Sam | -0.041 |
at | -0.041 |
Token | energ |
Token ID | 19647 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
smanship | +0.039 |
outage | +0.037 |
bush | +0.036 |
remedy | +0.035 |
inning | +0.035 |
Neg logit contributions | |
Tom | -0.024 |
Ben | -0.022 |
Sam | -0.020 |
their | -0.019 |
sw | -0.019 |
Token | ised |
Token ID | 1417 |
Feature activation | -6.96e+00 |
Pos logit contributions | |
smanship | +0.051 |
outage | +0.048 |
bush | +0.045 |
remedy | +0.042 |
occasions | +0.040 |
Neg logit contributions | |
Tom | -0.107 |
Ben | -0.103 |
their | -0.096 |
Sam | -0.095 |
sw | -0.095 |
Token | , |
Token ID | 11 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
bush | +0.270 |
smanship | +0.270 |
outage | +0.269 |
remedy | +0.258 |
First | +0.249 |
Neg logit contributions | |
Tom | -0.101 |
Ben | -0.088 |
their | -0.084 |
Sam | -0.074 |
his | -0.072 |
Token | and |
Token ID | 290 |
Feature activation | -4.06e-01 |
Pos logit contributions | |
smanship | +0.067 |
outage | +0.063 |
bush | +0.061 |
remedy | +0.059 |
pleasures | +0.058 |
Neg logit contributions | |
Tom | -0.049 |
Ben | -0.046 |
Sam | -0.041 |
Rex | -0.040 |
their | -0.039 |
Token | smiled |
Token ID | 13541 |
Feature activation | +6.23e-01 |
Pos logit contributions | |
smanship | +0.013 |
outage | +0.012 |
bush | +0.012 |
remedy | +0.012 |
pleasures | +0.012 |
Neg logit contributions | |
Tom | -0.008 |
Ben | -0.008 |
Sam | -0.007 |
Rex | -0.007 |
their | -0.007 |
Token | as |
Token ID | 355 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
Tom | +0.013 |
Ben | +0.012 |
arrest | +0.011 |
Sam | +0.011 |
Rex | +0.011 |
Neg logit contributions | |
smanship | -0.020 |
bush | -0.018 |
outage | -0.018 |
remedy | -0.018 |
pleasures | -0.017 |
Token | he |
Token ID | 339 |
Feature activation | +9.45e-01 |
Pos logit contributions | |
smanship | +0.023 |
outage | +0.022 |
bush | +0.022 |
remedy | +0.021 |
pleasures | +0.021 |
Neg logit contributions | |
Tom | -0.014 |
Ben | -0.013 |
Sam | -0.012 |
arrest | -0.012 |
Rex | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
smanship | +0.062 |
outage | +0.059 |
bush | +0.059 |
remedy | +0.057 |
First | +0.055 |
Neg logit contributions | |
Tom | -0.029 |
Ben | -0.027 |
Sam | -0.023 |
their | -0.023 |
Rex | -0.021 |
Token | He |
Token ID | 679 |
Feature activation | -7.21e-02 |
Pos logit contributions | |
Tom | +0.014 |
Ben | +0.013 |
Sam | +0.011 |
arrest | +0.011 |
Rex | +0.011 |
Neg logit contributions | |
smanship | -0.025 |
outage | -0.024 |
bush | -0.024 |
remedy | -0.023 |
pleasures | -0.023 |
Token | grabbed |
Token ID | 13176 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
smanship | +0.002 |
outage | +0.002 |
bush | +0.002 |
pleasures | +0.002 |
remedy | +0.002 |
Neg logit contributions | |
Tom | -0.001 |
Ben | -0.001 |
Sam | -0.001 |
sw | -0.001 |
their | -0.001 |
Token | different |
Token ID | 1180 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
smanship | +0.056 |
outage | +0.052 |
bush | +0.052 |
oils | +0.051 |
remedy | +0.051 |
Neg logit contributions | |
Tom | -0.022 |
Ben | -0.020 |
bye | -0.018 |
arrest | -0.018 |
Rex | -0.017 |
Token | tw |
Token ID | 665 |
Feature activation | -3.09e+00 |
Pos logit contributions | |
smanship | +0.055 |
bush | +0.054 |
outage | +0.054 |
remedy | +0.050 |
iona | +0.050 |
Neg logit contributions | |
Tom | -0.054 |
Ben | -0.052 |
their | -0.049 |
Sam | -0.048 |
sw | -0.045 |
Token | igs |
Token ID | 9235 |
Feature activation | -6.96e+00 |
Pos logit contributions | |
outage | +0.067 |
smanship | +0.065 |
remedy | +0.061 |
First | +0.057 |
bush | +0.057 |
Neg logit contributions | |
Ben | -0.087 |
Tom | -0.085 |
arrest | -0.083 |
sw | -0.082 |
their | -0.082 |
Token | and |
Token ID | 290 |
Feature activation | +4.64e-01 |
Pos logit contributions | |
smanship | +0.261 |
outage | +0.248 |
bush | +0.245 |
remedy | +0.243 |
occasions | +0.239 |
Neg logit contributions | |
Tom | -0.109 |
Ben | -0.099 |
Sam | -0.085 |
their | -0.084 |
sw | -0.077 |
Token | branches |
Token ID | 13737 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
Tom | +0.010 |
Ben | +0.010 |
sw | +0.009 |
Sam | +0.009 |
their | +0.009 |
Neg logit contributions | |
smanship | -0.015 |
outage | -0.015 |
inning | -0.014 |
bush | -0.014 |
iona | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -5.20e-01 |
Pos logit contributions | |
smanship | +0.092 |
outage | +0.086 |
remedy | +0.086 |
bush | +0.085 |
occasions | +0.085 |
Neg logit contributions | |
Tom | -0.041 |
Ben | -0.036 |
their | -0.032 |
Sam | -0.032 |
sw | -0.030 |
Token | some |
Token ID | 617 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
smanship | +0.018 |
outage | +0.017 |
bush | +0.016 |
remedy | +0.016 |
inning | +0.016 |
Neg logit contributions | |
Tom | -0.010 |
Ben | -0.010 |
Sam | -0.009 |
their | -0.009 |
sw | -0.008 |
Token | grass |
Token ID | 8701 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
smanship | +0.045 |
outage | +0.043 |
inning | +0.042 |
bush | +0.041 |
iona | +0.040 |
Neg logit contributions | |
Tom | -0.031 |
Ben | -0.030 |
sw | -0.028 |
their | -0.028 |
Sam | -0.027 |
Token | little |
Token ID | 1310 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
smanship | +0.020 |
outage | +0.019 |
bush | +0.018 |
remedy | +0.018 |
pleasures | +0.017 |
Neg logit contributions | |
Tom | -0.009 |
Ben | -0.009 |
Sam | -0.007 |
Rex | -0.007 |
sw | -0.007 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
Tom | +0.025 |
Ben | +0.025 |
sw | +0.022 |
Sam | +0.022 |
bye | +0.021 |
Neg logit contributions | |
smanship | -0.030 |
outage | -0.029 |
bush | -0.027 |
occasions | -0.026 |
inning | -0.026 |
Token | was |
Token ID | 373 |
Feature activation | -1.11e+00 |
Pos logit contributions | |
smanship | +0.004 |
outage | +0.004 |
bush | +0.004 |
remedy | +0.004 |
pleasures | +0.004 |
Neg logit contributions | |
Tom | -0.003 |
Ben | -0.002 |
Sam | -0.002 |
Rex | -0.002 |
sw | -0.002 |
Token | su |
Token ID | 424 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
smanship | +0.036 |
outage | +0.033 |
bush | +0.033 |
remedy | +0.032 |
oils | +0.031 |
Neg logit contributions | |
Tom | -0.023 |
Ben | -0.021 |
Sam | -0.019 |
arrest | -0.019 |
Rex | -0.019 |
Token | pr |
Token ID | 1050 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
outage | +0.040 |
smanship | +0.039 |
pleasures | +0.036 |
bush | +0.035 |
remedy | +0.034 |
Neg logit contributions | |
Tom | -0.070 |
arrest | -0.066 |
Ben | -0.066 |
Sam | -0.063 |
sw | -0.063 |
Token | ised |
Token ID | 1417 |
Feature activation | -6.96e+00 |
Pos logit contributions | |
smanship | +0.057 |
outage | +0.053 |
bush | +0.052 |
remedy | +0.051 |
pleasures | +0.048 |
Neg logit contributions | |
Tom | -0.116 |
Ben | -0.112 |
sw | -0.106 |
Sam | -0.105 |
bye | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | -7.94e-01 |
Pos logit contributions | |
outage | +0.256 |
smanship | +0.256 |
bush | +0.250 |
First | +0.241 |
pleasures | +0.236 |
Neg logit contributions | |
Tom | -0.112 |
Ben | -0.100 |
their | -0.093 |
at | -0.092 |
Sam | -0.086 |
Token | She |
Token ID | 1375 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
smanship | +0.024 |
outage | +0.023 |
bush | +0.022 |
remedy | +0.022 |
pleasures | +0.021 |
Neg logit contributions | |
Tom | -0.018 |
Ben | -0.017 |
Sam | -0.015 |
Rex | -0.015 |
their | -0.014 |
Token | had |
Token ID | 550 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
smanship | +0.042 |
outage | +0.040 |
pleasures | +0.038 |
bush | +0.038 |
inning | +0.037 |
Neg logit contributions | |
Tom | -0.022 |
Ben | -0.020 |
sw | -0.018 |
Sam | -0.018 |
Rex | -0.017 |
Token | never |
Token ID | 1239 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
smanship | +0.015 |
outage | +0.014 |
bush | +0.014 |
remedy | +0.013 |
pleasures | +0.013 |
Neg logit contributions | |
Tom | -0.008 |
Ben | -0.007 |
Sam | -0.006 |
Rex | -0.006 |
arrest | -0.006 |
Token | heard |
Token ID | 2982 |
Feature activation | +3.57e+00 |
Pos logit contributions | |
smanship | +0.004 |
outage | +0.004 |
bush | +0.004 |
remedy | +0.003 |
pleasures | +0.003 |
Neg logit contributions | |
Tom | -0.003 |
Ben | -0.002 |
Sam | -0.002 |
Rex | -0.002 |
arrest | -0.002 |
Token | The |
Token ID | 464 |
Feature activation | -7.08e-01 |
Pos logit contributions | |
Tom | +0.005 |
Ben | +0.005 |
Sam | +0.004 |
Leo | +0.004 |
their | +0.004 |
Neg logit contributions | |
smanship | -0.008 |
outage | -0.007 |
remedy | -0.007 |
occasions | -0.006 |
bush | -0.006 |
Token | little |
Token ID | 1310 |
Feature activation | +8.91e-01 |
Pos logit contributions | |
smanship | +0.025 |
outage | +0.023 |
bush | +0.022 |
First | +0.022 |
occasions | +0.021 |
Neg logit contributions | |
Tom | -0.014 |
Ben | -0.013 |
bye | -0.011 |
Sam | -0.011 |
ear | -0.011 |
Token | girl |
Token ID | 2576 |
Feature activation | -2.82e-01 |
Pos logit contributions | |
Tom | +0.019 |
Ben | +0.018 |
Sam | +0.015 |
ear | +0.014 |
bye | +0.014 |
Neg logit contributions | |
outage | -0.031 |
smanship | -0.030 |
inning | -0.029 |
occasions | -0.028 |
First | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
smanship | +0.009 |
bush | +0.008 |
outage | +0.008 |
remedy | +0.008 |
oils | +0.008 |
Neg logit contributions | |
Tom | -0.006 |
Ben | -0.006 |
Sam | -0.005 |
Rex | -0.005 |
arrest | -0.005 |
Token | mesmer |
Token ID | 46814 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
smanship | +0.028 |
bush | +0.027 |
outage | +0.027 |
remedy | +0.026 |
inning | +0.025 |
Neg logit contributions | |
Tom | -0.020 |
Ben | -0.019 |
arrest | -0.017 |
Sam | -0.017 |
Rex | -0.017 |
Token | ised |
Token ID | 1417 |
Feature activation | -6.87e+00 |
Pos logit contributions | |
smanship | +0.013 |
bush | +0.011 |
inning | +0.010 |
outage | +0.010 |
pleasures | +0.009 |
Neg logit contributions | |
Tom | -0.038 |
Ben | -0.037 |
Sam | -0.035 |
Rex | -0.035 |
arrest | -0.034 |
Token | . |
Token ID | 13 |
Feature activation | -8.86e-01 |
Pos logit contributions | |
outage | +0.234 |
smanship | +0.233 |
bush | +0.226 |
remedy | +0.220 |
First | +0.219 |
Neg logit contributions | |
Tom | -0.131 |
Ben | -0.120 |
their | -0.112 |
Sam | -0.107 |
at | -0.097 |
Token | " |
Token ID | 366 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
smanship | +0.030 |
outage | +0.028 |
bush | +0.027 |
remedy | +0.026 |
pleasures | +0.026 |
Neg logit contributions | |
Tom | -0.019 |
Ben | -0.018 |
Sam | -0.016 |
Rex | -0.015 |
Leo | -0.015 |
Token | You |
Token ID | 1639 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
smanship | +0.065 |
outage | +0.062 |
bush | +0.057 |
remedy | +0.056 |
occasions | +0.053 |
Neg logit contributions | |
Tom | -0.055 |
Ben | -0.052 |
Sam | -0.047 |
Dan | -0.045 |
sw | -0.045 |
Token | must |
Token ID | 1276 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
smanship | +0.034 |
outage | +0.033 |
bush | +0.032 |
remedy | +0.030 |
First | +0.030 |
Neg logit contributions | |
Tom | -0.024 |
Ben | -0.023 |
Rex | -0.021 |
Sam | -0.020 |
their | -0.020 |
Token | be |
Token ID | 307 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
smanship | +0.030 |
outage | +0.028 |
bars | +0.027 |
oils | +0.027 |
bush | +0.027 |
Neg logit contributions | |
Tom | -0.013 |
Ben | -0.012 |
Sam | -0.010 |
ear | -0.010 |
sw | -0.010 |
Token | z |
Token ID | 1976 |
Feature activation | +6.60e-01 |
Pos logit contributions | |
Tom | +0.008 |
Ben | +0.007 |
Sam | +0.007 |
arrest | +0.006 |
Rex | +0.006 |
Neg logit contributions | |
smanship | -0.012 |
bush | -0.011 |
outage | -0.011 |
remedy | -0.010 |
oils | -0.010 |
Token | ipped |
Token ID | 3949 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
Tom | +0.017 |
Ben | +0.016 |
Their | +0.015 |
their | +0.015 |
Sam | +0.015 |
Neg logit contributions | |
smanship | -0.016 |
bars | -0.014 |
bush | -0.014 |
ions | -0.014 |
outage | -0.013 |
Token | around |
Token ID | 1088 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
smanship | +0.027 |
bush | +0.026 |
outage | +0.026 |
remedy | +0.025 |
oils | +0.024 |
Neg logit contributions | |
Tom | -0.017 |
Ben | -0.016 |
Sam | -0.014 |
arrest | -0.014 |
Rex | -0.014 |
Token | collecting |
Token ID | 13157 |
Feature activation | -8.22e-01 |
Pos logit contributions | |
smanship | +0.043 |
outage | +0.040 |
bush | +0.040 |
remedy | +0.039 |
pleasures | +0.038 |
Neg logit contributions | |
Tom | -0.016 |
Ben | -0.015 |
Sam | -0.013 |
Rex | -0.012 |
arrest | -0.012 |
Token | tw |
Token ID | 665 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
smanship | +0.025 |
outage | +0.024 |
bush | +0.023 |
remedy | +0.022 |
pleasures | +0.022 |
Neg logit contributions | |
Tom | -0.018 |
Ben | -0.017 |
Sam | -0.016 |
Rex | -0.015 |
their | -0.015 |
Token | igs |
Token ID | 9235 |
Feature activation | -6.87e+00 |
Pos logit contributions | |
outage | +0.053 |
smanship | +0.051 |
remedy | +0.046 |
bush | +0.044 |
First | +0.041 |
Neg logit contributions | |
Ben | -0.086 |
Tom | -0.085 |
their | -0.081 |
sw | -0.081 |
Sam | -0.079 |
Token | and |
Token ID | 290 |
Feature activation | +7.14e-01 |
Pos logit contributions | |
smanship | +0.251 |
outage | +0.240 |
remedy | +0.235 |
bush | +0.235 |
occasions | +0.230 |
Neg logit contributions | |
Tom | -0.113 |
Ben | -0.103 |
their | -0.090 |
Sam | -0.089 |
sw | -0.084 |
Token | leaves |
Token ID | 5667 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
Tom | +0.015 |
Ben | +0.015 |
sw | +0.014 |
Sam | +0.014 |
their | +0.014 |
Neg logit contributions | |
outage | -0.023 |
smanship | -0.023 |
bush | -0.021 |
inning | -0.021 |
iona | -0.020 |
Token | , |
Token ID | 11 |
Feature activation | -5.34e-01 |
Pos logit contributions | |
smanship | +0.103 |
outage | +0.099 |
remedy | +0.096 |
bush | +0.096 |
occasions | +0.094 |
Neg logit contributions | |
Tom | -0.042 |
Ben | -0.038 |
their | -0.034 |
Sam | -0.033 |
sw | -0.032 |
Token | he |
Token ID | 339 |
Feature activation | +1.47e-01 |
Pos logit contributions | |
smanship | +0.018 |
outage | +0.017 |
bush | +0.016 |
remedy | +0.016 |
occasions | +0.015 |
Neg logit contributions | |
Tom | -0.011 |
Ben | -0.011 |
Sam | -0.009 |
their | -0.009 |
Rex | -0.009 |
Token | z |
Token ID | 1976 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
Tom | +0.003 |
Ben | +0.003 |
Sam | +0.003 |
sw | +0.003 |
their | +0.002 |
Neg logit contributions | |
smanship | -0.005 |
outage | -0.005 |
bush | -0.004 |
remedy | -0.004 |
pleasures | -0.004 |
Token | horn |
Token ID | 12718 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
smanship | +0.037 |
First | +0.034 |
outage | +0.034 |
bush | +0.033 |
pleasures | +0.033 |
Neg logit contributions | |
Tom | -0.018 |
Ben | -0.016 |
sw | -0.015 |
ear | -0.014 |
Sam | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -6.93e-03 |
Pos logit contributions | |
Tom | +0.035 |
Ben | +0.034 |
Sam | +0.030 |
arrest | +0.029 |
Their | +0.029 |
Neg logit contributions | |
smanship | -0.049 |
outage | -0.047 |
bush | -0.046 |
inning | -0.043 |
bars | -0.043 |
Token | He |
Token ID | 679 |
Feature activation | -1.93e-01 |
Pos logit contributions | |
smanship | +0.000 |
outage | +0.000 |
bush | +0.000 |
remedy | +0.000 |
pleasures | +0.000 |
Neg logit contributions | |
Tom | -0.000 |
Ben | -0.000 |
Sam | -0.000 |
arrest | -0.000 |
Rex | -0.000 |
Token | was |
Token ID | 373 |
Feature activation | -9.84e-01 |
Pos logit contributions | |
smanship | +0.006 |
bush | +0.006 |
outage | +0.006 |
remedy | +0.005 |
oils | +0.005 |
Neg logit contributions | |
Tom | -0.004 |
Ben | -0.004 |
Sam | -0.003 |
arrest | -0.003 |
Rex | -0.003 |
Token | mesmer |
Token ID | 46814 |
Feature activation | -8.26e-01 |
Pos logit contributions | |
smanship | +0.026 |
bush | +0.026 |
outage | +0.025 |
remedy | +0.024 |
First | +0.023 |
Neg logit contributions | |
Tom | -0.022 |
Ben | -0.022 |
arrest | -0.021 |
bye | -0.020 |
Sam | -0.019 |
Token | ised |
Token ID | 1417 |
Feature activation | -6.83e+00 |
Pos logit contributions | |
smanship | +0.009 |
izing | +0.008 |
inning | +0.008 |
bush | +0.008 |
heart | +0.007 |
Neg logit contributions | |
Tom | -0.033 |
Ben | -0.032 |
icks | -0.031 |
arrest | -0.031 |
Rex | -0.031 |
Token | by |
Token ID | 416 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
smanship | +0.228 |
outage | +0.221 |
bush | +0.220 |
remedy | +0.212 |
First | +0.211 |
Neg logit contributions | |
Tom | -0.139 |
Ben | -0.129 |
Sam | -0.118 |
their | -0.115 |
Rex | -0.106 |
Token | its |
Token ID | 663 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
smanship | +0.061 |
bush | +0.058 |
outage | +0.057 |
remedy | +0.056 |
pleasures | +0.056 |
Neg logit contributions | |
Tom | -0.032 |
Ben | -0.030 |
eg | -0.027 |
arrest | -0.027 |
Their | -0.025 |
Token | beauty |
Token ID | 8737 |
Feature activation | -5.67e-01 |
Pos logit contributions | |
Tom | +0.022 |
Ben | +0.021 |
Sam | +0.019 |
arrest | +0.018 |
Rex | +0.018 |
Neg logit contributions | |
smanship | -0.019 |
bush | -0.018 |
outage | -0.018 |
remedy | -0.017 |
pleasures | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
smanship | +0.022 |
First | +0.021 |
outage | +0.020 |
remedy | +0.020 |
bush | +0.020 |
Neg logit contributions | |
Tom | -0.009 |
Ben | -0.008 |
Sam | -0.006 |
their | -0.006 |
sw | -0.006 |
Token | wanted |
Token ID | 2227 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
Tom | +0.002 |
Ben | +0.002 |
arrest | +0.002 |
Sam | +0.002 |
Rex | +0.002 |
Neg logit contributions | |
smanship | -0.003 |
outage | -0.003 |
bush | -0.003 |
remedy | -0.003 |
pleasures | -0.003 |
Token | ! |
Token ID | 0 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
smanship | +0.065 |
outage | +0.061 |
oils | +0.061 |
remedy | +0.060 |
occasions | +0.060 |
Neg logit contributions | |
Tom | -0.030 |
Ben | -0.027 |
Sam | -0.024 |
their | -0.024 |
Rex | -0.022 |
Token | He |
Token ID | 679 |
Feature activation | -3.61e-01 |
Pos logit contributions | |
smanship | +0.020 |
bush | +0.019 |
outage | +0.019 |
First | +0.018 |
remedy | +0.018 |
Neg logit contributions | |
Tom | -0.011 |
Ben | -0.010 |
arrest | -0.009 |
their | -0.009 |
sw | -0.009 |
Token | gathered |
Token ID | 9272 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
smanship | +0.013 |
outage | +0.013 |
pleasures | +0.012 |
bush | +0.012 |
inning | +0.012 |
Neg logit contributions | |
Tom | -0.006 |
sw | -0.006 |
Ben | -0.006 |
Sam | -0.005 |
their | -0.005 |
Token | some |
Token ID | 617 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
smanship | +0.063 |
outage | +0.060 |
bush | +0.059 |
remedy | +0.056 |
pleasures | +0.055 |
Neg logit contributions | |
Tom | -0.031 |
Ben | -0.028 |
Sam | -0.025 |
their | -0.024 |
Rex | -0.023 |
Token | tw |
Token ID | 665 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
smanship | +0.106 |
outage | +0.104 |
bush | +0.096 |
inning | +0.095 |
iona | +0.093 |
Neg logit contributions | |
Tom | -0.063 |
sw | -0.060 |
their | -0.059 |
Ben | -0.059 |
Sam | -0.054 |
Token | igs |
Token ID | 9235 |
Feature activation | -6.82e+00 |
Pos logit contributions | |
smanship | +0.064 |
outage | +0.062 |
remedy | +0.054 |
First | +0.051 |
bush | +0.050 |
Neg logit contributions | |
sw | -0.089 |
Tom | -0.089 |
arrest | -0.087 |
their | -0.087 |
Ben | -0.086 |
Token | and |
Token ID | 290 |
Feature activation | -4.43e-03 |
Pos logit contributions | |
smanship | +0.257 |
outage | +0.244 |
bush | +0.239 |
remedy | +0.237 |
occasions | +0.235 |
Neg logit contributions | |
Tom | -0.107 |
Ben | -0.097 |
Sam | -0.084 |
their | -0.083 |
sw | -0.078 |
Token | leaves |
Token ID | 5667 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
smanship | +0.000 |
outage | +0.000 |
inning | +0.000 |
bush | +0.000 |
virtue | +0.000 |
Neg logit contributions | |
Tom | -0.000 |
sw | -0.000 |
Ben | -0.000 |
their | -0.000 |
Sam | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | -9.18e-01 |
Pos logit contributions | |
smanship | +0.121 |
outage | +0.115 |
remedy | +0.111 |
occasions | +0.111 |
bush | +0.111 |
Neg logit contributions | |
Tom | -0.051 |
Ben | -0.046 |
their | -0.043 |
Sam | -0.040 |
sw | -0.040 |
Token | and |
Token ID | 290 |
Feature activation | +4.42e-01 |
Pos logit contributions | |
smanship | +0.034 |
outage | +0.033 |
bush | +0.031 |
remedy | +0.031 |
pleasures | +0.030 |
Neg logit contributions | |
Tom | -0.016 |
Ben | -0.014 |
Sam | -0.013 |
sw | -0.012 |
their | -0.012 |
Token | organized |
Token ID | 8389 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
Tom | +0.009 |
Ben | +0.009 |
Sam | +0.008 |
sw | +0.008 |
their | +0.008 |
Neg logit contributions | |
smanship | -0.015 |
outage | -0.014 |
inning | -0.014 |
bush | -0.014 |
pleasures | -0.013 |
Token | would |
Token ID | 561 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
smanship | +0.003 |
outage | +0.003 |
bush | +0.003 |
pleasures | +0.003 |
iona | +0.003 |
Neg logit contributions | |
Tom | -0.003 |
Ben | -0.003 |
sw | -0.002 |
Sam | -0.002 |
their | -0.002 |
Token | take |
Token ID | 1011 |
Feature activation | -1.45e-01 |
Pos logit contributions | |
Tom | +0.003 |
Ben | +0.002 |
ear | +0.002 |
arrest | +0.002 |
Sam | +0.002 |
Neg logit contributions | |
smanship | -0.005 |
outage | -0.005 |
bush | -0.005 |
inning | -0.005 |
oils | -0.005 |
Token | out |
Token ID | 503 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
smanship | +0.005 |
occasions | +0.004 |
oils | +0.004 |
First | +0.004 |
pleasures | +0.004 |
Neg logit contributions | |
Tom | -0.002 |
Ben | -0.002 |
bye | -0.002 |
Rex | -0.002 |
arrest | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +3.07e-01 |
Pos logit contributions | |
Tom | +0.004 |
Ben | +0.004 |
Rex | +0.003 |
bye | +0.003 |
Sam | +0.003 |
Neg logit contributions | |
smanship | -0.009 |
outage | -0.008 |
bush | -0.008 |
remedy | -0.008 |
pleasures | -0.008 |
Token | j |
Token ID | 474 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
Tom | +0.006 |
Ben | +0.006 |
Sam | +0.005 |
their | +0.005 |
Leo | +0.005 |
Neg logit contributions | |
smanship | -0.010 |
outage | -0.009 |
bush | -0.009 |
inning | -0.009 |
pleasures | -0.009 |
Token | igsaw |
Token ID | 45636 |
Feature activation | -6.81e+00 |
Pos logit contributions | |
smanship | +0.043 |
outage | +0.041 |
bush | +0.041 |
remedy | +0.040 |
First | +0.039 |
Neg logit contributions | |
Tom | -0.037 |
Ben | -0.036 |
bye | -0.032 |
Sam | -0.032 |
arrest | -0.031 |
Token | puzzle |
Token ID | 15027 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
bush | +0.189 |
remedy | +0.183 |
iona | +0.182 |
oils | +0.181 |
pleasures | +0.177 |
Neg logit contributions | |
Tom | -0.144 |
Ben | -0.134 |
at | -0.133 |
their | -0.131 |
big | -0.125 |
Token | and |
Token ID | 290 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
smanship | +0.127 |
pleasures | +0.122 |
bush | +0.122 |
oils | +0.121 |
iona | +0.120 |
Neg logit contributions | |
Tom | -0.052 |
Ben | -0.047 |
Sam | -0.042 |
their | -0.041 |
at | -0.038 |
Token | try |
Token ID | 1949 |
Feature activation | -5.47e-01 |
Pos logit contributions | |
smanship | +0.032 |
outage | +0.031 |
bush | +0.030 |
inning | +0.029 |
remedy | +0.029 |
Neg logit contributions | |
Tom | -0.021 |
Ben | -0.020 |
Sam | -0.018 |
their | -0.017 |
arrest | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
smanship | +0.020 |
outage | +0.019 |
bush | +0.019 |
remedy | +0.018 |
iona | +0.018 |
Neg logit contributions | |
Tom | -0.010 |
Ben | -0.009 |
Sam | -0.008 |
their | -0.008 |
Rex | -0.007 |
Token | solve |
Token ID | 8494 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
outage | +0.035 |
smanship | +0.035 |
bush | +0.034 |
oils | +0.032 |
remedy | +0.032 |
Neg logit contributions | |
Tom | -0.028 |
Ben | -0.025 |
Sam | -0.023 |
arrest | -0.023 |
their | -0.023 |
Token | with |
Token ID | 351 |
Feature activation | +4.88e-01 |
Pos logit contributions | |
Tom | +0.002 |
Ben | +0.002 |
Sam | +0.002 |
their | +0.002 |
Rex | +0.002 |
Neg logit contributions | |
smanship | -0.004 |
outage | -0.003 |
bush | -0.003 |
remedy | -0.003 |
First | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | +3.26e-01 |
Pos logit contributions | |
Tom | +0.007 |
Ben | +0.007 |
bye | +0.006 |
arrest | +0.006 |
Rex | +0.006 |
Neg logit contributions | |
smanship | -0.018 |
bush | -0.016 |
outage | -0.016 |
remedy | -0.016 |
oils | -0.016 |
Token | friends |
Token ID | 2460 |
Feature activation | +1.50e-01 |
Pos logit contributions | |
Tom | +0.007 |
Ben | +0.006 |
Sam | +0.006 |
Rex | +0.006 |
their | +0.005 |
Neg logit contributions | |
smanship | -0.010 |
outage | -0.010 |
bush | -0.010 |
remedy | -0.009 |
pleasures | -0.009 |
Token | , |
Token ID | 11 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
Tom | +0.003 |
Ben | +0.002 |
Sam | +0.002 |
their | +0.002 |
Rex | +0.002 |
Neg logit contributions | |
smanship | -0.005 |
outage | -0.005 |
bush | -0.005 |
remedy | -0.005 |
pleasures | -0.005 |
Token | energ |
Token ID | 19647 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
smanship | +0.042 |
outage | +0.039 |
bush | +0.039 |
remedy | +0.037 |
pleasures | +0.037 |
Neg logit contributions | |
Tom | -0.030 |
Ben | -0.028 |
Sam | -0.025 |
Rex | -0.024 |
their | -0.024 |
Token | ised |
Token ID | 1417 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
smanship | +0.051 |
outage | +0.047 |
bush | +0.044 |
remedy | +0.041 |
pleasures | +0.039 |
Neg logit contributions | |
Tom | -0.119 |
Ben | -0.115 |
Sam | -0.108 |
their | -0.107 |
arrest | -0.106 |
Token | and |
Token ID | 290 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
outage | +0.235 |
smanship | +0.230 |
bush | +0.227 |
remedy | +0.217 |
First | +0.213 |
Neg logit contributions | |
Tom | -0.126 |
Ben | -0.117 |
their | -0.113 |
Sam | -0.103 |
his | -0.094 |
Token | ready |
Token ID | 3492 |
Feature activation | -2.26e-01 |
Pos logit contributions | |
smanship | +0.050 |
outage | +0.047 |
bush | +0.045 |
remedy | +0.044 |
inning | +0.044 |
Neg logit contributions | |
Tom | -0.036 |
Ben | -0.034 |
Sam | -0.031 |
their | -0.031 |
sw | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | -5.75e-01 |
Pos logit contributions | |
smanship | +0.008 |
outage | +0.007 |
bush | +0.007 |
remedy | +0.007 |
inning | +0.007 |
Neg logit contributions | |
Tom | -0.004 |
Ben | -0.004 |
Sam | -0.004 |
their | -0.003 |
bye | -0.003 |
Token | start |
Token ID | 923 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
smanship | +0.018 |
bush | +0.017 |
outage | +0.017 |
remedy | +0.016 |
occasions | +0.016 |
Neg logit contributions | |
Tom | -0.012 |
Ben | -0.011 |
Sam | -0.010 |
Rex | -0.010 |
arrest | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
smanship | +0.072 |
outage | +0.068 |
bush | +0.067 |
remedy | +0.065 |
pleasures | +0.064 |
Neg logit contributions | |
Tom | -0.032 |
Ben | -0.029 |
Sam | -0.025 |
their | -0.025 |
Rex | -0.023 |
Token | stack |
Token ID | 8931 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
smanship | +0.012 |
outage | +0.012 |
bush | +0.011 |
remedy | +0.011 |
oils | +0.010 |
Neg logit contributions | |
Tom | -0.011 |
Ben | -0.010 |
Sam | -0.009 |
Rex | -0.009 |
their | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -6.22e-01 |
Pos logit contributions | |
smanship | +0.074 |
outage | +0.071 |
bush | +0.069 |
remedy | +0.069 |
pleasures | +0.067 |
Neg logit contributions | |
Tom | -0.045 |
Ben | -0.041 |
Sam | -0.038 |
their | -0.037 |
Rex | -0.034 |
Token | They |
Token ID | 1119 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
smanship | +0.020 |
bush | +0.019 |
outage | +0.018 |
First | +0.018 |
pleasures | +0.018 |
Neg logit contributions | |
Tom | -0.012 |
Ben | -0.011 |
arrest | -0.011 |
bye | -0.010 |
sw | -0.010 |
Token | gathered |
Token ID | 9272 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
smanship | +0.031 |
outage | +0.030 |
bush | +0.030 |
remedy | +0.029 |
pleasures | +0.028 |
Neg logit contributions | |
Tom | -0.024 |
Ben | -0.022 |
Sam | -0.020 |
their | -0.020 |
sw | -0.020 |
Token | tw |
Token ID | 665 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
smanship | +0.053 |
outage | +0.049 |
bush | +0.049 |
remedy | +0.047 |
pleasures | +0.046 |
Neg logit contributions | |
Tom | -0.033 |
Ben | -0.031 |
Sam | -0.028 |
Rex | -0.027 |
arrest | -0.026 |
Token | igs |
Token ID | 9235 |
Feature activation | -6.79e+00 |
Pos logit contributions | |
outage | +0.065 |
smanship | +0.062 |
bush | +0.057 |
remedy | +0.056 |
pleasures | +0.049 |
Neg logit contributions | |
Tom | -0.114 |
Ben | -0.111 |
their | -0.108 |
Sam | -0.106 |
sw | -0.103 |
Token | , |
Token ID | 11 |
Feature activation | -1.51e+00 |
Pos logit contributions | |
smanship | +0.254 |
outage | +0.243 |
bush | +0.238 |
remedy | +0.235 |
occasions | +0.231 |
Neg logit contributions | |
Tom | -0.107 |
Ben | -0.098 |
Sam | -0.085 |
their | -0.083 |
Rex | -0.077 |
Token | stones |
Token ID | 14966 |
Feature activation | -3.26e+00 |
Pos logit contributions | |
smanship | +0.046 |
outage | +0.044 |
bush | +0.043 |
remedy | +0.041 |
pleasures | +0.040 |
Neg logit contributions | |
Tom | -0.036 |
Ben | -0.034 |
Sam | -0.031 |
their | -0.030 |
sw | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
smanship | +0.125 |
outage | +0.119 |
bush | +0.116 |
remedy | +0.116 |
pleasures | +0.114 |
Neg logit contributions | |
Tom | -0.049 |
Ben | -0.044 |
Sam | -0.038 |
their | -0.038 |
sw | -0.035 |
Token | leaves |
Token ID | 5667 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
smanship | +0.029 |
outage | +0.028 |
bush | +0.027 |
remedy | +0.026 |
pleasures | +0.026 |
Neg logit contributions | |
Tom | -0.014 |
Ben | -0.013 |
Sam | -0.012 |
their | -0.011 |
sw | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -6.92e-01 |
Pos logit contributions | |
smanship | +0.135 |
outage | +0.131 |
remedy | +0.127 |
bush | +0.125 |
occasions | +0.125 |
Neg logit contributions | |
Tom | -0.044 |
Ben | -0.039 |
their | -0.035 |
Sam | -0.034 |
sw | -0.031 |
Token | of |
Token ID | 286 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
smanship | +0.109 |
bush | +0.105 |
remedy | +0.105 |
iona | +0.101 |
pleasures | +0.101 |
Neg logit contributions | |
Tom | -0.058 |
Ben | -0.050 |
Sam | -0.045 |
their | -0.044 |
Rex | -0.038 |
Token | kicking |
Token ID | 17997 |
Feature activation | +2.66e-01 |
Pos logit contributions | |
smanship | +0.046 |
outage | +0.044 |
bush | +0.043 |
inning | +0.041 |
remedy | +0.041 |
Neg logit contributions | |
Tom | -0.027 |
Ben | -0.025 |
Sam | -0.022 |
their | -0.022 |
Rex | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | +7.21e-02 |
Pos logit contributions | |
Tom | +0.005 |
Ben | +0.005 |
their | +0.004 |
Sam | +0.004 |
Rex | +0.004 |
Neg logit contributions | |
smanship | -0.010 |
outage | -0.009 |
bush | -0.009 |
remedy | -0.009 |
iona | -0.008 |
Token | He |
Token ID | 679 |
Feature activation | -2.66e-01 |
Pos logit contributions | |
Tom | +0.001 |
Ben | +0.001 |
Sam | +0.001 |
Rex | +0.001 |
their | +0.001 |
Neg logit contributions | |
smanship | -0.003 |
outage | -0.003 |
bush | -0.003 |
remedy | -0.003 |
pleasures | -0.003 |
Token | pract |
Token ID | 1970 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
smanship | +0.009 |
outage | +0.008 |
bush | +0.008 |
pleasures | +0.008 |
remedy | +0.008 |
Neg logit contributions | |
Tom | -0.006 |
Ben | -0.005 |
Sam | -0.005 |
sw | -0.005 |
Rex | -0.005 |
Token | ised |
Token ID | 1417 |
Feature activation | -6.77e+00 |
Pos logit contributions | |
outage | +0.041 |
bush | +0.041 |
smanship | +0.039 |
remedy | +0.036 |
iona | +0.029 |
Neg logit contributions | |
Tom | -0.109 |
Ben | -0.106 |
their | -0.099 |
Sam | -0.099 |
both | -0.095 |
Token | every |
Token ID | 790 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
bush | +0.232 |
smanship | +0.230 |
outage | +0.229 |
remedy | +0.216 |
quet | +0.206 |
Neg logit contributions | |
Tom | -0.136 |
Ben | -0.130 |
Sam | -0.117 |
their | -0.116 |
his | -0.107 |
Token | day |
Token ID | 1110 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
smanship | +0.052 |
bush | +0.047 |
outage | +0.046 |
inning | +0.043 |
First | +0.043 |
Neg logit contributions | |
Tom | -0.052 |
Ben | -0.051 |
Sam | -0.046 |
ear | -0.046 |
bye | -0.045 |
Token | in |
Token ID | 287 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
smanship | +0.062 |
outage | +0.058 |
bush | +0.058 |
remedy | +0.056 |
pleasures | +0.054 |
Neg logit contributions | |
Tom | -0.037 |
Ben | -0.035 |
Sam | -0.031 |
Rex | -0.029 |
their | -0.029 |
Token | his |
Token ID | 465 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
Tom | +0.005 |
Ben | +0.005 |
Sam | +0.004 |
Rex | +0.004 |
bye | +0.004 |
Neg logit contributions | |
smanship | -0.016 |
outage | -0.015 |
bush | -0.015 |
remedy | -0.014 |
pleasures | -0.014 |
Token | garden |
Token ID | 11376 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
Tom | +0.046 |
Ben | +0.042 |
Sam | +0.039 |
arrest | +0.038 |
Rex | +0.038 |
Neg logit contributions | |
smanship | -0.051 |
bush | -0.046 |
remedy | -0.046 |
outage | -0.046 |
occasions | -0.045 |
Token | fingertips |
Token ID | 40142 |
Feature activation | +2.31e-01 |
Pos logit contributions | |
Tom | +0.044 |
Ben | +0.041 |
Sam | +0.035 |
Rex | +0.034 |
arrest | +0.033 |
Neg logit contributions | |
smanship | -0.095 |
outage | -0.089 |
bush | -0.088 |
remedy | -0.086 |
pleasures | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
Tom | +0.004 |
Ben | +0.004 |
Sam | +0.003 |
Rex | +0.003 |
their | +0.003 |
Neg logit contributions | |
smanship | -0.008 |
outage | -0.008 |
bush | -0.008 |
remedy | -0.007 |
pleasures | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | +1.21e-02 |
Pos logit contributions | |
smanship | +0.005 |
outage | +0.005 |
bush | +0.005 |
remedy | +0.004 |
pleasures | +0.004 |
Neg logit contributions | |
Tom | -0.002 |
Ben | -0.002 |
Sam | -0.002 |
Rex | -0.002 |
their | -0.002 |
Token | was |
Token ID | 373 |
Feature activation | -6.88e-01 |
Pos logit contributions | |
Tom | +0.000 |
Ben | +0.000 |
Sam | +0.000 |
sw | +0.000 |
their | +0.000 |
Neg logit contributions | |
smanship | -0.000 |
outage | -0.000 |
pleasures | -0.000 |
bush | -0.000 |
remedy | -0.000 |
Token | mesmer |
Token ID | 46814 |
Feature activation | -6.04e-01 |
Pos logit contributions | |
smanship | +0.024 |
outage | +0.022 |
bush | +0.022 |
occasions | +0.021 |
pleasures | +0.021 |
Neg logit contributions | |
Tom | -0.014 |
Ben | -0.013 |
Sam | -0.011 |
their | -0.011 |
ear | -0.011 |
Token | ised |
Token ID | 1417 |
Feature activation | -6.76e+00 |
Pos logit contributions | |
smanship | +0.008 |
bush | +0.007 |
outage | +0.006 |
inning | +0.006 |
remedy | +0.006 |
Neg logit contributions | |
Tom | -0.024 |
Ben | -0.023 |
Sam | -0.022 |
Rex | -0.022 |
arrest | -0.022 |
Token | by |
Token ID | 416 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
outage | +0.249 |
bush | +0.249 |
smanship | +0.248 |
remedy | +0.236 |
First | +0.233 |
Neg logit contributions | |
Tom | -0.110 |
Ben | -0.100 |
their | -0.094 |
Sam | -0.088 |
his | -0.080 |
Token | the |
Token ID | 262 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
smanship | +0.061 |
outage | +0.057 |
bush | +0.057 |
remedy | +0.056 |
pleasures | +0.055 |
Neg logit contributions | |
Tom | -0.023 |
Ben | -0.020 |
arrest | -0.017 |
Sam | -0.017 |
Rex | -0.017 |
Token | vibrant |
Token ID | 21266 |
Feature activation | -7.83e-01 |
Pos logit contributions | |
outage | +0.047 |
smanship | +0.045 |
iona | +0.045 |
bush | +0.044 |
remedy | +0.043 |
Neg logit contributions | |
Tom | -0.036 |
Ben | -0.035 |
their | -0.032 |
sw | -0.032 |
Sam | -0.031 |
Token | h |
Token ID | 289 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
outage | +0.020 |
smanship | +0.019 |
remedy | +0.019 |
First | +0.019 |
bush | +0.018 |
Neg logit contributions | |
Tom | -0.021 |
Ben | -0.020 |
their | -0.020 |
eyes | -0.019 |
ear | -0.019 |
Token | ues |
Token ID | 947 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
smanship | +0.035 |
remedy | +0.032 |
First | +0.032 |
outage | +0.031 |
bush | +0.030 |
Neg logit contributions | |
Tom | -0.037 |
Ben | -0.035 |
arrest | -0.033 |
Sam | -0.032 |
Dan | -0.031 |
Token | forget |
Token ID | 6044 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
Tom | +0.061 |
Ben | +0.057 |
Sam | +0.051 |
Rex | +0.049 |
arrest | +0.049 |
Neg logit contributions | |
smanship | -0.094 |
outage | -0.088 |
bush | -0.087 |
remedy | -0.084 |
pleasures | -0.082 |
Token | reality |
Token ID | 3950 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Tom | +0.034 |
Ben | +0.031 |
Sam | +0.027 |
Rex | +0.026 |
their | +0.026 |
Neg logit contributions | |
smanship | -0.064 |
outage | -0.061 |
bush | -0.060 |
remedy | -0.058 |
pleasures | -0.057 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Tom | +0.023 |
Ben | +0.021 |
their | +0.017 |
Sam | +0.017 |
Rex | +0.017 |
Neg logit contributions | |
smanship | -0.056 |
bush | -0.053 |
outage | -0.052 |
remedy | -0.051 |
First | -0.050 |
Token |
|
Token ID | 198 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
arrest | +0.019 |
Tom | +0.018 |
sw | +0.017 |
ked | +0.017 |
ear | +0.016 |
Neg logit contributions | |
outage | -0.030 |
bush | -0.029 |
smanship | -0.029 |
First | -0.029 |
pleasures | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
Tom | +0.019 |
Ben | +0.018 |
arrest | +0.016 |
Sam | +0.016 |
ear | +0.015 |
Neg logit contributions | |
smanship | -0.028 |
outage | -0.027 |
bush | -0.027 |
remedy | -0.025 |
First | -0.025 |
Token | S |
Token ID | 50 |
Feature activation | +2.98e+00 |
Pos logit contributions | |
Tom | +0.028 |
Ben | +0.026 |
Sam | +0.023 |
their | +0.023 |
Rex | +0.022 |
Neg logit contributions | |
smanship | -0.044 |
outage | -0.041 |
bush | -0.040 |
remedy | -0.039 |
pleasures | -0.038 |
Token | ara |
Token ID | 3301 |
Feature activation | +3.33e-01 |
Pos logit contributions | |
Tom | +0.067 |
Ben | +0.063 |
Sam | +0.057 |
Rex | +0.055 |
arrest | +0.055 |
Neg logit contributions | |
smanship | -0.092 |
bush | -0.085 |
outage | -0.085 |
remedy | -0.081 |
pleasures | -0.080 |
Token | and |
Token ID | 290 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
Tom | +0.006 |
Ben | +0.006 |
Sam | +0.005 |
arrest | +0.005 |
their | +0.005 |
Neg logit contributions | |
smanship | -0.011 |
outage | -0.010 |
bush | -0.010 |
remedy | -0.010 |
oils | -0.010 |
Token | Ben |
Token ID | 3932 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
arrest | +0.048 |
eg | +0.038 |
sw | +0.035 |
cannon | +0.034 |
icks | +0.034 |
Neg logit contributions | |
oils | -0.169 |
smanship | -0.162 |
remedy | -0.157 |
exercises | -0.157 |
First | -0.157 |
Token | nod |
Token ID | 18666 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
Tom | +0.045 |
Ben | +0.041 |
Sam | +0.040 |
arrest | +0.039 |
Rex | +0.039 |
Neg logit contributions | |
smanship | -0.062 |
bush | -0.057 |
outage | -0.056 |
pleasures | -0.054 |
remedy | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | +7.62e-01 |
Pos logit contributions | |
arrest | +0.032 |
Tom | +0.031 |
Ben | +0.028 |
Sam | +0.027 |
Dan | +0.027 |
Neg logit contributions | |
smanship | -0.036 |
pleasures | -0.036 |
outage | -0.035 |
inning | -0.034 |
remedy | -0.034 |
Token | okay |
Token ID | 8788 |
Feature activation | +7.49e-01 |
Pos logit contributions | |
Tom | +0.009 |
Ben | +0.009 |
arrest | +0.008 |
eg | +0.008 |
Their | +0.008 |
Neg logit contributions | |
smanship | -0.008 |
remedy | -0.007 |
outage | -0.007 |
bush | -0.007 |
inning | -0.007 |
Token | , |
Token ID | 11 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
Tom | +0.015 |
Ben | +0.014 |
arrest | +0.014 |
sw | +0.013 |
ear | +0.013 |
Neg logit contributions | |
smanship | -0.023 |
outage | -0.022 |
bush | -0.021 |
remedy | -0.020 |
inning | -0.020 |
Token | kids |
Token ID | 3988 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
outage | +0.012 |
smanship | +0.012 |
bush | +0.011 |
guard | +0.011 |
place | +0.011 |
Neg logit contributions | |
eg | -0.007 |
icks | -0.006 |
ked | -0.006 |
ear | -0.006 |
cks | -0.006 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
Tom | +0.047 |
Ben | +0.045 |
Sam | +0.041 |
Rex | +0.040 |
arrest | +0.039 |
Neg logit contributions | |
smanship | -0.054 |
outage | -0.050 |
bush | -0.049 |
remedy | -0.047 |
pleasures | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
icks | +0.026 |
eg | +0.026 |
arrest | +0.024 |
ked | +0.024 |
ss | +0.023 |
Neg logit contributions | |
outage | -0.039 |
smanship | -0.039 |
guard | -0.038 |
Sometimes | -0.038 |
First | -0.037 |
Token | park |
Token ID | 3952 |
Feature activation | +3.50e+00 |
Pos logit contributions | |
Tom | +0.015 |
Ben | +0.015 |
icks | +0.014 |
eg | +0.014 |
ear | +0.014 |
Neg logit contributions | |
smanship | -0.015 |
bush | -0.015 |
remedy | -0.013 |
pleasures | -0.013 |
place | -0.013 |
Token | ranger |
Token ID | 43570 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
arrest | +0.102 |
Ben | +0.102 |
Tom | +0.101 |
icks | +0.098 |
ear | +0.093 |
Neg logit contributions | |
smanship | -0.067 |
bush | -0.067 |
outage | -0.063 |
guard | -0.061 |
remedy | -0.059 |
Token | asked |
Token ID | 1965 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
Tom | +0.052 |
arrest | +0.051 |
Ben | +0.049 |
bye | +0.046 |
their | +0.045 |
Neg logit contributions | |
smanship | -0.072 |
outage | -0.069 |
bush | -0.066 |
remedy | -0.064 |
bars | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
smanship | +0.031 |
bush | +0.028 |
outage | +0.028 |
remedy | +0.027 |
pleasures | +0.027 |
Neg logit contributions | |
Tom | -0.020 |
Ben | -0.019 |
arrest | -0.019 |
bye | -0.017 |
sw | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +6.19e-01 |
Pos logit contributions | |
arrest | +0.003 |
ear | +0.002 |
sw | +0.002 |
bye | +0.002 |
Tom | +0.002 |
Neg logit contributions | |
outage | -0.003 |
bush | -0.003 |
smanship | -0.003 |
First | -0.003 |
opener | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +9.55e-01 |
Pos logit contributions | |
Tom | +0.011 |
Ben | +0.010 |
ear | +0.009 |
arrest | +0.009 |
bye | +0.009 |
Neg logit contributions | |
smanship | -0.020 |
outage | -0.020 |
bush | -0.019 |
First | -0.019 |
remedy | -0.018 |
Token | march |
Token ID | 9960 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
Tom | +0.012 |
Ben | +0.011 |
Sam | +0.010 |
arrest | +0.010 |
bye | +0.010 |
Neg logit contributions | |
smanship | -0.019 |
outage | -0.018 |
bush | -0.018 |
bars | -0.017 |
First | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
Tom | +0.030 |
Ben | +0.029 |
arrest | +0.027 |
Sam | +0.026 |
Leo | +0.025 |
Neg logit contributions | |
smanship | -0.042 |
outage | -0.040 |
bush | -0.039 |
pleasures | -0.038 |
First | -0.037 |
Token | play |
Token ID | 711 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
Tom | +0.049 |
Ben | +0.045 |
arrest | +0.042 |
Sam | +0.040 |
bye | +0.040 |
Neg logit contributions | |
smanship | -0.077 |
outage | -0.074 |
bush | -0.071 |
occasions | -0.069 |
bars | -0.068 |
Token | music |
Token ID | 2647 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
Tom | +0.031 |
Ben | +0.029 |
arrest | +0.027 |
Sam | +0.027 |
Leo | +0.026 |
Neg logit contributions | |
smanship | -0.037 |
outage | -0.035 |
bush | -0.035 |
pleasures | -0.034 |
inning | -0.034 |
Token | behind |
Token ID | 2157 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
Tom | +0.010 |
Ben | +0.009 |
Sam | +0.008 |
Rex | +0.008 |
their | +0.008 |
Neg logit contributions | |
smanship | -0.019 |
outage | -0.018 |
bush | -0.018 |
remedy | -0.017 |
pleasures | -0.017 |
Token | the |
Token ID | 262 |
Feature activation | +3.42e+00 |
Pos logit contributions | |
eg | +0.037 |
bye | +0.037 |
Tom | +0.036 |
arrest | +0.036 |
ked | +0.034 |
Neg logit contributions | |
smanship | -0.082 |
outage | -0.077 |
bush | -0.077 |
things | -0.077 |
occasions | -0.076 |
Token | big |
Token ID | 1263 |
Feature activation | +4.37e+00 |
Pos logit contributions | |
Tom | +0.081 |
Ben | +0.077 |
Sam | +0.071 |
arrest | +0.068 |
Leo | +0.068 |
Neg logit contributions | |
smanship | -0.096 |
outage | -0.091 |
bush | -0.090 |
remedy | -0.085 |
pleasures | -0.084 |
Token | band |
Token ID | 4097 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
Tom | +0.108 |
Ben | +0.102 |
Sam | +0.093 |
Rex | +0.090 |
their | +0.089 |
Neg logit contributions | |
smanship | -0.126 |
outage | -0.116 |
bush | -0.115 |
remedy | -0.111 |
pleasures | -0.108 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
Tom | +0.040 |
Ben | +0.039 |
Sam | +0.034 |
arrest | +0.033 |
Leo | +0.032 |
Neg logit contributions | |
smanship | -0.064 |
outage | -0.061 |
bush | -0.059 |
occasions | -0.056 |
pleasures | -0.056 |
Token | They |
Token ID | 1119 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
arrest | +0.023 |
sw | +0.021 |
ked | +0.020 |
ear | +0.020 |
eg | +0.020 |
Neg logit contributions | |
outage | -0.036 |
First | -0.036 |
bush | -0.034 |
smanship | -0.034 |
pleasures | -0.033 |
Token | make |
Token ID | 787 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
Tom | +0.016 |
Ben | +0.015 |
Sam | +0.014 |
arrest | +0.014 |
Leo | +0.013 |
Neg logit contributions | |
smanship | -0.025 |
outage | -0.024 |
bush | -0.022 |
pleasures | -0.022 |
First | -0.022 |
Token | bowl |
Token ID | 9396 |
Feature activation | +3.01e-01 |
Pos logit contributions | |
Tom | +0.012 |
Ben | +0.011 |
Sam | +0.010 |
Rex | +0.010 |
their | +0.010 |
Neg logit contributions | |
smanship | -0.014 |
outage | -0.013 |
bush | -0.013 |
remedy | -0.012 |
pleasures | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
Tom | +0.006 |
Ben | +0.006 |
Sam | +0.005 |
Rex | +0.005 |
their | +0.005 |
Neg logit contributions | |
smanship | -0.010 |
outage | -0.009 |
bush | -0.009 |
remedy | -0.009 |
pleasures | -0.009 |
Token | He |
Token ID | 679 |
Feature activation | +5.09e-01 |
Pos logit contributions | |
Tom | +0.015 |
Ben | +0.014 |
arrest | +0.013 |
sw | +0.013 |
bye | +0.013 |
Neg logit contributions | |
smanship | -0.027 |
bush | -0.025 |
outage | -0.024 |
remedy | -0.024 |
First | -0.024 |
Token | didn |
Token ID | 1422 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
Tom | +0.012 |
Ben | +0.011 |
arrest | +0.010 |
Sam | +0.010 |
bye | +0.010 |
Neg logit contributions | |
smanship | -0.015 |
outage | -0.014 |
bush | -0.014 |
remedy | -0.013 |
oils | -0.013 |
Token | 't |
Token ID | 470 |
Feature activation | +2.69e-01 |
Pos logit contributions | |
Tom | +0.039 |
Ben | +0.036 |
Sam | +0.033 |
Rex | +0.032 |
their | +0.031 |
Neg logit contributions | |
smanship | -0.052 |
bush | -0.048 |
outage | -0.048 |
remedy | -0.046 |
pleasures | -0.046 |
Token | want |
Token ID | 765 |
Feature activation | +4.31e+00 |
Pos logit contributions | |
Tom | +0.006 |
Ben | +0.005 |
Sam | +0.005 |
Rex | +0.005 |
arrest | +0.005 |
Neg logit contributions | |
smanship | -0.009 |
outage | -0.008 |
bush | -0.008 |
remedy | -0.008 |
pleasures | -0.008 |
Token | to |
Token ID | 284 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
Tom | +0.085 |
Ben | +0.079 |
bye | +0.072 |
arrest | +0.072 |
sw | +0.071 |
Neg logit contributions | |
smanship | -0.133 |
outage | -0.128 |
bush | -0.123 |
remedy | -0.122 |
occasions | -0.120 |
Token | be |
Token ID | 307 |
Feature activation | -8.58e-02 |
Pos logit contributions | |
Tom | +0.026 |
Ben | +0.025 |
Sam | +0.022 |
arrest | +0.022 |
Rex | +0.022 |
Neg logit contributions | |
smanship | -0.041 |
outage | -0.041 |
bush | -0.039 |
remedy | -0.038 |
occasions | -0.037 |
Token | scared |
Token ID | 12008 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
outage | +0.002 |
smanship | +0.002 |
bush | +0.002 |
remedy | +0.002 |
heart | +0.002 |
Neg logit contributions | |
Tom | -0.002 |
Ben | -0.002 |
bye | -0.002 |
eg | -0.002 |
arrest | -0.002 |
Token | so |
Token ID | 523 |
Feature activation | -8.15e-02 |
Pos logit contributions | |
Tom | +0.040 |
Ben | +0.038 |
Sam | +0.035 |
arrest | +0.034 |
Rex | +0.034 |
Neg logit contributions | |
smanship | -0.049 |
outage | -0.046 |
bush | -0.045 |
remedy | -0.043 |
pleasures | -0.043 |
Token | he |
Token ID | 339 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
smanship | +0.002 |
outage | +0.002 |
bush | +0.002 |
pleasures | +0.002 |
remedy | +0.002 |
Neg logit contributions | |
Tom | -0.002 |
Ben | -0.002 |
sw | -0.002 |
ear | -0.002 |
eg | -0.002 |
Token | said |
Token ID | 531 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
Tom | +0.002 |
Ben | +0.002 |
arrest | +0.002 |
bye | +0.002 |
Sam | +0.002 |
Neg logit contributions | |
smanship | -0.003 |
outage | -0.003 |
bush | -0.003 |
First | -0.003 |
remedy | -0.003 |
Token | no |
Token ID | 645 |
Feature activation | -5.25e-01 |
Pos logit contributions | |
Tom | +0.008 |
arrest | +0.008 |
Ben | +0.008 |
eg | +0.007 |
Sam | +0.007 |
Neg logit contributions | |
outage | -0.016 |
smanship | -0.016 |
bush | -0.016 |
remedy | -0.015 |
oils | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
smanship | +0.020 |
bush | +0.019 |
outage | +0.018 |
remedy | +0.018 |
inning | +0.018 |
Neg logit contributions | |
Tom | -0.010 |
Ben | -0.008 |
Sam | -0.008 |
their | -0.007 |
Rex | -0.007 |
Token | their |
Token ID | 511 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
Tom | +0.032 |
Ben | +0.030 |
arrest | +0.026 |
Sam | +0.026 |
Rex | +0.026 |
Neg logit contributions | |
smanship | -0.054 |
outage | -0.052 |
bush | -0.051 |
remedy | -0.049 |
occasions | -0.049 |
Token | mom |
Token ID | 1995 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
Tom | +0.057 |
Ben | +0.052 |
Sam | +0.047 |
arrest | +0.046 |
ked | +0.044 |
Neg logit contributions | |
smanship | -0.131 |
outage | -0.127 |
remedy | -0.123 |
occasions | -0.123 |
bush | -0.122 |
Token | and |
Token ID | 290 |
Feature activation | +3.41e+00 |
Pos logit contributions | |
Tom | +0.039 |
Ben | +0.038 |
arrest | +0.035 |
Sam | +0.033 |
sw | +0.033 |
Neg logit contributions | |
smanship | -0.068 |
outage | -0.064 |
bush | -0.063 |
remedy | -0.060 |
pleasures | -0.059 |
Token | turned |
Token ID | 2900 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
Tom | +0.052 |
Ben | +0.049 |
arrest | +0.045 |
eg | +0.042 |
sw | +0.042 |
Neg logit contributions | |
smanship | -0.117 |
outage | -0.114 |
bush | -0.109 |
remedy | -0.108 |
occasions | -0.106 |
Token | the |
Token ID | 262 |
Feature activation | -5.76e-02 |
Pos logit contributions | |
Tom | +0.035 |
Ben | +0.032 |
Sam | +0.028 |
arrest | +0.027 |
Rex | +0.027 |
Neg logit contributions | |
smanship | -0.073 |
outage | -0.070 |
bush | -0.069 |
remedy | -0.067 |
oils | -0.066 |
Token | TV |
Token ID | 3195 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
smanship | +0.002 |
outage | +0.002 |
bush | +0.002 |
remedy | +0.001 |
pleasures | +0.001 |
Neg logit contributions | |
Tom | -0.001 |
Ben | -0.001 |
Sam | -0.001 |
Rex | -0.001 |
arrest | -0.001 |
Token | louder |
Token ID | 27089 |
Feature activation | +9.76e-01 |
Pos logit contributions | |
Tom | +0.046 |
Ben | +0.043 |
arrest | +0.039 |
Sam | +0.039 |
Rex | +0.037 |
Neg logit contributions | |
smanship | -0.078 |
outage | -0.074 |
bush | -0.072 |
remedy | -0.069 |
pleasures | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | +7.76e-01 |
Pos logit contributions | |
Tom | +0.018 |
Ben | +0.016 |
Sam | +0.014 |
Rex | +0.014 |
arrest | +0.014 |
Neg logit contributions | |
smanship | -0.034 |
outage | -0.032 |
bush | -0.031 |
remedy | -0.030 |
pleasures | -0.030 |
Token | Tim |
Token ID | 5045 |
Feature activation | +2.03e-01 |
Pos logit contributions | |
smanship | +0.018 |
occasions | +0.017 |
bush | +0.016 |
ions | +0.016 |
remedy | +0.016 |
Neg logit contributions | |
eg | -0.007 |
Ben | -0.007 |
bye | -0.007 |
realizes | -0.006 |
icks | -0.006 |
Token | my |
Token ID | 1820 |
Feature activation | -1.97e-02 |
Pos logit contributions | |
Tom | +0.007 |
Ben | +0.006 |
Sam | +0.006 |
arrest | +0.006 |
Rex | +0.006 |
Neg logit contributions | |
smanship | -0.004 |
outage | -0.004 |
bush | -0.004 |
remedy | -0.003 |
pleasures | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | -1.49e-01 |
Pos logit contributions | |
smanship | +0.001 |
outage | +0.001 |
bush | +0.001 |
remedy | +0.001 |
First | +0.001 |
Neg logit contributions | |
Tom | -0.000 |
Ben | -0.000 |
arrest | -0.000 |
bye | -0.000 |
Sam | -0.000 |
Token | " |
Token ID | 366 |
Feature activation | -1.49e+00 |
Pos logit contributions | |
smanship | +0.005 |
bush | +0.005 |
outage | +0.005 |
remedy | +0.004 |
First | +0.004 |
Neg logit contributions | |
Tom | -0.003 |
Ben | -0.003 |
arrest | -0.002 |
Rex | -0.002 |
Sam | -0.002 |
Token | Mom |
Token ID | 29252 |
Feature activation | -1.08e-01 |
Pos logit contributions | |
smanship | +0.043 |
outage | +0.040 |
bush | +0.040 |
remedy | +0.038 |
pleasures | +0.037 |
Neg logit contributions | |
Tom | -0.037 |
Ben | -0.035 |
Sam | -0.031 |
Rex | -0.030 |
their | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
smanship | +0.003 |
outage | +0.002 |
bush | +0.002 |
remedy | +0.002 |
pleasures | +0.002 |
Neg logit contributions | |
Tom | -0.003 |
Ben | -0.003 |
Sam | -0.003 |
Rex | -0.003 |
bye | -0.003 |
Token | can |
Token ID | 460 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
Tom | +0.007 |
Ben | +0.006 |
arrest | +0.006 |
Sam | +0.006 |
Rex | +0.005 |
Neg logit contributions | |
smanship | -0.011 |
outage | -0.010 |
bush | -0.010 |
remedy | -0.010 |
pleasures | -0.010 |
Token | we |
Token ID | 356 |
Feature activation | -1.16e+00 |
Pos logit contributions | |
smanship | +0.001 |
outage | +0.001 |
bush | +0.001 |
remedy | +0.001 |
occasions | +0.001 |
Neg logit contributions | |
Tom | -0.001 |
Ben | -0.001 |
Sam | -0.001 |
Rex | -0.001 |
arrest | -0.001 |
Token | buy |
Token ID | 2822 |
Feature activation | -6.99e-01 |
Pos logit contributions | |
smanship | +0.032 |
bush | +0.029 |
outage | +0.028 |
remedy | +0.028 |
First | +0.027 |
Neg logit contributions | |
Tom | -0.028 |
Ben | -0.027 |
Sam | -0.024 |
Leo | -0.024 |
Rex | -0.024 |
Token | this |
Token ID | 428 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
smanship | +0.022 |
bush | +0.021 |
outage | +0.021 |
remedy | +0.020 |
oils | +0.020 |
Neg logit contributions | |
Tom | -0.012 |
Ben | -0.012 |
arrest | -0.011 |
Sam | -0.010 |
ear | -0.010 |
Token | je |
Token ID | 11223 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
smanship | +0.053 |
outage | +0.050 |
bush | +0.050 |
remedy | +0.047 |
bars | +0.046 |
Neg logit contributions | |
Tom | -0.039 |
Ben | -0.038 |
arrest | -0.034 |
Leo | -0.034 |
Sam | -0.033 |
Token | Max |
Token ID | 5436 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
eg | +0.022 |
arrest | +0.021 |
sw | +0.017 |
icks | +0.017 |
boarding | +0.017 |
Neg logit contributions | |
smanship | -0.134 |
remedy | -0.126 |
oils | -0.125 |
iona | -0.125 |
bush | -0.124 |
Token | nod |
Token ID | 18666 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
Tom | +0.040 |
Ben | +0.037 |
arrest | +0.036 |
Rex | +0.035 |
Sam | +0.035 |
Neg logit contributions | |
smanship | -0.053 |
bush | -0.049 |
First | -0.047 |
remedy | -0.047 |
outage | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +6.98e-01 |
Pos logit contributions | |
Tom | +0.028 |
Ben | +0.026 |
arrest | +0.026 |
Sam | +0.023 |
Leo | +0.023 |
Neg logit contributions | |
smanship | -0.042 |
outage | -0.040 |
pleasures | -0.039 |
bush | -0.039 |
remedy | -0.038 |
Token | They |
Token ID | 1119 |
Feature activation | -1.17e-01 |
Pos logit contributions | |
Tom | +0.010 |
Ben | +0.009 |
arrest | +0.009 |
sw | +0.008 |
Sam | +0.008 |
Neg logit contributions | |
smanship | -0.025 |
outage | -0.024 |
bush | -0.024 |
First | -0.023 |
remedy | -0.023 |
Token | sit |
Token ID | 1650 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
smanship | +0.004 |
bush | +0.004 |
outage | +0.003 |
First | +0.003 |
remedy | +0.003 |
Neg logit contributions | |
Tom | -0.002 |
Ben | -0.002 |
Sam | -0.002 |
Rex | -0.002 |
arrest | -0.002 |
Token | on |
Token ID | 319 |
Feature activation | +1.39e-02 |
Pos logit contributions | |
smanship | +0.000 |
bush | +0.000 |
outage | +0.000 |
inning | +0.000 |
remedy | +0.000 |
Neg logit contributions | |
Tom | -0.000 |
Ben | -0.000 |
arrest | -0.000 |
Sam | -0.000 |
Rex | -0.000 |
Token | the |
Token ID | 262 |
Feature activation | +5.46e-01 |
Pos logit contributions | |
Tom | +0.000 |
bye | +0.000 |
icks | +0.000 |
arrest | +0.000 |
Ben | +0.000 |
Neg logit contributions | |
smanship | -0.000 |
oils | -0.000 |
bush | -0.000 |
First | -0.000 |
remedy | -0.000 |
Token | grass |
Token ID | 8701 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
Tom | +0.014 |
Ben | +0.013 |
Sam | +0.012 |
Rex | +0.012 |
their | +0.012 |
Neg logit contributions | |
smanship | -0.016 |
outage | -0.014 |
bush | -0.014 |
remedy | -0.014 |
pleasures | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
smanship | +0.023 |
outage | +0.021 |
bush | +0.021 |
remedy | +0.020 |
pleasures | +0.020 |
Neg logit contributions | |
Tom | -0.012 |
Ben | -0.011 |
Sam | -0.010 |
arrest | -0.009 |
Rex | -0.009 |
Token | watch |
Token ID | 2342 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
Tom | +0.032 |
Ben | +0.030 |
Sam | +0.026 |
Rex | +0.025 |
arrest | +0.025 |
Neg logit contributions | |
smanship | -0.054 |
outage | -0.051 |
bush | -0.051 |
remedy | -0.049 |
pleasures | -0.048 |
Token | the |
Token ID | 262 |
Feature activation | +4.95e-01 |
Pos logit contributions | |
arrest | +0.014 |
Tom | +0.014 |
Ben | +0.013 |
eg | +0.012 |
sw | +0.011 |
Neg logit contributions | |
smanship | -0.039 |
bush | -0.037 |
outage | -0.037 |
oils | -0.036 |
pleasures | -0.036 |
Token | Mary |
Token ID | 5335 |
Feature activation | +1.98e+00 |
Pos logit contributions | |
smanship | +0.002 |
outage | +0.002 |
bush | +0.002 |
remedy | +0.002 |
oils | +0.002 |
Neg logit contributions | |
Tom | -0.002 |
Ben | -0.002 |
arrest | -0.001 |
sw | -0.001 |
Rex | -0.001 |
Token | was |
Token ID | 373 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
Tom | +0.047 |
Ben | +0.044 |
Sam | +0.041 |
their | +0.039 |
Rex | +0.039 |
Neg logit contributions | |
smanship | -0.056 |
bush | -0.052 |
outage | -0.051 |
remedy | -0.050 |
oils | -0.049 |
Token | sleeping |
Token ID | 11029 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
Tom | +0.013 |
Ben | +0.012 |
Sam | +0.011 |
Rex | +0.011 |
their | +0.010 |
Neg logit contributions | |
smanship | -0.020 |
outage | -0.018 |
bush | -0.018 |
remedy | -0.017 |
pleasures | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -8.33e-01 |
Pos logit contributions | |
Tom | +0.022 |
Ben | +0.020 |
Sam | +0.016 |
their | +0.016 |
Rex | +0.015 |
Neg logit contributions | |
smanship | -0.063 |
outage | -0.062 |
bush | -0.059 |
First | -0.058 |
pleasures | -0.058 |
Token | a |
Token ID | 257 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
smanship | +0.023 |
outage | +0.021 |
bush | +0.021 |
remedy | +0.020 |
pleasures | +0.019 |
Neg logit contributions | |
Tom | -0.021 |
Ben | -0.020 |
Sam | -0.018 |
Rex | -0.018 |
arrest | -0.018 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +2.54e-01 |
Pos logit contributions | |
Tom | +0.021 |
Ben | +0.019 |
Sam | +0.017 |
Rex | +0.016 |
sw | +0.016 |
Neg logit contributions | |
smanship | -0.047 |
outage | -0.044 |
bush | -0.044 |
pleasures | -0.043 |
occasions | -0.043 |
Token | fairy |
Token ID | 25607 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
Tom | +0.006 |
Ben | +0.005 |
Sam | +0.005 |
bye | +0.004 |
sw | +0.004 |
Neg logit contributions | |
smanship | -0.008 |
outage | -0.008 |
First | -0.007 |
bush | -0.007 |
pleasures | -0.007 |
Token | flew |
Token ID | 13112 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
Tom | +0.012 |
Ben | +0.011 |
Sam | +0.010 |
Rex | +0.010 |
bye | +0.010 |
Neg logit contributions | |
smanship | -0.020 |
bush | -0.019 |
outage | -0.019 |
remedy | -0.018 |
occasions | -0.017 |
Token | down |
Token ID | 866 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Tom | +0.028 |
Ben | +0.027 |
arrest | +0.025 |
Sam | +0.024 |
Rex | +0.024 |
Neg logit contributions | |
smanship | -0.034 |
bush | -0.034 |
outage | -0.032 |
remedy | -0.031 |
heart | -0.030 |
Token | from |
Token ID | 422 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
Tom | +0.019 |
Ben | +0.018 |
eg | +0.018 |
bye | +0.017 |
arrest | +0.016 |
Neg logit contributions | |
smanship | -0.032 |
bush | -0.030 |
outage | -0.030 |
remedy | -0.028 |
First | -0.028 |
Token | the |
Token ID | 262 |
Feature activation | +5.10e-01 |
Pos logit contributions | |
Tom | +0.036 |
eg | +0.036 |
Ben | +0.035 |
bye | +0.033 |
Their | +0.031 |
Neg logit contributions | |
smanship | -0.077 |
bush | -0.075 |
outage | -0.073 |
remedy | -0.071 |
iona | -0.070 |
Token | stream |
Token ID | 4269 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
smanship | +0.049 |
outage | +0.047 |
bush | +0.045 |
bars | +0.044 |
heart | +0.043 |
Neg logit contributions | |
Ben | -0.034 |
Tom | -0.034 |
sw | -0.031 |
Rex | -0.030 |
arrest | -0.029 |
Token | for |
Token ID | 329 |
Feature activation | -4.88e-01 |
Pos logit contributions | |
smanship | +0.127 |
outage | +0.126 |
occasions | +0.122 |
pleasures | +0.121 |
oils | +0.121 |
Neg logit contributions | |
Tom | -0.053 |
Ben | -0.049 |
Sam | -0.043 |
their | -0.042 |
sw | -0.041 |
Token | something |
Token ID | 1223 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
smanship | +0.017 |
remedy | +0.016 |
bush | +0.016 |
occasions | +0.015 |
oils | +0.015 |
Neg logit contributions | |
Tom | -0.008 |
Ben | -0.007 |
bye | -0.007 |
Sam | -0.006 |
eg | -0.006 |
Token | that |
Token ID | 326 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
smanship | +0.033 |
outage | +0.031 |
bush | +0.030 |
pleasures | +0.029 |
remedy | +0.029 |
Neg logit contributions | |
Tom | -0.022 |
Ben | -0.021 |
Sam | -0.019 |
their | -0.019 |
sw | -0.018 |
Token | could |
Token ID | 714 |
Feature activation | +6.01e-01 |
Pos logit contributions | |
smanship | +0.032 |
outage | +0.030 |
bush | +0.030 |
remedy | +0.028 |
pleasures | +0.028 |
Neg logit contributions | |
Tom | -0.025 |
Ben | -0.023 |
Sam | -0.021 |
their | -0.020 |
Rex | -0.020 |
Token | break |
Token ID | 2270 |
Feature activation | +4.11e-01 |
Pos logit contributions | |
Tom | +0.012 |
Ben | +0.011 |
Sam | +0.010 |
their | +0.010 |
Rex | +0.010 |
Neg logit contributions | |
smanship | -0.020 |
outage | -0.018 |
bush | -0.018 |
pleasures | -0.018 |
remedy | -0.018 |
Token | the |
Token ID | 262 |
Feature activation | +3.21e-01 |
Pos logit contributions | |
Tom | +0.007 |
Ben | +0.007 |
Sam | +0.006 |
Rex | +0.006 |
arrest | +0.006 |
Neg logit contributions | |
smanship | -0.014 |
outage | -0.013 |
bush | -0.013 |
remedy | -0.013 |
pleasures | -0.013 |
Token | spell |
Token ID | 4822 |
Feature activation | +2.48e-02 |
Pos logit contributions | |
Tom | +0.007 |
Ben | +0.006 |
Sam | +0.006 |
Rex | +0.006 |
arrest | +0.005 |
Neg logit contributions | |
smanship | -0.010 |
outage | -0.010 |
bush | -0.010 |
remedy | -0.009 |
pleasures | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -1.14e-01 |
Pos logit contributions | |
Tom | +0.000 |
Ben | +0.000 |
Sam | +0.000 |
their | +0.000 |
Rex | +0.000 |
Neg logit contributions | |
smanship | -0.001 |
outage | -0.001 |
bush | -0.001 |
remedy | -0.001 |
pleasures | -0.001 |
Token | Finally |
Token ID | 9461 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
smanship | +0.003 |
bush | +0.003 |
outage | +0.003 |
remedy | +0.003 |
First | +0.003 |
Neg logit contributions | |
Tom | -0.003 |
Ben | -0.003 |
arrest | -0.003 |
sw | -0.002 |
Rex | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +1.59e-02 |
Pos logit contributions | |
smanship | +0.021 |
bush | +0.019 |
remedy | +0.018 |
iona | +0.018 |
oils | +0.018 |
Neg logit contributions | |
Tom | -0.016 |
eg | -0.016 |
arrest | -0.015 |
Ben | -0.015 |
Rex | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
Tom | +0.011 |
Ben | +0.010 |
arrest | +0.009 |
Sam | +0.009 |
Rex | +0.009 |
Neg logit contributions | |
smanship | -0.020 |
outage | -0.019 |
bush | -0.019 |
remedy | -0.018 |
pleasures | -0.018 |
Token | started |
Token ID | 2067 |
Feature activation | -8.05e-01 |
Pos logit contributions | |
Tom | +0.013 |
Ben | +0.012 |
Sam | +0.011 |
their | +0.011 |
Rex | +0.011 |
Neg logit contributions | |
smanship | -0.019 |
outage | -0.018 |
bush | -0.018 |
remedy | -0.017 |
inning | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
smanship | +0.024 |
outage | +0.022 |
bush | +0.021 |
occasions | +0.021 |
remedy | +0.021 |
Neg logit contributions | |
Tom | -0.018 |
Ben | -0.017 |
bye | -0.016 |
Rex | -0.016 |
Leo | -0.015 |
Token | argue |
Token ID | 7267 |
Feature activation | -6.13e-02 |
Pos logit contributions | |
smanship | +0.035 |
outage | +0.033 |
bush | +0.033 |
remedy | +0.031 |
pleasures | +0.031 |
Neg logit contributions | |
Tom | -0.029 |
Ben | -0.027 |
Sam | -0.025 |
Rex | -0.024 |
their | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
smanship | +0.002 |
bush | +0.002 |
remedy | +0.002 |
outage | +0.002 |
iona | +0.002 |
Neg logit contributions | |
Tom | -0.001 |
Ben | -0.001 |
Sam | -0.001 |
their | -0.001 |
Rex | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +2.42e-01 |
Pos logit contributions | |
arrest | +0.004 |
Tom | +0.004 |
sw | +0.004 |
ear | +0.004 |
bye | +0.004 |
Neg logit contributions | |
smanship | -0.008 |
First | -0.007 |
bush | -0.007 |
outage | -0.007 |
oils | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
Tom | +0.004 |
Ben | +0.003 |
Sam | +0.003 |
Rex | +0.003 |
arrest | +0.003 |
Neg logit contributions | |
smanship | -0.009 |
outage | -0.009 |
bush | -0.009 |
remedy | -0.008 |
pleasures | -0.008 |
Token | The |
Token ID | 464 |
Feature activation | -7.07e-01 |
Pos logit contributions | |
Tom | +0.014 |
Ben | +0.013 |
Sam | +0.012 |
their | +0.012 |
Rex | +0.012 |
Neg logit contributions | |
smanship | -0.016 |
outage | -0.015 |
bush | -0.014 |
remedy | -0.014 |
bars | -0.013 |
Token | argument |
Token ID | 4578 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
smanship | +0.020 |
outage | +0.018 |
bush | +0.018 |
remedy | +0.017 |
pleasures | +0.017 |
Neg logit contributions | |
Tom | -0.018 |
Ben | -0.017 |
Sam | -0.016 |
Rex | -0.015 |
their | -0.015 |
Token | got |
Token ID | 1392 |
Feature activation | +5.94e-01 |
Pos logit contributions | |
Tom | +0.025 |
Ben | +0.023 |
Sam | +0.021 |
their | +0.019 |
sw | +0.019 |
Neg logit contributions | |
smanship | -0.042 |
bush | -0.040 |
outage | -0.039 |
remedy | -0.039 |
iona | -0.038 |
Token | bigger |
Token ID | 5749 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
Tom | +0.011 |
Ben | +0.011 |
Sam | +0.009 |
Rex | +0.009 |
arrest | +0.009 |
Neg logit contributions | |
smanship | -0.020 |
outage | -0.019 |
bush | -0.019 |
remedy | -0.018 |
pleasures | -0.018 |
Token | toy |
Token ID | 13373 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
smanship | +0.017 |
outage | +0.016 |
bush | +0.016 |
remedy | +0.015 |
pleasures | +0.015 |
Neg logit contributions | |
Tom | -0.012 |
Ben | -0.011 |
Sam | -0.010 |
Rex | -0.010 |
arrest | -0.010 |
Token | car |
Token ID | 1097 |
Feature activation | +5.00e-01 |
Pos logit contributions | |
smanship | +0.007 |
outage | +0.007 |
bush | +0.007 |
remedy | +0.006 |
pleasures | +0.006 |
Neg logit contributions | |
Tom | -0.004 |
Ben | -0.003 |
Sam | -0.003 |
Rex | -0.003 |
arrest | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +5.87e-01 |
Pos logit contributions | |
Tom | +0.009 |
Ben | +0.009 |
Sam | +0.008 |
Rex | +0.007 |
arrest | +0.007 |
Neg logit contributions | |
smanship | -0.017 |
outage | -0.016 |
bush | -0.016 |
remedy | -0.015 |
pleasures | -0.015 |
Token | Lily |
Token ID | 20037 |
Feature activation | -1.79e-01 |
Pos logit contributions | |
arrest | +0.011 |
icks | +0.010 |
cor | +0.010 |
cks | +0.010 |
sw | +0.010 |
Neg logit contributions | |
smanship | -0.017 |
bush | -0.016 |
First | -0.016 |
Em | -0.016 |
remedy | -0.015 |
Token | remembered |
Token ID | 12086 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
smanship | +0.005 |
bush | +0.004 |
remedy | +0.004 |
outage | +0.004 |
heart | +0.004 |
Neg logit contributions | |
Tom | -0.004 |
Ben | -0.004 |
arrest | -0.004 |
Rex | -0.004 |
bye | -0.004 |
Token | she |
Token ID | 673 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
Tom | +0.006 |
eg | +0.005 |
Ben | +0.005 |
bye | +0.005 |
ear | +0.005 |
Neg logit contributions | |
smanship | -0.009 |
bush | -0.009 |
outage | -0.009 |
remedy | -0.008 |
occasions | -0.008 |
Token | had |
Token ID | 550 |
Feature activation | -6.56e-02 |
Pos logit contributions | |
smanship | +0.036 |
outage | +0.032 |
bush | +0.031 |
remedy | +0.031 |
oils | +0.029 |
Neg logit contributions | |
Tom | -0.030 |
Ben | -0.028 |
arrest | -0.026 |
Leo | -0.026 |
Rex | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | +6.54e-01 |
Pos logit contributions | |
smanship | +0.002 |
outage | +0.002 |
bush | +0.002 |
remedy | +0.002 |
occasions | +0.002 |
Neg logit contributions | |
Tom | -0.001 |
Ben | -0.001 |
Sam | -0.001 |
Rex | -0.001 |
Leo | -0.001 |
Token | toy |
Token ID | 13373 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
Tom | +0.014 |
Ben | +0.013 |
Sam | +0.011 |
Leo | +0.011 |
Rex | +0.011 |
Neg logit contributions | |
smanship | -0.021 |
outage | -0.020 |
bush | -0.019 |
remedy | -0.019 |
pleasures | -0.018 |
Token | car |
Token ID | 1097 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
smanship | +0.033 |
outage | +0.032 |
bush | +0.030 |
remedy | +0.029 |
bars | +0.029 |
Neg logit contributions | |
Tom | -0.020 |
Ben | -0.019 |
Sam | -0.017 |
Leo | -0.017 |
arrest | -0.016 |
Token | just |
Token ID | 655 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
smanship | +0.006 |
outage | +0.005 |
bush | +0.005 |
remedy | +0.005 |
pleasures | +0.005 |
Neg logit contributions | |
Tom | -0.003 |
Ben | -0.003 |
Sam | -0.003 |
arrest | -0.003 |
Rex | -0.003 |
Token | Rainbow |
Token ID | 19909 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
smanship | +0.030 |
bush | +0.029 |
outage | +0.029 |
iona | +0.027 |
occasions | +0.027 |
Neg logit contributions | |
Tom | -0.015 |
Ben | -0.013 |
ked | -0.013 |
Sam | -0.012 |
Rex | -0.012 |
Token | land |
Token ID | 1044 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
Tom | +0.024 |
Ben | +0.022 |
Sam | +0.021 |
Rex | +0.020 |
arrest | +0.020 |
Neg logit contributions | |
smanship | -0.033 |
bush | -0.031 |
outage | -0.030 |
occasions | -0.029 |
iona | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | -7.45e-01 |
Pos logit contributions | |
Tom | +0.030 |
Ben | +0.029 |
arrest | +0.027 |
Rex | +0.026 |
Sam | +0.026 |
Neg logit contributions | |
smanship | -0.044 |
bush | -0.041 |
outage | -0.040 |
pleasures | -0.038 |
occasions | -0.038 |
Token | there |
Token ID | 612 |
Feature activation | -2.92e-01 |
Pos logit contributions | |
smanship | +0.021 |
bush | +0.020 |
outage | +0.019 |
First | +0.018 |
iona | +0.018 |
Neg logit contributions | |
Tom | -0.016 |
Ben | -0.015 |
arrest | -0.015 |
icks | -0.014 |
ear | -0.014 |
Token | were |
Token ID | 547 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
smanship | +0.010 |
outage | +0.010 |
bush | +0.010 |
remedy | +0.009 |
pleasures | +0.009 |
Neg logit contributions | |
Tom | -0.006 |
Ben | -0.005 |
their | -0.005 |
Sam | -0.005 |
sw | -0.005 |
Token | lots |
Token ID | 6041 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
Tom | +0.018 |
Ben | +0.017 |
Sam | +0.015 |
arrest | +0.015 |
Rex | +0.015 |
Neg logit contributions | |
smanship | -0.032 |
bush | -0.030 |
outage | -0.030 |
First | -0.029 |
remedy | -0.029 |
Token | of |
Token ID | 286 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
smanship | +0.052 |
outage | +0.047 |
bush | +0.047 |
remedy | +0.046 |
First | +0.045 |
Neg logit contributions | |
Tom | -0.052 |
Ben | -0.049 |
Sam | -0.045 |
their | -0.044 |
Rex | -0.044 |
Token | different |
Token ID | 1180 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
smanship | +0.067 |
outage | +0.063 |
bush | +0.062 |
remedy | +0.060 |
pleasures | +0.059 |
Neg logit contributions | |
Tom | -0.051 |
Ben | -0.048 |
Sam | -0.044 |
Rex | -0.042 |
arrest | -0.042 |
Token | colors |
Token ID | 7577 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
smanship | +0.080 |
outage | +0.075 |
bush | +0.074 |
remedy | +0.071 |
iona | +0.069 |
Neg logit contributions | |
Tom | -0.062 |
Ben | -0.057 |
their | -0.054 |
sw | -0.052 |
Sam | -0.051 |
Token | in |
Token ID | 287 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
smanship | +0.111 |
remedy | +0.105 |
iona | +0.103 |
outage | +0.103 |
bush | +0.103 |
Neg logit contributions | |
Tom | -0.043 |
Ben | -0.038 |
Sam | -0.033 |
their | -0.033 |
sw | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
Tom | +0.004 |
Ben | +0.004 |
bye | +0.003 |
ked | +0.003 |
Rex | +0.003 |
Neg logit contributions | |
smanship | -0.009 |
outage | -0.008 |
bush | -0.008 |
occasions | -0.008 |
oils | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -5.72e-01 |
Pos logit contributions | |
Tom | +0.005 |
Ben | +0.005 |
arrest | +0.004 |
Sam | +0.004 |
Rex | +0.004 |
Neg logit contributions | |
smanship | -0.010 |
outage | -0.009 |
bush | -0.009 |
remedy | -0.009 |
pleasures | -0.009 |
Token | where |
Token ID | 810 |
Feature activation | +1.11e+00 |
Pos logit contributions | |
smanship | +0.018 |
outage | +0.017 |
bush | +0.017 |
remedy | +0.017 |
pleasures | +0.016 |
Neg logit contributions | |
Tom | -0.012 |
Ben | -0.011 |
Sam | -0.010 |
Rex | -0.010 |
arrest | -0.009 |
Token | is |
Token ID | 318 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
Tom | +0.018 |
Ben | +0.017 |
Sam | +0.014 |
their | +0.014 |
Rex | +0.013 |
Neg logit contributions | |
smanship | -0.043 |
bush | -0.040 |
outage | -0.040 |
remedy | -0.039 |
inning | -0.039 |
Token | the |
Token ID | 262 |
Feature activation | -8.55e-01 |
Pos logit contributions | |
Tom | +0.013 |
Ben | +0.012 |
Sam | +0.010 |
their | +0.009 |
Rex | +0.009 |
Neg logit contributions | |
smanship | -0.042 |
outage | -0.039 |
bush | -0.039 |
remedy | -0.038 |
pleasures | -0.038 |
Token | lot |
Token ID | 1256 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
smanship | +0.029 |
outage | +0.027 |
inning | +0.025 |
First | +0.025 |
bush | +0.025 |
Neg logit contributions | |
Tom | -0.017 |
Ben | -0.016 |
sw | -0.014 |
Rex | -0.014 |
ear | -0.014 |
Token | ion |
Token ID | 295 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
smanship | +0.028 |
bench | +0.022 |
adows | +0.022 |
inning | +0.021 |
outage | +0.021 |
Neg logit contributions | |
Tom | -0.037 |
their | -0.035 |
Ben | -0.035 |
Sara | -0.034 |
Rex | -0.033 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
smanship | +0.073 |
outage | +0.067 |
pleasures | +0.067 |
bush | +0.066 |
remedy | +0.066 |
Neg logit contributions | |
Tom | -0.051 |
Ben | -0.048 |
Sam | -0.042 |
their | -0.042 |
Rex | -0.040 |
Token | Ben |
Token ID | 3932 |
Feature activation | +3.68e-01 |
Pos logit contributions | |
Tom | +0.009 |
arrest | +0.007 |
Ben | +0.006 |
bye | +0.006 |
eg | +0.006 |
Neg logit contributions | |
smanship | -0.052 |
outage | -0.049 |
bush | -0.049 |
oils | -0.049 |
remedy | -0.048 |
Token | asks |
Token ID | 7893 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
Tom | +0.006 |
Ben | +0.005 |
Sam | +0.004 |
Rex | +0.004 |
their | +0.004 |
Neg logit contributions | |
smanship | -0.014 |
outage | -0.013 |
bush | -0.013 |
remedy | -0.013 |
pleasures | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
smanship | +0.045 |
outage | +0.041 |
bush | +0.041 |
remedy | +0.040 |
oils | +0.040 |
Neg logit contributions | |
Tom | -0.026 |
arrest | -0.025 |
Ben | -0.023 |
bye | -0.022 |
Sam | -0.021 |
Token | He |
Token ID | 679 |
Feature activation | +1.78e-01 |
Pos logit contributions | |
smanship | +0.001 |
outage | +0.001 |
bush | +0.001 |
remedy | +0.001 |
First | +0.001 |
Neg logit contributions | |
Tom | -0.001 |
Ben | -0.001 |
arrest | -0.001 |
Sam | -0.001 |
bye | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +4.61e-01 |
Pos logit contributions | |
Tom | +0.014 |
Ben | +0.013 |
arrest | +0.013 |
bye | +0.012 |
ear | +0.012 |
Neg logit contributions | |
smanship | -0.031 |
bush | -0.029 |
outage | -0.029 |
oils | -0.028 |
remedy | -0.028 |
Token | big |
Token ID | 1263 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
Tom | +0.008 |
Ben | +0.007 |
Sam | +0.006 |
sw | +0.006 |
Rex | +0.006 |
Neg logit contributions | |
smanship | -0.017 |
outage | -0.016 |
bush | -0.016 |
pleasures | -0.015 |
remedy | -0.015 |
Token | pond |
Token ID | 16723 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
smanship | +0.005 |
outage | +0.005 |
bush | +0.005 |
remedy | +0.004 |
First | +0.004 |
Neg logit contributions | |
Tom | -0.003 |
Ben | -0.003 |
Sam | -0.002 |
Rex | -0.002 |
their | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.97e-02 |
Pos logit contributions | |
smanship | +0.053 |
outage | +0.049 |
occasions | +0.048 |
remedy | +0.048 |
pleasures | +0.048 |
Neg logit contributions | |
Tom | -0.020 |
Ben | -0.018 |
sw | -0.016 |
their | -0.015 |
Sam | -0.015 |
Token | She |
Token ID | 1375 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
Tom | +0.000 |
Ben | +0.000 |
Sam | +0.000 |
their | +0.000 |
Rex | +0.000 |
Neg logit contributions | |
smanship | -0.001 |
outage | -0.001 |
bush | -0.001 |
remedy | -0.001 |
pleasures | -0.001 |
Token | said |
Token ID | 531 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
smanship | +0.055 |
outage | +0.051 |
bush | +0.050 |
pleasures | +0.050 |
remedy | +0.049 |
Neg logit contributions | |
Tom | -0.026 |
Ben | -0.024 |
sw | -0.021 |
Sam | -0.021 |
their | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -5.86e-01 |
Pos logit contributions | |
smanship | +0.035 |
outage | +0.034 |
bush | +0.033 |
remedy | +0.032 |
oils | +0.031 |
Neg logit contributions | |
Tom | -0.019 |
Ben | -0.018 |
Sam | -0.016 |
arrest | -0.015 |
Rex | -0.015 |
Token | Jimmy |
Token ID | 12963 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
smanship | +0.016 |
iona | +0.015 |
oils | +0.015 |
occasions | +0.015 |
remedy | +0.015 |
Neg logit contributions | |
Tom | -0.012 |
arrest | -0.012 |
bye | -0.011 |
icks | -0.011 |
eg | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
Tom | +0.004 |
Ben | +0.004 |
Sam | +0.003 |
Rex | +0.003 |
their | +0.003 |
Neg logit contributions | |
smanship | -0.009 |
outage | -0.009 |
bush | -0.009 |
remedy | -0.008 |
pleasures | -0.008 |
Token | � |
Token ID | 6184 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
smanship | +0.046 |
outage | +0.043 |
bush | +0.042 |
pleasures | +0.041 |
remedy | +0.040 |
Neg logit contributions | |
Tom | -0.027 |
Ben | -0.025 |
Sam | -0.022 |
Rex | -0.021 |
their | -0.021 |
Token | � |
Token ID | 95 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
smanship | +0.043 |
outage | +0.039 |
bush | +0.039 |
remedy | +0.037 |
pleasures | +0.036 |
Neg logit contributions | |
Tom | -0.041 |
Ben | -0.039 |
Sam | -0.035 |
Rex | -0.034 |
arrest | -0.034 |
Token | it |
Token ID | 340 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
Tom | +0.025 |
Ben | +0.024 |
arrest | +0.022 |
bye | +0.021 |
Sam | +0.021 |
Neg logit contributions | |
smanship | -0.050 |
outage | -0.047 |
bush | -0.047 |
remedy | -0.045 |
oils | -0.044 |
Token | closer |
Token ID | 5699 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
smanship | +0.026 |
outage | +0.025 |
bush | +0.024 |
remedy | +0.024 |
pleasures | +0.023 |
Neg logit contributions | |
Tom | -0.016 |
Ben | -0.015 |
Sam | -0.013 |
their | -0.013 |
Rex | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | +5.02e-01 |
Pos logit contributions | |
Tom | +0.023 |
Ben | +0.021 |
Sam | +0.019 |
Rex | +0.018 |
arrest | +0.018 |
Neg logit contributions | |
smanship | -0.042 |
outage | -0.040 |
bush | -0.039 |
remedy | -0.038 |
pleasures | -0.037 |
Token |
|
Token ID | 198 |
Feature activation | +5.64e-01 |
Pos logit contributions | |
arrest | +0.009 |
Tom | +0.009 |
bye | +0.008 |
sw | +0.008 |
Ben | +0.008 |
Neg logit contributions | |
First | -0.015 |
smanship | -0.015 |
bush | -0.015 |
outage | -0.014 |
iona | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +8.26e-01 |
Pos logit contributions | |
Tom | +0.008 |
Ben | +0.007 |
Sam | +0.006 |
Rex | +0.006 |
their | +0.005 |
Neg logit contributions | |
smanship | -0.023 |
outage | -0.021 |
bush | -0.021 |
remedy | -0.021 |
pleasures | -0.021 |
Token | " |
Token ID | 1 |
Feature activation | -1.87e+00 |
Pos logit contributions | |
Tom | +0.020 |
Ben | +0.018 |
Sam | +0.017 |
their | +0.017 |
Rex | +0.017 |
Neg logit contributions | |
smanship | -0.027 |
outage | -0.024 |
remedy | -0.023 |
bush | -0.023 |
pleasures | -0.022 |
Token | Let |
Token ID | 5756 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
smanship | +0.056 |
outage | +0.051 |
bush | +0.049 |
remedy | +0.046 |
pleasures | +0.046 |
Neg logit contributions | |
Tom | -0.048 |
Ben | -0.045 |
Sam | -0.041 |
Rex | -0.040 |
sw | -0.040 |
Token | 's |
Token ID | 338 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
smanship | +0.033 |
bush | +0.032 |
heart | +0.031 |
remedy | +0.030 |
First | +0.030 |
Neg logit contributions | |
Tom | -0.024 |
Ben | -0.022 |
arrest | -0.022 |
ked | -0.021 |
Rex | -0.021 |
Token | go |
Token ID | 467 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
Tom | +0.004 |
Ben | +0.004 |
Rex | +0.003 |
bye | +0.003 |
Their | +0.003 |
Neg logit contributions | |
smanship | -0.006 |
bush | -0.006 |
outage | -0.006 |
remedy | -0.006 |
First | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -1.86e-01 |
Pos logit contributions | |
Tom | +0.031 |
Ben | +0.029 |
Sam | +0.025 |
arrest | +0.024 |
Rex | +0.024 |
Neg logit contributions | |
smanship | -0.050 |
outage | -0.048 |
bush | -0.047 |
remedy | -0.045 |
First | -0.044 |
Token | get |
Token ID | 651 |
Feature activation | +2.94e-02 |
Pos logit contributions | |
smanship | +0.006 |
bush | +0.006 |
outage | +0.006 |
remedy | +0.006 |
First | +0.006 |
Neg logit contributions | |
Tom | -0.003 |
Ben | -0.003 |
Sam | -0.002 |
bye | -0.002 |
their | -0.002 |
Token | spotted |
Token ID | 13489 |
Feature activation | +2.06e-01 |
Pos logit contributions | |
smanship | +0.017 |
bush | +0.016 |
remedy | +0.016 |
outage | +0.015 |
First | +0.015 |
Neg logit contributions | |
Tom | -0.012 |
Ben | -0.011 |
bye | -0.010 |
icks | -0.010 |
Rex | -0.010 |
Token | some |
Token ID | 617 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
Tom | +0.003 |
Ben | +0.002 |
Sam | +0.002 |
Rex | +0.002 |
their | +0.002 |
Neg logit contributions | |
smanship | -0.009 |
outage | -0.008 |
bush | -0.008 |
remedy | -0.008 |
pleasures | -0.008 |
Token | tasty |
Token ID | 25103 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
smanship | +0.086 |
outage | +0.085 |
bush | +0.080 |
First | +0.077 |
iona | +0.077 |
Neg logit contributions | |
Tom | -0.047 |
Ben | -0.044 |
sw | -0.038 |
Sam | -0.038 |
their | -0.036 |
Token | - |
Token ID | 12 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
smanship | +0.044 |
outage | +0.044 |
bush | +0.041 |
bars | +0.040 |
First | +0.039 |
Neg logit contributions | |
Tom | -0.025 |
Ben | -0.023 |
sw | -0.021 |
Sam | -0.020 |
their | -0.020 |
Token | looking |
Token ID | 11534 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
smanship | +0.032 |
outage | +0.029 |
bush | +0.028 |
remedy | +0.026 |
pleasures | +0.026 |
Neg logit contributions | |
Tom | -0.045 |
Ben | -0.042 |
Sam | -0.039 |
their | -0.039 |
arrest | -0.038 |
Token | oil |
Token ID | 3056 |
Feature activation | -4.78e+00 |
Pos logit contributions | |
smanship | +0.020 |
outage | +0.019 |
bush | +0.018 |
First | +0.017 |
inning | +0.017 |
Neg logit contributions | |
Tom | -0.013 |
Ben | -0.012 |
Sam | -0.010 |
sw | -0.010 |
their | -0.010 |
Token | near |
Token ID | 1474 |
Feature activation | +9.04e-02 |
Pos logit contributions | |
smanship | +0.177 |
outage | +0.168 |
bush | +0.164 |
pleasures | +0.161 |
remedy | +0.161 |
Neg logit contributions | |
Tom | -0.081 |
Ben | -0.073 |
Sam | -0.063 |
their | -0.061 |
sw | -0.059 |
Token | a |
Token ID | 257 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
Tom | +0.001 |
Ben | +0.001 |
bye | +0.001 |
Sam | +0.001 |
arrest | +0.001 |
Neg logit contributions | |
smanship | -0.003 |
bush | -0.003 |
outage | -0.003 |
remedy | -0.003 |
oils | -0.003 |
Token | pond |
Token ID | 16723 |
Feature activation | -6.03e-01 |
Pos logit contributions | |
Tom | +0.058 |
Ben | +0.055 |
sw | +0.049 |
Sam | +0.049 |
Rex | +0.049 |
Neg logit contributions | |
smanship | -0.085 |
outage | -0.078 |
pleasures | -0.077 |
bush | -0.075 |
occasions | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | -2.29e-01 |
Pos logit contributions | |
smanship | +0.023 |
outage | +0.022 |
bush | +0.021 |
remedy | +0.021 |
oils | +0.021 |
Neg logit contributions | |
Tom | -0.009 |
Ben | -0.008 |
Sam | -0.007 |
their | -0.007 |
sw | -0.007 |
Token | Exc |
Token ID | 25268 |
Feature activation | +5.01e-01 |
Pos logit contributions | |
smanship | +0.008 |
outage | +0.008 |
bush | +0.007 |
pleasures | +0.007 |
inning | +0.007 |
Neg logit contributions | |
Tom | -0.005 |
Ben | -0.004 |
Sam | -0.004 |
Rex | -0.003 |
Leo | -0.003 |
Token | The |
Token ID | 383 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
Tom | +0.019 |
Ben | +0.018 |
arrest | +0.016 |
sw | +0.015 |
their | +0.015 |
Neg logit contributions | |
smanship | -0.049 |
outage | -0.048 |
bush | -0.047 |
First | -0.046 |
remedy | -0.045 |
Token | tray |
Token ID | 26473 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
smanship | +0.031 |
outage | +0.029 |
bush | +0.028 |
remedy | +0.027 |
pleasures | +0.026 |
Neg logit contributions | |
Tom | -0.032 |
Ben | -0.030 |
Sam | -0.028 |
Rex | -0.027 |
arrest | -0.027 |
Token | was |
Token ID | 373 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
Tom | +0.003 |
Ben | +0.003 |
Sam | +0.003 |
sw | +0.003 |
their | +0.003 |
Neg logit contributions | |
smanship | -0.005 |
outage | -0.005 |
bush | -0.004 |
pleasures | -0.004 |
remedy | -0.004 |
Token | made |
Token ID | 925 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
smanship | +0.017 |
outage | +0.017 |
bush | +0.017 |
remedy | +0.016 |
iona | +0.015 |
Neg logit contributions | |
Tom | -0.013 |
Ben | -0.013 |
arrest | -0.012 |
bye | -0.011 |
Sam | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
smanship | +0.080 |
outage | +0.072 |
bush | +0.072 |
remedy | +0.069 |
pleasures | +0.069 |
Neg logit contributions | |
Tom | -0.073 |
Ben | -0.068 |
their | -0.064 |
Sam | -0.063 |
Rex | -0.059 |
Token | wood |
Token ID | 4898 |
Feature activation | -4.82e+00 |
Pos logit contributions | |
smanship | +0.049 |
outage | +0.047 |
bush | +0.046 |
inning | +0.044 |
pleasures | +0.043 |
Neg logit contributions | |
Tom | -0.038 |
Ben | -0.036 |
Sam | -0.032 |
their | -0.032 |
Rex | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
smanship | +0.178 |
outage | +0.168 |
bush | +0.167 |
remedy | +0.165 |
pleasures | +0.164 |
Neg logit contributions | |
Tom | -0.075 |
Ben | -0.068 |
their | -0.060 |
Sam | -0.059 |
sw | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | +1.40e-01 |
Pos logit contributions | |
smanship | +0.058 |
outage | +0.055 |
bush | +0.053 |
remedy | +0.052 |
pleasures | +0.052 |
Neg logit contributions | |
Tom | -0.028 |
Ben | -0.026 |
Sam | -0.023 |
their | -0.022 |
sw | -0.022 |
Token | it |
Token ID | 340 |
Feature activation | -5.94e-01 |
Pos logit contributions | |
Tom | +0.002 |
Ben | +0.002 |
their | +0.002 |
Sam | +0.002 |
sw | +0.002 |
Neg logit contributions | |
smanship | -0.006 |
outage | -0.005 |
bush | -0.005 |
inning | -0.005 |
pleasures | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -2.60e-01 |
Pos logit contributions | |
smanship | +0.021 |
outage | +0.020 |
pleasures | +0.019 |
bush | +0.019 |
occasions | +0.019 |
Neg logit contributions | |
Tom | -0.011 |
Ben | -0.010 |
sw | -0.010 |
their | -0.009 |
Sam | -0.009 |
Token | very |
Token ID | 845 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
smanship | +0.009 |
outage | +0.008 |
bush | +0.008 |
pleasures | +0.008 |
remedy | +0.008 |
Neg logit contributions | |
Tom | -0.005 |
Ben | -0.005 |
Sam | -0.004 |
their | -0.004 |
Rex | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -4.11e-01 |
Pos logit contributions | |
smanship | +0.060 |
outage | +0.057 |
bush | +0.057 |
remedy | +0.055 |
pleasures | +0.054 |
Neg logit contributions | |
Tom | -0.020 |
Ben | -0.018 |
Sam | -0.015 |
their | -0.014 |
Rex | -0.014 |
Token | equipment |
Token ID | 5112 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
smanship | +0.012 |
outage | +0.011 |
bush | +0.011 |
iona | +0.011 |
First | +0.010 |
Neg logit contributions | |
Tom | -0.010 |
Ben | -0.009 |
ear | -0.008 |
Sam | -0.008 |
arrest | -0.008 |
Token | . |
Token ID | 13 |
Feature activation | -6.47e-01 |
Pos logit contributions | |
smanship | +0.041 |
outage | +0.040 |
bush | +0.040 |
remedy | +0.040 |
pleasures | +0.039 |
Neg logit contributions | |
Tom | -0.016 |
Ben | -0.014 |
Sam | -0.012 |
their | -0.012 |
Rex | -0.010 |
Token | They |
Token ID | 1119 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
smanship | +0.022 |
outage | +0.021 |
bush | +0.021 |
First | +0.020 |
remedy | +0.020 |
Neg logit contributions | |
Tom | -0.011 |
Ben | -0.011 |
sw | -0.009 |
arrest | -0.009 |
bye | -0.009 |
Token | used |
Token ID | 973 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
smanship | +0.034 |
outage | +0.034 |
bush | +0.033 |
remedy | +0.032 |
pleasures | +0.032 |
Neg logit contributions | |
Tom | -0.029 |
Ben | -0.027 |
Sam | -0.025 |
their | -0.025 |
sw | -0.024 |
Token | screws |
Token ID | 23742 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
smanship | +0.111 |
outage | +0.108 |
bush | +0.107 |
inning | +0.103 |
remedy | +0.103 |
Neg logit contributions | |
Tom | -0.040 |
Ben | -0.035 |
their | -0.031 |
Sam | -0.030 |
Rex | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
smanship | +0.198 |
bush | +0.190 |
outage | +0.190 |
remedy | +0.189 |
iona | +0.183 |
Neg logit contributions | |
Tom | -0.084 |
Ben | -0.072 |
their | -0.067 |
Sam | -0.065 |
Rex | -0.055 |
Token | w |
Token ID | 266 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
Tom | +0.011 |
Ben | +0.010 |
Sam | +0.010 |
their | +0.010 |
sw | +0.009 |
Neg logit contributions | |
bush | -0.012 |
smanship | -0.011 |
outage | -0.011 |
inning | -0.011 |
iona | -0.011 |
Token | renches |
Token ID | 33650 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
Tom | +0.031 |
Ben | +0.029 |
their | +0.027 |
Sam | +0.027 |
arrest | +0.027 |
Neg logit contributions | |
smanship | -0.025 |
outage | -0.025 |
bush | -0.025 |
remedy | -0.023 |
bars | -0.021 |
Token | . |
Token ID | 13 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
smanship | +0.104 |
bush | +0.100 |
outage | +0.100 |
remedy | +0.098 |
iona | +0.095 |
Neg logit contributions | |
Tom | -0.053 |
Ben | -0.048 |
their | -0.043 |
Sam | -0.042 |
Rex | -0.039 |
Token | After |
Token ID | 2293 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
smanship | +0.001 |
outage | +0.001 |
bush | +0.001 |
First | +0.001 |
remedy | +0.001 |
Neg logit contributions | |
Tom | -0.000 |
Ben | -0.000 |
sw | -0.000 |
arrest | -0.000 |
bye | -0.000 |
Token | they |
Token ID | 484 |
Feature activation | -1.21e+00 |
Pos logit contributions | |
Tom | +0.020 |
Ben | +0.019 |
Sam | +0.016 |
Rex | +0.016 |
arrest | +0.016 |
Neg logit contributions | |
smanship | -0.040 |
outage | -0.037 |
bush | -0.037 |
remedy | -0.036 |
First | -0.035 |
Token | got |
Token ID | 1392 |
Feature activation | -7.36e-01 |
Pos logit contributions | |
smanship | +0.038 |
bush | +0.034 |
outage | +0.034 |
First | +0.033 |
remedy | +0.033 |
Neg logit contributions | |
Tom | -0.026 |
Ben | -0.024 |
arrest | -0.022 |
Rex | -0.022 |
Sam | -0.022 |
Token | some |
Token ID | 617 |
Feature activation | -3.42e+00 |
Pos logit contributions | |
smanship | +0.028 |
outage | +0.027 |
bush | +0.026 |
inning | +0.025 |
iona | +0.025 |
Neg logit contributions | |
Tom | -0.012 |
Ben | -0.011 |
their | -0.010 |
Sam | -0.009 |
sw | -0.009 |
Token | special |
Token ID | 2041 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
outage | +0.117 |
smanship | +0.115 |
bars | +0.111 |
any | +0.108 |
belt | +0.108 |
Neg logit contributions | |
their | -0.065 |
sw | -0.058 |
Ben | -0.057 |
at | -0.056 |
Tom | -0.056 |
Token | green |
Token ID | 4077 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
bars | +0.073 |
smanship | +0.072 |
outage | +0.072 |
belt | +0.069 |
bush | +0.068 |
Neg logit contributions | |
their | -0.055 |
sw | -0.052 |
eyes | -0.049 |
pet | -0.049 |
at | -0.049 |
Token | fertilizer |
Token ID | 37113 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
outage | +0.073 |
smanship | +0.071 |
bars | +0.067 |
iona | +0.065 |
Em | +0.065 |
Neg logit contributions | |
their | -0.040 |
sw | -0.040 |
Ben | -0.038 |
Tom | -0.036 |
at | -0.035 |
Token | . |
Token ID | 13 |
Feature activation | -6.36e-01 |
Pos logit contributions | |
smanship | +0.200 |
outage | +0.193 |
pleasures | +0.188 |
iona | +0.188 |
bush | +0.187 |
Neg logit contributions | |
Tom | -0.065 |
Ben | -0.060 |
their | -0.056 |
Sam | -0.048 |
sw | -0.047 |
Token | He |
Token ID | 679 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
smanship | +0.020 |
bush | +0.019 |
outage | +0.019 |
First | +0.019 |
remedy | +0.019 |
Neg logit contributions | |
Tom | -0.012 |
Ben | -0.011 |
arrest | -0.010 |
sw | -0.010 |
bye | -0.010 |
Token | sprinkled |
Token ID | 49692 |
Feature activation | -2.68e+00 |
Pos logit contributions | |
smanship | +0.018 |
outage | +0.017 |
pleasures | +0.017 |
bush | +0.016 |
inning | +0.016 |
Neg logit contributions | |
Tom | -0.010 |
Ben | -0.010 |
sw | -0.009 |
Sam | -0.008 |
their | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
smanship | +0.109 |
outage | +0.108 |
bush | +0.102 |
occasions | +0.099 |
remedy | +0.098 |
Neg logit contributions | |
Tom | -0.037 |
Ben | -0.035 |
their | -0.031 |
Sam | -0.028 |
sw | -0.026 |
Token | on |
Token ID | 319 |
Feature activation | -4.52e-01 |
Pos logit contributions | |
smanship | +0.111 |
outage | +0.105 |
bush | +0.103 |
remedy | +0.100 |
pleasures | +0.098 |
Neg logit contributions | |
Tom | -0.061 |
Ben | -0.057 |
Sam | -0.050 |
their | -0.048 |
Rex | -0.048 |
Token | sky |
Token ID | 6766 |
Feature activation | +4.25e-01 |
Pos logit contributions | |
Tom | +0.021 |
Ben | +0.020 |
Sam | +0.018 |
Rex | +0.017 |
their | +0.017 |
Neg logit contributions | |
smanship | -0.023 |
outage | -0.021 |
bush | -0.021 |
remedy | -0.020 |
pleasures | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +4.66e-02 |
Pos logit contributions | |
Tom | +0.008 |
Ben | +0.008 |
Sam | +0.007 |
arrest | +0.007 |
Rex | +0.007 |
Neg logit contributions | |
smanship | -0.014 |
bush | -0.013 |
outage | -0.013 |
remedy | -0.012 |
pleasures | -0.012 |
Token | She |
Token ID | 1375 |
Feature activation | -3.53e-01 |
Pos logit contributions | |
Tom | +0.001 |
Ben | +0.001 |
Sam | +0.001 |
Rex | +0.001 |
arrest | +0.001 |
Neg logit contributions | |
smanship | -0.002 |
outage | -0.002 |
bush | -0.002 |
remedy | -0.001 |
pleasures | -0.001 |
Token | felt |
Token ID | 2936 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
smanship | +0.010 |
outage | +0.010 |
bush | +0.010 |
remedy | +0.009 |
oils | +0.009 |
Neg logit contributions | |
Tom | -0.008 |
Ben | -0.007 |
arrest | -0.007 |
Sam | -0.007 |
Rex | -0.007 |
Token | it |
Token ID | 340 |
Feature activation | -3.90e+00 |
Pos logit contributions | |
smanship | +0.054 |
outage | +0.051 |
bush | +0.051 |
remedy | +0.049 |
pleasures | +0.048 |
Neg logit contributions | |
Tom | -0.023 |
Ben | -0.021 |
Sam | -0.018 |
Rex | -0.017 |
their | -0.017 |
Token | r |
Token ID | 374 |
Feature activation | -4.75e+00 |
Pos logit contributions | |
smanship | +0.130 |
bush | +0.120 |
outage | +0.119 |
occasions | +0.118 |
remedy | +0.118 |
Neg logit contributions | |
Tom | -0.076 |
Ben | -0.071 |
Sam | -0.064 |
their | -0.063 |
sw | -0.062 |
Token | umbling |
Token ID | 14739 |
Feature activation | -7.18e-01 |
Pos logit contributions | |
smanship | +0.099 |
outage | +0.092 |
bush | +0.091 |
remedy | +0.090 |
occasions | +0.090 |
Neg logit contributions | |
Tom | -0.152 |
Ben | -0.141 |
Sam | -0.135 |
Dan | -0.129 |
Rex | -0.129 |
Token | beneath |
Token ID | 11061 |
Feature activation | +9.40e-01 |
Pos logit contributions | |
smanship | +0.023 |
outage | +0.021 |
bush | +0.021 |
remedy | +0.020 |
pleasures | +0.020 |
Neg logit contributions | |
Tom | -0.015 |
Ben | -0.014 |
Sam | -0.012 |
arrest | -0.012 |
Rex | -0.012 |
Token | her |
Token ID | 607 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
Tom | +0.017 |
Ben | +0.015 |
bye | +0.015 |
sw | +0.014 |
eg | +0.014 |
Neg logit contributions | |
smanship | -0.030 |
bush | -0.028 |
outage | -0.027 |
oils | -0.027 |
remedy | -0.027 |
Token | feet |
Token ID | 3625 |
Feature activation | -2.89e-01 |
Pos logit contributions | |
Tom | +0.032 |
Ben | +0.029 |
Sam | +0.026 |
bye | +0.026 |
Jolly | +0.026 |
Neg logit contributions | |
smanship | -0.044 |
outage | -0.042 |
bush | -0.040 |
occasions | -0.039 |
oils | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +4.29e-02 |
Pos logit contributions | |
smanship | +0.010 |
outage | +0.010 |
bush | +0.010 |
remedy | +0.009 |
pleasures | +0.009 |
Neg logit contributions | |
Tom | -0.005 |
Ben | -0.005 |
Sam | -0.004 |
Rex | -0.004 |
their | -0.004 |