Token | listen |
Token ID | 6004 |
Feature activation | -3.47e-01 |
Pos logit contributions | |
rum | +0.031 |
pain | +0.027 |
ez | +0.026 |
aged | +0.025 |
mischief | +0.025 |
Neg logit contributions | |
ory | -0.022 |
oph | -0.022 |
ll | -0.022 |
of | -0.020 |
would | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
oph | +0.007 |
ll | +0.007 |
ory | +0.007 |
THE | +0.007 |
ari | +0.006 |
Neg logit contributions | |
rum | -0.010 |
pain | -0.009 |
ez | -0.008 |
mischief | -0.008 |
aged | -0.008 |
Token | She |
Token ID | 1375 |
Feature activation | +1.25e-01 |
Pos logit contributions | |
rum | +0.032 |
pain | +0.030 |
ez | +0.027 |
mischief | +0.025 |
udge | +0.025 |
Neg logit contributions | |
ll | -0.030 |
oph | -0.029 |
ory | -0.028 |
THE | -0.027 |
ari | -0.027 |
Token | threw |
Token ID | 9617 |
Feature activation | +8.87e-01 |
Pos logit contributions | |
rum | +0.004 |
pain | +0.003 |
ez | +0.003 |
aged | +0.003 |
mischief | +0.003 |
Neg logit contributions | |
oph | -0.003 |
ll | -0.002 |
THE | -0.002 |
ory | -0.002 |
ari | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
rum | +0.030 |
pain | +0.026 |
ez | +0.024 |
aged | +0.024 |
udge | +0.024 |
Neg logit contributions | |
oph | -0.014 |
ory | -0.014 |
ll | -0.013 |
upon | -0.013 |
THE | -0.013 |
Token | tant |
Token ID | 24246 |
Feature activation | +7.82e+00 |
Pos logit contributions | |
rum | +0.034 |
pain | +0.027 |
ez | +0.026 |
aged | +0.025 |
mischief | +0.025 |
Neg logit contributions | |
ory | -0.048 |
upon | -0.047 |
ll | -0.046 |
oph | -0.046 |
of | -0.045 |
Token | rum |
Token ID | 6582 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
mischief | +0.099 |
pain | +0.089 |
trouble | +0.076 |
elbows | +0.057 |
situations | +0.047 |
Neg logit contributions | |
ll | -0.265 |
of | -0.259 |
ppy | -0.250 |
ie | -0.247 |
pp | -0.247 |
Token | in |
Token ID | 287 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
rum | +0.076 |
pain | +0.071 |
ez | +0.065 |
mischief | +0.064 |
udge | +0.061 |
Neg logit contributions | |
ll | -0.049 |
oph | -0.048 |
ory | -0.045 |
THE | -0.045 |
upon | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
rum | +0.102 |
oving | +0.090 |
ez | +0.088 |
aged | +0.088 |
attle | +0.084 |
Neg logit contributions | |
upon | -0.027 |
me | -0.026 |
of | -0.025 |
first | -0.024 |
last | -0.023 |
Token | store |
Token ID | 3650 |
Feature activation | +2.34e-01 |
Pos logit contributions | |
ll | +0.021 |
oph | +0.021 |
ory | +0.020 |
THE | +0.019 |
upon | +0.019 |
Neg logit contributions | |
rum | -0.036 |
pain | -0.032 |
ez | -0.030 |
aged | -0.029 |
udge | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
rum | +0.007 |
pain | +0.006 |
ez | +0.006 |
mischief | +0.006 |
aged | +0.005 |
Neg logit contributions | |
oph | -0.005 |
ll | -0.005 |
ory | -0.004 |
THE | -0.004 |
ari | -0.004 |
Token | sad |
Token ID | 6507 |
Feature activation | -6.93e-01 |
Pos logit contributions | |
oph | +0.021 |
ll | +0.021 |
ory | +0.019 |
THE | +0.019 |
ari | +0.019 |
Neg logit contributions | |
rum | -0.024 |
pain | -0.022 |
ez | -0.020 |
mischief | -0.019 |
aged | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +7.09e-01 |
Pos logit contributions | |
ll | +0.012 |
oph | +0.011 |
ory | +0.011 |
upon | +0.011 |
THE | +0.010 |
Neg logit contributions | |
rum | -0.022 |
pain | -0.021 |
ez | -0.020 |
mischief | -0.019 |
udge | -0.019 |
Token | She |
Token ID | 1375 |
Feature activation | -5.08e-02 |
Pos logit contributions | |
rum | +0.021 |
pain | +0.019 |
ez | +0.018 |
mischief | +0.017 |
aged | +0.017 |
Neg logit contributions | |
oph | -0.014 |
ll | -0.014 |
ory | -0.014 |
THE | -0.013 |
ari | -0.013 |
Token | threw |
Token ID | 9617 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
oph | +0.001 |
ll | +0.001 |
ory | +0.001 |
THE | +0.001 |
ari | +0.001 |
Neg logit contributions | |
rum | -0.001 |
pain | -0.001 |
ez | -0.001 |
mischief | -0.001 |
aged | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
rum | +0.041 |
pain | +0.035 |
ez | +0.034 |
aged | +0.033 |
mischief | +0.033 |
Neg logit contributions | |
oph | -0.015 |
upon | -0.014 |
ory | -0.013 |
of | -0.013 |
THE | -0.013 |
Token | tant |
Token ID | 24246 |
Feature activation | +7.78e+00 |
Pos logit contributions | |
rum | +0.048 |
pain | +0.037 |
ez | +0.037 |
mischief | +0.036 |
aged | +0.036 |
Neg logit contributions | |
upon | -0.060 |
ory | -0.057 |
of | -0.057 |
oph | -0.057 |
may | -0.056 |
Token | rum |
Token ID | 6582 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
mischief | +0.089 |
pain | +0.086 |
trouble | +0.072 |
elbows | +0.051 |
scrape | +0.043 |
Neg logit contributions | |
ll | -0.273 |
of | -0.263 |
ppy | -0.253 |
pp | -0.253 |
oph | -0.253 |
Token | and |
Token ID | 290 |
Feature activation | -7.13e-01 |
Pos logit contributions | |
rum | +0.087 |
pain | +0.082 |
ez | +0.075 |
mischief | +0.075 |
udge | +0.072 |
Neg logit contributions | |
ll | -0.047 |
oph | -0.044 |
upon | -0.043 |
THE | -0.043 |
would | -0.042 |
Token | cried |
Token ID | 16896 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
oph | +0.013 |
ll | +0.013 |
would | +0.012 |
ory | +0.012 |
upon | +0.012 |
Neg logit contributions | |
rum | -0.023 |
pain | -0.019 |
ez | -0.019 |
udge | -0.019 |
mischief | -0.018 |
Token | loudly |
Token ID | 23112 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
rum | +0.037 |
pain | +0.034 |
ez | +0.032 |
mischief | +0.031 |
udge | +0.030 |
Neg logit contributions | |
oph | -0.018 |
ll | -0.018 |
ory | -0.017 |
upon | -0.017 |
THE | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
rum | +0.034 |
pain | +0.031 |
ez | +0.029 |
mischief | +0.028 |
udge | +0.027 |
Neg logit contributions | |
oph | -0.022 |
ll | -0.021 |
ory | -0.020 |
THE | -0.019 |
ari | -0.019 |
Token | She |
Token ID | 1375 |
Feature activation | +9.67e-02 |
Pos logit contributions | |
rum | +0.010 |
pain | +0.009 |
aged | +0.008 |
mischief | +0.008 |
ez | +0.008 |
Neg logit contributions | |
ll | -0.013 |
oph | -0.013 |
ory | -0.013 |
THE | -0.012 |
arium | -0.012 |
Token | cried |
Token ID | 16896 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
rum | +0.003 |
pain | +0.003 |
ez | +0.002 |
aged | +0.002 |
mischief | +0.002 |
Neg logit contributions | |
ll | -0.002 |
oph | -0.002 |
THE | -0.002 |
ory | -0.002 |
ari | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -5.03e-01 |
Pos logit contributions | |
rum | +0.024 |
pain | +0.022 |
ez | +0.021 |
mischief | +0.020 |
udge | +0.020 |
Neg logit contributions | |
oph | -0.013 |
ll | -0.012 |
ory | -0.012 |
THE | -0.011 |
upon | -0.011 |
Token | threw |
Token ID | 9617 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
oph | +0.009 |
ll | +0.008 |
would | +0.008 |
ory | +0.008 |
THE | +0.007 |
Neg logit contributions | |
rum | -0.017 |
pain | -0.015 |
udge | -0.014 |
ez | -0.014 |
mischief | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
rum | +0.042 |
udge | +0.033 |
aged | +0.033 |
pain | +0.032 |
ez | +0.032 |
Neg logit contributions | |
oph | -0.017 |
would | -0.017 |
upon | -0.017 |
of | -0.017 |
me | -0.016 |
Token | tant |
Token ID | 24246 |
Feature activation | +7.76e+00 |
Pos logit contributions | |
rum | +0.044 |
ez | +0.034 |
pain | +0.033 |
rums | +0.033 |
aged | +0.032 |
Neg logit contributions | |
upon | -0.050 |
ory | -0.048 |
of | -0.047 |
oph | -0.047 |
would | -0.047 |
Token | rum |
Token ID | 6582 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
mischief | +0.088 |
pain | +0.085 |
trouble | +0.069 |
elbows | +0.055 |
bruises | +0.046 |
Neg logit contributions | |
ll | -0.270 |
of | -0.258 |
pp | -0.253 |
ory | -0.251 |
ppy | -0.251 |
Token | . |
Token ID | 13 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
rum | +0.091 |
pain | +0.086 |
ez | +0.078 |
mischief | +0.077 |
udge | +0.074 |
Neg logit contributions | |
ll | -0.058 |
oph | -0.056 |
THE | -0.053 |
ory | -0.052 |
upon | -0.052 |
Token | Her |
Token ID | 2332 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
rum | +0.036 |
pain | +0.033 |
ez | +0.030 |
mischief | +0.028 |
aged | +0.028 |
Neg logit contributions | |
oph | -0.032 |
ll | -0.032 |
ory | -0.030 |
THE | -0.029 |
ari | -0.029 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
rum | +0.048 |
ez | +0.042 |
udge | +0.040 |
pain | +0.040 |
mischief | +0.038 |
Neg logit contributions | |
ll | -0.016 |
upon | -0.014 |
oph | -0.014 |
ory | -0.014 |
ocular | -0.013 |
Token | tried |
Token ID | 3088 |
Feature activation | +2.60e-01 |
Pos logit contributions | |
rum | +0.058 |
pain | +0.054 |
ez | +0.049 |
mischief | +0.049 |
udge | +0.047 |
Neg logit contributions | |
ll | -0.031 |
oph | -0.031 |
ory | -0.028 |
ari | -0.027 |
THE | -0.027 |
Token | kept |
Token ID | 4030 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
rum | +0.014 |
pain | +0.013 |
ez | +0.012 |
mischief | +0.012 |
aged | +0.011 |
Neg logit contributions | |
oph | -0.010 |
ll | -0.010 |
ory | -0.009 |
THE | -0.009 |
ari | -0.009 |
Token | crying |
Token ID | 13774 |
Feature activation | +9.93e-01 |
Pos logit contributions | |
rum | +0.036 |
udge | +0.028 |
policy | +0.027 |
ump | +0.027 |
ases | +0.025 |
Neg logit contributions | |
me | -0.022 |
ll | -0.021 |
back | -0.020 |
both | -0.020 |
upon | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -1.82e-01 |
Pos logit contributions | |
rum | +0.034 |
pain | +0.031 |
ez | +0.030 |
mischief | +0.029 |
udge | +0.028 |
Neg logit contributions | |
ll | -0.015 |
oph | -0.014 |
THE | -0.013 |
ory | -0.013 |
upon | -0.013 |
Token | throwing |
Token ID | 9644 |
Feature activation | +8.58e-01 |
Pos logit contributions | |
ll | +0.004 |
upon | +0.004 |
would | +0.004 |
oph | +0.004 |
THE | +0.004 |
Neg logit contributions | |
rum | -0.005 |
pain | -0.004 |
ez | -0.004 |
udge | -0.004 |
mischief | -0.004 |
Token | a |
Token ID | 257 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
rum | +0.029 |
ez | +0.024 |
pain | +0.024 |
udge | +0.023 |
aged | +0.023 |
Neg logit contributions | |
oph | -0.013 |
ory | -0.012 |
would | -0.012 |
THE | -0.012 |
upon | -0.012 |
Token | tant |
Token ID | 24246 |
Feature activation | +7.53e+00 |
Pos logit contributions | |
rum | +0.057 |
ez | +0.047 |
pain | +0.047 |
mischief | +0.045 |
aged | +0.044 |
Neg logit contributions | |
upon | -0.059 |
oph | -0.059 |
ory | -0.058 |
ll | -0.058 |
of | -0.057 |
Token | rum |
Token ID | 6582 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
mischief | +0.080 |
pain | +0.074 |
trouble | +0.061 |
elbows | +0.042 |
situations | +0.034 |
Neg logit contributions | |
ll | -0.269 |
of | -0.262 |
ppy | -0.253 |
oph | -0.251 |
pp | -0.247 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
rum | +0.092 |
pain | +0.086 |
ez | +0.079 |
mischief | +0.078 |
udge | +0.074 |
Neg logit contributions | |
ll | -0.054 |
oph | -0.052 |
THE | -0.049 |
upon | -0.049 |
would | -0.049 |
Token |
|
Token ID | 198 |
Feature activation | -4.09e-02 |
Pos logit contributions | |
rum | +0.044 |
pain | +0.041 |
ez | +0.037 |
mischief | +0.035 |
udge | +0.035 |
Neg logit contributions | |
oph | -0.028 |
ll | -0.028 |
ory | -0.026 |
THE | -0.025 |
upon | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -3.18e-01 |
Pos logit contributions | |
ll | +0.001 |
oph | +0.001 |
upon | +0.001 |
THE | +0.001 |
ory | +0.001 |
Neg logit contributions | |
rum | -0.001 |
pain | -0.001 |
ez | -0.001 |
mischief | -0.001 |
aged | -0.001 |
Token | Finally |
Token ID | 11158 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
oph | +0.006 |
ll | +0.006 |
THE | +0.005 |
ory | +0.005 |
upon | +0.005 |
Neg logit contributions | |
rum | -0.010 |
pain | -0.009 |
ez | -0.009 |
mischief | -0.008 |
udge | -0.008 |
Token | surprise |
Token ID | 5975 |
Feature activation | +4.87e-01 |
Pos logit contributions | |
ll | +0.035 |
oph | +0.035 |
ory | +0.034 |
upon | +0.032 |
THE | +0.032 |
Neg logit contributions | |
rum | -0.049 |
pain | -0.043 |
ez | -0.041 |
aged | -0.039 |
udge | -0.038 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e+00 |
Pos logit contributions | |
rum | +0.016 |
pain | +0.014 |
ez | +0.014 |
mischief | +0.013 |
aged | +0.013 |
Neg logit contributions | |
ll | -0.009 |
oph | -0.008 |
ory | -0.008 |
would | -0.008 |
ari | -0.008 |
Token | He |
Token ID | 679 |
Feature activation | +7.33e-01 |
Pos logit contributions | |
rum | +0.052 |
pain | +0.048 |
ez | +0.048 |
aged | +0.044 |
mischief | +0.043 |
Neg logit contributions | |
upon | -0.029 |
oph | -0.029 |
THE | -0.028 |
ll | -0.028 |
ory | -0.027 |
Token | threw |
Token ID | 9617 |
Feature activation | +8.59e-01 |
Pos logit contributions | |
rum | +0.024 |
pain | +0.022 |
ez | +0.020 |
mischief | +0.020 |
udge | +0.019 |
Neg logit contributions | |
oph | -0.013 |
ll | -0.013 |
ory | -0.012 |
would | -0.011 |
ari | -0.011 |
Token | a |
Token ID | 257 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
rum | +0.028 |
pain | +0.024 |
ez | +0.023 |
udge | +0.023 |
aged | +0.023 |
Neg logit contributions | |
oph | -0.014 |
ory | -0.013 |
upon | -0.013 |
THE | -0.013 |
ll | -0.013 |
Token | tant |
Token ID | 24246 |
Feature activation | +7.33e+00 |
Pos logit contributions | |
rum | +0.050 |
pain | +0.042 |
ez | +0.042 |
mischief | +0.040 |
aged | +0.040 |
Neg logit contributions | |
ory | -0.039 |
upon | -0.039 |
oph | -0.038 |
ll | -0.037 |
may | -0.036 |
Token | rum |
Token ID | 6582 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
mischief | +0.077 |
pain | +0.074 |
trouble | +0.051 |
elbows | +0.038 |
scrape | +0.034 |
Neg logit contributions | |
ll | -0.274 |
of | -0.257 |
pper | -0.250 |
ory | -0.248 |
pp | -0.245 |
Token | . |
Token ID | 13 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
rum | +0.086 |
pain | +0.082 |
ez | +0.075 |
mischief | +0.075 |
udge | +0.071 |
Neg logit contributions | |
ll | -0.054 |
oph | -0.050 |
THE | -0.049 |
upon | -0.049 |
ory | -0.048 |
Token | He |
Token ID | 679 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
rum | +0.072 |
ez | +0.065 |
pain | +0.063 |
aged | +0.059 |
mischief | +0.059 |
Neg logit contributions | |
upon | -0.033 |
oph | -0.030 |
ll | -0.029 |
ocular | -0.029 |
may | -0.028 |
Token | kicked |
Token ID | 12165 |
Feature activation | +9.56e-01 |
Pos logit contributions | |
rum | +0.024 |
pain | +0.020 |
mischief | +0.020 |
udge | +0.019 |
ez | +0.019 |
Neg logit contributions | |
ll | -0.014 |
would | -0.014 |
oph | -0.014 |
ory | -0.013 |
may | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
rum | +0.031 |
pain | +0.028 |
ez | +0.027 |
mischief | +0.026 |
aged | +0.026 |
Neg logit contributions | |
oph | -0.015 |
ll | -0.015 |
ory | -0.015 |
upon | -0.014 |
THE | -0.014 |
Token | her |
Token ID | 607 |
Feature activation | -6.94e-02 |
Pos logit contributions | |
rum | +0.023 |
pain | +0.019 |
ez | +0.019 |
udge | +0.019 |
policy | +0.019 |
Neg logit contributions | |
upon | -0.010 |
oph | -0.010 |
ory | -0.009 |
me | -0.009 |
of | -0.009 |
Token | feet |
Token ID | 3625 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
ll | +0.002 |
oph | +0.002 |
ory | +0.002 |
upon | +0.002 |
ocular | +0.002 |
Neg logit contributions | |
rum | -0.002 |
ez | -0.002 |
pain | -0.002 |
mischief | -0.001 |
udge | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
rum | +0.062 |
pain | +0.058 |
ez | +0.055 |
mischief | +0.054 |
udge | +0.051 |
Neg logit contributions | |
ll | -0.030 |
oph | -0.027 |
upon | -0.027 |
ory | -0.025 |
ocular | -0.025 |
Token | threw |
Token ID | 9617 |
Feature activation | +9.37e-01 |
Pos logit contributions | |
would | +0.020 |
oph | +0.019 |
ll | +0.019 |
upon | +0.018 |
may | +0.018 |
Neg logit contributions | |
rum | -0.036 |
udge | -0.030 |
pain | -0.030 |
mischief | -0.029 |
ez | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
rum | +0.031 |
pain | +0.027 |
ez | +0.026 |
aged | +0.025 |
mischief | +0.025 |
Neg logit contributions | |
oph | -0.015 |
ory | -0.014 |
upon | -0.014 |
of | -0.013 |
ocular | -0.013 |
Token | tant |
Token ID | 24246 |
Feature activation | +7.29e+00 |
Pos logit contributions | |
rum | +0.036 |
pain | +0.027 |
ez | +0.026 |
mischief | +0.025 |
aged | +0.025 |
Neg logit contributions | |
ory | -0.065 |
upon | -0.065 |
oph | -0.065 |
of | -0.064 |
ll | -0.063 |
Token | rum |
Token ID | 6582 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
mischief | +0.086 |
pain | +0.083 |
trouble | +0.072 |
elbows | +0.048 |
bruises | +0.045 |
Neg logit contributions | |
ll | -0.254 |
of | -0.244 |
ppy | -0.237 |
pper | -0.236 |
pp | -0.235 |
Token | . |
Token ID | 13 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
rum | +0.079 |
pain | +0.075 |
ez | +0.069 |
mischief | +0.067 |
udge | +0.064 |
Neg logit contributions | |
ll | -0.048 |
oph | -0.047 |
THE | -0.044 |
upon | -0.044 |
ory | -0.044 |
Token | She |
Token ID | 1375 |
Feature activation | +6.86e-01 |
Pos logit contributions | |
rum | +0.042 |
pain | +0.038 |
ez | +0.036 |
mischief | +0.033 |
udge | +0.033 |
Neg logit contributions | |
oph | -0.029 |
ll | -0.028 |
ory | -0.027 |
upon | -0.026 |
ari | -0.026 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +1.92e+00 |
Pos logit contributions | |
rum | +0.023 |
pain | +0.019 |
udge | +0.018 |
mischief | +0.018 |
ez | +0.018 |
Neg logit contributions | |
would | -0.012 |
ll | -0.012 |
oph | -0.012 |
ory | -0.011 |
may | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -4.25e-01 |
Pos logit contributions | |
rum | +0.067 |
pain | +0.057 |
ez | +0.054 |
mischief | +0.053 |
policy | +0.052 |
Neg logit contributions | |
oph | -0.029 |
ory | -0.028 |
upon | -0.026 |
of | -0.026 |
ocular | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
ll | +0.004 |
oph | +0.004 |
ory | +0.004 |
upon | +0.004 |
THE | +0.003 |
Neg logit contributions | |
rum | -0.007 |
pain | -0.007 |
ez | -0.006 |
mischief | -0.006 |
udge | -0.006 |
Token | He |
Token ID | 679 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
rum | +0.044 |
ez | +0.043 |
pain | +0.040 |
udge | +0.037 |
mischief | +0.037 |
Neg logit contributions | |
oph | -0.019 |
upon | -0.018 |
ory | -0.017 |
ocular | -0.017 |
ari | -0.017 |
Token | kept |
Token ID | 4030 |
Feature activation | +7.08e-01 |
Pos logit contributions | |
rum | +0.008 |
pain | +0.007 |
ez | +0.007 |
mischief | +0.006 |
aged | +0.006 |
Neg logit contributions | |
oph | -0.004 |
ll | -0.004 |
ory | -0.004 |
THE | -0.004 |
ari | -0.004 |
Token | throwing |
Token ID | 9644 |
Feature activation | +3.14e-01 |
Pos logit contributions | |
rum | +0.021 |
udge | +0.017 |
pain | +0.016 |
ez | +0.016 |
policy | +0.016 |
Neg logit contributions | |
ll | -0.013 |
me | -0.013 |
upon | -0.013 |
back | -0.012 |
ory | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
rum | +0.010 |
pain | +0.008 |
ez | +0.008 |
udge | +0.008 |
aged | +0.008 |
Neg logit contributions | |
ory | -0.005 |
oph | -0.005 |
upon | -0.005 |
THE | -0.005 |
ll | -0.005 |
Token | tant |
Token ID | 24246 |
Feature activation | +7.28e+00 |
Pos logit contributions | |
rum | +0.051 |
pain | +0.044 |
ez | +0.043 |
mischief | +0.041 |
aged | +0.041 |
Neg logit contributions | |
ory | -0.037 |
oph | -0.036 |
ll | -0.035 |
upon | -0.035 |
ari | -0.033 |
Token | rum |
Token ID | 6582 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
mischief | +0.072 |
pain | +0.069 |
trouble | +0.046 |
elbows | +0.038 |
bruises | +0.029 |
Neg logit contributions | |
ll | -0.272 |
of | -0.259 |
pper | -0.250 |
pp | -0.250 |
ory | -0.248 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
rum | +0.082 |
pain | +0.079 |
ez | +0.074 |
mischief | +0.074 |
udge | +0.068 |
Neg logit contributions | |
ll | -0.044 |
THE | -0.040 |
upon | -0.040 |
oph | -0.040 |
ory | -0.039 |
Token | His |
Token ID | 2399 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
rum | +0.059 |
ez | +0.054 |
pain | +0.051 |
udge | +0.048 |
aged | +0.047 |
Neg logit contributions | |
upon | -0.029 |
oph | -0.028 |
ory | -0.025 |
ll | -0.025 |
THE | -0.025 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
rum | +0.047 |
ez | +0.043 |
pain | +0.040 |
udge | +0.040 |
mischief | +0.039 |
Neg logit contributions | |
ll | -0.015 |
upon | -0.014 |
ory | -0.014 |
would | -0.013 |
ocular | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
rum | +0.066 |
pain | +0.061 |
ez | +0.056 |
mischief | +0.055 |
udge | +0.053 |
Neg logit contributions | |
ll | -0.035 |
oph | -0.034 |
ory | -0.031 |
ari | -0.030 |
would | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
rum | +0.060 |
ez | +0.050 |
pain | +0.050 |
udge | +0.048 |
ump | +0.048 |
Neg logit contributions | |
upon | -0.012 |
would | -0.010 |
ll | -0.010 |
oph | -0.008 |
arium | -0.007 |
Token | cry |
Token ID | 3960 |
Feature activation | +8.67e-02 |
Pos logit contributions | |
rum | +0.035 |
ez | +0.029 |
pain | +0.028 |
udge | +0.027 |
aged | +0.027 |
Neg logit contributions | |
ll | -0.030 |
oph | -0.030 |
upon | -0.029 |
ory | -0.029 |
would | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
rum | +0.003 |
pain | +0.003 |
ez | +0.002 |
mischief | +0.002 |
udge | +0.002 |
Neg logit contributions | |
ll | -0.001 |
oph | -0.001 |
ory | -0.001 |
upon | -0.001 |
THE | -0.001 |
Token | threw |
Token ID | 9617 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
oph | +0.026 |
ll | +0.026 |
ory | +0.024 |
THE | +0.023 |
upon | +0.023 |
Neg logit contributions | |
rum | -0.036 |
pain | -0.033 |
ez | -0.030 |
mischief | -0.029 |
udge | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
rum | +0.039 |
aged | +0.031 |
oving | +0.031 |
udge | +0.030 |
policy | +0.030 |
Neg logit contributions | |
oph | -0.014 |
upon | -0.013 |
me | -0.013 |
of | -0.013 |
back | -0.013 |
Token | tant |
Token ID | 24246 |
Feature activation | +7.25e+00 |
Pos logit contributions | |
rum | +0.048 |
aged | +0.038 |
ez | +0.038 |
rums | +0.038 |
mischief | +0.038 |
Neg logit contributions | |
upon | -0.045 |
of | -0.044 |
would | -0.043 |
may | -0.042 |
ory | -0.042 |
Token | rum |
Token ID | 6582 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
mischief | +0.077 |
pain | +0.073 |
trouble | +0.060 |
elbows | +0.044 |
bruises | +0.037 |
Neg logit contributions | |
ll | -0.258 |
of | -0.247 |
ppy | -0.243 |
oph | -0.241 |
pp | -0.240 |
Token | . |
Token ID | 13 |
Feature activation | +5.75e-01 |
Pos logit contributions | |
rum | +0.080 |
pain | +0.075 |
mischief | +0.070 |
ez | +0.070 |
udge | +0.066 |
Neg logit contributions | |
ll | -0.042 |
oph | -0.041 |
THE | -0.040 |
upon | -0.039 |
would | -0.039 |
Token | She |
Token ID | 1375 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
rum | +0.015 |
pain | +0.014 |
ez | +0.012 |
mischief | +0.012 |
aged | +0.011 |
Neg logit contributions | |
ll | -0.014 |
oph | -0.014 |
ory | -0.013 |
THE | -0.013 |
ari | -0.013 |
Token | didn |
Token ID | 1422 |
Feature activation | -8.80e-01 |
Pos logit contributions | |
rum | +0.001 |
pain | +0.001 |
mischief | +0.001 |
udge | +0.001 |
ez | +0.001 |
Neg logit contributions | |
ll | -0.000 |
oph | -0.000 |
would | -0.000 |
ory | -0.000 |
upon | -0.000 |
Token | 't |
Token ID | 470 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
ll | +0.018 |
oph | +0.018 |
ory | +0.017 |
THE | +0.017 |
ari | +0.016 |
Neg logit contributions | |
rum | -0.025 |
pain | -0.024 |
ez | -0.022 |
mischief | -0.021 |
aged | -0.020 |
Token | temper |
Token ID | 4124 |
Feature activation | +2.85e+00 |
Pos logit contributions | |
rum | +0.099 |
ez | +0.083 |
pain | +0.083 |
udge | +0.079 |
mischief | +0.072 |
Neg logit contributions | |
ory | -0.086 |
would | -0.084 |
upon | -0.084 |
may | -0.082 |
ll | -0.081 |
Token | and |
Token ID | 290 |
Feature activation | +9.08e-01 |
Pos logit contributions | |
rum | +0.090 |
pain | +0.082 |
ez | +0.077 |
udge | +0.075 |
mischief | +0.074 |
Neg logit contributions | |
would | -0.047 |
ll | -0.046 |
ory | -0.045 |
upon | -0.044 |
ari | -0.044 |
Token | often |
Token ID | 1690 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
rum | +0.031 |
pain | +0.027 |
udge | +0.027 |
ez | +0.026 |
mischief | +0.025 |
Neg logit contributions | |
would | -0.014 |
ll | -0.013 |
upon | -0.013 |
oph | -0.013 |
'd | -0.013 |
Token | threw |
Token ID | 9617 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
rum | +0.037 |
pain | +0.034 |
ez | +0.032 |
mischief | +0.031 |
udge | +0.031 |
Neg logit contributions | |
ll | -0.020 |
oph | -0.020 |
ory | -0.019 |
would | -0.018 |
arium | -0.017 |
Token | temper |
Token ID | 4124 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
rum | +0.034 |
pain | +0.028 |
aged | +0.027 |
ez | +0.027 |
udge | +0.026 |
Neg logit contributions | |
ory | -0.019 |
oph | -0.019 |
upon | -0.019 |
would | -0.018 |
of | -0.018 |
Token | tant |
Token ID | 24246 |
Feature activation | +7.16e+00 |
Pos logit contributions | |
rum | +0.063 |
pain | +0.057 |
ez | +0.050 |
mischief | +0.050 |
udge | +0.048 |
Neg logit contributions | |
ll | -0.053 |
ory | -0.052 |
oph | -0.051 |
upon | -0.050 |
would | -0.049 |
Token | rums |
Token ID | 45241 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
pain | +0.101 |
mischief | +0.073 |
trouble | +0.062 |
scrape | +0.055 |
sensation | +0.054 |
Neg logit contributions | |
ll | -0.257 |
oph | -0.228 |
of | -0.220 |
ail | -0.217 |
pp | -0.216 |
Token | . |
Token ID | 13 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
rum | +0.058 |
pain | +0.056 |
ez | +0.051 |
mischief | +0.050 |
udge | +0.048 |
Neg logit contributions | |
ll | -0.033 |
oph | -0.031 |
ory | -0.030 |
THE | -0.029 |
upon | -0.029 |
Token | One |
Token ID | 1881 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
rum | +0.046 |
pain | +0.045 |
ez | +0.042 |
udge | +0.040 |
aged | +0.039 |
Neg logit contributions | |
oph | -0.023 |
ll | -0.021 |
upon | -0.021 |
THE | -0.020 |
ory | -0.020 |
Token | day |
Token ID | 1110 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
rum | +0.045 |
pain | +0.039 |
ez | +0.038 |
aged | +0.037 |
elbows | +0.037 |
Neg logit contributions | |
upon | -0.020 |
would | -0.020 |
ll | -0.019 |
ory | -0.018 |
oph | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
rum | +0.119 |
pain | +0.110 |
ez | +0.108 |
udge | +0.104 |
mischief | +0.101 |
Neg logit contributions | |
oph | -0.043 |
upon | -0.042 |
ll | -0.040 |
ory | -0.038 |
would | -0.037 |
Token | stubborn |
Token ID | 24444 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
rum | +0.009 |
pain | +0.007 |
ez | +0.007 |
udge | +0.007 |
mischief | +0.007 |
Neg logit contributions | |
ll | -0.006 |
upon | -0.006 |
oph | -0.006 |
ory | -0.006 |
THE | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
rum | +0.020 |
pain | +0.018 |
ez | +0.018 |
mischief | +0.017 |
udge | +0.017 |
Neg logit contributions | |
ll | -0.010 |
oph | -0.010 |
ory | -0.009 |
upon | -0.009 |
would | -0.009 |
Token | She |
Token ID | 1375 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
rum | +0.055 |
pain | +0.049 |
ez | +0.048 |
aged | +0.046 |
mischief | +0.044 |
Neg logit contributions | |
oph | -0.023 |
upon | -0.021 |
ll | -0.020 |
THE | -0.020 |
ory | -0.020 |
Token | throws |
Token ID | 12542 |
Feature activation | +6.72e-01 |
Pos logit contributions | |
rum | +0.002 |
pain | +0.002 |
ez | +0.002 |
mischief | +0.002 |
aged | +0.002 |
Neg logit contributions | |
oph | -0.002 |
ll | -0.002 |
ory | -0.001 |
THE | -0.001 |
ari | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
rum | +0.022 |
pain | +0.019 |
ez | +0.019 |
aged | +0.018 |
mischief | +0.018 |
Neg logit contributions | |
oph | -0.011 |
ory | -0.010 |
ll | -0.010 |
upon | -0.010 |
THE | -0.010 |
Token | tant |
Token ID | 24246 |
Feature activation | +7.11e+00 |
Pos logit contributions | |
rum | +0.040 |
pain | +0.034 |
ez | +0.032 |
aged | +0.030 |
mischief | +0.030 |
Neg logit contributions | |
oph | -0.053 |
ory | -0.053 |
upon | -0.052 |
ll | -0.052 |
of | -0.051 |
Token | rum |
Token ID | 6582 |
Feature activation | +2.19e+00 |
Pos logit contributions | |
pain | +0.070 |
mischief | +0.068 |
trouble | +0.045 |
scrape | +0.032 |
elbows | +0.032 |
Neg logit contributions | |
ll | -0.270 |
of | -0.251 |
oph | -0.244 |
pper | -0.242 |
ory | -0.238 |
Token | . |
Token ID | 13 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
rum | +0.063 |
pain | +0.059 |
ez | +0.054 |
mischief | +0.052 |
udge | +0.050 |
Neg logit contributions | |
ll | -0.046 |
oph | -0.045 |
ory | -0.042 |
THE | -0.041 |
upon | -0.040 |
Token | She |
Token ID | 1375 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
rum | +0.062 |
pain | +0.055 |
ez | +0.054 |
aged | +0.050 |
mischief | +0.049 |
Neg logit contributions | |
oph | -0.030 |
upon | -0.027 |
ll | -0.027 |
ory | -0.025 |
THE | -0.025 |
Token | kicks |
Token ID | 17364 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
rum | +0.003 |
pain | +0.003 |
ez | +0.002 |
mischief | +0.002 |
udge | +0.002 |
Neg logit contributions | |
ll | -0.003 |
oph | -0.002 |
ory | -0.002 |
upon | -0.002 |
THE | -0.002 |
Token | and |
Token ID | 290 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
rum | +0.033 |
pain | +0.029 |
ez | +0.028 |
mischief | +0.027 |
aged | +0.027 |
Neg logit contributions | |
oph | -0.015 |
ll | -0.014 |
ory | -0.014 |
upon | -0.014 |
THE | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
ll | +0.041 |
oph | +0.040 |
ory | +0.038 |
ari | +0.037 |
THE | +0.037 |
Neg logit contributions | |
rum | -0.045 |
pain | -0.043 |
ez | -0.038 |
mischief | -0.036 |
aged | -0.035 |
Token | daddy |
Token ID | 35822 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
rum | +0.033 |
pain | +0.031 |
ez | +0.028 |
mischief | +0.027 |
aged | +0.026 |
Neg logit contributions | |
oph | -0.024 |
ll | -0.024 |
ory | -0.022 |
THE | -0.021 |
ari | -0.021 |
Token | who |
Token ID | 508 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
rum | +0.044 |
pain | +0.041 |
mischief | +0.038 |
ez | +0.036 |
aged | +0.035 |
Neg logit contributions | |
ll | -0.025 |
ory | -0.023 |
oph | -0.023 |
would | -0.022 |
ari | -0.022 |
Token | had |
Token ID | 550 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
rum | +0.047 |
pain | +0.044 |
ez | +0.039 |
mischief | +0.039 |
udge | +0.039 |
Neg logit contributions | |
ll | -0.024 |
oph | -0.023 |
would | -0.022 |
ory | -0.022 |
THE | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
rum | +0.047 |
pain | +0.042 |
ez | +0.040 |
udge | +0.038 |
mischief | +0.037 |
Neg logit contributions | |
oph | -0.025 |
ll | -0.024 |
ory | -0.023 |
THE | -0.022 |
upon | -0.022 |
Token | 3 |
Token ID | 513 |
Feature activation | +7.02e+00 |
Pos logit contributions | |
rum | +0.122 |
pain | +0.106 |
ez | +0.103 |
udge | +0.096 |
aged | +0.095 |
Neg logit contributions | |
oph | -0.073 |
ll | -0.072 |
ory | -0.070 |
upon | -0.066 |
would | -0.066 |
Token | year |
Token ID | 614 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
rum | +0.222 |
elbows | +0.209 |
bleed | +0.207 |
udge | +0.203 |
pain | +0.203 |
Neg logit contributions | |
would | -0.072 |
ory | -0.072 |
ari | -0.071 |
oph | -0.069 |
ie | -0.067 |
Token | old |
Token ID | 1468 |
Feature activation | +3.25e+00 |
Pos logit contributions | |
rum | +0.014 |
pain | +0.013 |
ez | +0.012 |
mischief | +0.011 |
aged | +0.011 |
Neg logit contributions | |
oph | -0.013 |
ll | -0.013 |
THE | -0.012 |
ory | -0.012 |
upon | -0.012 |
Token | child |
Token ID | 1200 |
Feature activation | +3.24e+00 |
Pos logit contributions | |
rum | +0.108 |
pain | +0.095 |
ez | +0.094 |
udge | +0.088 |
mischief | +0.088 |
Neg logit contributions | |
ory | -0.055 |
would | -0.053 |
oph | -0.051 |
ari | -0.049 |
upon | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +6.24e-01 |
Pos logit contributions | |
rum | +0.097 |
pain | +0.094 |
mischief | +0.083 |
ez | +0.079 |
udge | +0.078 |
Neg logit contributions | |
ll | -0.062 |
ari | -0.059 |
would | -0.058 |
ory | -0.057 |
oph | -0.057 |
Token | Each |
Token ID | 5501 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
rum | +0.017 |
pain | +0.016 |
ez | +0.014 |
mischief | +0.014 |
aged | +0.013 |
Neg logit contributions | |
oph | -0.014 |
ll | -0.014 |
ory | -0.013 |
THE | -0.013 |
ari | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +3.52e-01 |
Pos logit contributions | |
rum | +0.040 |
pain | +0.037 |
ez | +0.035 |
mischief | +0.033 |
udge | +0.033 |
Neg logit contributions | |
ll | -0.020 |
oph | -0.019 |
ory | -0.018 |
upon | -0.017 |
ari | -0.017 |
Token | so |
Token ID | 523 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
rum | +0.011 |
pain | +0.011 |
ez | +0.010 |
mischief | +0.010 |
aged | +0.010 |
Neg logit contributions | |
oph | -0.006 |
ll | -0.006 |
ory | -0.006 |
THE | -0.005 |
ari | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
rum | +0.071 |
pain | +0.066 |
ez | +0.062 |
mischief | +0.059 |
udge | +0.059 |
Neg logit contributions | |
ll | -0.038 |
oph | -0.037 |
ory | -0.034 |
upon | -0.033 |
THE | -0.033 |
Token | threw |
Token ID | 9617 |
Feature activation | +6.04e-01 |
Pos logit contributions | |
rum | +0.010 |
pain | +0.009 |
ez | +0.009 |
mischief | +0.008 |
aged | +0.008 |
Neg logit contributions | |
oph | -0.007 |
ll | -0.007 |
ory | -0.006 |
THE | -0.006 |
ari | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
rum | +0.020 |
pain | +0.016 |
ez | +0.015 |
aged | +0.015 |
udge | +0.015 |
Neg logit contributions | |
oph | -0.011 |
ory | -0.010 |
THE | -0.010 |
upon | -0.010 |
of | -0.010 |
Token | tant |
Token ID | 24246 |
Feature activation | +6.87e+00 |
Pos logit contributions | |
rum | +0.055 |
pain | +0.048 |
ez | +0.046 |
mischief | +0.044 |
aged | +0.044 |
Neg logit contributions | |
ory | -0.038 |
ll | -0.037 |
oph | -0.037 |
upon | -0.036 |
would | -0.034 |
Token | rum |
Token ID | 6582 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
pain | +0.078 |
mischief | +0.072 |
trouble | +0.060 |
elbows | +0.046 |
bruises | +0.042 |
Neg logit contributions | |
ll | -0.248 |
of | -0.225 |
ie | -0.225 |
ory | -0.221 |
pp | -0.221 |
Token | when |
Token ID | 618 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
rum | +0.068 |
pain | +0.065 |
ez | +0.059 |
mischief | +0.058 |
udge | +0.056 |
Neg logit contributions | |
ll | -0.042 |
oph | -0.040 |
THE | -0.039 |
upon | -0.039 |
would | -0.038 |
Token | her |
Token ID | 607 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
rum | +0.037 |
pain | +0.035 |
ez | +0.031 |
mischief | +0.030 |
aged | +0.029 |
Neg logit contributions | |
oph | -0.024 |
ll | -0.024 |
ory | -0.022 |
THE | -0.021 |
ari | -0.021 |
Token | parents |
Token ID | 3397 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
rum | +0.035 |
pain | +0.031 |
ez | +0.030 |
udge | +0.028 |
mischief | +0.028 |
Neg logit contributions | |
ll | -0.017 |
oph | -0.016 |
ory | -0.016 |
ari | -0.015 |
upon | -0.015 |
Token | said |
Token ID | 531 |
Feature activation | +2.12e-01 |
Pos logit contributions | |
rum | +0.049 |
pain | +0.047 |
ez | +0.043 |
mischief | +0.041 |
aged | +0.040 |
Neg logit contributions | |
oph | -0.029 |
ll | -0.028 |
ory | -0.026 |
THE | -0.026 |
ari | -0.025 |
Token | daddy |
Token ID | 35822 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
rum | +0.023 |
pain | +0.022 |
ez | +0.019 |
mischief | +0.019 |
aged | +0.018 |
Neg logit contributions | |
ll | -0.018 |
oph | -0.018 |
ory | -0.016 |
THE | -0.016 |
ari | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +6.61e-01 |
Pos logit contributions | |
rum | +0.037 |
pain | +0.035 |
mischief | +0.031 |
ez | +0.031 |
aged | +0.030 |
Neg logit contributions | |
ll | -0.023 |
oph | -0.022 |
ory | -0.021 |
ari | -0.020 |
THE | -0.020 |
Token | They |
Token ID | 1119 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
rum | +0.019 |
pain | +0.018 |
ez | +0.017 |
mischief | +0.015 |
aged | +0.015 |
Neg logit contributions | |
oph | -0.014 |
ll | -0.013 |
ory | -0.013 |
upon | -0.012 |
THE | -0.012 |
Token | had |
Token ID | 550 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
ll | +0.031 |
oph | +0.031 |
ari | +0.029 |
ete | +0.028 |
arium | +0.028 |
Neg logit contributions | |
pain | -0.027 |
rum | -0.026 |
ez | -0.024 |
aged | -0.021 |
mischief | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
rum | +0.043 |
pain | +0.039 |
ez | +0.036 |
udge | +0.035 |
mischief | +0.034 |
Neg logit contributions | |
oph | -0.024 |
ll | -0.024 |
ory | -0.022 |
THE | -0.022 |
upon | -0.021 |
Token | 3 |
Token ID | 513 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
rum | +0.105 |
pain | +0.094 |
ez | +0.089 |
udge | +0.083 |
aged | +0.083 |
Neg logit contributions | |
oph | -0.067 |
ll | -0.066 |
ory | -0.063 |
upon | -0.060 |
ari | -0.059 |
Token | year |
Token ID | 614 |
Feature activation | +5.59e-01 |
Pos logit contributions | |
rum | +0.213 |
elbows | +0.197 |
bleed | +0.193 |
pain | +0.193 |
mischief | +0.192 |
Neg logit contributions | |
ari | -0.086 |
oph | -0.084 |
would | -0.080 |
party | -0.079 |
ory | -0.078 |
Token | old |
Token ID | 1468 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
rum | +0.014 |
pain | +0.013 |
ez | +0.011 |
mischief | +0.011 |
aged | +0.011 |
Neg logit contributions | |
oph | -0.014 |
ll | -0.014 |
THE | -0.013 |
ory | -0.013 |
upon | -0.012 |
Token | girl |
Token ID | 2576 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
rum | +0.117 |
ez | +0.100 |
pain | +0.099 |
udge | +0.096 |
mischief | +0.094 |
Neg logit contributions | |
would | -0.054 |
ory | -0.053 |
ari | -0.050 |
oph | -0.048 |
upon | -0.048 |
Token | who |
Token ID | 508 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
rum | +0.088 |
pain | +0.080 |
mischief | +0.071 |
ez | +0.069 |
udge | +0.066 |
Neg logit contributions | |
ll | -0.062 |
ari | -0.060 |
would | -0.059 |
oph | -0.059 |
ory | -0.058 |
Token | was |
Token ID | 373 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
rum | +0.060 |
pain | +0.057 |
ez | +0.052 |
mischief | +0.049 |
aged | +0.048 |
Neg logit contributions | |
oph | -0.040 |
ll | -0.040 |
ory | -0.037 |
THE | -0.036 |
ari | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
rum | +0.051 |
pain | +0.048 |
ez | +0.046 |
aged | +0.044 |
mischief | +0.043 |
Neg logit contributions | |
ll | -0.025 |
ory | -0.023 |
oph | -0.023 |
would | -0.023 |
upon | -0.022 |
Token | The |
Token ID | 383 |
Feature activation | -4.10e-01 |
Pos logit contributions | |
rum | +0.034 |
pain | +0.032 |
ez | +0.029 |
mischief | +0.027 |
aged | +0.026 |
Neg logit contributions | |
oph | -0.031 |
ll | -0.031 |
ory | -0.030 |
THE | -0.029 |
ari | -0.028 |
Token | mouse |
Token ID | 10211 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
ll | +0.008 |
oph | +0.008 |
ari | +0.007 |
upon | +0.007 |
THE | +0.007 |
Neg logit contributions | |
rum | -0.012 |
ez | -0.011 |
pain | -0.010 |
udge | -0.010 |
mischief | -0.010 |
Token | used |
Token ID | 973 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
rum | +0.089 |
pain | +0.083 |
ez | +0.076 |
mischief | +0.073 |
udge | +0.072 |
Neg logit contributions | |
ll | -0.057 |
oph | -0.057 |
ory | -0.053 |
THE | -0.051 |
ari | -0.051 |
Token | her |
Token ID | 607 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
rum | +0.093 |
pain | +0.081 |
ez | +0.080 |
udge | +0.077 |
mischief | +0.075 |
Neg logit contributions | |
upon | -0.068 |
ll | -0.065 |
would | -0.065 |
may | -0.064 |
oph | -0.063 |
Token | sharp |
Token ID | 7786 |
Feature activation | +6.77e+00 |
Pos logit contributions | |
rum | +0.087 |
pain | +0.077 |
ez | +0.076 |
udge | +0.073 |
mischief | +0.071 |
Neg logit contributions | |
ll | -0.077 |
upon | -0.073 |
may | -0.072 |
would | -0.071 |
ari | -0.070 |
Token | teeth |
Token ID | 9941 |
Feature activation | +2.90e+00 |
Pos logit contributions | |
udge | +0.130 |
rum | +0.121 |
ez | +0.119 |
mischief | +0.118 |
pain | +0.113 |
Neg logit contributions | |
may | -0.170 |
would | -0.165 |
upon | -0.164 |
ocular | -0.149 |
ll | -0.147 |
Token | to |
Token ID | 284 |
Feature activation | +2.65e+00 |
Pos logit contributions | |
rum | +0.089 |
pain | +0.084 |
ez | +0.077 |
mischief | +0.074 |
udge | +0.072 |
Neg logit contributions | |
ll | -0.054 |
oph | -0.053 |
ory | -0.049 |
THE | -0.048 |
upon | -0.048 |
Token | make |
Token ID | 787 |
Feature activation | +8.25e-01 |
Pos logit contributions | |
rum | +0.073 |
ez | +0.065 |
pain | +0.065 |
mischief | +0.060 |
udge | +0.059 |
Neg logit contributions | |
ll | -0.053 |
would | -0.050 |
may | -0.050 |
of | -0.049 |
upon | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
rum | +0.026 |
pain | +0.023 |
ez | +0.023 |
udge | +0.022 |
aged | +0.021 |
Neg logit contributions | |
oph | -0.013 |
ll | -0.013 |
ory | -0.012 |
upon | -0.012 |
THE | -0.012 |
Token | hole |
Token ID | 7604 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
rum | +0.015 |
ez | +0.012 |
udge | +0.012 |
pain | +0.012 |
aged | +0.011 |
Neg logit contributions | |
ll | -0.011 |
ari | -0.010 |
upon | -0.010 |
oph | -0.010 |
would | -0.010 |
Token | his |
Token ID | 465 |
Feature activation | +8.74e-01 |
Pos logit contributions | |
rum | +0.096 |
mischief | +0.085 |
pain | +0.084 |
ez | +0.081 |
cigarette | +0.077 |
Neg logit contributions | |
upon | -0.075 |
ory | -0.072 |
of | -0.070 |
oph | -0.069 |
would | -0.066 |
Token | feet |
Token ID | 3625 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
rum | +0.022 |
ez | +0.019 |
pain | +0.018 |
udge | +0.018 |
mischief | +0.017 |
Neg logit contributions | |
ll | -0.020 |
ory | -0.019 |
upon | -0.019 |
oph | -0.019 |
ocular | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
rum | +0.045 |
pain | +0.042 |
ez | +0.039 |
mischief | +0.039 |
udge | +0.037 |
Neg logit contributions | |
ll | -0.025 |
oph | -0.024 |
upon | -0.023 |
ory | -0.023 |
THE | -0.022 |
Token | threw |
Token ID | 9617 |
Feature activation | +7.21e-01 |
Pos logit contributions | |
ll | +0.016 |
oph | +0.015 |
ory | +0.015 |
upon | +0.015 |
would | +0.014 |
Neg logit contributions | |
rum | -0.023 |
pain | -0.020 |
ez | -0.019 |
udge | -0.019 |
mischief | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
rum | +0.021 |
pain | +0.019 |
ez | +0.018 |
udge | +0.017 |
mischief | +0.017 |
Neg logit contributions | |
oph | -0.014 |
ory | -0.014 |
ll | -0.013 |
upon | -0.013 |
THE | -0.013 |
Token | tant |
Token ID | 24246 |
Feature activation | +6.76e+00 |
Pos logit contributions | |
rum | +0.065 |
pain | +0.056 |
ez | +0.055 |
mischief | +0.054 |
aged | +0.052 |
Neg logit contributions | |
oph | -0.051 |
ory | -0.050 |
upon | -0.050 |
ll | -0.049 |
of | -0.049 |
Token | rum |
Token ID | 6582 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
pain | +0.067 |
mischief | +0.063 |
trouble | +0.041 |
apy | +0.032 |
sensation | +0.028 |
Neg logit contributions | |
ll | -0.264 |
pper | -0.242 |
of | -0.234 |
oph | -0.234 |
ory | -0.231 |
Token | . |
Token ID | 13 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
rum | +0.073 |
pain | +0.070 |
ez | +0.064 |
mischief | +0.063 |
udge | +0.060 |
Neg logit contributions | |
ll | -0.049 |
oph | -0.047 |
ory | -0.045 |
THE | -0.044 |
upon | -0.044 |
Token |
|
Token ID | 198 |
Feature activation | -2.72e-01 |
Pos logit contributions | |
rum | +0.054 |
pain | +0.050 |
ez | +0.047 |
mischief | +0.044 |
aged | +0.043 |
Neg logit contributions | |
oph | -0.031 |
ll | -0.030 |
ory | -0.029 |
upon | -0.028 |
THE | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -2.49e-01 |
Pos logit contributions | |
ll | +0.005 |
oph | +0.005 |
ory | +0.004 |
THE | +0.004 |
upon | +0.004 |
Neg logit contributions | |
rum | -0.009 |
pain | -0.008 |
ez | -0.008 |
mischief | -0.007 |
aged | -0.007 |
Token | " |
Token ID | 1 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
ll | +0.004 |
oph | +0.004 |
ory | +0.004 |
THE | +0.004 |
upon | +0.004 |
Neg logit contributions | |
rum | -0.008 |
pain | -0.007 |
ez | -0.007 |
mischief | -0.007 |
aged | -0.006 |
Token | them |
Token ID | 606 |
Feature activation | -1.48e+00 |
Pos logit contributions | |
rum | +0.090 |
pain | +0.084 |
ez | +0.076 |
mischief | +0.072 |
udge | +0.071 |
Neg logit contributions | |
oph | -0.069 |
ll | -0.069 |
ory | -0.065 |
THE | -0.063 |
ari | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
oph | +0.041 |
ory | +0.035 |
ari | +0.035 |
ll | +0.035 |
ete | +0.033 |
Neg logit contributions | |
rum | -0.034 |
pain | -0.032 |
ez | -0.027 |
aged | -0.027 |
mischief | -0.026 |
Token | never |
Token ID | 1239 |
Feature activation | +7.30e-03 |
Pos logit contributions | |
ll | +0.025 |
oph | +0.024 |
ory | +0.022 |
THE | +0.022 |
upon | +0.021 |
Neg logit contributions | |
rum | -0.044 |
pain | -0.040 |
ez | -0.038 |
udge | -0.036 |
mischief | -0.036 |
Token | threw |
Token ID | 9617 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
rum | +0.000 |
pain | +0.000 |
ez | +0.000 |
mischief | +0.000 |
udge | +0.000 |
Neg logit contributions | |
oph | -0.000 |
ll | -0.000 |
ory | -0.000 |
THE | -0.000 |
ari | -0.000 |
Token | a |
Token ID | 257 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
rum | +0.020 |
pain | +0.019 |
ez | +0.017 |
mischief | +0.016 |
aged | +0.016 |
Neg logit contributions | |
oph | -0.012 |
ll | -0.011 |
ory | -0.011 |
THE | -0.010 |
upon | -0.010 |
Token | tant |
Token ID | 24246 |
Feature activation | +6.64e+00 |
Pos logit contributions | |
rum | +0.044 |
pain | +0.040 |
ez | +0.036 |
mischief | +0.034 |
aged | +0.034 |
Neg logit contributions | |
ll | -0.040 |
oph | -0.040 |
ory | -0.039 |
upon | -0.037 |
THE | -0.037 |
Token | rum |
Token ID | 6582 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
pain | +0.076 |
mischief | +0.063 |
trouble | +0.046 |
sensation | +0.036 |
apy | +0.036 |
Neg logit contributions | |
ll | -0.251 |
oph | -0.228 |
ory | -0.222 |
pp | -0.221 |
pper | -0.221 |
Token | again |
Token ID | 757 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
rum | +0.066 |
pain | +0.062 |
ez | +0.056 |
mischief | +0.054 |
udge | +0.052 |
Neg logit contributions | |
ll | -0.049 |
oph | -0.049 |
ory | -0.046 |
THE | -0.045 |
ari | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +4.38e-01 |
Pos logit contributions | |
rum | +0.052 |
pain | +0.048 |
ez | +0.045 |
udge | +0.043 |
mischief | +0.042 |
Neg logit contributions | |
ll | -0.030 |
oph | -0.029 |
ory | -0.027 |
upon | -0.026 |
THE | -0.026 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
rum | +0.011 |
pain | +0.010 |
ez | +0.010 |
mischief | +0.009 |
aged | +0.009 |
Neg logit contributions | |
ll | -0.010 |
oph | -0.010 |
ory | -0.010 |
ari | -0.009 |
arium | -0.009 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
oph | +0.009 |
ll | +0.009 |
ory | +0.009 |
ari | +0.008 |
THE | +0.008 |
Neg logit contributions | |
rum | -0.013 |
pain | -0.012 |
ez | -0.011 |
mischief | -0.011 |
udge | -0.011 |
Token | hat |
Token ID | 6877 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
rum | +0.085 |
pain | +0.077 |
ez | +0.073 |
mischief | +0.072 |
udge | +0.071 |
Neg logit contributions | |
oph | -0.055 |
ory | -0.052 |
ll | -0.051 |
upon | -0.051 |
THE | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +1.21e+00 |
Pos logit contributions | |
rum | +0.037 |
pain | +0.034 |
ez | +0.031 |
mischief | +0.030 |
udge | +0.029 |
Neg logit contributions | |
ll | -0.026 |
oph | -0.025 |
ory | -0.024 |
THE | -0.023 |
ari | -0.023 |
Token | He |
Token ID | 679 |
Feature activation | +3.92e-01 |
Pos logit contributions | |
rum | +0.026 |
pain | +0.024 |
ez | +0.021 |
mischief | +0.020 |
aged | +0.019 |
Neg logit contributions | |
ll | -0.034 |
oph | -0.034 |
ory | -0.032 |
THE | -0.032 |
upon | -0.030 |
Token | had |
Token ID | 550 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
rum | +0.010 |
pain | +0.010 |
ez | +0.009 |
aged | +0.008 |
mischief | +0.008 |
Neg logit contributions | |
oph | -0.009 |
ll | -0.008 |
THE | -0.008 |
ory | -0.008 |
ari | -0.008 |
Token | an |
Token ID | 281 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
rum | +0.066 |
pain | +0.060 |
ez | +0.055 |
udge | +0.054 |
mischief | +0.053 |
Neg logit contributions | |
ll | -0.042 |
oph | -0.040 |
upon | -0.037 |
THE | -0.037 |
would | -0.037 |
Token | x |
Token ID | 2124 |
Feature activation | +6.58e+00 |
Pos logit contributions | |
rum | +0.115 |
udge | +0.105 |
ez | +0.103 |
ges | +0.099 |
pain | +0.098 |
Neg logit contributions | |
ari | -0.082 |
oph | -0.079 |
ll | -0.076 |
ory | -0.076 |
would | -0.075 |
Token | - |
Token ID | 12 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
mischief | +0.185 |
rum | +0.183 |
udge | +0.172 |
pain | +0.165 |
situations | +0.158 |
Neg logit contributions | |
ari | -0.094 |
would | -0.093 |
'd | -0.082 |
fty | -0.082 |
map | -0.081 |
Token | ray |
Token ID | 2433 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
rum | +0.048 |
pain | +0.045 |
ez | +0.041 |
mischief | +0.040 |
udge | +0.039 |
Neg logit contributions | |
ll | -0.026 |
oph | -0.025 |
ory | -0.023 |
THE | -0.023 |
ari | -0.023 |
Token | that |
Token ID | 326 |
Feature activation | +6.18e-01 |
Pos logit contributions | |
rum | +0.094 |
pain | +0.086 |
mischief | +0.084 |
udge | +0.078 |
ez | +0.078 |
Neg logit contributions | |
ll | -0.054 |
would | -0.054 |
ari | -0.053 |
may | -0.049 |
arium | -0.048 |
Token | he |
Token ID | 339 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
rum | +0.019 |
pain | +0.018 |
ez | +0.017 |
mischief | +0.016 |
udge | +0.016 |
Neg logit contributions | |
ll | -0.011 |
oph | -0.011 |
ory | -0.010 |
THE | -0.010 |
ari | -0.010 |
Token | shone |
Token ID | 44193 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
rum | +0.036 |
pain | +0.034 |
ez | +0.031 |
mischief | +0.030 |
aged | +0.029 |
Neg logit contributions | |
oph | -0.020 |
ll | -0.019 |
ory | -0.018 |
THE | -0.017 |
ari | -0.017 |
Token | that |
Token ID | 326 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
ll | +0.005 |
oph | +0.005 |
ory | +0.005 |
THE | +0.005 |
upon | +0.005 |
Neg logit contributions | |
rum | -0.010 |
pain | -0.009 |
ez | -0.009 |
mischief | -0.008 |
udge | -0.008 |
Token | the |
Token ID | 262 |
Feature activation | -6.52e-01 |
Pos logit contributions | |
rum | +0.027 |
pain | +0.023 |
ez | +0.023 |
udge | +0.022 |
aged | +0.022 |
Neg logit contributions | |
would | -0.012 |
ll | -0.012 |
oph | -0.012 |
upon | -0.012 |
THE | -0.012 |
Token | rabbit |
Token ID | 22746 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
oph | +0.013 |
ll | +0.013 |
ory | +0.012 |
THE | +0.012 |
ari | +0.012 |
Neg logit contributions | |
rum | -0.019 |
pain | -0.019 |
ez | -0.016 |
mischief | -0.016 |
aged | -0.015 |
Token | had |
Token ID | 550 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
rum | +0.046 |
pain | +0.045 |
ez | +0.041 |
mischief | +0.038 |
aged | +0.038 |
Neg logit contributions | |
oph | -0.033 |
ll | -0.031 |
ory | -0.031 |
ari | -0.029 |
THE | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +3.73e+00 |
Pos logit contributions | |
rum | +0.045 |
pain | +0.044 |
ez | +0.038 |
mischief | +0.036 |
aged | +0.035 |
Neg logit contributions | |
oph | -0.046 |
ll | -0.045 |
ory | -0.043 |
ari | -0.043 |
THE | -0.042 |
Token | sharp |
Token ID | 7786 |
Feature activation | +6.55e+00 |
Pos logit contributions | |
rum | +0.107 |
pain | +0.098 |
ez | +0.091 |
mischief | +0.085 |
aged | +0.085 |
Neg logit contributions | |
ll | -0.079 |
oph | -0.078 |
ory | -0.074 |
THE | -0.071 |
ari | -0.070 |
Token | knife |
Token ID | 9845 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
rum | +0.149 |
udge | +0.127 |
irens | +0.127 |
ases | +0.122 |
rums | +0.122 |
Neg logit contributions | |
may | -0.151 |
would | -0.151 |
upon | -0.144 |
ory | -0.143 |
'd | -0.142 |
Token | hidden |
Token ID | 7104 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
rum | +0.117 |
pain | +0.109 |
ez | +0.100 |
mischief | +0.098 |
udge | +0.095 |
Neg logit contributions | |
ll | -0.079 |
oph | -0.075 |
ory | -0.072 |
THE | -0.070 |
upon | -0.069 |
Token | in |
Token ID | 287 |
Feature activation | +3.19e+00 |
Pos logit contributions | |
rum | +0.051 |
pain | +0.047 |
ez | +0.043 |
mischief | +0.041 |
aged | +0.040 |
Neg logit contributions | |
ll | -0.039 |
oph | -0.038 |
ory | -0.037 |
upon | -0.036 |
THE | -0.035 |
Token | his |
Token ID | 465 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
rum | +0.100 |
aged | +0.089 |
ez | +0.088 |
pain | +0.086 |
udge | +0.084 |
Neg logit contributions | |
upon | -0.051 |
arium | -0.046 |
may | -0.046 |
oph | -0.045 |
THE | -0.044 |
Token | pocket |
Token ID | 10000 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
rum | +0.041 |
pain | +0.036 |
ez | +0.034 |
udge | +0.032 |
mischief | +0.031 |
Neg logit contributions | |
ll | -0.035 |
oph | -0.035 |
ory | -0.034 |
ari | -0.033 |
upon | -0.032 |
Token | wise |
Token ID | 10787 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
rum | +0.046 |
ez | +0.040 |
pain | +0.040 |
udge | +0.036 |
mischief | +0.036 |
Neg logit contributions | |
ll | -0.038 |
upon | -0.036 |
ory | -0.035 |
oph | -0.034 |
ari | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
rum | +0.012 |
pain | +0.012 |
ez | +0.010 |
mischief | +0.010 |
aged | +0.010 |
Neg logit contributions | |
oph | -0.009 |
ll | -0.009 |
ory | -0.008 |
THE | -0.008 |
ari | -0.008 |
Token | He |
Token ID | 679 |
Feature activation | +8.94e-01 |
Pos logit contributions | |
rum | +0.036 |
pain | +0.033 |
ez | +0.029 |
mischief | +0.028 |
udge | +0.027 |
Neg logit contributions | |
ll | -0.043 |
oph | -0.043 |
ory | -0.041 |
THE | -0.040 |
ari | -0.039 |
Token | used |
Token ID | 973 |
Feature activation | +3.33e+00 |
Pos logit contributions | |
rum | +0.025 |
pain | +0.024 |
ez | +0.022 |
aged | +0.021 |
mischief | +0.020 |
Neg logit contributions | |
oph | -0.019 |
ll | -0.018 |
ory | -0.017 |
THE | -0.017 |
ari | -0.016 |
Token | his |
Token ID | 465 |
Feature activation | +3.95e+00 |
Pos logit contributions | |
rum | +0.093 |
pain | +0.083 |
ez | +0.079 |
udge | +0.076 |
mischief | +0.074 |
Neg logit contributions | |
upon | -0.066 |
ll | -0.065 |
oph | -0.063 |
would | -0.063 |
may | -0.061 |
Token | sharp |
Token ID | 7786 |
Feature activation | +6.54e+00 |
Pos logit contributions | |
rum | +0.108 |
pain | +0.093 |
ez | +0.091 |
udge | +0.090 |
mischief | +0.082 |
Neg logit contributions | |
ll | -0.082 |
may | -0.082 |
would | -0.081 |
upon | -0.080 |
'd | -0.076 |
Token | eyes |
Token ID | 2951 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
rum | +0.135 |
udge | +0.128 |
pain | +0.121 |
ez | +0.120 |
mischief | +0.114 |
Neg logit contributions | |
may | -0.160 |
would | -0.156 |
upon | -0.156 |
'd | -0.141 |
ll | -0.134 |
Token | and |
Token ID | 290 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
rum | +0.044 |
pain | +0.041 |
ez | +0.037 |
mischief | +0.035 |
aged | +0.035 |
Neg logit contributions | |
oph | -0.031 |
ll | -0.031 |
ory | -0.029 |
THE | -0.028 |
ari | -0.028 |
Token | looked |
Token ID | 3114 |
Feature activation | -9.23e-01 |
Pos logit contributions | |
rum | +0.022 |
pain | +0.019 |
udge | +0.019 |
ez | +0.019 |
mischief | +0.018 |
Neg logit contributions | |
would | -0.011 |
ll | -0.011 |
oph | -0.010 |
may | -0.010 |
upon | -0.010 |
Token | at |
Token ID | 379 |
Feature activation | +9.61e-01 |
Pos logit contributions | |
oph | +0.021 |
ll | +0.021 |
ory | +0.019 |
THE | +0.019 |
ari | +0.019 |
Neg logit contributions | |
rum | -0.025 |
pain | -0.024 |
ez | -0.021 |
mischief | -0.020 |
aged | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
rum | +0.030 |
pain | +0.028 |
ez | +0.026 |
mischief | +0.025 |
aged | +0.024 |
Neg logit contributions | |
oph | -0.017 |
ll | -0.017 |
ory | -0.016 |
upon | -0.015 |
THE | -0.015 |
Token | out |
Token ID | 503 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
oph | +0.015 |
ll | +0.015 |
ory | +0.014 |
THE | +0.013 |
ari | +0.013 |
Neg logit contributions | |
rum | -0.020 |
pain | -0.019 |
ez | -0.017 |
mischief | -0.016 |
aged | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +7.42e-01 |
Pos logit contributions | |
rum | +0.045 |
pain | +0.042 |
ez | +0.038 |
mischief | +0.036 |
udge | +0.036 |
Neg logit contributions | |
ll | -0.042 |
upon | -0.039 |
oph | -0.039 |
THE | -0.039 |
ory | -0.038 |
Token | He |
Token ID | 679 |
Feature activation | +4.62e-01 |
Pos logit contributions | |
rum | +0.018 |
pain | +0.016 |
ez | +0.015 |
mischief | +0.015 |
udge | +0.014 |
Neg logit contributions | |
ll | -0.018 |
oph | -0.018 |
ory | -0.017 |
THE | -0.016 |
ari | -0.016 |
Token | used |
Token ID | 973 |
Feature activation | +3.29e+00 |
Pos logit contributions | |
rum | +0.012 |
pain | +0.012 |
ez | +0.011 |
aged | +0.010 |
mischief | +0.009 |
Neg logit contributions | |
oph | -0.011 |
ll | -0.010 |
ory | -0.010 |
THE | -0.010 |
ari | -0.009 |
Token | his |
Token ID | 465 |
Feature activation | +3.72e+00 |
Pos logit contributions | |
rum | +0.084 |
pain | +0.074 |
ez | +0.069 |
udge | +0.067 |
mischief | +0.065 |
Neg logit contributions | |
ll | -0.074 |
upon | -0.074 |
oph | -0.073 |
would | -0.071 |
may | -0.070 |
Token | sharp |
Token ID | 7786 |
Feature activation | +6.48e+00 |
Pos logit contributions | |
rum | +0.096 |
pain | +0.086 |
ez | +0.080 |
udge | +0.077 |
mischief | +0.075 |
Neg logit contributions | |
ll | -0.087 |
oph | -0.083 |
ory | -0.081 |
upon | -0.080 |
ari | -0.079 |
Token | be |
Token ID | 307 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
rum | +0.127 |
udge | +0.119 |
pain | +0.110 |
ez | +0.109 |
mischief | +0.104 |
Neg logit contributions | |
may | -0.168 |
would | -0.163 |
upon | -0.161 |
'd | -0.149 |
ll | -0.146 |
Token | ak |
Token ID | 461 |
Feature activation | -7.57e-01 |
Pos logit contributions | |
rum | +0.060 |
pain | +0.056 |
mischief | +0.049 |
ez | +0.048 |
udge | +0.047 |
Neg logit contributions | |
ll | -0.063 |
oph | -0.059 |
THE | -0.059 |
ari | -0.057 |
upon | -0.057 |
Token | to |
Token ID | 284 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
oph | +0.019 |
ll | +0.018 |
ory | +0.017 |
THE | +0.017 |
arium | +0.017 |
Neg logit contributions | |
rum | -0.019 |
pain | -0.018 |
aged | -0.016 |
ez | -0.016 |
mischief | -0.015 |
Token | carefully |
Token ID | 7773 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
rum | +0.062 |
pain | +0.056 |
ez | +0.053 |
udge | +0.050 |
aged | +0.049 |
Neg logit contributions | |
ll | -0.047 |
oph | -0.045 |
ory | -0.043 |
upon | -0.042 |
would | -0.042 |
Token | break |
Token ID | 2270 |
Feature activation | +2.21e+00 |
Pos logit contributions | |
rum | +0.038 |
pain | +0.036 |
ez | +0.034 |
udge | +0.032 |
mischief | +0.032 |
Neg logit contributions | |
upon | -0.021 |
ll | -0.020 |
arium | -0.019 |
may | -0.019 |
would | -0.019 |
Token | H |
Token ID | 39 |
Feature activation | -2.99e-01 |
Pos logit contributions | |
rum | +0.012 |
pain | +0.011 |
ez | +0.010 |
mischief | +0.010 |
aged | +0.009 |
Neg logit contributions | |
oph | -0.009 |
ll | -0.009 |
ory | -0.008 |
THE | -0.008 |
ari | -0.008 |
Token | oor |
Token ID | 2675 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
oph | +0.007 |
ll | +0.006 |
THE | +0.006 |
would | +0.006 |
upon | +0.006 |
Neg logit contributions | |
rum | -0.009 |
pain | -0.007 |
ez | -0.007 |
udge | -0.007 |
aged | -0.006 |
Token | ay |
Token ID | 323 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ll | +0.148 |
arium | +0.138 |
oph | +0.137 |
'd | +0.137 |
ocular | +0.136 |
Neg logit contributions | |
rum | -0.087 |
pain | -0.080 |
ez | -0.070 |
ump | -0.069 |
iren | -0.065 |
Token | , |
Token ID | 11 |
Feature activation | -2.19e+00 |
Pos logit contributions | |
oph | +0.035 |
arium | +0.034 |
ll | +0.034 |
THE | +0.033 |
ory | +0.033 |
Neg logit contributions | |
rum | -0.049 |
pain | -0.045 |
ez | -0.042 |
aged | -0.039 |
ases | -0.036 |
Token | h |
Token ID | 289 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
oph | +0.056 |
ll | +0.054 |
ory | +0.053 |
ari | +0.049 |
arium | +0.049 |
Neg logit contributions | |
rum | -0.052 |
pain | -0.052 |
ez | -0.041 |
mischief | -0.040 |
aged | -0.038 |
Token | oor |
Token ID | 2675 |
Feature activation | -5.60e+00 |
Pos logit contributions | |
oph | +0.035 |
arium | +0.033 |
THE | +0.032 |
would | +0.032 |
upon | +0.032 |
Neg logit contributions | |
rum | -0.036 |
pain | -0.029 |
aged | -0.029 |
udge | -0.027 |
ez | -0.027 |
Token | ay |
Token ID | 323 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ll | +0.170 |
arium | +0.161 |
'd | +0.158 |
oph | +0.157 |
ory | +0.157 |
Neg logit contributions | |
rum | -0.091 |
pain | -0.081 |
ump | -0.072 |
ez | -0.068 |
iren | -0.067 |
Token | , |
Token ID | 11 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
oph | +0.030 |
arium | +0.029 |
ll | +0.028 |
ory | +0.028 |
THE | +0.027 |
Neg logit contributions | |
rum | -0.042 |
pain | -0.038 |
ez | -0.036 |
aged | -0.033 |
ases | -0.031 |
Token | h |
Token ID | 289 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
oph | +0.061 |
ll | +0.059 |
ory | +0.057 |
arium | +0.052 |
ingu | +0.050 |
Neg logit contributions | |
rum | -0.075 |
pain | -0.075 |
ez | -0.063 |
mischief | -0.061 |
aged | -0.058 |
Token | oor |
Token ID | 2675 |
Feature activation | -5.88e+00 |
Pos logit contributions | |
oph | +0.040 |
arium | +0.038 |
THE | +0.038 |
would | +0.038 |
upon | +0.037 |
Neg logit contributions | |
rum | -0.043 |
pain | -0.034 |
aged | -0.034 |
udge | -0.032 |
ez | -0.032 |
Token | ay |
Token ID | 323 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
ll | +0.178 |
arium | +0.171 |
oph | +0.167 |
ory | +0.166 |
'd | +0.165 |
Neg logit contributions | |
rum | -0.094 |
pain | -0.086 |
ump | -0.074 |
ez | -0.070 |
iren | -0.068 |
Token | play |
Token ID | 711 |
Feature activation | -1.75e+00 |
Pos logit contributions | |
rum | +0.000 |
pain | +0.000 |
ez | +0.000 |
mischief | +0.000 |
udge | +0.000 |
Neg logit contributions | |
ll | -0.000 |
oph | -0.000 |
ory | -0.000 |
THE | -0.000 |
ari | -0.000 |
Token | on |
Token ID | 319 |
Feature activation | +6.27e-01 |
Pos logit contributions | |
oph | +0.046 |
ll | +0.046 |
ory | +0.043 |
ari | +0.042 |
THE | +0.042 |
Neg logit contributions | |
rum | -0.041 |
pain | -0.038 |
ez | -0.034 |
mischief | -0.032 |
udge | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
rum | +0.018 |
pain | +0.017 |
ez | +0.015 |
mischief | +0.015 |
udge | +0.014 |
Neg logit contributions | |
ll | -0.014 |
oph | -0.013 |
ory | -0.013 |
ari | -0.012 |
THE | -0.012 |
Token | sand |
Token ID | 6450 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
oph | +0.072 |
ll | +0.069 |
ory | +0.069 |
omed | +0.066 |
ari | +0.065 |
Neg logit contributions | |
pain | -0.095 |
rum | -0.094 |
mischief | -0.087 |
cigarette | -0.081 |
aged | -0.078 |
Token | near |
Token ID | 1474 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
oph | +0.047 |
ll | +0.047 |
ory | +0.044 |
THE | +0.043 |
ari | +0.042 |
Neg logit contributions | |
rum | -0.062 |
pain | -0.058 |
ez | -0.053 |
mischief | -0.050 |
aged | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
rum | +0.011 |
pain | +0.010 |
ez | +0.009 |
aged | +0.009 |
mischief | +0.009 |
Neg logit contributions | |
oph | -0.005 |
upon | -0.004 |
ll | -0.004 |
THE | -0.004 |
arium | -0.004 |
Token | sea |
Token ID | 5417 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
oph | +0.122 |
ll | +0.115 |
omed | +0.103 |
ari | +0.103 |
ory | +0.102 |
Neg logit contributions | |
pain | -0.146 |
rum | -0.141 |
mischief | -0.131 |
udge | -0.125 |
cigarette | -0.121 |
Token | . |
Token ID | 13 |
Feature activation | +2.93e-01 |
Pos logit contributions | |
oph | +0.071 |
ll | +0.065 |
ory | +0.062 |
THE | +0.061 |
ari | +0.060 |
Neg logit contributions | |
rum | -0.051 |
pain | -0.046 |
udge | -0.040 |
ez | -0.038 |
mischief | -0.037 |
Token | They |
Token ID | 1119 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
rum | +0.008 |
pain | +0.007 |
ez | +0.006 |
mischief | +0.006 |
udge | +0.006 |
Neg logit contributions | |
ll | -0.007 |
oph | -0.007 |
ory | -0.007 |
ari | -0.006 |
THE | -0.006 |
Token | make |
Token ID | 787 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
oph | +0.049 |
ll | +0.047 |
ory | +0.044 |
ari | +0.044 |
THE | +0.044 |
Neg logit contributions | |
rum | -0.043 |
pain | -0.042 |
ez | -0.036 |
mischief | -0.034 |
udge | -0.033 |
Token | castles |
Token ID | 49203 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
ll | +0.039 |
oph | +0.038 |
ory | +0.036 |
ari | +0.036 |
THE | +0.034 |
Neg logit contributions | |
rum | -0.040 |
pain | -0.040 |
mischief | -0.035 |
ez | -0.035 |
aged | -0.033 |
Token | " |
Token ID | 366 |
Feature activation | +3.88e-03 |
Pos logit contributions | |
oph | +0.029 |
ll | +0.027 |
ory | +0.026 |
ari | +0.025 |
arium | +0.024 |
Neg logit contributions | |
rum | -0.026 |
pain | -0.023 |
aged | -0.021 |
pushing | -0.021 |
ez | -0.021 |
Token | Wow |
Token ID | 22017 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
rum | +0.000 |
pain | +0.000 |
ez | +0.000 |
mischief | +0.000 |
udge | +0.000 |
Neg logit contributions | |
ll | -0.000 |
oph | -0.000 |
ory | -0.000 |
THE | -0.000 |
arium | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
oph | +0.104 |
ory | +0.094 |
THE | +0.094 |
ari | +0.093 |
arium | +0.093 |
Neg logit contributions | |
rum | -0.059 |
pain | -0.052 |
pushing | -0.042 |
aged | -0.040 |
pulling | -0.038 |
Token | wow |
Token ID | 28796 |
Feature activation | -4.93e+00 |
Pos logit contributions | |
ll | +0.043 |
oph | +0.040 |
ory | +0.037 |
THE | +0.037 |
arium | +0.036 |
Neg logit contributions | |
pain | -0.046 |
rum | -0.044 |
ez | -0.037 |
mischief | -0.036 |
ear | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
oph | +0.130 |
THE | +0.130 |
arium | +0.126 |
ocular | +0.124 |
ll | +0.123 |
Neg logit contributions | |
rum | -0.093 |
pain | -0.082 |
trouble | -0.066 |
ump | -0.064 |
udge | -0.062 |
Token | wow |
Token ID | 28796 |
Feature activation | -5.51e+00 |
Pos logit contributions | |
ll | +0.078 |
oph | +0.071 |
ory | +0.067 |
arium | +0.065 |
ete | +0.065 |
Neg logit contributions | |
pain | -0.067 |
rum | -0.062 |
ear | -0.054 |
ez | -0.053 |
trouble | -0.051 |
Token | !" |
Token ID | 2474 |
Feature activation | +5.04e-01 |
Pos logit contributions | |
oph | +0.148 |
isk | +0.145 |
THE | +0.144 |
ari | +0.143 |
ingu | +0.142 |
Neg logit contributions | |
rum | -0.100 |
pain | -0.086 |
trouble | -0.069 |
ump | -0.066 |
udge | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
rum | +0.013 |
pain | +0.013 |
ez | +0.011 |
mischief | +0.011 |
aged | +0.011 |
Neg logit contributions | |
ll | -0.012 |
oph | -0.011 |
ory | -0.011 |
ari | -0.010 |
arium | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -9.48e-01 |
Pos logit contributions | |
oph | +0.022 |
ll | +0.021 |
ory | +0.020 |
THE | +0.019 |
ari | +0.019 |
Neg logit contributions | |
rum | -0.033 |
pain | -0.031 |
ez | -0.028 |
mischief | -0.027 |
aged | -0.027 |
Token | The |
Token ID | 464 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
oph | +0.021 |
ll | +0.021 |
ory | +0.020 |
ari | +0.019 |
arium | +0.019 |
Neg logit contributions | |
rum | -0.026 |
pain | -0.024 |
ez | -0.022 |
aged | -0.021 |
mischief | -0.021 |
Token | par |
Token ID | 1582 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
ll | +0.060 |
oph | +0.058 |
arium | +0.055 |
ory | +0.054 |
ete | +0.054 |
Neg logit contributions | |
pain | -0.056 |
rum | -0.050 |
ez | -0.045 |
mischief | -0.042 |
aged | -0.040 |
Token | " |
Token ID | 366 |
Feature activation | +1.75e-01 |
Pos logit contributions | |
oph | +0.025 |
ll | +0.023 |
ory | +0.023 |
ari | +0.020 |
arium | +0.020 |
Neg logit contributions | |
rum | -0.024 |
pain | -0.022 |
aged | -0.020 |
ez | -0.020 |
pushing | -0.018 |
Token | Wow |
Token ID | 22017 |
Feature activation | -2.93e+00 |
Pos logit contributions | |
rum | +0.005 |
pain | +0.005 |
ez | +0.004 |
mischief | +0.004 |
udge | +0.004 |
Neg logit contributions | |
ll | -0.004 |
oph | -0.004 |
ory | -0.003 |
THE | -0.003 |
ari | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
oph | +0.092 |
ory | +0.084 |
assion | +0.083 |
ari | +0.083 |
ocular | +0.082 |
Neg logit contributions | |
rum | -0.055 |
pain | -0.049 |
pushing | -0.038 |
aged | -0.038 |
apy | -0.035 |
Token | wow |
Token ID | 28796 |
Feature activation | -4.94e+00 |
Pos logit contributions | |
ll | +0.061 |
oph | +0.058 |
ory | +0.057 |
pp | +0.052 |
omed | +0.050 |
Neg logit contributions | |
pain | -0.060 |
rum | -0.056 |
trouble | -0.047 |
mischief | -0.046 |
ez | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
assion | +0.137 |
THE | +0.136 |
oph | +0.134 |
ocular | +0.134 |
arium | +0.133 |
Neg logit contributions | |
rum | -0.085 |
pain | -0.079 |
trouble | -0.065 |
ump | -0.057 |
mischief | -0.057 |
Token | wow |
Token ID | 28796 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
ll | +0.085 |
oph | +0.082 |
ory | +0.082 |
pp | +0.071 |
ete | +0.071 |
Neg logit contributions | |
pain | -0.079 |
rum | -0.072 |
trouble | -0.063 |
mischief | -0.060 |
pushing | -0.060 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.06e-01 |
Pos logit contributions | |
assion | +0.146 |
oph | +0.144 |
ocular | +0.144 |
ari | +0.143 |
THE | +0.143 |
Neg logit contributions | |
rum | -0.096 |
pain | -0.087 |
trouble | -0.072 |
ump | -0.064 |
mischief | -0.063 |
Token |
|
Token ID | 198 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
rum | +0.009 |
pain | +0.008 |
ez | +0.007 |
mischief | +0.007 |
aged | +0.007 |
Neg logit contributions | |
ll | -0.006 |
oph | -0.006 |
ory | -0.006 |
THE | -0.006 |
ari | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
oph | +0.021 |
ll | +0.020 |
ory | +0.019 |
ari | +0.018 |
THE | +0.018 |
Neg logit contributions | |
rum | -0.032 |
pain | -0.030 |
ez | -0.027 |
mischief | -0.026 |
aged | -0.026 |
Token | They |
Token ID | 2990 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
oph | +0.021 |
ll | +0.021 |
ory | +0.019 |
THE | +0.019 |
ari | +0.018 |
Neg logit contributions | |
rum | -0.031 |
pain | -0.029 |
ez | -0.027 |
mischief | -0.026 |
aged | -0.025 |
Token | were |
Token ID | 547 |
Feature activation | -9.32e-01 |
Pos logit contributions | |
idents | +0.050 |
ll | +0.049 |
assion | +0.049 |
THE | +0.049 |
oph | +0.048 |
Neg logit contributions | |
pain | -0.046 |
rum | -0.040 |
aged | -0.039 |
ez | -0.039 |
pushing | -0.034 |
Token | " |
Token ID | 1 |
Feature activation | +9.65e-01 |
Pos logit contributions | |
oph | +0.019 |
ll | +0.018 |
ory | +0.017 |
ari | +0.016 |
arium | +0.016 |
Neg logit contributions | |
rum | -0.020 |
pain | -0.019 |
ez | -0.017 |
udge | -0.016 |
mischief | -0.015 |
Token | Wow |
Token ID | 22017 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
rum | +0.029 |
pain | +0.027 |
mischief | +0.024 |
ez | +0.024 |
aged | +0.024 |
Neg logit contributions | |
oph | -0.020 |
ll | -0.019 |
THE | -0.018 |
ory | -0.018 |
ari | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
oph | +0.095 |
THE | +0.087 |
ari | +0.087 |
ocular | +0.087 |
arium | +0.087 |
Neg logit contributions | |
rum | -0.067 |
pain | -0.061 |
ez | -0.046 |
aged | -0.043 |
pushing | -0.042 |
Token | dragon |
Token ID | 10441 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
ll | +0.038 |
oph | +0.037 |
ory | +0.034 |
THE | +0.033 |
ari | +0.033 |
Neg logit contributions | |
rum | -0.054 |
pain | -0.054 |
ez | -0.047 |
mischief | -0.045 |
udge | -0.042 |
Token | , |
Token ID | 11 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
oph | +0.035 |
ll | +0.032 |
THE | +0.032 |
ory | +0.031 |
upon | +0.029 |
Neg logit contributions | |
rum | -0.051 |
pain | -0.047 |
ez | -0.043 |
udge | -0.039 |
aged | -0.038 |
Token | wow |
Token ID | 28796 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
oph | +0.054 |
ll | +0.054 |
ory | +0.050 |
ari | +0.048 |
THE | +0.047 |
Neg logit contributions | |
pain | -0.075 |
rum | -0.072 |
ez | -0.063 |
mischief | -0.061 |
trouble | -0.058 |
Token | !" |
Token ID | 2474 |
Feature activation | +8.90e-01 |
Pos logit contributions | |
THE | +0.140 |
ocular | +0.136 |
oph | +0.135 |
arium | +0.135 |
Reserve | +0.134 |
Neg logit contributions | |
rum | -0.112 |
pain | -0.102 |
trouble | -0.083 |
ez | -0.077 |
ump | -0.075 |
Token | he |
Token ID | 339 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
rum | +0.029 |
pain | +0.027 |
ez | +0.025 |
mischief | +0.024 |
aged | +0.023 |
Neg logit contributions | |
oph | -0.016 |
ll | -0.016 |
ory | -0.015 |
THE | -0.014 |
upon | -0.014 |
Token | exclaimed |
Token ID | 33552 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
ll | +0.014 |
oph | +0.014 |
ory | +0.013 |
THE | +0.013 |
ari | +0.013 |
Neg logit contributions | |
rum | -0.021 |
pain | -0.021 |
ez | -0.019 |
aged | -0.018 |
mischief | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
ll | +0.017 |
oph | +0.017 |
ory | +0.016 |
upon | +0.015 |
THE | +0.015 |
Neg logit contributions | |
rum | -0.025 |
pain | -0.023 |
ez | -0.021 |
mischief | -0.021 |
udge | -0.020 |
Token | " |
Token ID | 366 |
Feature activation | -9.44e-01 |
Pos logit contributions | |
rum | +0.019 |
pain | +0.018 |
ez | +0.017 |
mischief | +0.016 |
aged | +0.016 |
Neg logit contributions | |
oph | -0.009 |
ll | -0.009 |
ory | -0.008 |
THE | -0.008 |
ari | -0.008 |
Token | they |
Token ID | 484 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
oph | +0.052 |
ll | +0.051 |
ory | +0.049 |
ari | +0.046 |
THE | +0.045 |
Neg logit contributions | |
rum | -0.064 |
pain | -0.061 |
ez | -0.054 |
mischief | -0.052 |
aged | -0.051 |
Token | were |
Token ID | 547 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
oph | +0.034 |
ll | +0.033 |
ory | +0.031 |
THE | +0.029 |
ari | +0.029 |
Neg logit contributions | |
rum | -0.062 |
pain | -0.059 |
ez | -0.054 |
mischief | -0.052 |
aged | -0.051 |
Token | astronauts |
Token ID | 26835 |
Feature activation | -4.64e-01 |
Pos logit contributions | |
oph | +0.043 |
ll | +0.040 |
ory | +0.040 |
arium | +0.036 |
of | +0.036 |
Neg logit contributions | |
rum | -0.032 |
pain | -0.031 |
aged | -0.026 |
ez | -0.025 |
mischief | -0.025 |
Token | going |
Token ID | 1016 |
Feature activation | -1.73e+00 |
Pos logit contributions | |
oph | +0.012 |
ll | +0.011 |
ory | +0.011 |
THE | +0.010 |
ete | +0.010 |
Neg logit contributions | |
rum | -0.012 |
pain | -0.011 |
ez | -0.010 |
aged | -0.009 |
udge | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
oph | +0.056 |
ory | +0.049 |
ll | +0.048 |
ete | +0.045 |
ari | +0.044 |
Neg logit contributions | |
rum | -0.034 |
pain | -0.032 |
pushing | -0.027 |
ez | -0.026 |
mischief | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -5.27e+00 |
Pos logit contributions | |
oph | +0.037 |
ll | +0.036 |
ory | +0.034 |
THE | +0.033 |
ari | +0.032 |
Neg logit contributions | |
rum | -0.052 |
pain | -0.049 |
ez | -0.045 |
mischief | -0.043 |
udge | -0.042 |
Token | moon |
Token ID | 8824 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
ll | +0.150 |
ory | +0.144 |
omed | +0.143 |
oph | +0.140 |
pp | +0.135 |
Neg logit contributions | |
pain | -0.106 |
mischief | -0.090 |
trouble | -0.083 |
emergency | -0.082 |
x | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | +8.27e-01 |
Pos logit contributions | |
oph | +0.058 |
ory | +0.055 |
ll | +0.054 |
ete | +0.049 |
THE | +0.048 |
Neg logit contributions | |
rum | -0.059 |
pain | -0.054 |
ez | -0.051 |
udge | -0.046 |
mischief | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | -7.77e-01 |
Pos logit contributions | |
rum | +0.023 |
pain | +0.022 |
ez | +0.020 |
mischief | +0.019 |
aged | +0.018 |
Neg logit contributions | |
oph | -0.018 |
ll | -0.018 |
ory | -0.017 |
ari | -0.016 |
THE | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
ll | +0.012 |
oph | +0.012 |
upon | +0.011 |
THE | +0.011 |
arium | +0.010 |
Neg logit contributions | |
rum | -0.027 |
pain | -0.026 |
ez | -0.023 |
mischief | -0.023 |
aged | -0.022 |
Token | " |
Token ID | 1 |
Feature activation | +9.66e-01 |
Pos logit contributions | |
ll | +0.012 |
oph | +0.012 |
ory | +0.011 |
THE | +0.010 |
ari | +0.010 |
Neg logit contributions | |
rum | -0.022 |
pain | -0.021 |
ez | -0.019 |
mischief | -0.019 |
aged | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
ll | +0.063 |
oph | +0.060 |
ari | +0.056 |
ory | +0.056 |
THE | +0.053 |
Neg logit contributions | |
pain | -0.055 |
rum | -0.051 |
mischief | -0.045 |
ez | -0.044 |
aged | -0.043 |
Token | big |
Token ID | 1263 |
Feature activation | +2.56e-01 |
Pos logit contributions | |
ll | +0.034 |
oph | +0.034 |
THE | +0.031 |
ari | +0.031 |
ory | +0.030 |
Neg logit contributions | |
pain | -0.033 |
rum | -0.031 |
mischief | -0.028 |
udge | -0.027 |
cigarette | -0.026 |
Token | surf |
Token ID | 9053 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
rum | +0.007 |
pain | +0.007 |
ez | +0.006 |
mischief | +0.006 |
udge | +0.006 |
Neg logit contributions | |
ll | -0.005 |
oph | -0.005 |
ory | -0.005 |
THE | -0.005 |
ari | -0.005 |
Token | board |
Token ID | 3096 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
oph | +0.032 |
ll | +0.031 |
ory | +0.029 |
THE | +0.028 |
upon | +0.027 |
Neg logit contributions | |
rum | -0.037 |
pain | -0.035 |
ez | -0.031 |
udge | -0.030 |
mischief | -0.029 |
Token | near |
Token ID | 1474 |
Feature activation | -4.67e-01 |
Pos logit contributions | |
oph | +0.037 |
ll | +0.036 |
ory | +0.034 |
THE | +0.033 |
ari | +0.033 |
Neg logit contributions | |
rum | -0.039 |
pain | -0.037 |
ez | -0.033 |
mischief | -0.031 |
udge | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
oph | +0.009 |
ll | +0.008 |
ory | +0.008 |
THE | +0.008 |
upon | +0.008 |
Neg logit contributions | |
rum | -0.015 |
pain | -0.014 |
ez | -0.013 |
mischief | -0.012 |
aged | -0.012 |
Token | shore |
Token ID | 15191 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
oph | +0.125 |
ll | +0.123 |
pp | +0.108 |
ari | +0.108 |
arium | +0.107 |
Neg logit contributions | |
pain | -0.133 |
mischief | -0.114 |
rum | -0.113 |
udge | -0.105 |
trouble | -0.102 |
Token | . |
Token ID | 13 |
Feature activation | +8.00e-01 |
Pos logit contributions | |
oph | +0.019 |
ll | +0.018 |
ory | +0.017 |
THE | +0.016 |
ari | +0.016 |
Neg logit contributions | |
rum | -0.020 |
pain | -0.018 |
ez | -0.016 |
udge | -0.015 |
mischief | -0.015 |
Token | It |
Token ID | 632 |
Feature activation | -9.79e-01 |
Pos logit contributions | |
rum | +0.021 |
pain | +0.020 |
ez | +0.018 |
mischief | +0.017 |
udge | +0.016 |
Neg logit contributions | |
ll | -0.019 |
oph | -0.019 |
ory | -0.018 |
THE | -0.017 |
ari | -0.017 |
Token | is |
Token ID | 318 |
Feature activation | +4.92e-02 |
Pos logit contributions | |
oph | +0.023 |
ory | +0.021 |
ll | +0.021 |
THE | +0.020 |
ari | +0.020 |
Neg logit contributions | |
rum | -0.026 |
pain | -0.025 |
ez | -0.022 |
mischief | -0.021 |
udge | -0.020 |
Token | red |
Token ID | 2266 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
rum | +0.002 |
pain | +0.001 |
ez | +0.001 |
mischief | +0.001 |
udge | +0.001 |
Neg logit contributions | |
ll | -0.001 |
oph | -0.001 |
upon | -0.001 |
THE | -0.001 |
ory | -0.001 |
Token | " |
Token ID | 366 |
Feature activation | +5.24e-01 |
Pos logit contributions | |
oph | +0.009 |
ll | +0.009 |
ory | +0.008 |
ari | +0.008 |
arium | +0.008 |
Neg logit contributions | |
rum | -0.011 |
pain | -0.010 |
ez | -0.010 |
aged | -0.009 |
mischief | -0.009 |
Token | Wow |
Token ID | 22017 |
Feature activation | -2.71e+00 |
Pos logit contributions | |
rum | +0.015 |
pain | +0.014 |
ez | +0.013 |
mischief | +0.012 |
aged | +0.012 |
Neg logit contributions | |
oph | -0.011 |
ll | -0.011 |
ory | -0.011 |
THE | -0.010 |
ari | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
oph | +0.079 |
THE | +0.073 |
ory | +0.073 |
arium | +0.072 |
Reserve | +0.071 |
Neg logit contributions | |
rum | -0.057 |
pain | -0.047 |
pushing | -0.039 |
ez | -0.037 |
aged | -0.036 |
Token | wow |
Token ID | 28796 |
Feature activation | -4.68e+00 |
Pos logit contributions | |
ll | +0.027 |
oph | +0.027 |
ory | +0.026 |
ari | +0.024 |
THE | +0.024 |
Neg logit contributions | |
rum | -0.036 |
pain | -0.034 |
ez | -0.029 |
mischief | -0.028 |
aged | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -2.12e+00 |
Pos logit contributions | |
THE | +0.120 |
ocular | +0.117 |
assion | +0.116 |
Reserve | +0.115 |
arium | +0.115 |
Neg logit contributions | |
rum | -0.096 |
pain | -0.083 |
trouble | -0.068 |
ump | -0.066 |
mischief | -0.065 |
Token | wow |
Token ID | 28796 |
Feature activation | -5.24e+00 |
Pos logit contributions | |
ll | +0.049 |
oph | +0.048 |
ory | +0.046 |
pp | +0.042 |
ari | +0.042 |
Neg logit contributions | |
rum | -0.057 |
pain | -0.055 |
ez | -0.047 |
mischief | -0.044 |
ear | -0.042 |
Token | ! |
Token ID | 0 |
Feature activation | -2.09e+00 |
Pos logit contributions | |
THE | +0.131 |
ocular | +0.130 |
Reserve | +0.130 |
pp | +0.129 |
assion | +0.128 |
Neg logit contributions | |
rum | -0.105 |
pain | -0.089 |
trouble | -0.074 |
ump | -0.072 |
mischief | -0.070 |
Token | Thank |
Token ID | 6952 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
ll | +0.053 |
oph | +0.052 |
ory | +0.049 |
THE | +0.047 |
arium | +0.046 |
Neg logit contributions | |
rum | -0.052 |
pain | -0.047 |
ez | -0.043 |
mischief | -0.040 |
udge | -0.039 |
Token | you |
Token ID | 345 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
ll | +0.033 |
oph | +0.032 |
ory | +0.029 |
arium | +0.028 |
upon | +0.028 |
Neg logit contributions | |
rum | -0.054 |
pain | -0.052 |
ez | -0.048 |
mischief | -0.045 |
aged | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | -1.66e+00 |
Pos logit contributions | |
ll | +0.075 |
oph | +0.069 |
assion | +0.069 |
Reserve | +0.068 |
'd | +0.067 |
Neg logit contributions | |
rum | -0.063 |
pain | -0.052 |
ez | -0.043 |
mischief | -0.042 |
ear | -0.042 |
Token | thank |
Token ID | 5875 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
ll | +0.039 |
oph | +0.039 |
ory | +0.036 |
THE | +0.034 |
ari | +0.034 |
Neg logit contributions | |
rum | -0.044 |
pain | -0.042 |
ez | -0.036 |
mischief | -0.034 |
udge | -0.032 |
Token | " |
Token ID | 366 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
oph | +0.012 |
ll | +0.012 |
ory | +0.011 |
ari | +0.011 |
arium | +0.010 |
Neg logit contributions | |
rum | -0.015 |
pain | -0.014 |
ez | -0.013 |
aged | -0.012 |
mischief | -0.012 |
Token | Wow |
Token ID | 22017 |
Feature activation | -2.59e+00 |
Pos logit contributions | |
rum | +0.004 |
pain | +0.004 |
ez | +0.004 |
mischief | +0.004 |
aged | +0.003 |
Neg logit contributions | |
oph | -0.003 |
ll | -0.003 |
ory | -0.003 |
THE | -0.003 |
ari | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -1.86e+00 |
Pos logit contributions | |
oph | +0.074 |
ari | +0.072 |
THE | +0.071 |
arium | +0.070 |
ll | +0.070 |
Neg logit contributions | |
rum | -0.052 |
pain | -0.048 |
aged | -0.037 |
pushing | -0.036 |
ez | -0.035 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.52e+00 |
Pos logit contributions | |
ll | +0.037 |
oph | +0.035 |
ory | +0.034 |
THE | +0.032 |
ari | +0.032 |
Neg logit contributions | |
rum | -0.056 |
pain | -0.055 |
ez | -0.048 |
mischief | -0.046 |
udge | -0.045 |
Token | , |
Token ID | 11 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
THE | +0.031 |
ete | +0.030 |
oph | +0.030 |
ll | +0.030 |
ory | +0.029 |
Neg logit contributions | |
rum | -0.042 |
pain | -0.037 |
ez | -0.035 |
udge | -0.032 |
ump | -0.031 |
Token | wow |
Token ID | 28796 |
Feature activation | -5.16e+00 |
Pos logit contributions | |
ll | +0.052 |
oph | +0.050 |
ory | +0.048 |
ari | +0.046 |
THE | +0.045 |
Neg logit contributions | |
pain | -0.071 |
rum | -0.069 |
ez | -0.060 |
mischief | -0.058 |
trouble | -0.055 |
Token | ! |
Token ID | 0 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
ocular | +0.137 |
THE | +0.137 |
ari | +0.136 |
arium | +0.134 |
assion | +0.131 |
Neg logit contributions | |
rum | -0.095 |
pain | -0.089 |
trouble | -0.072 |
ump | -0.066 |
mischief | -0.066 |
Token | I |
Token ID | 314 |
Feature activation | +9.07e-01 |
Pos logit contributions | |
ll | +0.045 |
oph | +0.045 |
ory | +0.042 |
THE | +0.041 |
ari | +0.040 |
Neg logit contributions | |
rum | -0.054 |
pain | -0.050 |
ez | -0.045 |
mischief | -0.043 |
udge | -0.042 |
Token | look |
Token ID | 804 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
rum | +0.030 |
pain | +0.026 |
aged | +0.024 |
mischief | +0.024 |
ez | +0.024 |
Neg logit contributions | |
ll | -0.016 |
oph | -0.016 |
would | -0.015 |
ory | -0.015 |
'd | -0.015 |
Token | pretty |
Token ID | 2495 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
ll | +0.076 |
oph | +0.072 |
ari | +0.069 |
arium | +0.067 |
THE | +0.066 |
Neg logit contributions | |
rum | -0.074 |
pain | -0.073 |
ez | -0.063 |
mischief | -0.062 |
udge | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
ll | +0.037 |
oph | +0.035 |
arium | +0.034 |
ari | +0.033 |
ory | +0.032 |
Neg logit contributions | |
rum | -0.044 |
pain | -0.041 |
ez | -0.037 |
aged | -0.035 |
mischief | -0.034 |
Token | with |
Token ID | 351 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
ll | +0.043 |
oph | +0.043 |
ory | +0.041 |
THE | +0.040 |
arium | +0.039 |
Neg logit contributions | |
rum | -0.046 |
pain | -0.042 |
ez | -0.038 |
mischief | -0.036 |
aged | -0.035 |
Token | their |
Token ID | 511 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
rum | +0.033 |
pain | +0.029 |
ez | +0.028 |
mischief | +0.026 |
aged | +0.026 |
Neg logit contributions | |
oph | -0.018 |
ll | -0.018 |
upon | -0.017 |
ory | -0.017 |
arium | -0.017 |
Token | toy |
Token ID | 13373 |
Feature activation | -1.60e-01 |
Pos logit contributions | |
ll | +0.001 |
oph | +0.001 |
ory | +0.001 |
upon | +0.001 |
THE | +0.001 |
Neg logit contributions | |
rum | -0.002 |
pain | -0.001 |
ez | -0.001 |
udge | -0.001 |
mischief | -0.001 |
Token | boats |
Token ID | 16659 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
oph | +0.004 |
ll | +0.004 |
ory | +0.004 |
THE | +0.004 |
ari | +0.004 |
Neg logit contributions | |
rum | -0.004 |
pain | -0.004 |
ez | -0.003 |
mischief | -0.003 |
aged | -0.003 |
Token | at |
Token ID | 379 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
oph | +0.048 |
ll | +0.043 |
ory | +0.042 |
ete | +0.041 |
THE | +0.040 |
Neg logit contributions | |
rum | -0.034 |
pain | -0.032 |
ez | -0.028 |
udge | -0.026 |
aged | -0.025 |
Token | the |
Token ID | 262 |
Feature activation | -5.13e+00 |
Pos logit contributions | |
oph | +0.020 |
ll | +0.020 |
ory | +0.018 |
THE | +0.018 |
ari | +0.018 |
Neg logit contributions | |
rum | -0.030 |
pain | -0.028 |
ez | -0.026 |
mischief | -0.025 |
aged | -0.024 |
Token | pond |
Token ID | 16723 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
ll | +0.131 |
oph | +0.126 |
omed | +0.126 |
ory | +0.118 |
of | +0.115 |
Neg logit contributions | |
pain | -0.111 |
mischief | -0.102 |
cigarette | -0.092 |
trouble | -0.090 |
emergency | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
oph | +0.050 |
ll | +0.048 |
ory | +0.046 |
THE | +0.045 |
ari | +0.044 |
Neg logit contributions | |
rum | -0.049 |
pain | -0.046 |
ez | -0.040 |
aged | -0.038 |
udge | -0.038 |
Token | They |
Token ID | 1119 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
rum | +0.009 |
pain | +0.009 |
ez | +0.008 |
mischief | +0.008 |
udge | +0.008 |
Neg logit contributions | |
ll | -0.008 |
oph | -0.008 |
ory | -0.008 |
THE | -0.007 |
ari | -0.007 |
Token | made |
Token ID | 925 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
oph | +0.030 |
ll | +0.028 |
THE | +0.026 |
ory | +0.026 |
ari | +0.026 |
Neg logit contributions | |
rum | -0.048 |
pain | -0.046 |
ez | -0.043 |
mischief | -0.040 |
aged | -0.040 |
Token | sails |
Token ID | 48370 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
oph | +0.032 |
ll | +0.032 |
ory | +0.030 |
ari | +0.029 |
THE | +0.029 |
Neg logit contributions | |
rum | -0.040 |
pain | -0.038 |
ez | -0.034 |
mischief | -0.033 |
aged | -0.032 |
Token | " |
Token ID | 366 |
Feature activation | +7.40e-01 |
Pos logit contributions | |
ll | +0.042 |
oph | +0.042 |
ory | +0.039 |
ari | +0.036 |
THE | +0.035 |
Neg logit contributions | |
rum | -0.047 |
pain | -0.044 |
ez | -0.038 |
aged | -0.038 |
mischief | -0.036 |
Token | wow |
Token ID | 42773 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
rum | +0.022 |
pain | +0.021 |
ez | +0.018 |
mischief | +0.018 |
aged | +0.018 |
Neg logit contributions | |
oph | -0.015 |
ll | -0.015 |
ory | -0.014 |
THE | -0.014 |
ari | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
ll | +0.065 |
oph | +0.064 |
ocular | +0.063 |
arium | +0.061 |
ory | +0.059 |
Neg logit contributions | |
rum | -0.068 |
pain | -0.056 |
ez | -0.054 |
ges | -0.049 |
udge | -0.049 |
Token | wow |
Token ID | 28796 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
ll | +0.063 |
oph | +0.059 |
ory | +0.058 |
THE | +0.053 |
upon | +0.052 |
Neg logit contributions | |
pain | -0.071 |
rum | -0.066 |
ez | -0.058 |
mischief | -0.055 |
cigarette | -0.054 |
Token | , |
Token ID | 11 |
Feature activation | -3.23e+00 |
Pos logit contributions | |
ll | +0.101 |
oph | +0.101 |
ocular | +0.100 |
arium | +0.099 |
THE | +0.097 |
Neg logit contributions | |
rum | -0.107 |
pain | -0.093 |
ez | -0.081 |
ump | -0.079 |
udge | -0.079 |
Token | wow |
Token ID | 28796 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
ll | +0.076 |
oph | +0.072 |
ory | +0.070 |
ari | +0.062 |
THE | +0.062 |
Neg logit contributions | |
pain | -0.089 |
rum | -0.082 |
ez | -0.073 |
mischief | -0.070 |
cigarette | -0.067 |
Token | !" |
Token ID | 2474 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
ocular | +0.124 |
oph | +0.122 |
ll | +0.120 |
arium | +0.120 |
ari | +0.119 |
Neg logit contributions | |
rum | -0.112 |
pain | -0.095 |
ump | -0.080 |
ez | -0.080 |
udge | -0.080 |
Token | and |
Token ID | 290 |
Feature activation | -3.13e+00 |
Pos logit contributions | |
rum | +0.024 |
pain | +0.024 |
ez | +0.021 |
mischief | +0.020 |
udge | +0.020 |
Neg logit contributions | |
ll | -0.021 |
oph | -0.021 |
ory | -0.019 |
ari | -0.019 |
THE | -0.019 |
Token | cl |
Token ID | 537 |
Feature activation | +7.73e-01 |
Pos logit contributions | |
oph | +0.075 |
ll | +0.073 |
ari | +0.068 |
ory | +0.067 |
THE | +0.067 |
Neg logit contributions | |
rum | -0.080 |
pain | -0.079 |
aged | -0.070 |
ez | -0.068 |
mischief | -0.064 |
Token | ap |
Token ID | 499 |
Feature activation | +8.52e-01 |
Pos logit contributions | |
rum | +0.017 |
pain | +0.015 |
ez | +0.014 |
mischief | +0.013 |
udge | +0.012 |
Neg logit contributions | |
ll | -0.022 |
oph | -0.022 |
ory | -0.021 |
THE | -0.020 |
ari | -0.020 |
Token | their |
Token ID | 511 |
Feature activation | -4.44e-01 |
Pos logit contributions | |
rum | +0.020 |
pain | +0.018 |
ez | +0.016 |
mischief | +0.015 |
aged | +0.015 |
Neg logit contributions | |
ll | -0.023 |
oph | -0.023 |
ory | -0.021 |
ari | -0.021 |
THE | -0.021 |
Token | to |
Token ID | 284 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
rum | +0.019 |
pain | +0.018 |
ez | +0.016 |
mischief | +0.016 |
aged | +0.015 |
Neg logit contributions | |
oph | -0.014 |
ll | -0.014 |
ory | -0.013 |
THE | -0.013 |
ari | -0.013 |
Token | ride |
Token ID | 6594 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
oph | +0.002 |
ll | +0.002 |
ory | +0.002 |
THE | +0.002 |
ari | +0.002 |
Neg logit contributions | |
rum | -0.003 |
pain | -0.003 |
ez | -0.003 |
mischief | -0.002 |
aged | -0.002 |
Token | her |
Token ID | 607 |
Feature activation | -8.63e-01 |
Pos logit contributions | |
oph | +0.001 |
ll | +0.001 |
ory | +0.001 |
THE | +0.001 |
upon | +0.001 |
Neg logit contributions | |
rum | -0.001 |
pain | -0.001 |
ez | -0.001 |
mischief | -0.001 |
aged | -0.001 |
Token | bike |
Token ID | 7161 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
oph | +0.021 |
ll | +0.021 |
ory | +0.019 |
THE | +0.019 |
ari | +0.019 |
Neg logit contributions | |
rum | -0.022 |
pain | -0.021 |
ez | -0.018 |
mischief | -0.017 |
aged | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
oph | +0.012 |
ll | +0.012 |
ory | +0.011 |
THE | +0.010 |
arium | +0.010 |
Neg logit contributions | |
rum | -0.012 |
pain | -0.011 |
ez | -0.010 |
mischief | -0.010 |
udge | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
ll | +0.023 |
oph | +0.023 |
ory | +0.021 |
ari | +0.021 |
THE | +0.020 |
Neg logit contributions | |
rum | -0.031 |
pain | -0.030 |
ez | -0.026 |
mischief | -0.026 |
udge | -0.025 |
Token | park |
Token ID | 3952 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
ll | +0.123 |
oph | +0.118 |
omed | +0.111 |
ory | +0.109 |
may | +0.103 |
Neg logit contributions | |
pain | -0.121 |
rum | -0.110 |
mischief | -0.108 |
cigarette | -0.097 |
udge | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
ll | +0.053 |
oph | +0.053 |
ory | +0.049 |
THE | +0.048 |
ari | +0.046 |
Neg logit contributions | |
rum | -0.047 |
pain | -0.043 |
ez | -0.038 |
udge | -0.036 |
mischief | -0.036 |
Token | She |
Token ID | 1375 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
rum | +0.001 |
pain | +0.001 |
ez | +0.001 |
mischief | +0.001 |
aged | +0.001 |
Neg logit contributions | |
oph | -0.001 |
ll | -0.001 |
ory | -0.001 |
THE | -0.001 |
ari | -0.001 |
Token | likes |
Token ID | 7832 |
Feature activation | -5.04e-01 |
Pos logit contributions | |
oph | +0.024 |
ll | +0.023 |
ory | +0.022 |
THE | +0.021 |
ari | +0.021 |
Neg logit contributions | |
rum | -0.036 |
pain | -0.033 |
ez | -0.031 |
mischief | -0.029 |
aged | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +4.18e-01 |
Pos logit contributions | |
ll | +0.010 |
oph | +0.010 |
ory | +0.009 |
THE | +0.009 |
ari | +0.009 |
Neg logit contributions | |
rum | -0.015 |
pain | -0.014 |
ez | -0.013 |
mischief | -0.012 |
udge | -0.012 |
Token | and |
Token ID | 290 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
ll | +0.039 |
oph | +0.038 |
ocular | +0.036 |
THE | +0.036 |
ari | +0.035 |
Neg logit contributions | |
rum | -0.050 |
pain | -0.047 |
ez | -0.043 |
mischief | -0.040 |
aged | -0.038 |
Token | his |
Token ID | 465 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
oph | +0.053 |
ory | +0.049 |
ll | +0.049 |
THE | +0.046 |
arium | +0.046 |
Neg logit contributions | |
rum | -0.084 |
pain | -0.078 |
ez | -0.073 |
udge | -0.070 |
mischief | -0.069 |
Token | dad |
Token ID | 9955 |
Feature activation | -8.48e-02 |
Pos logit contributions | |
rum | +0.005 |
pain | +0.005 |
ez | +0.004 |
mischief | +0.004 |
aged | +0.004 |
Neg logit contributions | |
oph | -0.004 |
ll | -0.004 |
ory | -0.003 |
THE | -0.003 |
arium | -0.003 |
Token | went |
Token ID | 1816 |
Feature activation | -2.73e+00 |
Pos logit contributions | |
ll | +0.002 |
oph | +0.002 |
THE | +0.002 |
arium | +0.002 |
ocular | +0.002 |
Neg logit contributions | |
rum | -0.002 |
pain | -0.002 |
ez | -0.002 |
mischief | -0.002 |
aged | -0.002 |
Token | to |
Token ID | 284 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
oph | +0.071 |
ll | +0.066 |
ory | +0.063 |
THE | +0.061 |
ari | +0.059 |
Neg logit contributions | |
rum | -0.065 |
pain | -0.061 |
ez | -0.055 |
mischief | -0.052 |
aged | -0.052 |
Token | the |
Token ID | 262 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
ll | +0.057 |
oph | +0.055 |
ari | +0.051 |
ory | +0.050 |
ocular | +0.050 |
Neg logit contributions | |
pain | -0.055 |
rum | -0.054 |
mischief | -0.050 |
ez | -0.046 |
trouble | -0.043 |
Token | beach |
Token ID | 10481 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
ll | +0.144 |
omed | +0.129 |
ory | +0.127 |
oph | +0.126 |
ppy | +0.126 |
Neg logit contributions | |
pain | -0.099 |
mischief | -0.091 |
emergency | -0.085 |
x | -0.084 |
trouble | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
oph | +0.079 |
ll | +0.077 |
THE | +0.072 |
ory | +0.072 |
ari | +0.069 |
Neg logit contributions | |
rum | -0.083 |
pain | -0.075 |
ez | -0.068 |
mischief | -0.065 |
udge | -0.064 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.93e+00 |
Pos logit contributions | |
ll | +0.043 |
oph | +0.042 |
ory | +0.039 |
THE | +0.038 |
ari | +0.037 |
Neg logit contributions | |
rum | -0.037 |
pain | -0.034 |
ez | -0.029 |
mischief | -0.029 |
udge | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | -6.01e-01 |
Pos logit contributions | |
oph | +0.051 |
THE | +0.045 |
ari | +0.043 |
ory | +0.043 |
ocular | +0.043 |
Neg logit contributions | |
rum | -0.044 |
pain | -0.040 |
ez | -0.037 |
aged | -0.036 |
pushing | -0.034 |
Token | very |
Token ID | 845 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
ll | +0.010 |
oph | +0.010 |
upon | +0.010 |
ory | +0.009 |
THE | +0.009 |
Neg logit contributions | |
rum | -0.020 |
pain | -0.018 |
ez | -0.017 |
udge | -0.016 |
mischief | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | -7.75e-01 |
Pos logit contributions | |
oph | +0.014 |
ll | +0.014 |
ory | +0.013 |
THE | +0.012 |
ari | +0.012 |
Neg logit contributions | |
rum | -0.025 |
pain | -0.024 |
ez | -0.022 |
mischief | -0.021 |
aged | -0.021 |
Token | " |
Token ID | 366 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
oph | +0.017 |
ll | +0.016 |
ory | +0.016 |
arium | +0.015 |
ari | +0.015 |
Neg logit contributions | |
rum | -0.022 |
pain | -0.020 |
ez | -0.018 |
aged | -0.018 |
mischief | -0.017 |
Token | Let |
Token ID | 5756 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
oph | +0.001 |
ll | +0.001 |
ory | +0.001 |
THE | +0.001 |
ari | +0.001 |
Neg logit contributions | |
rum | -0.001 |
pain | -0.001 |
ez | -0.001 |
mischief | -0.001 |
aged | -0.001 |
Token | 's |
Token ID | 338 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
ll | +0.053 |
arium | +0.051 |
ari | +0.050 |
ory | +0.048 |
ocular | +0.047 |
Neg logit contributions | |
pain | -0.071 |
rum | -0.069 |
ez | -0.061 |
mischief | -0.060 |
aged | -0.055 |
Token | explore |
Token ID | 7301 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
ll | +0.046 |
oph | +0.046 |
ory | +0.043 |
THE | +0.041 |
ari | +0.040 |
Neg logit contributions | |
rum | -0.076 |
pain | -0.070 |
ez | -0.066 |
mischief | -0.062 |
aged | -0.061 |
Token | nature |
Token ID | 3450 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
oph | +0.069 |
ll | +0.067 |
ory | +0.064 |
ari | +0.063 |
ocular | +0.058 |
Neg logit contributions | |
rum | -0.079 |
pain | -0.074 |
ez | -0.067 |
mischief | -0.066 |
udge | -0.062 |
Token | together |
Token ID | 1978 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
oph | +0.125 |
ory | +0.117 |
ete | +0.110 |
ll | +0.109 |
ari | +0.107 |
Neg logit contributions | |
rum | -0.117 |
pain | -0.106 |
ez | -0.099 |
mischief | -0.090 |
udge | -0.088 |
Token | ". |
Token ID | 1911 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
oph | +0.046 |
ll | +0.044 |
ory | +0.042 |
ari | +0.041 |
arium | +0.040 |
Neg logit contributions | |
rum | -0.061 |
pain | -0.056 |
ez | -0.051 |
mischief | -0.049 |
udge | -0.048 |
Token | |
Token ID | 220 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
rum | +0.018 |
pain | +0.017 |
ez | +0.016 |
mischief | +0.015 |
udge | +0.015 |
Neg logit contributions | |
oph | -0.012 |
ll | -0.012 |
ory | -0.011 |
THE | -0.011 |
ari | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -7.85e-01 |
Pos logit contributions | |
oph | +0.021 |
ory | +0.020 |
ll | +0.019 |
arium | +0.019 |
THE | +0.018 |
Neg logit contributions | |
rum | -0.022 |
pain | -0.019 |
ez | -0.018 |
udge | -0.017 |
aged | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -9.64e-01 |
Pos logit contributions | |
oph | +0.016 |
ll | +0.015 |
ory | +0.015 |
arium | +0.014 |
ari | +0.014 |
Neg logit contributions | |
rum | -0.023 |
pain | -0.022 |
ez | -0.020 |
mischief | -0.019 |
udge | -0.019 |
Token | " |
Token ID | 366 |
Feature activation | +8.35e-01 |
Pos logit contributions | |
oph | +0.006 |
ll | +0.006 |
ory | +0.006 |
ari | +0.005 |
THE | +0.005 |
Neg logit contributions | |
rum | -0.008 |
pain | -0.008 |
ez | -0.007 |
aged | -0.006 |
mischief | -0.006 |
Token | Wow |
Token ID | 22017 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
rum | +0.027 |
pain | +0.025 |
ez | +0.023 |
mischief | +0.022 |
aged | +0.022 |
Neg logit contributions | |
oph | -0.015 |
ll | -0.015 |
ory | -0.014 |
THE | -0.014 |
ari | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
oph | +0.075 |
THE | +0.068 |
ory | +0.067 |
ari | +0.066 |
arium | +0.065 |
Neg logit contributions | |
rum | -0.057 |
pain | -0.049 |
ez | -0.039 |
pushing | -0.038 |
aged | -0.038 |
Token | wow |
Token ID | 28796 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
ll | +0.031 |
oph | +0.030 |
ory | +0.029 |
THE | +0.028 |
arium | +0.027 |
Neg logit contributions | |
rum | -0.041 |
pain | -0.040 |
ez | -0.034 |
mischief | -0.033 |
aged | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
THE | +0.115 |
oph | +0.114 |
ocular | +0.110 |
arium | +0.110 |
assion | +0.110 |
Neg logit contributions | |
rum | -0.100 |
pain | -0.088 |
trouble | -0.072 |
mischief | -0.070 |
ez | -0.068 |
Token | wow |
Token ID | 28796 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
ll | +0.056 |
oph | +0.053 |
ory | +0.050 |
THE | +0.049 |
arium | +0.048 |
Neg logit contributions | |
pain | -0.064 |
rum | -0.064 |
ez | -0.053 |
mischief | -0.052 |
trouble | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
oph | +0.129 |
THE | +0.127 |
pp | +0.126 |
ocular | +0.126 |
ari | +0.125 |
Neg logit contributions | |
rum | -0.109 |
pain | -0.095 |
trouble | -0.078 |
mischief | -0.074 |
ez | -0.073 |
Token | thank |
Token ID | 5875 |
Feature activation | -2.62e+00 |
Pos logit contributions | |
ll | +0.074 |
oph | +0.072 |
ory | +0.066 |
THE | +0.063 |
arium | +0.063 |
Neg logit contributions | |
pain | -0.082 |
rum | -0.081 |
ez | -0.069 |
mischief | -0.065 |
aged | -0.062 |
Token | you |
Token ID | 345 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
ll | +0.058 |
oph | +0.055 |
arium | +0.052 |
'd | +0.051 |
THE | +0.050 |
Neg logit contributions | |
rum | -0.070 |
pain | -0.067 |
ez | -0.060 |
mischief | -0.057 |
e | -0.055 |
Token | , |
Token ID | 11 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
oph | +0.067 |
ll | +0.066 |
ory | +0.061 |
THE | +0.058 |
arium | +0.058 |
Neg logit contributions | |
rum | -0.061 |
pain | -0.053 |
ez | -0.044 |
mischief | -0.043 |
trouble | -0.042 |
Token | thank |
Token ID | 5875 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
ll | +0.072 |
oph | +0.067 |
ory | +0.062 |
THE | +0.062 |
arium | +0.062 |
Neg logit contributions | |
rum | -0.076 |
pain | -0.076 |
ez | -0.063 |
mischief | -0.062 |
trouble | -0.058 |
Token | Mom |
Token ID | 11254 |
Feature activation | -1.02e+00 |
Pos logit contributions | |
oph | +0.060 |
ll | +0.059 |
ory | +0.056 |
THE | +0.054 |
ari | +0.053 |
Neg logit contributions | |
rum | -0.088 |
pain | -0.082 |
ez | -0.075 |
mischief | -0.072 |
aged | -0.070 |
Token | my |
Token ID | 1820 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
oph | +0.018 |
ll | +0.018 |
arium | +0.018 |
THE | +0.017 |
ari | +0.017 |
Neg logit contributions | |
rum | -0.030 |
pain | -0.029 |
ez | -0.028 |
aged | -0.025 |
mischief | -0.025 |
Token | were |
Token ID | 547 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
ll | +0.022 |
oph | +0.022 |
ari | +0.020 |
THE | +0.020 |
ory | +0.020 |
Neg logit contributions | |
rum | -0.034 |
pain | -0.033 |
ez | -0.030 |
mischief | -0.028 |
aged | -0.028 |
Token | headed |
Token ID | 9153 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
oph | +0.033 |
ll | +0.033 |
ory | +0.031 |
THE | +0.030 |
ari | +0.030 |
Neg logit contributions | |
rum | -0.030 |
pain | -0.028 |
ez | -0.025 |
mischief | -0.024 |
aged | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | -2.20e+00 |
Pos logit contributions | |
ll | +0.073 |
oph | +0.073 |
ory | +0.067 |
ari | +0.064 |
THE | +0.064 |
Neg logit contributions | |
rum | -0.066 |
pain | -0.062 |
mischief | -0.055 |
ez | -0.055 |
udge | -0.051 |
Token | the |
Token ID | 262 |
Feature activation | -5.10e+00 |
Pos logit contributions | |
ll | +0.056 |
oph | +0.052 |
ari | +0.050 |
ory | +0.049 |
ocular | +0.048 |
Neg logit contributions | |
pain | -0.052 |
rum | -0.052 |
mischief | -0.049 |
ez | -0.044 |
udge | -0.041 |
Token | gym |
Token ID | 11550 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
ll | +0.127 |
oph | +0.113 |
omed | +0.109 |
ory | +0.109 |
pp | +0.107 |
Neg logit contributions | |
pain | -0.113 |
mischief | -0.106 |
rum | -0.101 |
cigarette | -0.094 |
udge | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | -3.57e-01 |
Pos logit contributions | |
oph | +0.055 |
ll | +0.054 |
ory | +0.051 |
THE | +0.050 |
ari | +0.048 |
Neg logit contributions | |
rum | -0.060 |
pain | -0.055 |
ez | -0.050 |
udge | -0.047 |
mischief | -0.047 |
Token | It |
Token ID | 632 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
ll | +0.008 |
oph | +0.008 |
ory | +0.008 |
THE | +0.007 |
ari | +0.007 |
Neg logit contributions | |
rum | -0.010 |
pain | -0.009 |
ez | -0.008 |
mischief | -0.008 |
aged | -0.007 |
Token | was |
Token ID | 373 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
oph | +0.025 |
ory | +0.025 |
ll | +0.024 |
THE | +0.023 |
ari | +0.023 |
Neg logit contributions | |
rum | -0.023 |
pain | -0.022 |
ez | -0.019 |
aged | -0.018 |
mischief | -0.018 |
Token | dark |
Token ID | 3223 |
Feature activation | +1.26e-01 |
Pos logit contributions | |
rum | +0.001 |
pain | +0.001 |
ez | +0.001 |
mischief | +0.001 |
aged | +0.001 |
Neg logit contributions | |
ll | -0.001 |
oph | -0.001 |
ory | -0.001 |
ari | -0.001 |
THE | -0.001 |
Token | " |
Token ID | 1 |
Feature activation | +9.74e-01 |
Pos logit contributions | |
oph | +0.018 |
ll | +0.018 |
ory | +0.016 |
THE | +0.016 |
ari | +0.015 |
Neg logit contributions | |
rum | -0.032 |
pain | -0.030 |
ez | -0.027 |
mischief | -0.026 |
udge | -0.026 |
Token | Wow |
Token ID | 22017 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
rum | +0.029 |
pain | +0.027 |
ez | +0.024 |
mischief | +0.023 |
aged | +0.023 |
Neg logit contributions | |
oph | -0.021 |
ll | -0.020 |
THE | -0.020 |
ory | -0.019 |
upon | -0.018 |
Token | , |
Token ID | 11 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
oph | +0.089 |
THE | +0.084 |
ari | +0.084 |
arium | +0.083 |
ory | +0.080 |
Neg logit contributions | |
rum | -0.062 |
pain | -0.056 |
aged | -0.044 |
pushing | -0.043 |
pulling | -0.041 |
Token | wow |
Token ID | 28796 |
Feature activation | -4.53e+00 |
Pos logit contributions | |
ll | +0.037 |
oph | +0.035 |
ari | +0.034 |
arium | +0.034 |
THE | +0.034 |
Neg logit contributions | |
rum | -0.041 |
pain | -0.041 |
ez | -0.033 |
mischief | -0.033 |
aged | -0.032 |
Token | , |
Token ID | 11 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
THE | +0.115 |
arium | +0.110 |
oph | +0.110 |
ari | +0.108 |
assion | +0.105 |
Neg logit contributions | |
rum | -0.101 |
pain | -0.092 |
trouble | -0.072 |
mischief | -0.071 |
ez | -0.070 |
Token | wow |
Token ID | 28796 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
ll | +0.059 |
oph | +0.053 |
arium | +0.052 |
ari | +0.052 |
THE | +0.051 |
Neg logit contributions | |
pain | -0.060 |
rum | -0.058 |
mischief | -0.048 |
trouble | -0.046 |
aged | -0.046 |
Token | , |
Token ID | 11 |
Feature activation | -3.10e+00 |
Pos logit contributions | |
THE | +0.127 |
arium | +0.125 |
oph | +0.124 |
ari | +0.124 |
ingu | +0.119 |
Neg logit contributions | |
rum | -0.111 |
pain | -0.100 |
trouble | -0.079 |
mischief | -0.076 |
ez | -0.076 |
Token | they |
Token ID | 484 |
Feature activation | -4.28e+00 |
Pos logit contributions | |
ll | +0.077 |
oph | +0.071 |
ory | +0.068 |
arium | +0.065 |
ari | +0.064 |
Neg logit contributions | |
pain | -0.075 |
rum | -0.074 |
mischief | -0.061 |
ez | -0.059 |
pushing | -0.059 |
Token | are |
Token ID | 389 |
Feature activation | -2.44e+00 |
Pos logit contributions | |
oph | +0.111 |
ll | +0.104 |
ete | +0.101 |
ory | +0.100 |
THE | +0.100 |
Neg logit contributions | |
pain | -0.097 |
rum | -0.083 |
ez | -0.079 |
e | -0.075 |
mischief | -0.074 |
Token | so |
Token ID | 523 |
Feature activation | +1.43e-01 |
Pos logit contributions | |
oph | +0.060 |
ll | +0.059 |
ory | +0.056 |
of | +0.055 |
ari | +0.053 |
Neg logit contributions | |
pain | -0.060 |
rum | -0.060 |
mischief | -0.052 |
aged | -0.049 |
ez | -0.048 |
Token | pretty |
Token ID | 2495 |
Feature activation | -2.83e+00 |
Pos logit contributions | |
rum | +0.004 |
pain | +0.004 |
mischief | +0.003 |
ez | +0.003 |
aged | +0.003 |
Neg logit contributions | |
oph | -0.003 |
ll | -0.003 |
ory | -0.003 |
ari | -0.003 |
THE | -0.003 |
Token | day |
Token ID | 1110 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
oph | +0.002 |
ll | +0.002 |
ory | +0.002 |
THE | +0.002 |
arium | +0.002 |
Neg logit contributions | |
rum | -0.003 |
pain | -0.003 |
ez | -0.002 |
mischief | -0.002 |
aged | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +1.54e-01 |
Pos logit contributions | |
ll | +0.002 |
oph | +0.002 |
ory | +0.002 |
THE | +0.002 |
ari | +0.002 |
Neg logit contributions | |
rum | -0.003 |
pain | -0.003 |
ez | -0.003 |
mischief | -0.003 |
aged | -0.002 |
Token | They |
Token ID | 1119 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
rum | +0.005 |
pain | +0.004 |
ez | +0.004 |
mischief | +0.004 |
aged | +0.004 |
Neg logit contributions | |
oph | -0.003 |
ll | -0.003 |
ory | -0.003 |
THE | -0.003 |
ari | -0.003 |
Token | go |
Token ID | 467 |
Feature activation | -1.89e+00 |
Pos logit contributions | |
oph | +0.057 |
ll | +0.056 |
THE | +0.053 |
ari | +0.052 |
ocular | +0.050 |
Neg logit contributions | |
pain | -0.046 |
rum | -0.044 |
ez | -0.038 |
mischief | -0.037 |
udge | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | -2.06e+00 |
Pos logit contributions | |
oph | +0.055 |
ory | +0.047 |
ll | +0.045 |
ete | +0.045 |
THE | +0.043 |
Neg logit contributions | |
rum | -0.039 |
pain | -0.037 |
ez | -0.032 |
udge | -0.032 |
aged | -0.031 |
Token | the |
Token ID | 262 |
Feature activation | -5.09e+00 |
Pos logit contributions | |
ll | +0.047 |
oph | +0.045 |
ory | +0.042 |
ari | +0.042 |
THE | +0.041 |
Neg logit contributions | |
rum | -0.055 |
pain | -0.054 |
mischief | -0.048 |
ez | -0.046 |
udge | -0.044 |
Token | park |
Token ID | 3952 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
ll | +0.133 |
oph | +0.126 |
ory | +0.123 |
omed | +0.120 |
pp | +0.117 |
Neg logit contributions | |
pain | -0.109 |
mischief | -0.095 |
rum | -0.088 |
cigarette | -0.087 |
trouble | -0.086 |
Token | with |
Token ID | 351 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
oph | +0.078 |
ll | +0.075 |
ory | +0.073 |
THE | +0.070 |
ari | +0.068 |
Neg logit contributions | |
rum | -0.071 |
pain | -0.064 |
ez | -0.057 |
aged | -0.054 |
udge | -0.054 |
Token | their |
Token ID | 511 |
Feature activation | -4.50e-01 |
Pos logit contributions | |
rum | +0.020 |
pain | +0.020 |
ez | +0.017 |
mischief | +0.017 |
udge | +0.015 |
Neg logit contributions | |
ll | -0.023 |
oph | -0.022 |
ari | -0.021 |
ory | -0.021 |
THE | -0.021 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.22e+00 |
Pos logit contributions | |
oph | +0.010 |
ll | +0.009 |
ory | +0.009 |
THE | +0.008 |
ari | +0.008 |
Neg logit contributions | |
rum | -0.012 |
pain | -0.012 |
mischief | -0.011 |
ez | -0.011 |
aged | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
oph | +0.034 |
ll | +0.032 |
ory | +0.031 |
THE | +0.031 |
ete | +0.030 |
Neg logit contributions | |
rum | -0.025 |
pain | -0.021 |
ez | -0.020 |
udge | -0.018 |
aged | -0.018 |
Token | " |
Token ID | 1 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
ll | +0.015 |
oph | +0.014 |
ory | +0.013 |
THE | +0.013 |
ari | +0.013 |
Neg logit contributions | |
rum | -0.029 |
pain | -0.027 |
ez | -0.025 |
mischief | -0.024 |
aged | -0.024 |
Token | Wow |
Token ID | 22017 |
Feature activation | -3.08e+00 |
Pos logit contributions | |
rum | +0.029 |
pain | +0.027 |
ez | +0.024 |
mischief | +0.023 |
aged | +0.023 |
Neg logit contributions | |
oph | -0.024 |
ll | -0.023 |
ory | -0.022 |
THE | -0.022 |
ari | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
oph | +0.096 |
assion | +0.089 |
ocular | +0.087 |
Reserve | +0.087 |
ory | +0.087 |
Neg logit contributions | |
rum | -0.054 |
pain | -0.050 |
pushing | -0.038 |
aged | -0.037 |
trouble | -0.036 |
Token | wow |
Token ID | 28796 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
ll | +0.045 |
oph | +0.043 |
ory | +0.041 |
THE | +0.039 |
ari | +0.038 |
Neg logit contributions | |
rum | -0.060 |
pain | -0.060 |
ez | -0.051 |
mischief | -0.050 |
aged | -0.048 |
Token | , |
Token ID | 11 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
THE | +0.122 |
oph | +0.120 |
ocular | +0.119 |
assion | +0.118 |
arium | +0.117 |
Neg logit contributions | |
rum | -0.092 |
pain | -0.083 |
trouble | -0.067 |
udge | -0.062 |
ump | -0.062 |
Token | wow |
Token ID | 28796 |
Feature activation | -5.08e+00 |
Pos logit contributions | |
ll | +0.070 |
oph | +0.066 |
ory | +0.063 |
THE | +0.060 |
ari | +0.058 |
Neg logit contributions | |
pain | -0.081 |
rum | -0.078 |
ez | -0.065 |
mischief | -0.065 |
trouble | -0.063 |
Token | , |
Token ID | 11 |
Feature activation | -3.58e+00 |
Pos logit contributions | |
THE | +0.131 |
oph | +0.130 |
ocular | +0.129 |
ingu | +0.128 |
assion | +0.127 |
Neg logit contributions | |
rum | -0.103 |
pain | -0.093 |
trouble | -0.076 |
udge | -0.069 |
ump | -0.069 |
Token | birds |
Token ID | 10087 |
Feature activation | -3.22e+00 |
Pos logit contributions | |
ll | +0.088 |
oph | +0.082 |
ory | +0.079 |
THE | +0.072 |
ari | +0.072 |
Neg logit contributions | |
pain | -0.091 |
rum | -0.086 |
ez | -0.072 |
mischief | -0.072 |
pushing | -0.070 |
Token |
|
Token ID | 198 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
oph | +0.068 |
ll | +0.061 |
ory | +0.060 |
ari | +0.058 |
THE | +0.057 |
Neg logit contributions | |
rum | -0.094 |
pain | -0.089 |
ez | -0.081 |
udge | -0.075 |
mischief | -0.074 |
Token | You |
Token ID | 1639 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
oph | +0.046 |
ll | +0.045 |
ory | +0.042 |
THE | +0.040 |
ari | +0.040 |
Neg logit contributions | |
rum | -0.071 |
pain | -0.066 |
ez | -0.061 |
mischief | -0.058 |
udge | -0.057 |
Token | can |
Token ID | 460 |
Feature activation | -5.61e-01 |
Pos logit contributions | |
ll | +0.035 |
oph | +0.034 |
ory | +0.033 |
ail | +0.031 |
ete | +0.031 |
Neg logit contributions | |
pain | -0.026 |
e | -0.020 |
ez | -0.020 |
ases | -0.019 |
trouble | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | -3.82e+00 |
Pos logit contributions | |
oph | +0.027 |
ll | +0.026 |
THE | +0.024 |
ory | +0.024 |
ari | +0.024 |
Neg logit contributions | |
rum | -0.036 |
pain | -0.033 |
ez | -0.032 |
mischief | -0.028 |
aged | -0.028 |
Token | Mia |
Token ID | 32189 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
oph | +0.077 |
ory | +0.074 |
would | +0.073 |
ll | +0.071 |
THE | +0.070 |
Neg logit contributions | |
rum | -0.115 |
pain | -0.099 |
ez | -0.095 |
udge | -0.093 |
mischief | -0.091 |
Token | are |
Token ID | 389 |
Feature activation | -1.82e+00 |
Pos logit contributions | |
oph | +0.054 |
ll | +0.053 |
ari | +0.050 |
THE | +0.049 |
ocular | +0.048 |
Neg logit contributions | |
pain | -0.063 |
rum | -0.062 |
ez | -0.056 |
mischief | -0.051 |
udge | -0.048 |
Token | going |
Token ID | 1016 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
oph | +0.053 |
ll | +0.049 |
ory | +0.048 |
ari | +0.048 |
arium | +0.047 |
Neg logit contributions | |
rum | -0.036 |
pain | -0.034 |
ez | -0.029 |
mischief | -0.028 |
aged | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -2.86e+00 |
Pos logit contributions | |
oph | +0.053 |
ll | +0.050 |
ory | +0.048 |
THE | +0.047 |
arium | +0.046 |
Neg logit contributions | |
rum | -0.044 |
pain | -0.040 |
ez | -0.036 |
aged | -0.034 |
mischief | -0.034 |
Token | the |
Token ID | 262 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
ll | +0.065 |
oph | +0.063 |
ory | +0.059 |
ari | +0.058 |
THE | +0.056 |
Neg logit contributions | |
rum | -0.077 |
pain | -0.074 |
mischief | -0.066 |
ez | -0.065 |
udge | -0.061 |
Token | park |
Token ID | 3952 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
ll | +0.118 |
oph | +0.114 |
ory | +0.108 |
omed | +0.105 |
may | +0.103 |
Neg logit contributions | |
pain | -0.116 |
rum | -0.109 |
mischief | -0.107 |
udge | -0.098 |
cigarette | -0.097 |
Token | with |
Token ID | 351 |
Feature activation | +4.31e-01 |
Pos logit contributions | |
ll | +0.080 |
oph | +0.080 |
ory | +0.076 |
THE | +0.074 |
ari | +0.074 |
Neg logit contributions | |
rum | -0.079 |
pain | -0.073 |
ez | -0.065 |
mischief | -0.061 |
aged | -0.059 |
Token | their |
Token ID | 511 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
rum | +0.012 |
pain | +0.011 |
ez | +0.010 |
mischief | +0.010 |
aged | +0.009 |
Neg logit contributions | |
oph | -0.010 |
ll | -0.009 |
ory | -0.009 |
upon | -0.009 |
THE | -0.009 |
Token | mom |
Token ID | 1995 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
oph | +0.016 |
ll | +0.016 |
ory | +0.015 |
THE | +0.014 |
arium | +0.014 |
Neg logit contributions | |
rum | -0.020 |
pain | -0.019 |
mischief | -0.017 |
ez | -0.016 |
aged | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +3.02e-03 |
Pos logit contributions | |
oph | +0.046 |
ll | +0.043 |
THE | +0.041 |
ory | +0.041 |
arium | +0.041 |
Neg logit contributions | |
rum | -0.038 |
pain | -0.032 |
ez | -0.029 |
udge | -0.028 |
mischief | -0.027 |
Token | beautiful |
Token ID | 4950 |
Feature activation | +3.61e-01 |
Pos logit contributions | |
pain | +0.002 |
rum | +0.002 |
ez | +0.001 |
mischief | +0.001 |
udge | +0.001 |
Neg logit contributions | |
ll | -0.001 |
oph | -0.001 |
THE | -0.001 |
ory | -0.001 |
ari | -0.001 |
Token | girl |
Token ID | 2576 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
pain | +0.009 |
rum | +0.009 |
ez | +0.007 |
mischief | +0.007 |
udge | +0.007 |
Neg logit contributions | |
ll | -0.009 |
oph | -0.008 |
THE | -0.008 |
ari | -0.007 |
ory | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
rum | +0.056 |
pain | +0.050 |
mischief | +0.047 |
tant | +0.044 |
ez | +0.044 |
Neg logit contributions | |
would | -0.029 |
arium | -0.029 |
ll | -0.028 |
ari | -0.028 |
ory | -0.027 |
Token | She |
Token ID | 1375 |
Feature activation | -1.36e-01 |
Pos logit contributions | |
rum | +0.020 |
pain | +0.018 |
ez | +0.017 |
aged | +0.016 |
mischief | +0.016 |
Neg logit contributions | |
oph | -0.013 |
ll | -0.011 |
ory | -0.011 |
ari | -0.011 |
upon | -0.011 |
Token | had |
Token ID | 550 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
oph | +0.003 |
ll | +0.003 |
ory | +0.003 |
ari | +0.003 |
THE | +0.003 |
Neg logit contributions | |
rum | -0.004 |
pain | -0.004 |
ez | -0.003 |
mischief | -0.003 |
aged | -0.003 |
Token | long |
Token ID | 890 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
rum | +0.064 |
pain | +0.054 |
ez | +0.052 |
udge | +0.051 |
mischief | +0.048 |
Neg logit contributions | |
oph | -0.025 |
ll | -0.023 |
THE | -0.023 |
upon | -0.022 |
would | -0.022 |
Token | black |
Token ID | 2042 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
rum | +0.103 |
pain | +0.081 |
udge | +0.079 |
ez | +0.076 |
mischief | +0.067 |
Neg logit contributions | |
oph | -0.134 |
ll | -0.130 |
upon | -0.130 |
ory | -0.128 |
would | -0.127 |
Token | hair |
Token ID | 4190 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
rum | +0.126 |
pain | +0.097 |
udge | +0.093 |
ez | +0.093 |
oving | +0.087 |
Neg logit contributions | |
oph | -0.097 |
als | -0.096 |
ory | -0.094 |
ari | -0.093 |
would | -0.091 |
Token | , |
Token ID | 11 |
Feature activation | +5.46e-02 |
Pos logit contributions | |
rum | +0.056 |
pain | +0.051 |
ez | +0.048 |
mischief | +0.048 |
udge | +0.044 |
Neg logit contributions | |
ll | -0.026 |
oph | -0.025 |
ory | -0.024 |
ari | -0.024 |
would | -0.023 |
Token | a |
Token ID | 257 |
Feature activation | +2.35e+00 |
Pos logit contributions | |
rum | +0.002 |
pain | +0.001 |
ez | +0.001 |
udge | +0.001 |
mischief | +0.001 |
Neg logit contributions | |
oph | -0.001 |
would | -0.001 |
upon | -0.001 |
ll | -0.001 |
ory | -0.001 |
Token | sparkling |
Token ID | 39072 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
rum | +0.069 |
pain | +0.062 |
ez | +0.058 |
mischief | +0.054 |
udge | +0.053 |
Neg logit contributions | |
oph | -0.049 |
ll | -0.049 |
ory | -0.047 |
THE | -0.045 |
upon | -0.045 |
Token | walking |
Token ID | 6155 |
Feature activation | +4.89e-01 |
Pos logit contributions | |
ll | +0.001 |
oph | +0.001 |
ory | +0.001 |
upon | +0.001 |
arium | +0.001 |
Neg logit contributions | |
rum | -0.001 |
pain | -0.001 |
ez | -0.001 |
udge | -0.001 |
mischief | -0.001 |
Token | , |
Token ID | 11 |
Feature activation | -3.24e-01 |
Pos logit contributions | |
rum | +0.015 |
pain | +0.014 |
ez | +0.013 |
mischief | +0.012 |
aged | +0.012 |
Neg logit contributions | |
oph | -0.010 |
ll | -0.010 |
ory | -0.009 |
THE | -0.009 |
ari | -0.008 |
Token | Mary |
Token ID | 5335 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
oph | +0.006 |
ll | +0.006 |
ory | +0.005 |
THE | +0.005 |
ari | +0.005 |
Neg logit contributions | |
rum | -0.010 |
pain | -0.010 |
ez | -0.009 |
mischief | -0.008 |
udge | -0.008 |
Token | felt |
Token ID | 2936 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
oph | +0.034 |
ll | +0.033 |
THE | +0.032 |
ory | +0.031 |
arium | +0.030 |
Neg logit contributions | |
pain | -0.035 |
rum | -0.034 |
ez | -0.032 |
aged | -0.030 |
mischief | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | +2.16e+00 |
Pos logit contributions | |
rum | +0.020 |
pain | +0.019 |
ez | +0.017 |
mischief | +0.016 |
aged | +0.016 |
Neg logit contributions | |
oph | -0.018 |
ll | -0.018 |
ory | -0.017 |
ari | -0.016 |
THE | -0.016 |
Token | sharp |
Token ID | 7786 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
rum | +0.068 |
pain | +0.059 |
ez | +0.058 |
aged | +0.054 |
udge | +0.054 |
Neg logit contributions | |
oph | -0.040 |
ll | -0.039 |
ory | -0.038 |
upon | -0.036 |
may | -0.035 |
Token | pain |
Token ID | 2356 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
rum | +0.091 |
ases | +0.080 |
rums | +0.080 |
irens | +0.077 |
olds | +0.070 |
Neg logit contributions | |
would | -0.110 |
end | -0.106 |
last | -0.105 |
ory | -0.102 |
may | -0.102 |
Token | in |
Token ID | 287 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
rum | +0.088 |
mischief | +0.077 |
pain | +0.077 |
ez | +0.073 |
rums | +0.070 |
Neg logit contributions | |
would | -0.046 |
ll | -0.043 |
upon | -0.042 |
'd | -0.041 |
ory | -0.040 |
Token | her |
Token ID | 607 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
rum | +0.112 |
ez | +0.101 |
aged | +0.100 |
udge | +0.096 |
oving | +0.095 |
Neg logit contributions | |
oph | -0.049 |
upon | -0.044 |
me | -0.041 |
THE | -0.039 |
of | -0.037 |
Token | stomach |
Token ID | 11384 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
rum | +0.030 |
ez | +0.024 |
udge | +0.023 |
pain | +0.023 |
mischief | +0.021 |
Neg logit contributions | |
ll | -0.028 |
oph | -0.028 |
ory | -0.028 |
may | -0.027 |
upon | -0.027 |
Token | . |
Token ID | 13 |
Feature activation | +8.72e-01 |
Pos logit contributions | |
rum | +0.041 |
pain | +0.039 |
ez | +0.035 |
mischief | +0.033 |
aged | +0.032 |
Neg logit contributions | |
oph | -0.034 |
ll | -0.034 |
ory | -0.032 |
THE | -0.031 |
ari | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -6.56e-01 |
Pos logit contributions | |
rum | +0.015 |
pain | +0.015 |
aged | +0.013 |
ez | +0.013 |
mischief | +0.013 |
Neg logit contributions | |
ll | -0.011 |
oph | -0.010 |
ory | -0.010 |
ari | -0.010 |
THE | -0.009 |
Token | Sandra |
Token ID | 32464 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
ll | +0.013 |
oph | +0.013 |
ory | +0.012 |
ari | +0.012 |
THE | +0.012 |
Neg logit contributions | |
rum | -0.019 |
pain | -0.018 |
ez | -0.016 |
mischief | -0.016 |
aged | -0.015 |
Token | always |
Token ID | 1464 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
oph | +0.030 |
ll | +0.029 |
ory | +0.028 |
arium | +0.027 |
ari | +0.027 |
Neg logit contributions | |
rum | -0.045 |
pain | -0.042 |
ez | -0.040 |
aged | -0.038 |
mischief | -0.036 |
Token | enjoyed |
Token ID | 8359 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
rum | +0.040 |
pain | +0.035 |
udge | +0.034 |
mischief | +0.033 |
ez | +0.033 |
Neg logit contributions | |
would | -0.017 |
ll | -0.016 |
oph | -0.016 |
'd | -0.015 |
ory | -0.015 |
Token | her |
Token ID | 607 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
rum | +0.053 |
pain | +0.045 |
ez | +0.043 |
udge | +0.041 |
policy | +0.038 |
Neg logit contributions | |
oph | -0.028 |
ll | -0.027 |
upon | -0.027 |
THE | -0.026 |
ory | -0.026 |
Token | favorite |
Token ID | 4004 |
Feature activation | +4.48e+00 |
Pos logit contributions | |
rum | +0.081 |
pain | +0.074 |
ez | +0.069 |
mischief | +0.065 |
udge | +0.064 |
Neg logit contributions | |
ll | -0.054 |
oph | -0.053 |
ory | -0.050 |
THE | -0.049 |
upon | -0.048 |
Token | past |
Token ID | 1613 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
rum | +0.137 |
pain | +0.119 |
ez | +0.113 |
udge | +0.111 |
aged | +0.108 |
Neg logit contributions | |
oph | -0.082 |
would | -0.082 |
upon | -0.081 |
ory | -0.080 |
may | -0.078 |
Token | ime |
Token ID | 524 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
rum | +0.055 |
pain | +0.050 |
ez | +0.044 |
mischief | +0.042 |
aged | +0.040 |
Neg logit contributions | |
oph | -0.060 |
ll | -0.060 |
ory | -0.058 |
upon | -0.057 |
THE | -0.056 |
Token | : |
Token ID | 25 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
rum | +0.038 |
pain | +0.036 |
ez | +0.031 |
mischief | +0.030 |
aged | +0.029 |
Neg logit contributions | |
ll | -0.039 |
oph | -0.039 |
ory | -0.037 |
THE | -0.036 |
ari | -0.036 |
Token | giving |
Token ID | 3501 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
rum | +0.041 |
pain | +0.038 |
ez | +0.035 |
mischief | +0.033 |
udge | +0.033 |
Neg logit contributions | |
oph | -0.025 |
ll | -0.025 |
ory | -0.023 |
THE | -0.023 |
upon | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
rum | +0.017 |
pain | +0.015 |
ez | +0.014 |
mischief | +0.013 |
aged | +0.013 |
Neg logit contributions | |
oph | -0.012 |
ll | -0.012 |
ory | -0.011 |
THE | -0.011 |
ari | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
rum | +0.061 |
ez | +0.052 |
pain | +0.052 |
aged | +0.051 |
udge | +0.049 |
Neg logit contributions | |
oph | -0.033 |
ory | -0.031 |
arium | -0.031 |
ll | -0.031 |
would | -0.030 |
Token | furry |
Token ID | 40857 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
would | +0.030 |
upon | +0.030 |
oph | +0.029 |
may | +0.029 |
ory | +0.027 |
Neg logit contributions | |
rum | -0.060 |
ez | -0.050 |
aged | -0.049 |
ases | -0.048 |
udge | -0.047 |
Token | creature |
Token ID | 7185 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
rum | +0.079 |
pain | +0.066 |
ez | +0.066 |
aged | +0.063 |
mischief | +0.061 |
Neg logit contributions | |
oph | -0.053 |
ory | -0.051 |
upon | -0.049 |
ari | -0.048 |
arium | -0.048 |
Token | with |
Token ID | 351 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
rum | +0.036 |
pain | +0.034 |
mischief | +0.031 |
ez | +0.030 |
aged | +0.029 |
Neg logit contributions | |
ll | -0.020 |
oph | -0.019 |
ory | -0.018 |
upon | -0.018 |
ari | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
rum | +0.044 |
pain | +0.037 |
udge | +0.036 |
ez | +0.035 |
aged | +0.034 |
Neg logit contributions | |
oph | -0.019 |
als | -0.017 |
ocular | -0.017 |
upon | -0.017 |
would | -0.017 |
Token | long |
Token ID | 890 |
Feature activation | +4.84e+00 |
Pos logit contributions | |
rum | +0.088 |
pain | +0.075 |
ez | +0.074 |
udge | +0.071 |
ases | +0.070 |
Neg logit contributions | |
oph | -0.055 |
may | -0.054 |
upon | -0.053 |
ll | -0.052 |
ory | -0.052 |
Token | tail |
Token ID | 7894 |
Feature activation | +9.46e-01 |
Pos logit contributions | |
rum | +0.134 |
pain | +0.117 |
udge | +0.116 |
ez | +0.115 |
mischief | +0.113 |
Neg logit contributions | |
oph | -0.094 |
upon | -0.092 |
may | -0.091 |
would | -0.087 |
ory | -0.087 |
Token | and |
Token ID | 290 |
Feature activation | -1.03e+00 |
Pos logit contributions | |
rum | +0.028 |
pain | +0.026 |
ez | +0.024 |
mischief | +0.024 |
udge | +0.023 |
Neg logit contributions | |
ll | -0.018 |
oph | -0.018 |
ory | -0.017 |
THE | -0.017 |
upon | -0.016 |
Token | big |
Token ID | 1263 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
oph | +0.016 |
would | +0.015 |
upon | +0.015 |
may | +0.014 |
ll | +0.014 |
Neg logit contributions | |
rum | -0.035 |
pain | -0.030 |
udge | -0.029 |
ez | -0.029 |
mischief | -0.027 |
Token | eyes |
Token ID | 2951 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
rum | +0.116 |
udge | +0.104 |
ez | +0.101 |
pain | +0.097 |
aged | +0.096 |
Neg logit contributions | |
may | -0.056 |
upon | -0.051 |
oph | -0.049 |
als | -0.048 |
would | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +6.75e-01 |
Pos logit contributions | |
rum | +0.051 |
pain | +0.047 |
mischief | +0.043 |
ez | +0.043 |
udge | +0.041 |
Neg logit contributions | |
ll | -0.029 |
oph | -0.029 |
ory | -0.027 |
THE | -0.027 |
upon | -0.026 |
Token | he |
Token ID | 339 |
Feature activation | +3.93e-01 |
Pos logit contributions | |
rum | +0.043 |
pain | +0.041 |
ez | +0.038 |
mischief | +0.036 |
udge | +0.035 |
Neg logit contributions | |
oph | -0.022 |
ll | -0.022 |
ory | -0.020 |
THE | -0.019 |
ari | -0.019 |
Token | never |
Token ID | 1239 |
Feature activation | -6.85e-02 |
Pos logit contributions | |
rum | +0.013 |
pain | +0.012 |
ez | +0.011 |
mischief | +0.011 |
aged | +0.010 |
Neg logit contributions | |
oph | -0.007 |
ll | -0.007 |
ory | -0.006 |
ari | -0.006 |
THE | -0.006 |
Token | forgot |
Token ID | 16453 |
Feature activation | +4.08e-02 |
Pos logit contributions | |
THE | +0.001 |
oph | +0.001 |
ll | +0.001 |
ari | +0.001 |
ocular | +0.001 |
Neg logit contributions | |
pain | -0.002 |
rum | -0.002 |
ez | -0.002 |
mischief | -0.002 |
aged | -0.002 |
Token | his |
Token ID | 465 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
rum | +0.001 |
pain | +0.001 |
ez | +0.001 |
mischief | +0.001 |
aged | +0.001 |
Neg logit contributions | |
ll | -0.001 |
oph | -0.001 |
ory | -0.001 |
ari | -0.001 |
THE | -0.001 |
Token | love |
Token ID | 1842 |
Feature activation | +1.57e+00 |
Pos logit contributions | |
rum | +0.073 |
pain | +0.068 |
ez | +0.062 |
mischief | +0.059 |
udge | +0.058 |
Neg logit contributions | |
ll | -0.055 |
oph | -0.054 |
ory | -0.051 |
THE | -0.049 |
ari | -0.048 |
Token | for |
Token ID | 329 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
rum | +0.050 |
pain | +0.046 |
ez | +0.042 |
aged | +0.042 |
mischief | +0.041 |
Neg logit contributions | |
oph | -0.028 |
ll | -0.027 |
ory | -0.026 |
would | -0.026 |
THE | -0.024 |
Token | caul |
Token ID | 46087 |
Feature activation | +1.71e-01 |
Pos logit contributions | |
rum | +0.133 |
pain | +0.123 |
ez | +0.112 |
udge | +0.106 |
mischief | +0.105 |
Neg logit contributions | |
oph | -0.106 |
ll | -0.105 |
ory | -0.099 |
THE | -0.097 |
arium | -0.095 |
Token | iflower |
Token ID | 42642 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
rum | +0.005 |
pain | +0.005 |
ez | +0.004 |
mischief | +0.004 |
aged | +0.004 |
Neg logit contributions | |
oph | -0.004 |
ll | -0.003 |
ory | -0.003 |
ari | -0.003 |
THE | -0.003 |
Token | and |
Token ID | 290 |
Feature activation | -6.80e-01 |
Pos logit contributions | |
oph | +0.005 |
ll | +0.005 |
ory | +0.005 |
ari | +0.005 |
THE | +0.005 |
Neg logit contributions | |
rum | -0.007 |
pain | -0.007 |
ez | -0.006 |
mischief | -0.006 |
udge | -0.006 |
Token | would |
Token ID | 561 |
Feature activation | -2.31e-01 |
Pos logit contributions | |
ll | +0.012 |
oph | +0.012 |
ory | +0.011 |
THE | +0.011 |
upon | +0.011 |
Neg logit contributions | |
rum | -0.021 |
pain | -0.020 |
ez | -0.019 |
mischief | -0.018 |
udge | -0.018 |
Token | still |
Token ID | 991 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
oph | +0.005 |
ll | +0.004 |
ory | +0.004 |
ari | +0.004 |
THE | +0.004 |
Neg logit contributions | |
rum | -0.007 |
pain | -0.007 |
ez | -0.006 |
mischief | -0.006 |
aged | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
rum | +0.030 |
udge | +0.024 |
ez | +0.024 |
policy | +0.023 |
aged | +0.023 |
Neg logit contributions | |
THE | -0.016 |
upon | -0.016 |
may | -0.016 |
would | -0.015 |
ory | -0.015 |
Token | sharp |
Token ID | 7786 |
Feature activation | +5.12e+00 |
Pos logit contributions | |
rum | +0.075 |
ez | +0.062 |
ases | +0.060 |
rums | +0.060 |
udge | +0.059 |
Neg logit contributions | |
may | -0.049 |
oph | -0.048 |
upon | -0.047 |
would | -0.046 |
ory | -0.046 |
Token | pain |
Token ID | 2356 |
Feature activation | +2.63e+00 |
Pos logit contributions | |
rum | +0.068 |
rums | +0.061 |
irens | +0.059 |
mischief | +0.054 |
oving | +0.052 |
Neg logit contributions | |
end | -0.151 |
last | -0.149 |
back | -0.142 |
would | -0.142 |
may | -0.141 |
Token | in |
Token ID | 287 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
rum | +0.087 |
mischief | +0.078 |
pain | +0.074 |
ez | +0.073 |
rums | +0.071 |
Neg logit contributions | |
would | -0.041 |
ll | -0.039 |
upon | -0.038 |
'd | -0.036 |
oph | -0.035 |
Token | her |
Token ID | 607 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
rum | +0.115 |
ez | +0.103 |
aged | +0.099 |
oving | +0.098 |
udge | +0.095 |
Neg logit contributions | |
oph | -0.051 |
me | -0.044 |
upon | -0.043 |
THE | -0.040 |
of | -0.040 |
Token | finger |
Token ID | 7660 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
rum | +0.045 |
ez | +0.039 |
udge | +0.037 |
mischief | +0.036 |
rums | +0.036 |
Neg logit contributions | |
upon | -0.031 |
may | -0.031 |
ll | -0.030 |
last | -0.029 |
back | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
rum | +0.091 |
pain | +0.083 |
mischief | +0.081 |
ez | +0.079 |
udge | +0.078 |
Neg logit contributions | |
ll | -0.040 |
would | -0.037 |
oph | -0.036 |
upon | -0.036 |
of | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | -6.02e-01 |
Pos logit contributions | |
rum | +0.045 |
pain | +0.042 |
ez | +0.039 |
mischief | +0.037 |
aged | +0.036 |
Neg logit contributions | |
oph | -0.026 |
ll | -0.026 |
ory | -0.024 |
upon | -0.023 |
THE | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -6.68e-01 |
Pos logit contributions | |
ll | +0.011 |
oph | +0.011 |
ory | +0.010 |
THE | +0.010 |
upon | +0.009 |
Neg logit contributions | |
rum | -0.019 |
pain | -0.018 |
ez | -0.017 |
mischief | -0.016 |
aged | -0.016 |
Token | " |
Token ID | 1 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
ll | +0.013 |
oph | +0.013 |
ory | +0.012 |
ari | +0.012 |
arium | +0.012 |
Neg logit contributions | |
rum | -0.020 |
pain | -0.019 |
ez | -0.017 |
aged | -0.016 |
udge | -0.016 |
Token | O |
Token ID | 46 |
Feature activation | +7.60e-02 |
Pos logit contributions | |
rum | +0.054 |
ez | +0.041 |
aged | +0.041 |
mischief | +0.041 |
pain | +0.041 |
Neg logit contributions | |
oph | -0.028 |
THE | -0.024 |
ll | -0.023 |
ory | -0.023 |
upon | -0.022 |
Token | home |
Token ID | 1363 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
oph | +0.030 |
ll | +0.028 |
ory | +0.027 |
THE | +0.026 |
ari | +0.026 |
Neg logit contributions | |
rum | -0.036 |
pain | -0.034 |
ez | -0.031 |
mischief | -0.029 |
aged | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
rum | +0.005 |
pain | +0.004 |
ez | +0.004 |
mischief | +0.004 |
udge | +0.004 |
Neg logit contributions | |
ll | -0.003 |
oph | -0.003 |
ory | -0.003 |
upon | -0.003 |
THE | -0.002 |
Token | told |
Token ID | 1297 |
Feature activation | +2.89e-02 |
Pos logit contributions | |
oph | +0.038 |
ll | +0.037 |
ory | +0.035 |
ari | +0.034 |
THE | +0.034 |
Neg logit contributions | |
rum | -0.056 |
pain | -0.054 |
ez | -0.049 |
mischief | -0.047 |
aged | -0.047 |
Token | her |
Token ID | 607 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
rum | +0.001 |
pain | +0.001 |
ez | +0.001 |
mischief | +0.001 |
udge | +0.001 |
Neg logit contributions | |
oph | -0.001 |
ll | -0.001 |
ory | -0.001 |
THE | -0.001 |
ari | -0.001 |
Token | mom |
Token ID | 1995 |
Feature activation | -4.54e-01 |
Pos logit contributions | |
oph | +0.029 |
ll | +0.029 |
ory | +0.028 |
ari | +0.026 |
arium | +0.026 |
Neg logit contributions | |
rum | -0.034 |
pain | -0.033 |
mischief | -0.029 |
ez | -0.028 |
aged | -0.028 |
Token | all |
Token ID | 477 |
Feature activation | +1.22e+00 |
Pos logit contributions | |
oph | +0.011 |
ory | +0.011 |
ll | +0.010 |
ari | +0.010 |
arium | +0.010 |
Neg logit contributions | |
rum | -0.011 |
pain | -0.010 |
ez | -0.009 |
aged | -0.008 |
mischief | -0.008 |
Token | about |
Token ID | 546 |
Feature activation | +3.27e-01 |
Pos logit contributions | |
rum | +0.030 |
pain | +0.029 |
ez | +0.025 |
mischief | +0.024 |
aged | +0.022 |
Neg logit contributions | |
oph | -0.032 |
ll | -0.031 |
ory | -0.030 |
ari | -0.029 |
THE | -0.028 |
Token | it |
Token ID | 340 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
rum | +0.009 |
pain | +0.008 |
ez | +0.007 |
mischief | +0.007 |
aged | +0.007 |
Neg logit contributions | |
oph | -0.008 |
ll | -0.008 |
ory | -0.007 |
THE | -0.007 |
ari | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
oph | +0.043 |
ory | +0.040 |
ari | +0.039 |
ll | +0.039 |
THE | +0.038 |
Neg logit contributions | |
rum | -0.032 |
pain | -0.031 |
ez | -0.025 |
mischief | -0.024 |
aged | -0.023 |
Token | Her |
Token ID | 2332 |
Feature activation | +2.40e-01 |
Pos logit contributions | |
rum | +0.000 |
pain | +0.000 |
ez | +0.000 |
mischief | +0.000 |
aged | +0.000 |
Neg logit contributions | |
ll | -0.000 |
oph | -0.000 |
ory | -0.000 |
THE | -0.000 |
ari | -0.000 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
rum | +0.007 |
pain | +0.007 |
ez | +0.006 |
mischief | +0.006 |
aged | +0.006 |
Neg logit contributions | |
oph | -0.005 |
ll | -0.005 |
ory | -0.005 |
ari | -0.005 |
arium | -0.005 |
Token | Tom |
Token ID | 4186 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
rum | +0.043 |
pain | +0.040 |
ez | +0.036 |
aged | +0.034 |
mischief | +0.034 |
Neg logit contributions | |
oph | -0.035 |
ll | -0.034 |
ory | -0.033 |
THE | -0.032 |
upon | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
rum | +0.041 |
pain | +0.037 |
mischief | +0.035 |
ez | +0.034 |
udge | +0.033 |
Neg logit contributions | |
ll | -0.022 |
oph | -0.021 |
ory | -0.019 |
would | -0.018 |
upon | -0.018 |
Token | sad |
Token ID | 6507 |
Feature activation | -8.00e-01 |
Pos logit contributions | |
rum | +0.042 |
policy | +0.035 |
udge | +0.035 |
ez | +0.034 |
mischief | +0.033 |
Neg logit contributions | |
upon | -0.021 |
ll | -0.020 |
THE | -0.019 |
both | -0.019 |
back | -0.019 |
Token | and |
Token ID | 290 |
Feature activation | -6.71e-01 |
Pos logit contributions | |
ll | +0.011 |
upon | +0.010 |
ory | +0.010 |
would | +0.009 |
oph | +0.009 |
Neg logit contributions | |
rum | -0.030 |
ez | -0.027 |
pain | -0.026 |
mischief | -0.026 |
aged | -0.025 |
Token | angry |
Token ID | 7954 |
Feature activation | +6.12e-02 |
Pos logit contributions | |
ll | +0.018 |
oph | +0.018 |
ory | +0.017 |
THE | +0.017 |
ari | +0.017 |
Neg logit contributions | |
rum | -0.015 |
pain | -0.014 |
ez | -0.012 |
mischief | -0.012 |
udge | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
rum | +0.002 |
pain | +0.002 |
ez | +0.002 |
mischief | +0.002 |
udge | +0.002 |
Neg logit contributions | |
ll | -0.001 |
oph | -0.001 |
ory | -0.001 |
THE | -0.001 |
upon | -0.001 |
Token | He |
Token ID | 679 |
Feature activation | +4.04e-01 |
Pos logit contributions | |
rum | +0.045 |
pain | +0.042 |
ez | +0.040 |
aged | +0.037 |
udge | +0.036 |
Neg logit contributions | |
oph | -0.027 |
upon | -0.026 |
ll | -0.026 |
ory | -0.025 |
ete | -0.024 |
Token | pushed |
Token ID | 7121 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
rum | +0.012 |
pain | +0.011 |
ez | +0.010 |
mischief | +0.010 |
udge | +0.010 |
Neg logit contributions | |
oph | -0.008 |
ll | -0.008 |
ory | -0.008 |
THE | -0.007 |
ari | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
rum | +0.052 |
ez | +0.044 |
aged | +0.044 |
pain | +0.044 |
mischief | +0.043 |
Neg logit contributions | |
upon | -0.020 |
of | -0.019 |
me | -0.019 |
ory | -0.019 |
oph | -0.018 |
Token | barrel |
Token ID | 9036 |
Feature activation | -4.40e-01 |
Pos logit contributions | |
oph | +0.042 |
ll | +0.042 |
ory | +0.039 |
THE | +0.038 |
ari | +0.038 |
Neg logit contributions | |
rum | -0.047 |
pain | -0.044 |
ez | -0.039 |
mischief | -0.037 |
aged | -0.036 |
Token | hard |
Token ID | 1327 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
ll | +0.008 |
oph | +0.008 |
ory | +0.007 |
THE | +0.007 |
ari | +0.007 |
Neg logit contributions | |
rum | -0.014 |
pain | -0.013 |
ez | -0.012 |
mischief | -0.012 |
udge | -0.011 |
Token | day |
Token ID | 1110 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
rum | +0.119 |
aged | +0.102 |
udge | +0.101 |
pain | +0.101 |
ez | +0.100 |
Neg logit contributions | |
would | -0.060 |
oph | -0.058 |
THE | -0.057 |
arium | -0.056 |
upon | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
rum | +0.038 |
pain | +0.035 |
ez | +0.032 |
mischief | +0.031 |
udge | +0.030 |
Neg logit contributions | |
oph | -0.026 |
ll | -0.026 |
ory | -0.024 |
THE | -0.023 |
ari | -0.023 |
Token | Her |
Token ID | 2332 |
Feature activation | +9.25e-01 |
Pos logit contributions | |
rum | +0.026 |
pain | +0.023 |
ez | +0.022 |
mischief | +0.020 |
aged | +0.020 |
Neg logit contributions | |
ll | -0.025 |
oph | -0.024 |
ory | -0.023 |
THE | -0.022 |
ari | -0.022 |
Token | pony |
Token ID | 26902 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
rum | +0.028 |
pain | +0.026 |
ez | +0.024 |
mischief | +0.023 |
aged | +0.022 |
Neg logit contributions | |
oph | -0.018 |
ll | -0.018 |
ory | -0.017 |
THE | -0.016 |
ari | -0.016 |
Token | grew |
Token ID | 6348 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
rum | +0.047 |
pain | +0.046 |
ez | +0.043 |
aged | +0.040 |
mischief | +0.035 |
Neg logit contributions | |
oph | -0.041 |
ory | -0.040 |
ll | -0.039 |
upon | -0.037 |
arium | -0.037 |
Token | bigger |
Token ID | 5749 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
oph | +0.032 |
arium | +0.030 |
ll | +0.029 |
ari | +0.029 |
ory | +0.028 |
Neg logit contributions | |
pain | -0.032 |
rum | -0.031 |
aged | -0.028 |
ez | -0.026 |
mischief | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | -1.33e+00 |
Pos logit contributions | |
rum | +0.042 |
pain | +0.038 |
ez | +0.036 |
mischief | +0.034 |
udge | +0.034 |
Neg logit contributions | |
ll | -0.024 |
oph | -0.024 |
ory | -0.022 |
THE | -0.021 |
ari | -0.021 |
Token | stronger |
Token ID | 7387 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
oph | +0.027 |
ll | +0.026 |
ory | +0.026 |
ari | +0.026 |
ete | +0.024 |
Neg logit contributions | |
pain | -0.036 |
rum | -0.035 |
ez | -0.031 |
aged | -0.031 |
mischief | -0.029 |
Token | each |
Token ID | 1123 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
rum | +0.042 |
pain | +0.039 |
ez | +0.036 |
mischief | +0.035 |
udge | +0.034 |
Neg logit contributions | |
ll | -0.028 |
oph | -0.028 |
ory | -0.026 |
THE | -0.026 |
ari | -0.025 |
Token | day |
Token ID | 1110 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
rum | +0.084 |
pain | +0.074 |
udge | +0.073 |
aged | +0.072 |
mischief | +0.072 |
Neg logit contributions | |
would | -0.045 |
oph | -0.044 |
of | -0.044 |
ll | -0.042 |
THE | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | +8.78e-01 |
Pos logit contributions | |
rum | +0.017 |
pain | +0.015 |
ez | +0.014 |
mischief | +0.014 |
udge | +0.013 |
Neg logit contributions | |
oph | -0.010 |
ll | -0.010 |
ory | -0.010 |
THE | -0.009 |
ari | -0.009 |
Token | noise |
Token ID | 7838 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
rum | +0.023 |
pain | +0.020 |
ez | +0.018 |
udge | +0.018 |
aged | +0.018 |
Neg logit contributions | |
oph | -0.029 |
ll | -0.029 |
may | -0.028 |
would | -0.028 |
upon | -0.028 |
Token | . |
Token ID | 13 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
rum | +0.050 |
pain | +0.045 |
ez | +0.042 |
mischief | +0.041 |
aged | +0.040 |
Neg logit contributions | |
ll | -0.029 |
oph | -0.028 |
ory | -0.027 |
would | -0.027 |
upon | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
rum | +0.037 |
pain | +0.035 |
ez | +0.032 |
mischief | +0.030 |
udge | +0.030 |
Neg logit contributions | |
oph | -0.022 |
ll | -0.022 |
ory | -0.020 |
THE | -0.020 |
upon | -0.019 |
Token |
|
Token ID | 198 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
ll | +0.009 |
oph | +0.009 |
THE | +0.008 |
ory | +0.008 |
upon | +0.008 |
Neg logit contributions | |
rum | -0.019 |
pain | -0.018 |
ez | -0.017 |
mischief | -0.016 |
aged | -0.016 |
Token | P |
Token ID | 47 |
Feature activation | +1.99e-01 |
Pos logit contributions | |
oph | +0.006 |
ll | +0.006 |
ory | +0.006 |
THE | +0.006 |
upon | +0.006 |
Neg logit contributions | |
rum | -0.012 |
pain | -0.011 |
ez | -0.010 |
mischief | -0.010 |
udge | -0.009 |
Token | apa |
Token ID | 32678 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
rum | +0.006 |
pain | +0.005 |
ez | +0.005 |
udge | +0.005 |
aged | +0.005 |
Neg logit contributions | |
THE | -0.004 |
oph | -0.003 |
arium | -0.003 |
ll | -0.003 |
would | -0.003 |
Token | took |
Token ID | 1718 |
Feature activation | +1.90e+00 |
Pos logit contributions | |
rum | +0.035 |
pain | +0.033 |
ez | +0.031 |
aged | +0.029 |
udge | +0.027 |
Neg logit contributions | |
oph | -0.029 |
THE | -0.029 |
ll | -0.029 |
arium | -0.027 |
ory | -0.027 |
Token | Lucy |
Token ID | 22162 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
rum | +0.065 |
pain | +0.056 |
ez | +0.055 |
udge | +0.053 |
mischief | +0.052 |
Neg logit contributions | |
oph | -0.028 |
ory | -0.026 |
upon | -0.024 |
ll | -0.024 |
arium | -0.024 |
Token | 's |
Token ID | 338 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
ll | +0.036 |
oph | +0.036 |
ory | +0.033 |
THE | +0.032 |
ari | +0.032 |
Neg logit contributions | |
rum | -0.057 |
pain | -0.053 |
ez | -0.049 |
mischief | -0.047 |
udge | -0.046 |
Token | hand |
Token ID | 1021 |
Feature activation | +2.35e-01 |
Pos logit contributions | |
rum | +0.031 |
pain | +0.026 |
ez | +0.026 |
udge | +0.023 |
mischief | +0.022 |
Neg logit contributions | |
upon | -0.032 |
ll | -0.031 |
may | -0.030 |
would | -0.030 |
ory | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -1.32e+00 |
Pos logit contributions | |
rum | +0.007 |
pain | +0.007 |
ez | +0.006 |
mischief | +0.006 |
udge | +0.006 |
Neg logit contributions | |
ll | -0.005 |
oph | -0.004 |
ory | -0.004 |
THE | -0.004 |
ari | -0.004 |
Token | some |
Token ID | 617 |
Feature activation | +2.45e-01 |
Pos logit contributions | |
oph | +0.035 |
ll | +0.035 |
ory | +0.033 |
THE | +0.031 |
ari | +0.031 |
Neg logit contributions | |
rum | -0.059 |
pain | -0.056 |
ez | -0.051 |
mischief | -0.049 |
aged | -0.048 |
Token | men |
Token ID | 1450 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
rum | +0.007 |
ez | +0.006 |
udge | +0.006 |
pain | +0.005 |
aged | +0.005 |
Neg logit contributions | |
would | -0.005 |
ari | -0.005 |
upon | -0.005 |
may | -0.005 |
ll | -0.005 |
Token | got |
Token ID | 1392 |
Feature activation | +5.73e-01 |
Pos logit contributions | |
rum | +0.064 |
pain | +0.060 |
ez | +0.055 |
mischief | +0.054 |
udge | +0.053 |
Neg logit contributions | |
ll | -0.041 |
upon | -0.038 |
would | -0.037 |
ory | -0.036 |
ari | -0.035 |
Token | out |
Token ID | 503 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
rum | +0.017 |
pain | +0.015 |
ez | +0.014 |
udge | +0.014 |
mischief | +0.014 |
Neg logit contributions | |
ll | -0.011 |
upon | -0.011 |
ory | -0.010 |
ocular | -0.010 |
would | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | +8.07e-01 |
Pos logit contributions | |
rum | +0.054 |
pain | +0.049 |
ez | +0.047 |
udge | +0.047 |
mischief | +0.045 |
Neg logit contributions | |
upon | -0.032 |
ll | -0.030 |
omed | -0.028 |
THE | -0.027 |
arium | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -4.89e-01 |
Pos logit contributions | |
rum | +0.023 |
pain | +0.021 |
ez | +0.019 |
mischief | +0.018 |
aged | +0.018 |
Neg logit contributions | |
oph | -0.018 |
ll | -0.017 |
ory | -0.017 |
THE | -0.016 |
ari | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | -6.16e-01 |
Pos logit contributions | |
ll | +0.009 |
oph | +0.008 |
ory | +0.008 |
THE | +0.008 |
ari | +0.007 |
Neg logit contributions | |
rum | -0.016 |
pain | -0.015 |
ez | -0.014 |
mischief | -0.013 |
aged | -0.013 |
Token | " |
Token ID | 1 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
ll | +0.011 |
oph | +0.011 |
ory | +0.010 |
THE | +0.010 |
ari | +0.009 |
Neg logit contributions | |
rum | -0.020 |
pain | -0.019 |
ez | -0.017 |
mischief | -0.017 |
udge | -0.016 |
Token | Exc |
Token ID | 40127 |
Feature activation | +1.54e+00 |
Pos logit contributions | |
rum | +0.041 |
pain | +0.038 |
ez | +0.034 |
mischief | +0.033 |
aged | +0.032 |
Neg logit contributions | |
oph | -0.035 |
ll | -0.035 |
ory | -0.033 |
THE | -0.032 |
ari | -0.031 |
Token | use |
Token ID | 1904 |
Feature activation | -8.85e-01 |
Pos logit contributions | |
rum | +0.059 |
pain | +0.056 |
ez | +0.051 |
mischief | +0.050 |
aged | +0.050 |
Neg logit contributions | |
ll | -0.018 |
oph | -0.018 |
ory | -0.017 |
ari | -0.015 |
THE | -0.015 |
Token | me |
Token ID | 502 |
Feature activation | -5.64e-01 |
Pos logit contributions | |
THE | +0.014 |
ll | +0.014 |
arium | +0.014 |
'd | +0.013 |
may | +0.013 |
Neg logit contributions | |
rum | -0.027 |
pain | -0.026 |
mischief | -0.024 |
cigarette | -0.024 |
trouble | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
rum | +0.108 |
pain | +0.102 |
ez | +0.092 |
mischief | +0.091 |
udge | +0.088 |
Neg logit contributions | |
ll | -0.067 |
oph | -0.066 |
ory | -0.061 |
ari | -0.059 |
THE | -0.059 |
Token | a |
Token ID | 257 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
rum | +0.035 |
pain | +0.032 |
ez | +0.030 |
udge | +0.029 |
mischief | +0.028 |
Neg logit contributions | |
ll | -0.020 |
oph | -0.020 |
THE | -0.019 |
upon | -0.018 |
ory | -0.018 |
Token | huge |
Token ID | 3236 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
rum | +0.035 |
pain | +0.034 |
ez | +0.030 |
mischief | +0.029 |
udge | +0.028 |
Neg logit contributions | |
ll | -0.027 |
oph | -0.027 |
ory | -0.025 |
THE | -0.024 |
ari | -0.024 |
Token | success |
Token ID | 1943 |
Feature activation | -1.00e-01 |
Pos logit contributions | |
rum | +0.069 |
ez | +0.058 |
aged | +0.057 |
pain | +0.056 |
udge | +0.054 |
Neg logit contributions | |
oph | -0.035 |
ory | -0.034 |
would | -0.032 |
ll | -0.032 |
arium | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -6.59e-01 |
Pos logit contributions | |
ll | +0.002 |
oph | +0.002 |
ory | +0.002 |
THE | +0.002 |
ari | +0.002 |
Neg logit contributions | |
rum | -0.003 |
pain | -0.003 |
ez | -0.003 |
mischief | -0.003 |
aged | -0.002 |
Token | everyone |
Token ID | 2506 |
Feature activation | +8.63e-01 |
Pos logit contributions | |
oph | +0.012 |
ll | +0.012 |
ory | +0.011 |
THE | +0.010 |
ari | +0.010 |
Neg logit contributions | |
rum | -0.021 |
pain | -0.020 |
ez | -0.018 |
mischief | -0.017 |
udge | -0.017 |
Token | was |
Token ID | 373 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
rum | +0.029 |
pain | +0.027 |
mischief | +0.025 |
ez | +0.024 |
udge | +0.024 |
Neg logit contributions | |
ll | -0.014 |
oph | -0.014 |
would | -0.013 |
ory | -0.013 |
THE | -0.013 |
Token | cl |
Token ID | 537 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
rum | +0.040 |
pain | +0.037 |
ez | +0.034 |
mischief | +0.033 |
udge | +0.033 |
Neg logit contributions | |
ll | -0.025 |
oph | -0.024 |
THE | -0.023 |
ory | -0.023 |
upon | -0.022 |
Token | apping |
Token ID | 5912 |
Feature activation | +8.05e-01 |
Pos logit contributions | |
rum | +0.032 |
pain | +0.030 |
ez | +0.025 |
mischief | +0.025 |
aged | +0.023 |
Neg logit contributions | |
oph | -0.036 |
ll | -0.036 |
ory | -0.035 |
ari | -0.034 |
THE | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
rum | +0.023 |
pain | +0.022 |
ez | +0.020 |
mischief | +0.019 |
udge | +0.018 |
Neg logit contributions | |
oph | -0.017 |
ll | -0.017 |
ory | -0.016 |
THE | -0.015 |
upon | -0.015 |
Token | cheering |
Token ID | 29732 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
ll | +0.027 |
oph | +0.026 |
ory | +0.025 |
THE | +0.025 |
upon | +0.024 |
Neg logit contributions | |
rum | -0.024 |
pain | -0.022 |
ez | -0.019 |
mischief | -0.018 |
udge | -0.018 |
Token | older |
Token ID | 4697 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
rum | +0.019 |
pain | +0.018 |
ez | +0.017 |
udge | +0.016 |
mischief | +0.016 |
Neg logit contributions | |
ll | -0.007 |
oph | -0.007 |
ory | -0.007 |
upon | -0.007 |
ari | -0.006 |
Token | sister |
Token ID | 6621 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
rum | +0.103 |
pain | +0.096 |
ez | +0.089 |
mischief | +0.082 |
udge | +0.082 |
Neg logit contributions | |
oph | -0.082 |
ll | -0.080 |
ory | -0.079 |
upon | -0.075 |
ari | -0.074 |
Token | came |
Token ID | 1625 |
Feature activation | -6.66e-01 |
Pos logit contributions | |
rum | +0.056 |
pain | +0.053 |
ez | +0.049 |
mischief | +0.047 |
aged | +0.046 |
Neg logit contributions | |
ll | -0.033 |
oph | -0.032 |
ory | -0.030 |
THE | -0.029 |
ari | -0.028 |
Token | over |
Token ID | 625 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
ll | +0.013 |
oph | +0.013 |
upon | +0.012 |
ory | +0.012 |
THE | +0.012 |
Neg logit contributions | |
rum | -0.020 |
pain | -0.019 |
ez | -0.017 |
mischief | -0.016 |
aged | -0.016 |
Token | to |
Token ID | 284 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
upon | +0.003 |
ll | +0.002 |
oph | +0.002 |
ory | +0.002 |
THE | +0.002 |
Neg logit contributions | |
rum | -0.006 |
pain | -0.005 |
ez | -0.005 |
aged | -0.005 |
mischief | -0.005 |
Token | him |
Token ID | 683 |
Feature activation | -3.90e-01 |
Pos logit contributions | |
rum | +0.010 |
pain | +0.009 |
ez | +0.008 |
mischief | +0.008 |
aged | +0.008 |
Neg logit contributions | |
oph | -0.007 |
ll | -0.007 |
ory | -0.007 |
THE | -0.006 |
upon | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -1.70e+00 |
Pos logit contributions | |
ll | +0.007 |
oph | +0.007 |
ory | +0.007 |
upon | +0.006 |
ari | +0.006 |
Neg logit contributions | |
rum | -0.012 |
pain | -0.012 |
ez | -0.011 |
mischief | -0.010 |
aged | -0.010 |
Token | said |
Token ID | 531 |
Feature activation | -3.60e-01 |
Pos logit contributions | |
oph | +0.034 |
ll | +0.033 |
THE | +0.031 |
ory | +0.031 |
ari | +0.030 |
Neg logit contributions | |
rum | -0.050 |
pain | -0.047 |
ez | -0.043 |
aged | -0.041 |
mischief | -0.041 |
Token | , |
Token ID | 11 |
Feature activation | -4.17e-01 |
Pos logit contributions | |
oph | +0.006 |
ll | +0.006 |
ory | +0.005 |
THE | +0.005 |
ari | +0.005 |
Neg logit contributions | |
rum | -0.012 |
pain | -0.011 |
ez | -0.010 |
mischief | -0.010 |
udge | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -9.42e-01 |
Pos logit contributions | |
oph | +0.007 |
ll | +0.007 |
ory | +0.006 |
THE | +0.006 |
ari | +0.006 |
Neg logit contributions | |
rum | -0.014 |
pain | -0.013 |
ez | -0.012 |
mischief | -0.011 |
udge | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -5.80e-01 |
Pos logit contributions | |
ll | +0.013 |
oph | +0.012 |
THE | +0.011 |
ory | +0.011 |
upon | +0.011 |
Neg logit contributions | |
rum | -0.033 |
pain | -0.032 |
ez | -0.030 |
mischief | -0.029 |
udge | -0.028 |
Token | great |
Token ID | 1049 |
Feature activation | +5.76e-01 |
Pos logit contributions | |
oph | +0.016 |
ll | +0.016 |
ory | +0.015 |
ari | +0.014 |
THE | +0.014 |
Neg logit contributions | |
rum | -0.020 |
pain | -0.019 |
ez | -0.017 |
mischief | -0.016 |
aged | -0.016 |
Token | on |
Token ID | 319 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
rum | +0.017 |
pain | +0.015 |
udge | +0.015 |
ez | +0.015 |
aged | +0.013 |
Neg logit contributions | |
ll | -0.011 |
oph | -0.011 |
ory | -0.010 |
THE | -0.010 |
would | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -1.63e+00 |
Pos logit contributions | |
rum | +0.054 |
pain | +0.050 |
ez | +0.046 |
udge | +0.044 |
aged | +0.043 |
Neg logit contributions | |
ll | -0.032 |
oph | -0.032 |
ory | -0.030 |
THE | -0.030 |
upon | -0.029 |
Token | exam |
Token ID | 2814 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
ll | +0.036 |
oph | +0.036 |
ory | +0.034 |
ari | +0.033 |
THE | +0.033 |
Neg logit contributions | |
rum | -0.043 |
pain | -0.043 |
mischief | -0.037 |
ez | -0.036 |
aged | -0.034 |
Token | !" |
Token ID | 2474 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
rum | +0.039 |
pain | +0.037 |
ez | +0.034 |
mischief | +0.032 |
aged | +0.031 |
Neg logit contributions | |
ll | -0.025 |
oph | -0.025 |
ory | -0.023 |
THE | -0.022 |
ari | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
rum | +0.017 |
pain | +0.016 |
ez | +0.015 |
mischief | +0.014 |
udge | +0.014 |
Neg logit contributions | |
ll | -0.009 |
oph | -0.009 |
ory | -0.008 |
THE | -0.008 |
upon | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -6.97e-01 |
Pos logit contributions | |
ll | +0.005 |
oph | +0.005 |
ory | +0.005 |
THE | +0.005 |
ari | +0.005 |
Neg logit contributions | |
rum | -0.010 |
pain | -0.009 |
ez | -0.008 |
mischief | -0.008 |
aged | -0.008 |
Token | After |
Token ID | 3260 |
Feature activation | +6.92e-01 |
Pos logit contributions | |
ll | +0.015 |
oph | +0.015 |
THE | +0.014 |
ory | +0.014 |
ari | +0.013 |
Neg logit contributions | |
rum | -0.020 |
pain | -0.019 |
ez | -0.017 |
mischief | -0.017 |
aged | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
rum | +0.023 |
pain | +0.021 |
ez | +0.020 |
udge | +0.019 |
mischief | +0.018 |
Neg logit contributions | |
oph | -0.012 |
ll | -0.011 |
THE | -0.011 |
ory | -0.011 |
upon | -0.010 |
Token | exam |
Token ID | 2814 |
Feature activation | +3.75e+00 |
Pos logit contributions | |
oph | +0.021 |
ll | +0.021 |
ory | +0.020 |
THE | +0.020 |
ari | +0.020 |
Neg logit contributions | |
rum | -0.019 |
pain | -0.018 |
ez | -0.016 |
mischief | -0.015 |
aged | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -3.81e-01 |
Pos logit contributions | |
rum | +0.134 |
pain | +0.124 |
ez | +0.115 |
mischief | +0.113 |
udge | +0.111 |
Neg logit contributions | |
ll | -0.055 |
oph | -0.055 |
ari | -0.050 |
would | -0.048 |
ory | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
rum | +0.052 |
pain | +0.046 |
ez | +0.044 |
aged | +0.041 |
mischief | +0.040 |
Neg logit contributions | |
oph | -0.036 |
ll | -0.034 |
ory | -0.034 |
upon | -0.034 |
THE | -0.033 |
Token | cob |
Token ID | 22843 |
Feature activation | +9.70e-01 |
Pos logit contributions | |
ll | +0.075 |
oph | +0.075 |
ory | +0.070 |
THE | +0.069 |
upon | +0.068 |
Neg logit contributions | |
rum | -0.077 |
pain | -0.069 |
ez | -0.064 |
aged | -0.059 |
mischief | -0.059 |
Token | web |
Token ID | 12384 |
Feature activation | +6.13e-01 |
Pos logit contributions | |
rum | +0.022 |
pain | +0.020 |
mischief | +0.018 |
ez | +0.017 |
aged | +0.016 |
Neg logit contributions | |
ll | -0.027 |
THE | -0.025 |
arium | -0.025 |
oph | -0.024 |
upon | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | +2.87e-01 |
Pos logit contributions | |
rum | +0.018 |
pain | +0.017 |
ez | +0.015 |
mischief | +0.015 |
aged | +0.014 |
Neg logit contributions | |
ll | -0.012 |
oph | -0.012 |
ory | -0.011 |
THE | -0.011 |
arium | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
rum | +0.006 |
pain | +0.005 |
aged | +0.005 |
ez | +0.005 |
mischief | +0.005 |
Neg logit contributions | |
ory | -0.008 |
oph | -0.008 |
ll | -0.008 |
ari | -0.007 |
arium | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -5.50e-01 |
Pos logit contributions | |
ll | +0.008 |
oph | +0.007 |
ory | +0.007 |
THE | +0.007 |
upon | +0.007 |
Neg logit contributions | |
rum | -0.014 |
pain | -0.013 |
ez | -0.012 |
mischief | -0.011 |
aged | -0.011 |
Token | As |
Token ID | 1722 |
Feature activation | +5.90e-01 |
Pos logit contributions | |
ll | +0.013 |
ory | +0.013 |
oph | +0.013 |
ete | +0.012 |
ari | +0.012 |
Neg logit contributions | |
rum | -0.014 |
pain | -0.013 |
ez | -0.012 |
aged | -0.011 |
mischief | -0.011 |
Token | she |
Token ID | 673 |
Feature activation | +9.57e-01 |
Pos logit contributions | |
pain | +0.015 |
rum | +0.014 |
mischief | +0.013 |
ez | +0.012 |
aged | +0.012 |
Neg logit contributions | |
ll | -0.014 |
oph | -0.013 |
ari | -0.013 |
ory | -0.013 |
ocular | -0.012 |
Token | played |
Token ID | 2826 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
rum | +0.030 |
pain | +0.028 |
ez | +0.026 |
mischief | +0.024 |
aged | +0.024 |
Neg logit contributions | |
oph | -0.018 |
ll | -0.018 |
ory | -0.017 |
THE | -0.016 |
ari | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +2.64e-01 |
Pos logit contributions | |
rum | +0.016 |
ez | +0.015 |
pain | +0.014 |
udge | +0.014 |
mischief | +0.014 |
Neg logit contributions | |
THE | -0.006 |
arium | -0.006 |
ll | -0.005 |
upon | -0.005 |
would | -0.005 |
Token | she |
Token ID | 673 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
rum | +0.007 |
pain | +0.007 |
ez | +0.007 |
mischief | +0.006 |
aged | +0.006 |
Neg logit contributions | |
ll | -0.006 |
oph | -0.005 |
ory | -0.005 |
ari | -0.005 |
THE | -0.005 |
Token | delicious |
Token ID | 12625 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
pain | +0.035 |
rum | +0.035 |
mischief | +0.031 |
ez | +0.029 |
udge | +0.028 |
Neg logit contributions | |
ll | -0.025 |
oph | -0.025 |
ari | -0.023 |
ory | -0.023 |
ocular | -0.022 |
Token | meal |
Token ID | 9799 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
rum | +0.075 |
pain | +0.067 |
ez | +0.066 |
aged | +0.063 |
udge | +0.062 |
Neg logit contributions | |
oph | -0.032 |
ll | -0.031 |
ory | -0.030 |
arium | -0.026 |
THE | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | -8.37e-03 |
Pos logit contributions | |
oph | +0.018 |
ll | +0.018 |
ory | +0.017 |
ari | +0.016 |
THE | +0.016 |
Neg logit contributions | |
rum | -0.020 |
pain | -0.019 |
ez | -0.016 |
mischief | -0.016 |
udge | -0.016 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -9.71e-01 |
Pos logit contributions | |
ll | +0.000 |
ory | +0.000 |
oph | +0.000 |
arium | +0.000 |
ari | +0.000 |
Neg logit contributions | |
rum | -0.000 |
pain | -0.000 |
ez | -0.000 |
aged | -0.000 |
mischief | -0.000 |
Token | Once |
Token ID | 7454 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
oph | +0.022 |
ll | +0.021 |
ory | +0.021 |
ari | +0.019 |
THE | +0.019 |
Neg logit contributions | |
rum | -0.026 |
pain | -0.025 |
ez | -0.023 |
mischief | -0.021 |
udge | -0.021 |
Token | upon |
Token ID | 2402 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
oph | +0.009 |
ory | +0.007 |
THE | +0.007 |
als | +0.007 |
ll | +0.007 |
Neg logit contributions | |
rum | -0.038 |
pain | -0.036 |
udge | -0.033 |
ez | -0.033 |
mischief | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | +9.88e-01 |
Pos logit contributions | |
ll | +0.071 |
oph | +0.070 |
ory | +0.067 |
ari | +0.065 |
arium | +0.062 |
Neg logit contributions | |
rum | -0.079 |
pain | -0.077 |
ez | -0.068 |
mischief | -0.065 |
udge | -0.061 |
Token | time |
Token ID | 640 |
Feature activation | +8.19e-01 |
Pos logit contributions | |
rum | +0.023 |
pain | +0.022 |
ez | +0.019 |
mischief | +0.018 |
udge | +0.017 |
Neg logit contributions | |
ll | -0.025 |
oph | -0.025 |
ory | -0.024 |
THE | -0.024 |
ari | -0.024 |
Token | , |
Token ID | 11 |
Feature activation | -4.56e-01 |
Pos logit contributions | |
rum | +0.023 |
pain | +0.021 |
ez | +0.018 |
aged | +0.017 |
mischief | +0.017 |
Neg logit contributions | |
oph | -0.019 |
ory | -0.017 |
ll | -0.017 |
THE | -0.017 |
ari | -0.016 |
Token | there |
Token ID | 612 |
Feature activation | -2.16e-02 |
Pos logit contributions | |
ll | +0.008 |
oph | +0.008 |
ory | +0.008 |
upon | +0.008 |
THE | +0.007 |
Neg logit contributions | |
rum | -0.014 |
pain | -0.013 |
ez | -0.012 |
mischief | -0.012 |
udge | -0.012 |
Token | was |
Token ID | 373 |
Feature activation | -5.02e-01 |
Pos logit contributions | |
oph | +0.000 |
ll | +0.000 |
ory | +0.000 |
upon | +0.000 |
THE | +0.000 |
Neg logit contributions | |
rum | -0.001 |
pain | -0.001 |
ez | -0.001 |
mischief | -0.001 |
aged | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | +5.21e-01 |
Pos logit contributions | |
ll | +0.005 |
oph | +0.005 |
ory | +0.005 |
upon | +0.005 |
THE | +0.005 |
Neg logit contributions | |
rum | -0.008 |
pain | -0.007 |
ez | -0.007 |
mischief | -0.006 |
udge | -0.006 |
Token | He |
Token ID | 679 |
Feature activation | -4.47e-01 |
Pos logit contributions | |
rum | +0.013 |
pain | +0.012 |
ez | +0.010 |
mischief | +0.010 |
aged | +0.010 |
Neg logit contributions | |
ll | -0.013 |
oph | -0.013 |
ory | -0.012 |
THE | -0.012 |
ari | -0.012 |
Token | wanted |
Token ID | 2227 |
Feature activation | +3.59e-02 |
Pos logit contributions | |
oph | +0.011 |
ll | +0.010 |
ory | +0.010 |
THE | +0.010 |
ari | +0.010 |
Neg logit contributions | |
rum | -0.012 |
pain | -0.011 |
ez | -0.010 |
mischief | -0.009 |
aged | -0.009 |
Token | to |
Token ID | 284 |
Feature activation | +5.14e-01 |
Pos logit contributions | |
rum | +0.001 |
pain | +0.001 |
ez | +0.001 |
mischief | +0.001 |
aged | +0.001 |
Neg logit contributions | |
oph | -0.001 |
ll | -0.001 |
ory | -0.001 |
THE | -0.001 |
ari | -0.001 |
Token | touch |
Token ID | 3638 |
Feature activation | +7.68e-01 |
Pos logit contributions | |
rum | +0.016 |
pain | +0.015 |
ez | +0.014 |
aged | +0.013 |
mischief | +0.013 |
Neg logit contributions | |
oph | -0.009 |
ll | -0.009 |
ory | -0.009 |
of | -0.009 |
upon | -0.008 |
Token | it |
Token ID | 340 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
rum | +0.024 |
pain | +0.022 |
ez | +0.020 |
mischief | +0.020 |
aged | +0.020 |
Neg logit contributions | |
oph | -0.014 |
ll | -0.014 |
ory | -0.013 |
THE | -0.013 |
upon | -0.013 |
Token | but |
Token ID | 475 |
Feature activation | +6.09e-01 |
Pos logit contributions | |
oph | +0.051 |
ll | +0.051 |
ory | +0.047 |
THE | +0.046 |
ari | +0.046 |
Neg logit contributions | |
rum | -0.076 |
pain | -0.071 |
ez | -0.065 |
mischief | -0.062 |
udge | -0.061 |
Token | he |
Token ID | 339 |
Feature activation | +3.66e-01 |
Pos logit contributions | |
rum | +0.016 |
pain | +0.015 |
ez | +0.013 |
mischief | +0.012 |
aged | +0.012 |
Neg logit contributions | |
oph | -0.015 |
ll | -0.015 |
ari | -0.014 |
ory | -0.014 |
THE | -0.013 |
Token | was |
Token ID | 373 |
Feature activation | +9.27e-01 |
Pos logit contributions | |
rum | +0.012 |
pain | +0.011 |
ez | +0.010 |
aged | +0.010 |
mischief | +0.010 |
Neg logit contributions | |
oph | -0.006 |
ll | -0.006 |
ory | -0.006 |
THE | -0.006 |
ari | -0.006 |
Token | scared |
Token ID | 12008 |
Feature activation | +1.58e-01 |
Pos logit contributions | |
rum | +0.026 |
pain | +0.024 |
ez | +0.022 |
mischief | +0.021 |
udge | +0.021 |
Neg logit contributions | |
ll | -0.019 |
oph | -0.019 |
upon | -0.018 |
ory | -0.018 |
THE | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +7.79e-01 |
Pos logit contributions | |
rum | +0.005 |
pain | +0.005 |
ez | +0.005 |
mischief | +0.005 |
aged | +0.005 |
Neg logit contributions | |
ll | -0.002 |
upon | -0.002 |
ory | -0.002 |
oph | -0.002 |
would | -0.002 |
Token | " |
Token ID | 1 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
ll | +0.017 |
oph | +0.016 |
ory | +0.015 |
THE | +0.015 |
ari | +0.014 |
Neg logit contributions | |
rum | -0.032 |
pain | -0.030 |
ez | -0.028 |
mischief | -0.027 |
udge | -0.026 |
Token | I |
Token ID | 40 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
rum | +0.036 |
pain | +0.032 |
ez | +0.029 |
mischief | +0.029 |
aged | +0.028 |
Neg logit contributions | |
oph | -0.028 |
ll | -0.027 |
THE | -0.026 |
ory | -0.026 |
ari | -0.024 |
Token | 'm |
Token ID | 1101 |
Feature activation | -1.30e+00 |
Pos logit contributions | |
rum | +0.037 |
pain | +0.033 |
ez | +0.030 |
mischief | +0.029 |
aged | +0.028 |
Neg logit contributions | |
ll | -0.039 |
oph | -0.037 |
ory | -0.036 |
upon | -0.035 |
THE | -0.035 |
Token | sorry |
Token ID | 7926 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
oph | +0.037 |
ll | +0.036 |
ory | +0.035 |
ari | +0.034 |
THE | +0.033 |
Neg logit contributions | |
rum | -0.029 |
pain | -0.027 |
ez | -0.023 |
mischief | -0.022 |
aged | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
oph | +0.061 |
ll | +0.057 |
THE | +0.056 |
arium | +0.056 |
ari | +0.055 |
Neg logit contributions | |
rum | -0.063 |
pain | -0.060 |
mischief | -0.047 |
ez | -0.047 |
trouble | -0.046 |
Token | Tom |
Token ID | 4186 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
ll | +0.052 |
oph | +0.050 |
arium | +0.049 |
ory | +0.048 |
ari | +0.047 |
Neg logit contributions | |
pain | -0.043 |
rum | -0.040 |
ez | -0.031 |
trouble | -0.030 |
mischief | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
oph | +0.062 |
ll | +0.059 |
ory | +0.058 |
THE | +0.057 |
arium | +0.056 |
Neg logit contributions | |
rum | -0.063 |
pain | -0.059 |
ez | -0.051 |
aged | -0.047 |
mischief | -0.046 |
Token | Are |
Token ID | 4231 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
ll | +0.017 |
oph | +0.016 |
ory | +0.016 |
may | +0.015 |
ari | +0.015 |
Neg logit contributions | |
rum | -0.040 |
pain | -0.038 |
ez | -0.036 |
mischief | -0.035 |
udge | -0.034 |
Token | you |
Token ID | 345 |
Feature activation | -4.94e-01 |
Pos logit contributions | |
oph | +0.044 |
ari | +0.043 |
arium | +0.040 |
horizon | +0.039 |
ory | +0.038 |
Neg logit contributions | |
pain | -0.034 |
rum | -0.029 |
ez | -0.027 |
trouble | -0.025 |
aged | -0.025 |
Token | okay |
Token ID | 8788 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
oph | +0.011 |
ll | +0.010 |
ari | +0.010 |
arium | +0.009 |
ory | +0.009 |
Neg logit contributions | |
rum | -0.014 |
pain | -0.014 |
ez | -0.013 |
aged | -0.012 |
mischief | -0.012 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
rum | +0.009 |
pain | +0.008 |
ez | +0.008 |
mischief | +0.008 |
aged | +0.007 |
Neg logit contributions | |
ll | -0.003 |
upon | -0.003 |
oph | -0.003 |
ory | -0.003 |
would | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -9.57e-01 |
Pos logit contributions | |
rum | +0.017 |
pain | +0.016 |
ez | +0.015 |
mischief | +0.014 |
aged | +0.014 |
Neg logit contributions | |
ll | -0.010 |
oph | -0.010 |
upon | -0.009 |
ory | -0.009 |
THE | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
ll | +0.017 |
oph | +0.016 |
THE | +0.015 |
ory | +0.015 |
upon | +0.014 |
Neg logit contributions | |
rum | -0.031 |
pain | -0.029 |
ez | -0.027 |
mischief | -0.026 |
aged | -0.025 |
Token | " |
Token ID | 1 |
Feature activation | +8.14e-01 |
Pos logit contributions | |
ll | +0.015 |
oph | +0.014 |
THE | +0.014 |
upon | +0.013 |
ory | +0.013 |
Neg logit contributions | |
rum | -0.032 |
pain | -0.031 |
ez | -0.028 |
mischief | -0.028 |
aged | -0.027 |
Token | Tom |
Token ID | 13787 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
rum | +0.026 |
pain | +0.022 |
ez | +0.021 |
mischief | +0.021 |
aged | +0.020 |
Neg logit contributions | |
ll | -0.016 |
oph | -0.016 |
THE | -0.015 |
ory | -0.014 |
upon | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -2.07e+00 |
Pos logit contributions | |
oph | +0.033 |
THE | +0.032 |
arium | +0.031 |
ory | +0.031 |
ll | +0.030 |
Neg logit contributions | |
rum | -0.038 |
pain | -0.038 |
ez | -0.033 |
aged | -0.031 |
mischief | -0.028 |
Token | are |
Token ID | 389 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
oph | +0.041 |
ll | +0.040 |
ory | +0.037 |
ari | +0.035 |
THE | +0.035 |
Neg logit contributions | |
rum | -0.063 |
pain | -0.062 |
ez | -0.054 |
mischief | -0.052 |
udge | -0.050 |
Token | you |
Token ID | 345 |
Feature activation | -5.87e-01 |
Pos logit contributions | |
oph | +0.043 |
ll | +0.041 |
ory | +0.038 |
ari | +0.036 |
THE | +0.035 |
Neg logit contributions | |
rum | -0.100 |
pain | -0.097 |
ez | -0.089 |
mischief | -0.085 |
aged | -0.084 |
Token | OK |
Token ID | 7477 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
oph | +0.012 |
ll | +0.011 |
ory | +0.011 |
ari | +0.010 |
THE | +0.010 |
Neg logit contributions | |
rum | -0.018 |
pain | -0.017 |
ez | -0.015 |
mischief | -0.015 |
aged | -0.015 |
Token | ? |
Token ID | 30 |
Feature activation | -3.05e-01 |
Pos logit contributions | |
rum | +0.023 |
pain | +0.021 |
ez | +0.021 |
mischief | +0.020 |
aged | +0.020 |
Neg logit contributions | |
ll | -0.008 |
oph | -0.008 |
upon | -0.008 |
ory | -0.008 |
THE | -0.007 |
Token | I |
Token ID | 314 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
may | +0.005 |
upon | +0.005 |
ll | +0.004 |
would | +0.004 |
ory | +0.004 |
Neg logit contributions | |
rum | -0.010 |
pain | -0.009 |
mischief | -0.009 |
aged | -0.008 |
udge | -0.008 |
Token | told |
Token ID | 1297 |
Feature activation | -2.13e-01 |
Pos logit contributions | |
rum | +0.065 |
pain | +0.055 |
mischief | +0.053 |
aged | +0.052 |
elbows | +0.051 |
Neg logit contributions | |
ll | -0.044 |
would | -0.042 |
upon | -0.041 |
may | -0.038 |
'd | -0.038 |
Token | garden |
Token ID | 11376 |
Feature activation | -5.58e-01 |
Pos logit contributions | |
ll | +0.025 |
oph | +0.025 |
ory | +0.024 |
ari | +0.023 |
arium | +0.023 |
Neg logit contributions | |
rum | -0.025 |
pain | -0.025 |
ez | -0.021 |
mischief | -0.021 |
aged | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | +7.75e-01 |
Pos logit contributions | |
oph | +0.012 |
ll | +0.012 |
ory | +0.012 |
THE | +0.011 |
ari | +0.011 |
Neg logit contributions | |
rum | -0.015 |
pain | -0.014 |
aged | -0.012 |
ez | -0.012 |
mischief | -0.012 |
Token | help |
Token ID | 1037 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
rum | +0.021 |
pain | +0.020 |
ez | +0.018 |
mischief | +0.017 |
aged | +0.017 |
Neg logit contributions | |
oph | -0.017 |
ll | -0.017 |
ory | -0.016 |
THE | -0.016 |
ari | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
rum | +0.031 |
pain | +0.028 |
ez | +0.027 |
aged | +0.025 |
mischief | +0.024 |
Neg logit contributions | |
oph | -0.020 |
ll | -0.018 |
ory | -0.018 |
would | -0.017 |
upon | -0.017 |
Token | baby |
Token ID | 5156 |
Feature activation | -1.37e-01 |
Pos logit contributions | |
oph | +0.070 |
ll | +0.070 |
ory | +0.067 |
THE | +0.065 |
ari | +0.064 |
Neg logit contributions | |
rum | -0.058 |
pain | -0.053 |
ez | -0.047 |
mischief | -0.044 |
aged | -0.043 |
Token | birds |
Token ID | 10087 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
oph | +0.003 |
ll | +0.003 |
ory | +0.003 |
arium | +0.003 |
THE | +0.003 |
Neg logit contributions | |
rum | -0.004 |
pain | -0.003 |
ez | -0.003 |
aged | -0.003 |
mischief | -0.003 |
Token | hatch |
Token ID | 25834 |
Feature activation | -6.96e-01 |
Pos logit contributions | |
oph | +0.067 |
ll | +0.060 |
ory | +0.059 |
ari | +0.057 |
THE | +0.056 |
Neg logit contributions | |
rum | -0.067 |
pain | -0.063 |
ez | -0.056 |
aged | -0.053 |
mischief | -0.053 |
Token | ! |
Token ID | 0 |
Feature activation | +4.26e-01 |
Pos logit contributions | |
oph | +0.017 |
ll | +0.017 |
ory | +0.016 |
ari | +0.016 |
arium | +0.015 |
Neg logit contributions | |
rum | -0.017 |
pain | -0.016 |
aged | -0.014 |
ez | -0.014 |
mischief | -0.014 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
rum | +0.010 |
pain | +0.009 |
ez | +0.008 |
mischief | +0.008 |
udge | +0.008 |
Neg logit contributions | |
ll | -0.011 |
ory | -0.010 |
oph | -0.010 |
ari | -0.010 |
arium | -0.009 |
Token | Once |
Token ID | 7454 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
oph | +0.025 |
ll | +0.024 |
ory | +0.023 |
ari | +0.022 |
ocular | +0.021 |
Neg logit contributions | |
rum | -0.033 |
pain | -0.032 |
ez | -0.030 |
mischief | -0.028 |
udge | -0.027 |
Token | upon |
Token ID | 2402 |
Feature activation | -3.00e+00 |
Pos logit contributions | |
oph | +0.009 |
ory | +0.007 |
ll | +0.007 |
THE | +0.007 |
als | +0.006 |
Neg logit contributions | |
rum | -0.040 |
pain | -0.038 |
udge | -0.035 |
ez | -0.034 |
mischief | -0.034 |