Token | travel |
Token ID | 3067 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
atmeal | +0.027 |
ancer | +0.027 |
rolling | +0.025 |
lifetime | +0.025 |
ouses | +0.024 |
Neg logit contributions | |
screams | -0.025 |
rs | -0.025 |
bites | -0.023 |
rum | -0.023 |
irk | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +2.10e-01 |
Pos logit contributions | |
atmeal | +0.079 |
rolling | +0.075 |
ancer | +0.074 |
highlight | +0.072 |
lifetime | +0.071 |
Neg logit contributions | |
rs | -0.016 |
irk | -0.014 |
screams | -0.013 |
ks | -0.012 |
bites | -0.012 |
Token | She |
Token ID | 1375 |
Feature activation | +1.77e+00 |
Pos logit contributions | |
rolling | +0.006 |
atmeal | +0.006 |
ancer | +0.005 |
highlight | +0.005 |
lifetime | +0.005 |
Neg logit contributions | |
rs | -0.004 |
irk | -0.004 |
tant | -0.004 |
rum | -0.004 |
ez | -0.004 |
Token | put |
Token ID | 1234 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
atmeal | +0.052 |
highlight | +0.047 |
ancer | +0.047 |
pieces | +0.046 |
nam | +0.045 |
Neg logit contributions | |
screams | -0.032 |
thinks | -0.032 |
and | -0.031 |
ks | -0.031 |
irk | -0.030 |
Token | her |
Token ID | 607 |
Feature activation | +2.94e+00 |
Pos logit contributions | |
rolling | +0.075 |
atmeal | +0.072 |
lifetime | +0.069 |
ancer | +0.069 |
inations | +0.066 |
Neg logit contributions | |
rs | -0.052 |
irk | -0.049 |
bites | -0.048 |
ks | -0.047 |
and | -0.047 |
Token | shoes |
Token ID | 10012 |
Feature activation | +6.26e+00 |
Pos logit contributions | |
atmeal | +0.078 |
ancer | +0.071 |
rolling | +0.071 |
lifetime | +0.066 |
Hatt | +0.066 |
Neg logit contributions | |
screams | -0.060 |
irk | -0.057 |
rs | -0.057 |
bites | -0.057 |
thinks | -0.057 |
Token | on |
Token ID | 319 |
Feature activation | +4.07e-01 |
Pos logit contributions | |
atmeal | +0.216 |
pieces | +0.199 |
lifetime | +0.198 |
ancer | +0.195 |
ital | +0.194 |
Neg logit contributions | |
and | -0.103 |
. | -0.066 |
than | -0.064 |
control | -0.063 |
rs | -0.062 |
Token | and |
Token ID | 290 |
Feature activation | +2.71e+00 |
Pos logit contributions | |
atmeal | +0.011 |
rolling | +0.011 |
Hatt | +0.011 |
lifetime | +0.011 |
ancer | +0.010 |
Neg logit contributions | |
irk | -0.008 |
screams | -0.007 |
rum | -0.007 |
rs | -0.007 |
ez | -0.007 |
Token | he |
Token ID | 339 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
atmeal | +0.073 |
ancer | +0.071 |
rolling | +0.067 |
highlight | +0.066 |
lifetime | +0.066 |
Neg logit contributions | |
screams | -0.055 |
thinks | -0.053 |
and | -0.052 |
bites | -0.052 |
ks | -0.051 |
Token | checked |
Token ID | 10667 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
atmeal | +0.064 |
ancer | +0.059 |
highlight | +0.058 |
pieces | +0.058 |
oming | +0.055 |
Neg logit contributions | |
screams | -0.043 |
ks | -0.043 |
thinks | -0.042 |
and | -0.041 |
bites | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
atmeal | +0.038 |
rolling | +0.036 |
ancer | +0.035 |
lifetime | +0.034 |
ital | +0.034 |
Neg logit contributions | |
rs | -0.019 |
screams | -0.018 |
rum | -0.018 |
ks | -0.018 |
irk | -0.017 |
Token | Lily |
Token ID | 20037 |
Feature activation | +5.86e-01 |
Pos logit contributions | |
atmeal | +0.061 |
rolling | +0.057 |
ancer | +0.057 |
lifetime | +0.054 |
highlight | +0.053 |
Neg logit contributions | |
rs | -0.052 |
screams | -0.052 |
irk | -0.049 |
ks | -0.049 |
bites | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
atmeal | +0.014 |
rolling | +0.013 |
ancer | +0.013 |
lifetime | +0.013 |
highlight | +0.012 |
Neg logit contributions | |
rs | -0.013 |
screams | -0.013 |
irk | -0.013 |
rum | -0.012 |
bites | -0.012 |
Token | Max |
Token ID | 5436 |
Feature activation | +7.17e-02 |
Pos logit contributions | |
atmeal | +0.074 |
rolling | +0.071 |
ancer | +0.070 |
lifetime | +0.068 |
highlight | +0.067 |
Neg logit contributions | |
rs | -0.041 |
screams | -0.040 |
irk | -0.039 |
rum | -0.038 |
bites | -0.037 |
Token | put |
Token ID | 1234 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
atmeal | +0.002 |
rolling | +0.002 |
ancer | +0.001 |
lifetime | +0.001 |
Hatt | +0.001 |
Neg logit contributions | |
rs | -0.002 |
irk | -0.002 |
screams | -0.002 |
rum | -0.002 |
bites | -0.002 |
Token | their |
Token ID | 511 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
atmeal | +0.037 |
ancer | +0.034 |
rolling | +0.033 |
Hatt | +0.032 |
highlight | +0.032 |
Neg logit contributions | |
irk | -0.033 |
screams | -0.032 |
rs | -0.032 |
rum | -0.032 |
ks | -0.030 |
Token | shoes |
Token ID | 10012 |
Feature activation | +6.15e+00 |
Pos logit contributions | |
atmeal | +0.052 |
rolling | +0.049 |
ancer | +0.048 |
lifetime | +0.046 |
highlight | +0.046 |
Neg logit contributions | |
rs | -0.047 |
irk | -0.046 |
rum | -0.045 |
screams | -0.044 |
ks | -0.043 |
Token | back |
Token ID | 736 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
atmeal | +0.187 |
rolling | +0.175 |
lifetime | +0.173 |
ancer | +0.170 |
Hatt | +0.166 |
Neg logit contributions | |
and | -0.103 |
rs | -0.099 |
tant | -0.091 |
ks | -0.088 |
bites | -0.087 |
Token | on |
Token ID | 319 |
Feature activation | -6.29e-01 |
Pos logit contributions | |
atmeal | +0.089 |
rolling | +0.082 |
ancer | +0.081 |
lifetime | +0.079 |
Hatt | +0.079 |
Neg logit contributions | |
rs | -0.060 |
ks | -0.056 |
screams | -0.055 |
bites | -0.053 |
rum | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
irk | +0.017 |
screams | +0.015 |
rum | +0.015 |
ez | +0.015 |
thinks | +0.015 |
Neg logit contributions | |
Hatt | -0.013 |
nam | -0.012 |
Eve | -0.012 |
rolling | -0.011 |
pieces | -0.011 |
Token | went |
Token ID | 1816 |
Feature activation | +2.42e+00 |
Pos logit contributions | |
atmeal | +0.091 |
ancer | +0.089 |
rolling | +0.087 |
lifetime | +0.083 |
highlight | +0.083 |
Neg logit contributions | |
screams | -0.072 |
rs | -0.070 |
bites | -0.069 |
ks | -0.068 |
thinks | -0.067 |
Token | home |
Token ID | 1363 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
atmeal | +0.079 |
highlight | +0.074 |
ancer | +0.073 |
rolling | +0.071 |
lifetime | +0.071 |
Neg logit contributions | |
rs | -0.038 |
ks | -0.033 |
bites | -0.033 |
and | -0.033 |
screams | -0.033 |
Token | Can |
Token ID | 6090 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
atmeal | +0.053 |
rolling | +0.052 |
ancer | +0.050 |
lifetime | +0.047 |
Hatt | +0.047 |
Neg logit contributions | |
rs | -0.034 |
Mine | -0.032 |
irk | -0.031 |
screams | -0.030 |
aron | -0.030 |
Token | I |
Token ID | 314 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
atmeal | +0.084 |
rolling | +0.082 |
lifetime | +0.081 |
ouses | +0.080 |
inations | +0.079 |
Neg logit contributions | |
and | -0.041 |
Mine | -0.041 |
Tom | -0.041 |
dog | -0.039 |
thinks | -0.038 |
Token | put |
Token ID | 1234 |
Feature activation | +2.61e+00 |
Pos logit contributions | |
lifetime | +0.074 |
atmeal | +0.073 |
ancer | +0.073 |
rolling | +0.072 |
nam | +0.070 |
Neg logit contributions | |
rs | -0.049 |
and | -0.048 |
bites | -0.048 |
screams | -0.045 |
word | -0.045 |
Token | the |
Token ID | 262 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
rolling | +0.083 |
atmeal | +0.080 |
lifetime | +0.079 |
ancer | +0.078 |
ital | +0.074 |
Neg logit contributions | |
rs | -0.043 |
bites | -0.040 |
screams | -0.037 |
thinks | -0.037 |
tant | -0.036 |
Token | cup |
Token ID | 6508 |
Feature activation | +5.21e+00 |
Pos logit contributions | |
rolling | +0.055 |
atmeal | +0.055 |
ancer | +0.052 |
lifetime | +0.051 |
Hatt | +0.049 |
Neg logit contributions | |
screams | -0.049 |
rs | -0.049 |
bites | -0.048 |
thinks | -0.047 |
word | -0.046 |
Token | cakes |
Token ID | 37263 |
Feature activation | +6.01e+00 |
Pos logit contributions | |
rolling | +0.113 |
lifetime | +0.107 |
ancer | +0.104 |
atmeal | +0.103 |
Hatt | +0.098 |
Neg logit contributions | |
rs | -0.132 |
bites | -0.126 |
tant | -0.123 |
and | -0.121 |
irk | -0.120 |
Token | in |
Token ID | 287 |
Feature activation | +9.34e-01 |
Pos logit contributions | |
rolling | +0.185 |
lifetime | +0.177 |
ancer | +0.173 |
atmeal | +0.173 |
Hatt | +0.167 |
Neg logit contributions | |
and | -0.098 |
rs | -0.098 |
bites | -0.089 |
tant | -0.086 |
aron | -0.084 |
Token | the |
Token ID | 262 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
atmeal | +0.027 |
rolling | +0.026 |
ancer | +0.026 |
lifetime | +0.025 |
highlight | +0.024 |
Neg logit contributions | |
rs | -0.017 |
screams | -0.016 |
irk | -0.016 |
rum | -0.015 |
bites | -0.015 |
Token | oven |
Token ID | 14361 |
Feature activation | +3.59e+00 |
Pos logit contributions | |
rolling | +0.061 |
ancer | +0.061 |
atmeal | +0.060 |
Hatt | +0.056 |
lifetime | +0.055 |
Neg logit contributions | |
rs | -0.043 |
screams | -0.042 |
bites | -0.042 |
word | -0.041 |
irk | -0.040 |
Token | ?" |
Token ID | 1701 |
Feature activation | -7.76e-01 |
Pos logit contributions | |
atmeal | +0.090 |
rolling | +0.087 |
ancer | +0.085 |
lifetime | +0.082 |
highlight | +0.080 |
Neg logit contributions | |
rs | -0.077 |
screams | -0.074 |
irk | -0.073 |
bites | -0.071 |
rum | -0.071 |
Token | June |
Token ID | 2795 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
screams | +0.019 |
rs | +0.018 |
irk | +0.018 |
bites | +0.017 |
rum | +0.017 |
Neg logit contributions | |
atmeal | -0.019 |
ancer | -0.017 |
rolling | -0.017 |
lifetime | -0.016 |
highlight | -0.016 |
Token | let |
Token ID | 1309 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
atmeal | +0.086 |
rolling | +0.083 |
ancer | +0.081 |
lifetime | +0.077 |
inations | +0.076 |
Neg logit contributions | |
rs | -0.051 |
thinks | -0.050 |
screams | -0.049 |
and | -0.048 |
bites | -0.047 |
Token | 's |
Token ID | 338 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
atmeal | +0.061 |
rolling | +0.059 |
ancer | +0.059 |
lifetime | +0.057 |
highlight | +0.055 |
Neg logit contributions | |
screams | -0.040 |
rs | -0.039 |
irk | -0.038 |
bites | -0.037 |
rum | -0.037 |
Token | get |
Token ID | 651 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
ancer | +0.085 |
lifetime | +0.084 |
atmeal | +0.082 |
angers | +0.079 |
rolling | +0.079 |
Neg logit contributions | |
and | -0.051 |
control | -0.048 |
thinks | -0.048 |
screams | -0.048 |
Mine | -0.046 |
Token | the |
Token ID | 262 |
Feature activation | +1.95e+00 |
Pos logit contributions | |
rolling | +0.073 |
atmeal | +0.073 |
ancer | +0.071 |
lifetime | +0.070 |
ital | +0.069 |
Neg logit contributions | |
bites | -0.024 |
and | -0.022 |
his | -0.022 |
blood | -0.022 |
its | -0.022 |
Token | orange |
Token ID | 10912 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
atmeal | +0.047 |
rolling | +0.045 |
ancer | +0.043 |
lifetime | +0.042 |
Hatt | +0.040 |
Neg logit contributions | |
rs | -0.044 |
screams | -0.043 |
irk | -0.043 |
bites | -0.042 |
thinks | -0.041 |
Token | shoes |
Token ID | 10012 |
Feature activation | +5.92e+00 |
Pos logit contributions | |
atmeal | +0.048 |
ancer | +0.043 |
rolling | +0.043 |
highlight | +0.041 |
lifetime | +0.041 |
Neg logit contributions | |
rs | -0.049 |
screams | -0.048 |
irk | -0.048 |
rum | -0.047 |
ks | -0.047 |
Token | !" |
Token ID | 2474 |
Feature activation | +7.57e-01 |
Pos logit contributions | |
atmeal | +0.181 |
rolling | +0.175 |
ancer | +0.170 |
lifetime | +0.167 |
Hatt | +0.165 |
Neg logit contributions | |
rs | -0.094 |
irk | -0.085 |
screams | -0.085 |
bites | -0.082 |
rum | -0.082 |
Token |
|
Token ID | 198 |
Feature activation | +7.52e-01 |
Pos logit contributions | |
atmeal | +0.019 |
rolling | +0.019 |
ancer | +0.018 |
Hatt | +0.017 |
lifetime | +0.017 |
Neg logit contributions | |
rum | -0.016 |
screams | -0.015 |
rs | -0.015 |
irk | -0.015 |
ks | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | +1.66e+00 |
Pos logit contributions | |
atmeal | +0.020 |
rolling | +0.020 |
ancer | +0.018 |
lifetime | +0.018 |
Hatt | +0.018 |
Neg logit contributions | |
rs | -0.015 |
screams | -0.014 |
irk | -0.014 |
bites | -0.014 |
rum | -0.014 |
Token | The |
Token ID | 464 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
atmeal | +0.043 |
rolling | +0.040 |
ancer | +0.040 |
lifetime | +0.038 |
highlight | +0.038 |
Neg logit contributions | |
rs | -0.036 |
screams | -0.035 |
irk | -0.034 |
rum | -0.033 |
bites | -0.033 |
Token | mom |
Token ID | 1995 |
Feature activation | +8.90e-02 |
Pos logit contributions | |
atmeal | +0.069 |
rolling | +0.064 |
ancer | +0.064 |
inations | +0.060 |
ouses | +0.060 |
Neg logit contributions | |
screams | -0.030 |
words | -0.028 |
thinks | -0.028 |
irk | -0.027 |
bites | -0.027 |
Token | park |
Token ID | 3952 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
atmeal | +0.028 |
rolling | +0.027 |
ancer | +0.027 |
ouses | +0.025 |
Hatt | +0.025 |
Neg logit contributions | |
screams | -0.025 |
rs | -0.024 |
bites | -0.023 |
irk | -0.023 |
thinks | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +1.07e+00 |
Pos logit contributions | |
atmeal | +0.069 |
rolling | +0.066 |
ancer | +0.066 |
lifetime | +0.064 |
highlight | +0.063 |
Neg logit contributions | |
rs | -0.017 |
irk | -0.016 |
screams | -0.016 |
rum | -0.014 |
ks | -0.014 |
Token | She |
Token ID | 1375 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
atmeal | +0.032 |
rolling | +0.030 |
ancer | +0.030 |
lifetime | +0.029 |
highlight | +0.029 |
Neg logit contributions | |
rs | -0.018 |
irk | -0.017 |
screams | -0.017 |
rum | -0.017 |
bites | -0.016 |
Token | put |
Token ID | 1234 |
Feature activation | +2.76e+00 |
Pos logit contributions | |
atmeal | +0.048 |
ancer | +0.045 |
highlight | +0.043 |
rolling | +0.043 |
lifetime | +0.042 |
Neg logit contributions | |
screams | -0.035 |
rs | -0.034 |
thinks | -0.033 |
bites | -0.033 |
irk | -0.033 |
Token | her |
Token ID | 607 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
rolling | +0.076 |
atmeal | +0.075 |
lifetime | +0.073 |
ancer | +0.072 |
inations | +0.068 |
Neg logit contributions | |
rs | -0.055 |
bites | -0.053 |
irk | -0.051 |
screams | -0.050 |
ks | -0.049 |
Token | shoes |
Token ID | 10012 |
Feature activation | +5.91e+00 |
Pos logit contributions | |
atmeal | +0.080 |
rolling | +0.076 |
ancer | +0.075 |
lifetime | +0.072 |
Hatt | +0.071 |
Neg logit contributions | |
screams | -0.064 |
rs | -0.063 |
irk | -0.061 |
bites | -0.060 |
rum | -0.059 |
Token | on |
Token ID | 319 |
Feature activation | +1.46e-02 |
Pos logit contributions | |
atmeal | +0.200 |
lifetime | +0.187 |
ancer | +0.182 |
pieces | +0.182 |
rolling | +0.180 |
Neg logit contributions | |
and | -0.094 |
rs | -0.072 |
tant | -0.063 |
than | -0.061 |
bites | -0.061 |
Token | and |
Token ID | 290 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
Hatt | +0.000 |
rolling | +0.000 |
atmeal | +0.000 |
nam | +0.000 |
ancer | +0.000 |
Neg logit contributions | |
irk | -0.000 |
rum | -0.000 |
screams | -0.000 |
ks | -0.000 |
ez | -0.000 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.91e+00 |
Pos logit contributions | |
atmeal | +0.080 |
ancer | +0.079 |
rolling | +0.075 |
lifetime | +0.074 |
highlight | +0.074 |
Neg logit contributions | |
screams | -0.062 |
bites | -0.061 |
thinks | -0.059 |
and | -0.058 |
rs | -0.057 |
Token | outside |
Token ID | 2354 |
Feature activation | +1.35e+00 |
Pos logit contributions | |
atmeal | +0.048 |
rolling | +0.046 |
ancer | +0.045 |
lifetime | +0.043 |
Hatt | +0.043 |
Neg logit contributions | |
rs | -0.040 |
irk | -0.040 |
screams | -0.040 |
rum | -0.039 |
bites | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
rolling | +0.044 |
atmeal | +0.044 |
ancer | +0.043 |
lifetime | +0.041 |
Hatt | +0.041 |
Neg logit contributions | |
irk | -0.018 |
rs | -0.018 |
screams | -0.017 |
rum | -0.017 |
bites | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
atmeal | +0.012 |
ancer | +0.011 |
lifetime | +0.011 |
ail | +0.011 |
Hatt | +0.011 |
Neg logit contributions | |
tant | -0.008 |
screams | -0.008 |
Mine | -0.008 |
irk | -0.008 |
rs | -0.007 |
Token | Let |
Token ID | 3914 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
atmeal | +0.090 |
inations | +0.081 |
rolling | +0.081 |
lifetime | +0.079 |
ital | +0.077 |
Neg logit contributions | |
rs | -0.033 |
thinks | -0.026 |
Mine | -0.026 |
irk | -0.024 |
It | -0.024 |
Token | 's |
Token ID | 338 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
atmeal | +0.041 |
rolling | +0.039 |
ancer | +0.039 |
lifetime | +0.037 |
highlight | +0.036 |
Neg logit contributions | |
screams | -0.026 |
rs | -0.026 |
irk | -0.025 |
bites | -0.024 |
thinks | -0.024 |
Token | put |
Token ID | 1234 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
atmeal | +0.062 |
ancer | +0.061 |
lifetime | +0.060 |
rolling | +0.057 |
ouses | +0.056 |
Neg logit contributions | |
rs | -0.044 |
thinks | -0.043 |
screams | -0.043 |
Mine | -0.043 |
and | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
rolling | +0.077 |
atmeal | +0.077 |
ancer | +0.073 |
lifetime | +0.072 |
highlight | +0.069 |
Neg logit contributions | |
rs | -0.045 |
bites | -0.042 |
screams | -0.040 |
thinks | -0.039 |
irk | -0.038 |
Token | carrots |
Token ID | 34397 |
Feature activation | +5.85e+00 |
Pos logit contributions | |
atmeal | +0.047 |
rolling | +0.044 |
ancer | +0.043 |
lifetime | +0.041 |
highlight | +0.040 |
Neg logit contributions | |
rs | -0.062 |
screams | -0.061 |
irk | -0.061 |
rum | -0.059 |
bites | -0.058 |
Token | in |
Token ID | 287 |
Feature activation | +6.38e-01 |
Pos logit contributions | |
atmeal | +0.159 |
rolling | +0.155 |
ancer | +0.147 |
lifetime | +0.146 |
Hatt | +0.142 |
Neg logit contributions | |
rs | -0.116 |
screams | -0.106 |
bites | -0.106 |
rum | -0.105 |
irk | -0.105 |
Token | one |
Token ID | 530 |
Feature activation | +3.74e+00 |
Pos logit contributions | |
atmeal | +0.017 |
rolling | +0.016 |
ancer | +0.016 |
lifetime | +0.016 |
highlight | +0.016 |
Neg logit contributions | |
irk | -0.012 |
screams | -0.012 |
rs | -0.012 |
rum | -0.012 |
ks | -0.011 |
Token | pile |
Token ID | 14540 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
atmeal | +0.103 |
rolling | +0.102 |
ancer | +0.098 |
Hatt | +0.095 |
lifetime | +0.094 |
Neg logit contributions | |
rs | -0.070 |
irk | -0.067 |
bites | -0.066 |
screams | -0.066 |
rum | -0.065 |
Token | and |
Token ID | 290 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
atmeal | +0.073 |
ancer | +0.070 |
rolling | +0.067 |
lifetime | +0.066 |
highlight | +0.065 |
Neg logit contributions | |
screams | -0.041 |
irk | -0.041 |
rs | -0.039 |
rum | -0.038 |
bites | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
rolling | +0.105 |
atmeal | +0.104 |
ancer | +0.103 |
lifetime | +0.100 |
ouses | +0.094 |
Neg logit contributions | |
bites | -0.083 |
rs | -0.078 |
and | -0.078 |
thinks | -0.077 |
screams | -0.076 |
Token | " |
Token ID | 366 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
atmeal | +0.013 |
ancer | +0.012 |
rolling | +0.012 |
lifetime | +0.012 |
highlight | +0.011 |
Neg logit contributions | |
rs | -0.006 |
screams | -0.006 |
irk | -0.006 |
thinks | -0.006 |
bites | -0.005 |
Token | Can |
Token ID | 6090 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
atmeal | +0.058 |
rolling | +0.055 |
ancer | +0.054 |
lifetime | +0.052 |
Hatt | +0.051 |
Neg logit contributions | |
rs | -0.043 |
irk | -0.041 |
Mine | -0.040 |
screams | -0.040 |
bites | -0.039 |
Token | I |
Token ID | 314 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
inations | +0.088 |
lifetime | +0.086 |
atmeal | +0.086 |
rolling | +0.084 |
ouses | +0.083 |
Neg logit contributions | |
dog | -0.037 |
words | -0.031 |
Tom | -0.031 |
and | -0.030 |
screams | -0.029 |
Token | wear |
Token ID | 5806 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
lifetime | +0.064 |
atmeal | +0.063 |
ations | +0.059 |
nam | +0.059 |
ths | +0.059 |
Neg logit contributions | |
and | -0.057 |
bites | -0.049 |
dog | -0.048 |
thinks | -0.046 |
rs | -0.046 |
Token | my |
Token ID | 616 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
atmeal | +0.072 |
rolling | +0.070 |
ancer | +0.069 |
lifetime | +0.068 |
highlight | +0.065 |
Neg logit contributions | |
rs | -0.028 |
bites | -0.025 |
and | -0.024 |
thinks | -0.023 |
its | -0.023 |
Token | sunglasses |
Token ID | 36251 |
Feature activation | +5.84e+00 |
Pos logit contributions | |
atmeal | +0.045 |
rolling | +0.043 |
ancer | +0.042 |
lifetime | +0.040 |
Hatt | +0.039 |
Neg logit contributions | |
rs | -0.047 |
screams | -0.046 |
irk | -0.045 |
rum | -0.044 |
bites | -0.044 |
Token | , |
Token ID | 11 |
Feature activation | +2.38e+00 |
Pos logit contributions | |
atmeal | +0.168 |
rolling | +0.163 |
lifetime | +0.162 |
highlight | +0.156 |
pieces | +0.156 |
Neg logit contributions | |
rs | -0.096 |
and | -0.094 |
tant | -0.091 |
bites | -0.088 |
irk | -0.088 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
atmeal | +0.064 |
rolling | +0.063 |
lifetime | +0.060 |
ancer | +0.059 |
ital | +0.057 |
Neg logit contributions | |
rs | -0.047 |
screams | -0.046 |
irk | -0.045 |
thinks | -0.044 |
word | -0.044 |
Token | ?" |
Token ID | 1701 |
Feature activation | -8.46e-01 |
Pos logit contributions | |
rolling | +0.074 |
atmeal | +0.073 |
lifetime | +0.069 |
highlight | +0.068 |
ancer | +0.068 |
Neg logit contributions | |
rs | -0.068 |
irk | -0.065 |
and | -0.063 |
rum | -0.063 |
thinks | -0.063 |
Token | she |
Token ID | 673 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
screams | +0.018 |
bites | +0.017 |
irk | +0.017 |
thinks | +0.016 |
rs | +0.016 |
Neg logit contributions | |
atmeal | -0.023 |
highlight | -0.021 |
ancer | -0.021 |
lifetime | -0.021 |
rolling | -0.021 |
Token | asked |
Token ID | 1965 |
Feature activation | +4.67e-01 |
Pos logit contributions | |
screams | +0.034 |
rs | +0.033 |
irk | +0.032 |
rum | +0.031 |
bites | +0.031 |
Neg logit contributions | |
atmeal | -0.045 |
rolling | -0.042 |
ancer | -0.042 |
highlight | -0.041 |
lifetime | -0.041 |
Token | outside |
Token ID | 2354 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
atmeal | +0.088 |
nam | +0.086 |
highlight | +0.085 |
lifetime | +0.084 |
Hatt | +0.082 |
Neg logit contributions | |
and | -0.038 |
. | -0.029 |
to | -0.026 |
bites | -0.026 |
his | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
atmeal | +0.048 |
rolling | +0.047 |
ancer | +0.046 |
lifetime | +0.045 |
Hatt | +0.044 |
Neg logit contributions | |
rs | -0.016 |
irk | -0.016 |
screams | -0.016 |
rum | -0.015 |
bites | -0.014 |
Token | He |
Token ID | 679 |
Feature activation | +5.57e-01 |
Pos logit contributions | |
rs | +0.022 |
irk | +0.021 |
ez | +0.021 |
ks | +0.020 |
screams | +0.020 |
Neg logit contributions | |
rolling | -0.034 |
atmeal | -0.033 |
ancer | -0.033 |
highlight | -0.031 |
lifetime | -0.031 |
Token | put |
Token ID | 1234 |
Feature activation | +1.62e+00 |
Pos logit contributions | |
atmeal | +0.014 |
ancer | +0.013 |
rolling | +0.013 |
highlight | +0.013 |
lifetime | +0.013 |
Neg logit contributions | |
screams | -0.012 |
rs | -0.012 |
irk | -0.011 |
bites | -0.011 |
thinks | -0.011 |
Token | his |
Token ID | 465 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
rolling | +0.043 |
atmeal | +0.043 |
ancer | +0.041 |
lifetime | +0.041 |
highlight | +0.039 |
Neg logit contributions | |
rs | -0.033 |
bites | -0.031 |
screams | -0.031 |
irk | -0.031 |
rum | -0.030 |
Token | shoes |
Token ID | 10012 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
atmeal | +0.063 |
rolling | +0.060 |
ancer | +0.059 |
lifetime | +0.056 |
Hatt | +0.055 |
Neg logit contributions | |
rs | -0.053 |
screams | -0.052 |
irk | -0.051 |
rum | -0.050 |
bites | -0.049 |
Token | on |
Token ID | 319 |
Feature activation | -6.21e-01 |
Pos logit contributions | |
atmeal | +0.185 |
lifetime | +0.173 |
pieces | +0.171 |
ancer | +0.168 |
ital | +0.167 |
Neg logit contributions | |
and | -0.102 |
rs | -0.080 |
tant | -0.075 |
control | -0.074 |
bites | -0.073 |
Token | and |
Token ID | 290 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
irk | +0.014 |
screams | +0.012 |
ks | +0.012 |
rum | +0.012 |
rs | +0.012 |
Neg logit contributions | |
atmeal | -0.016 |
rolling | -0.015 |
Hatt | -0.015 |
nam | -0.015 |
ancer | -0.015 |
Token | ran |
Token ID | 4966 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
atmeal | +0.068 |
ancer | +0.068 |
rolling | +0.066 |
lifetime | +0.063 |
highlight | +0.063 |
Neg logit contributions | |
screams | -0.050 |
bites | -0.049 |
thinks | -0.047 |
rs | -0.047 |
and | -0.046 |
Token | to |
Token ID | 284 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
atmeal | +0.029 |
rolling | +0.029 |
ancer | +0.027 |
lifetime | +0.026 |
Hatt | +0.026 |
Neg logit contributions | |
irk | -0.031 |
rs | -0.031 |
screams | -0.031 |
rum | -0.030 |
ks | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +8.22e-01 |
Pos logit contributions | |
rs | +0.003 |
screams | +0.002 |
irk | +0.002 |
rum | +0.002 |
bites | +0.002 |
Neg logit contributions | |
atmeal | -0.005 |
rolling | -0.004 |
ancer | -0.004 |
lifetime | -0.004 |
highlight | -0.004 |
Token | need |
Token ID | 761 |
Feature activation | +9.17e-01 |
Pos logit contributions | |
atmeal | +0.009 |
rolling | +0.008 |
ancer | +0.008 |
lifetime | +0.008 |
highlight | +0.008 |
Neg logit contributions | |
rs | -0.006 |
screams | -0.006 |
irk | -0.006 |
rum | -0.006 |
bites | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
atmeal | +0.031 |
rolling | +0.030 |
ancer | +0.029 |
lifetime | +0.028 |
highlight | +0.028 |
Neg logit contributions | |
rs | -0.013 |
screams | -0.012 |
bites | -0.011 |
rum | -0.011 |
irk | -0.011 |
Token | pack |
Token ID | 2353 |
Feature activation | +2.46e+00 |
Pos logit contributions | |
atmeal | +0.017 |
ancer | +0.016 |
rolling | +0.016 |
lifetime | +0.015 |
highlight | +0.015 |
Neg logit contributions | |
rs | -0.018 |
screams | -0.017 |
rum | -0.017 |
irk | -0.017 |
bites | -0.017 |
Token | these |
Token ID | 777 |
Feature activation | +3.13e+00 |
Pos logit contributions | |
atmeal | +0.073 |
rolling | +0.073 |
ancer | +0.070 |
lifetime | +0.068 |
highlight | +0.066 |
Neg logit contributions | |
rs | -0.043 |
screams | -0.039 |
bites | -0.039 |
rum | -0.038 |
ks | -0.037 |
Token | m |
Token ID | 285 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
atmeal | +0.079 |
rolling | +0.077 |
ancer | +0.074 |
lifetime | +0.071 |
pieces | +0.070 |
Neg logit contributions | |
rs | -0.066 |
screams | -0.064 |
bites | -0.064 |
thinks | -0.062 |
rum | -0.061 |
Token | ittens |
Token ID | 34978 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
nam | +0.068 |
lifetime | +0.066 |
rolling | +0.065 |
highlight | +0.064 |
atmeal | +0.063 |
Neg logit contributions | |
rum | -0.133 |
rs | -0.130 |
screams | -0.130 |
ud | -0.129 |
aron | -0.125 |
Token | so |
Token ID | 523 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
atmeal | +0.184 |
rolling | +0.178 |
ancer | +0.174 |
lifetime | +0.171 |
highlight | +0.168 |
Neg logit contributions | |
rs | -0.085 |
screams | -0.081 |
rum | -0.078 |
irk | -0.078 |
bites | -0.075 |
Token | they |
Token ID | 484 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
atmeal | +0.090 |
rolling | +0.088 |
pieces | +0.085 |
ital | +0.085 |
highlight | +0.083 |
Neg logit contributions | |
screams | -0.068 |
bites | -0.066 |
rum | -0.066 |
ks | -0.066 |
thinks | -0.065 |
Token | stay |
Token ID | 2652 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
atmeal | +0.094 |
rolling | +0.093 |
lifetime | +0.088 |
pieces | +0.086 |
ancer | +0.085 |
Neg logit contributions | |
thinks | -0.049 |
rs | -0.049 |
bites | -0.048 |
screams | -0.046 |
and | -0.045 |
Token | safe |
Token ID | 3338 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
atmeal | +0.065 |
ancer | +0.059 |
rolling | +0.058 |
highlight | +0.056 |
pieces | +0.056 |
Neg logit contributions | |
rs | -0.042 |
and | -0.040 |
rum | -0.038 |
bites | -0.038 |
aron | -0.038 |
Token | on |
Token ID | 319 |
Feature activation | +7.69e-01 |
Pos logit contributions | |
atmeal | +0.047 |
ancer | +0.045 |
rolling | +0.045 |
lifetime | +0.044 |
highlight | +0.043 |
Neg logit contributions | |
irk | -0.022 |
screams | -0.021 |
rs | -0.021 |
rum | -0.020 |
bites | -0.019 |
Token | , |
Token ID | 11 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
rolling | +0.098 |
atmeal | +0.095 |
ancer | +0.093 |
belt | +0.090 |
inations | +0.089 |
Neg logit contributions | |
and | -0.013 |
. | -0.009 |
its | -0.007 |
thinks | -0.005 |
each | -0.004 |
Token | they |
Token ID | 484 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
rolling | +0.113 |
atmeal | +0.107 |
lifetime | +0.105 |
inations | +0.103 |
adows | +0.097 |
Neg logit contributions | |
and | -0.043 |
its | -0.042 |
dog | -0.041 |
Tom | -0.039 |
Mine | -0.038 |
Token | would |
Token ID | 561 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
rolling | +0.076 |
ancer | +0.075 |
atmeal | +0.074 |
lifetime | +0.072 |
ital | +0.068 |
Neg logit contributions | |
rs | -0.069 |
bites | -0.068 |
thinks | -0.067 |
screams | -0.065 |
and | -0.065 |
Token | put |
Token ID | 1234 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
atmeal | +0.048 |
ancer | +0.046 |
rolling | +0.045 |
lifetime | +0.043 |
Hatt | +0.041 |
Neg logit contributions | |
rs | -0.062 |
screams | -0.060 |
irk | -0.058 |
bites | -0.058 |
rum | -0.058 |
Token | the |
Token ID | 262 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
rolling | +0.077 |
atmeal | +0.076 |
lifetime | +0.073 |
ancer | +0.073 |
ital | +0.069 |
Neg logit contributions | |
rs | -0.042 |
bites | -0.040 |
screams | -0.038 |
tant | -0.037 |
thinks | -0.037 |
Token | cookies |
Token ID | 14746 |
Feature activation | +5.78e+00 |
Pos logit contributions | |
rolling | +0.080 |
lifetime | +0.074 |
atmeal | +0.074 |
ancer | +0.072 |
Hatt | +0.069 |
Neg logit contributions | |
bites | -0.065 |
words | -0.062 |
screams | -0.062 |
word | -0.061 |
tant | -0.061 |
Token | in |
Token ID | 287 |
Feature activation | -3.65e-02 |
Pos logit contributions | |
rolling | +0.162 |
atmeal | +0.162 |
ancer | +0.156 |
lifetime | +0.156 |
Hatt | +0.147 |
Neg logit contributions | |
rs | -0.107 |
and | -0.104 |
bites | -0.099 |
ks | -0.095 |
aron | -0.093 |
Token | the |
Token ID | 262 |
Feature activation | +2.69e+00 |
Pos logit contributions | |
irk | +0.001 |
screams | +0.001 |
rs | +0.001 |
rum | +0.001 |
ks | +0.001 |
Neg logit contributions | |
atmeal | -0.001 |
rolling | -0.001 |
Hatt | -0.001 |
highlight | -0.001 |
ancer | -0.001 |
Token | oven |
Token ID | 14361 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
atmeal | +0.068 |
rolling | +0.067 |
ancer | +0.066 |
lifetime | +0.063 |
Hatt | +0.061 |
Neg logit contributions | |
rs | -0.056 |
screams | -0.055 |
irk | -0.054 |
bites | -0.054 |
tant | -0.052 |
Token | to |
Token ID | 284 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
atmeal | +0.083 |
ancer | +0.076 |
rolling | +0.076 |
lifetime | +0.074 |
ouses | +0.073 |
Neg logit contributions | |
rum | -0.038 |
irk | -0.038 |
screams | -0.038 |
rs | -0.036 |
ez | -0.034 |
Token | bake |
Token ID | 28450 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
rolling | +0.040 |
ancer | +0.040 |
lifetime | +0.038 |
atmeal | +0.038 |
ouses | +0.035 |
Neg logit contributions | |
rs | -0.035 |
bites | -0.033 |
screams | -0.032 |
thinks | -0.031 |
Mine | -0.031 |
Token | " |
Token ID | 366 |
Feature activation | -2.85e-01 |
Pos logit contributions | |
atmeal | +0.053 |
rolling | +0.050 |
ancer | +0.049 |
lifetime | +0.048 |
highlight | +0.048 |
Neg logit contributions | |
rs | -0.022 |
screams | -0.020 |
irk | -0.020 |
ks | -0.019 |
rum | -0.019 |
Token | Let |
Token ID | 5756 |
Feature activation | +3.94e-01 |
Pos logit contributions | |
rs | +0.006 |
screams | +0.006 |
rum | +0.006 |
irk | +0.006 |
bites | +0.005 |
Neg logit contributions | |
atmeal | -0.008 |
rolling | -0.007 |
ancer | -0.007 |
lifetime | -0.007 |
highlight | -0.007 |
Token | 's |
Token ID | 338 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
atmeal | +0.008 |
rolling | +0.008 |
ancer | +0.007 |
Hatt | +0.007 |
highlight | +0.007 |
Neg logit contributions | |
rs | -0.010 |
irk | -0.010 |
rum | -0.010 |
ks | -0.010 |
screams | -0.009 |
Token | put |
Token ID | 1234 |
Feature activation | +2.10e+00 |
Pos logit contributions | |
atmeal | +0.040 |
ancer | +0.040 |
lifetime | +0.038 |
rolling | +0.038 |
Hatt | +0.036 |
Neg logit contributions | |
rs | -0.038 |
screams | -0.038 |
bites | -0.037 |
rum | -0.037 |
thinks | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | +1.89e+00 |
Pos logit contributions | |
atmeal | +0.066 |
rolling | +0.064 |
ancer | +0.062 |
lifetime | +0.061 |
highlight | +0.059 |
Neg logit contributions | |
rs | -0.035 |
screams | -0.032 |
bites | -0.032 |
ks | -0.030 |
thinks | -0.030 |
Token | blocks |
Token ID | 7021 |
Feature activation | +5.75e+00 |
Pos logit contributions | |
atmeal | +0.048 |
rolling | +0.046 |
ancer | +0.045 |
lifetime | +0.043 |
Hatt | +0.042 |
Neg logit contributions | |
screams | -0.040 |
rs | -0.040 |
irk | -0.039 |
bites | -0.038 |
rum | -0.038 |
Token | in |
Token ID | 287 |
Feature activation | +1.62e-01 |
Pos logit contributions | |
atmeal | +0.155 |
rolling | +0.150 |
ancer | +0.145 |
lifetime | +0.143 |
Hatt | +0.139 |
Neg logit contributions | |
rs | -0.114 |
bites | -0.105 |
screams | -0.105 |
irk | -0.105 |
rum | -0.104 |
Token | a |
Token ID | 257 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
atmeal | +0.004 |
rolling | +0.004 |
Hatt | +0.004 |
nam | +0.004 |
lifetime | +0.004 |
Neg logit contributions | |
irk | -0.004 |
screams | -0.004 |
rum | -0.003 |
rs | -0.003 |
ks | -0.003 |
Token | z |
Token ID | 1976 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
atmeal | +0.029 |
ancer | +0.028 |
rolling | +0.027 |
Hatt | +0.026 |
highlight | +0.025 |
Neg logit contributions | |
rs | -0.020 |
screams | -0.020 |
irk | -0.019 |
bites | -0.019 |
tant | -0.019 |
Token | ig |
Token ID | 328 |
Feature activation | +2.86e+00 |
Pos logit contributions | |
atmeal | +0.025 |
rolling | +0.022 |
ancer | +0.021 |
lifetime | +0.019 |
highlight | +0.018 |
Neg logit contributions | |
rs | -0.079 |
screams | -0.077 |
irk | -0.077 |
rum | -0.076 |
bites | -0.075 |
Token | zag |
Token ID | 50183 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
atmeal | +0.055 |
ancer | +0.049 |
rolling | +0.048 |
ital | +0.044 |
lifetime | +0.043 |
Neg logit contributions | |
irk | -0.083 |
screams | -0.081 |
rs | -0.080 |
rum | -0.077 |
bites | -0.076 |
Token | the |
Token ID | 262 |
Feature activation | +7.10e-01 |
Pos logit contributions | |
irk | +0.004 |
rum | +0.004 |
rs | +0.004 |
screams | +0.004 |
aron | +0.004 |
Neg logit contributions | |
atmeal | -0.005 |
rolling | -0.005 |
highlight | -0.005 |
lifetime | -0.005 |
ancer | -0.005 |
Token | towel |
Token ID | 24808 |
Feature activation | +2.01e+00 |
Pos logit contributions | |
atmeal | +0.018 |
rolling | +0.017 |
ancer | +0.017 |
lifetime | +0.016 |
highlight | +0.016 |
Neg logit contributions | |
rs | -0.015 |
screams | -0.015 |
irk | -0.015 |
rum | -0.014 |
ks | -0.014 |
Token | and |
Token ID | 290 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
rolling | +0.063 |
atmeal | +0.062 |
ancer | +0.059 |
lifetime | +0.059 |
ail | +0.057 |
Neg logit contributions | |
irk | -0.030 |
rs | -0.029 |
rum | -0.028 |
screams | -0.028 |
Mine | -0.027 |
Token | put |
Token ID | 1234 |
Feature activation | +1.78e+00 |
Pos logit contributions | |
atmeal | +0.055 |
rolling | +0.053 |
ancer | +0.053 |
lifetime | +0.050 |
highlight | +0.049 |
Neg logit contributions | |
screams | -0.047 |
rs | -0.047 |
bites | -0.045 |
ks | -0.044 |
irk | -0.043 |
Token | their |
Token ID | 511 |
Feature activation | +2.75e+00 |
Pos logit contributions | |
atmeal | +0.052 |
rolling | +0.050 |
ancer | +0.049 |
lifetime | +0.047 |
highlight | +0.047 |
Neg logit contributions | |
rs | -0.031 |
screams | -0.030 |
irk | -0.030 |
rum | -0.029 |
bites | -0.028 |
Token | shoes |
Token ID | 10012 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
atmeal | +0.075 |
rolling | +0.071 |
ancer | +0.070 |
lifetime | +0.068 |
highlight | +0.067 |
Neg logit contributions | |
rs | -0.054 |
screams | -0.052 |
irk | -0.052 |
rum | -0.050 |
bites | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
atmeal | +0.190 |
rolling | +0.176 |
ancer | +0.176 |
lifetime | +0.175 |
Hatt | +0.171 |
Neg logit contributions | |
and | -0.082 |
rs | -0.078 |
tant | -0.071 |
control | -0.067 |
bites | -0.065 |
Token | socks |
Token ID | 24359 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
atmeal | +0.083 |
ancer | +0.083 |
rolling | +0.081 |
lifetime | +0.076 |
highlight | +0.074 |
Neg logit contributions | |
screams | -0.065 |
rs | -0.064 |
bites | -0.064 |
ks | -0.060 |
thinks | -0.060 |
Token | back |
Token ID | 736 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
atmeal | +0.106 |
rolling | +0.101 |
ancer | +0.099 |
lifetime | +0.095 |
highlight | +0.094 |
Neg logit contributions | |
rs | -0.077 |
screams | -0.076 |
irk | -0.075 |
rum | -0.073 |
bites | -0.071 |
Token | on |
Token ID | 319 |
Feature activation | -2.14e-01 |
Pos logit contributions | |
atmeal | +0.069 |
rolling | +0.066 |
ancer | +0.065 |
lifetime | +0.062 |
highlight | +0.061 |
Neg logit contributions | |
rs | -0.049 |
screams | -0.047 |
irk | -0.047 |
rum | -0.045 |
bites | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +1.66e-01 |
Pos logit contributions | |
irk | +0.006 |
screams | +0.005 |
rum | +0.005 |
ez | +0.005 |
thinks | +0.005 |
Neg logit contributions | |
rolling | -0.004 |
Hatt | -0.004 |
nam | -0.004 |
highlight | -0.004 |
atmeal | -0.004 |
Token | She |
Token ID | 1375 |
Feature activation | +5.38e-01 |
Pos logit contributions | |
atmeal | +0.012 |
rolling | +0.011 |
ancer | +0.011 |
lifetime | +0.011 |
highlight | +0.011 |
Neg logit contributions | |
rs | -0.009 |
irk | -0.008 |
screams | -0.008 |
rum | -0.008 |
ks | -0.008 |
Token | also |
Token ID | 635 |
Feature activation | +3.57e-01 |
Pos logit contributions | |
atmeal | +0.015 |
ancer | +0.014 |
rolling | +0.014 |
highlight | +0.014 |
lifetime | +0.014 |
Neg logit contributions | |
screams | -0.010 |
thinks | -0.010 |
bites | -0.010 |
rs | -0.010 |
ks | -0.010 |
Token | put |
Token ID | 1234 |
Feature activation | +2.11e+00 |
Pos logit contributions | |
atmeal | +0.009 |
rolling | +0.009 |
ancer | +0.009 |
lifetime | +0.008 |
highlight | +0.008 |
Neg logit contributions | |
rs | -0.008 |
screams | -0.007 |
irk | -0.007 |
bites | -0.007 |
ks | -0.007 |
Token | some |
Token ID | 617 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
rolling | +0.063 |
atmeal | +0.060 |
lifetime | +0.059 |
ancer | +0.056 |
inations | +0.055 |
Neg logit contributions | |
rs | -0.039 |
bites | -0.037 |
ks | -0.035 |
words | -0.035 |
tant | -0.035 |
Token | lip |
Token ID | 10645 |
Feature activation | +2.53e+00 |
Pos logit contributions | |
rolling | +0.053 |
atmeal | +0.052 |
ancer | +0.050 |
lifetime | +0.049 |
Hatt | +0.047 |
Neg logit contributions | |
bites | -0.038 |
screams | -0.038 |
rs | -0.038 |
tant | -0.037 |
words | -0.037 |
Token | bal |
Token ID | 3652 |
Feature activation | +5.74e+00 |
Pos logit contributions | |
rolling | +0.065 |
atmeal | +0.065 |
ancer | +0.064 |
lifetime | +0.064 |
highlight | +0.062 |
Neg logit contributions | |
rs | -0.049 |
bites | -0.048 |
screams | -0.048 |
ks | -0.048 |
words | -0.046 |
Token | m |
Token ID | 76 |
Feature activation | +1.32e-01 |
Pos logit contributions | |
lifetime | +0.174 |
happiest | +0.168 |
rolling | +0.164 |
Hatt | +0.162 |
ital | +0.161 |
Neg logit contributions | |
rs | -0.091 |
ks | -0.087 |
ud | -0.082 |
irk | -0.080 |
ez | -0.078 |
Token | on |
Token ID | 319 |
Feature activation | -3.77e-01 |
Pos logit contributions | |
atmeal | +0.003 |
ancer | +0.003 |
rolling | +0.003 |
highlight | +0.002 |
lifetime | +0.002 |
Neg logit contributions | |
rs | -0.003 |
screams | -0.003 |
irk | -0.003 |
rum | -0.003 |
bites | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | +1.50e+00 |
Pos logit contributions | |
irk | +0.009 |
rum | +0.008 |
rs | +0.008 |
screams | +0.008 |
ks | +0.008 |
Neg logit contributions | |
atmeal | -0.008 |
rolling | -0.008 |
Hatt | -0.008 |
nam | -0.008 |
exploring | -0.007 |
Token | lips |
Token ID | 11914 |
Feature activation | +1.36e+00 |
Pos logit contributions | |
atmeal | +0.041 |
rolling | +0.038 |
ancer | +0.038 |
lifetime | +0.036 |
highlight | +0.036 |
Neg logit contributions | |
rs | -0.030 |
screams | -0.029 |
irk | -0.029 |
rum | -0.028 |
bites | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -2.91e-01 |
Pos logit contributions | |
atmeal | +0.044 |
ancer | +0.042 |
rolling | +0.041 |
ouses | +0.039 |
Hatt | +0.039 |
Neg logit contributions | |
screams | -0.020 |
irk | -0.020 |
rs | -0.019 |
rum | -0.019 |
bites | -0.018 |
Token | . |
Token ID | 13 |
Feature activation | +1.23e+00 |
Pos logit contributions | |
atmeal | +0.011 |
ancer | +0.010 |
rolling | +0.010 |
lifetime | +0.010 |
ital | +0.010 |
Neg logit contributions | |
irk | -0.004 |
screams | -0.004 |
rs | -0.004 |
rum | -0.004 |
tant | -0.004 |
Token | Let |
Token ID | 3914 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
atmeal | +0.042 |
rolling | +0.039 |
lifetime | +0.037 |
ail | +0.037 |
ital | +0.037 |
Neg logit contributions | |
rs | -0.020 |
screams | -0.017 |
ks | -0.016 |
thinks | -0.016 |
irk | -0.016 |
Token | 's |
Token ID | 338 |
Feature activation | +2.32e+00 |
Pos logit contributions | |
atmeal | +0.025 |
rolling | +0.023 |
ancer | +0.023 |
lifetime | +0.022 |
highlight | +0.022 |
Neg logit contributions | |
rs | -0.023 |
irk | -0.023 |
rum | -0.022 |
screams | -0.022 |
ks | -0.021 |
Token | put |
Token ID | 1234 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
ancer | +0.061 |
atmeal | +0.061 |
lifetime | +0.059 |
rolling | +0.058 |
ouses | +0.056 |
Neg logit contributions | |
rs | -0.045 |
screams | -0.045 |
thinks | -0.043 |
bites | -0.043 |
rum | -0.042 |
Token | our |
Token ID | 674 |
Feature activation | +3.07e+00 |
Pos logit contributions | |
atmeal | +0.068 |
rolling | +0.067 |
ancer | +0.064 |
lifetime | +0.063 |
highlight | +0.061 |
Neg logit contributions | |
rs | -0.039 |
screams | -0.036 |
bites | -0.036 |
ks | -0.035 |
thinks | -0.034 |
Token | toys |
Token ID | 14958 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
atmeal | +0.080 |
rolling | +0.078 |
ancer | +0.078 |
lifetime | +0.073 |
Hatt | +0.072 |
Neg logit contributions | |
screams | -0.063 |
bites | -0.061 |
rs | -0.060 |
thinks | -0.059 |
rum | -0.057 |
Token | inside |
Token ID | 2641 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
atmeal | +0.165 |
rolling | +0.163 |
ancer | +0.154 |
lifetime | +0.153 |
Hatt | +0.150 |
Neg logit contributions | |
rs | -0.106 |
and | -0.098 |
bites | -0.096 |
ks | -0.094 |
tant | -0.092 |
Token | and |
Token ID | 290 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
atmeal | +0.076 |
rolling | +0.073 |
ancer | +0.072 |
lifetime | +0.069 |
highlight | +0.069 |
Neg logit contributions | |
rs | -0.030 |
screams | -0.029 |
irk | -0.029 |
rum | -0.027 |
bites | -0.026 |
Token | play |
Token ID | 711 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
ancer | +0.112 |
atmeal | +0.111 |
rolling | +0.109 |
lifetime | +0.105 |
oming | +0.102 |
Neg logit contributions | |
screams | -0.076 |
bites | -0.075 |
rs | -0.074 |
thinks | -0.073 |
and | -0.072 |
Token | ." |
Token ID | 526 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
atmeal | +0.012 |
rolling | +0.012 |
ancer | +0.012 |
highlight | +0.011 |
lifetime | +0.011 |
Neg logit contributions | |
rs | -0.007 |
screams | -0.006 |
ks | -0.006 |
bites | -0.006 |
rum | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | -5.14e-01 |
Pos logit contributions | |
rs | +0.015 |
screams | +0.014 |
rum | +0.014 |
irk | +0.014 |
ks | +0.013 |
Neg logit contributions | |
atmeal | -0.029 |
rolling | -0.028 |
ancer | -0.027 |
Hatt | -0.026 |
lifetime | -0.026 |
Token | then |
Token ID | 788 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
atmeal | +0.083 |
rolling | +0.074 |
ancer | +0.071 |
lifetime | +0.067 |
ouses | +0.067 |
Neg logit contributions | |
screams | -0.070 |
thinks | -0.069 |
and | -0.068 |
rs | -0.068 |
ks | -0.067 |
Token | we |
Token ID | 356 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
atmeal | +0.058 |
rolling | +0.055 |
ancer | +0.053 |
highlight | +0.052 |
lifetime | +0.050 |
Neg logit contributions | |
screams | -0.051 |
bites | -0.050 |
thinks | -0.050 |
rs | -0.050 |
and | -0.048 |
Token | can |
Token ID | 460 |
Feature activation | +9.73e-01 |
Pos logit contributions | |
atmeal | +0.041 |
rolling | +0.039 |
ancer | +0.038 |
lifetime | +0.038 |
highlight | +0.036 |
Neg logit contributions | |
rs | -0.025 |
screams | -0.024 |
bites | -0.023 |
thinks | -0.023 |
irk | -0.023 |
Token | put |
Token ID | 1234 |
Feature activation | +1.79e+00 |
Pos logit contributions | |
atmeal | +0.024 |
lifetime | +0.023 |
ancer | +0.023 |
rolling | +0.022 |
nam | +0.022 |
Neg logit contributions | |
screams | -0.021 |
rs | -0.021 |
bites | -0.020 |
thinks | -0.020 |
rum | -0.019 |
Token | our |
Token ID | 674 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
atmeal | +0.055 |
rolling | +0.053 |
ancer | +0.051 |
lifetime | +0.050 |
highlight | +0.048 |
Neg logit contributions | |
rs | -0.031 |
screams | -0.029 |
bites | -0.028 |
irk | -0.028 |
ks | -0.028 |
Token | shoes |
Token ID | 10012 |
Feature activation | +5.72e+00 |
Pos logit contributions | |
atmeal | +0.064 |
rolling | +0.060 |
ancer | +0.059 |
lifetime | +0.056 |
highlight | +0.055 |
Neg logit contributions | |
rs | -0.075 |
screams | -0.073 |
irk | -0.073 |
rum | -0.071 |
bites | -0.070 |
Token | and |
Token ID | 290 |
Feature activation | +3.32e+00 |
Pos logit contributions | |
atmeal | +0.179 |
rolling | +0.174 |
lifetime | +0.170 |
ancer | +0.167 |
Hatt | +0.164 |
Neg logit contributions | |
and | -0.091 |
rs | -0.090 |
bites | -0.079 |
tant | -0.079 |
ater | -0.079 |
Token | socks |
Token ID | 24359 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
atmeal | +0.084 |
ancer | +0.081 |
rolling | +0.081 |
lifetime | +0.077 |
highlight | +0.074 |
Neg logit contributions | |
rs | -0.073 |
screams | -0.073 |
bites | -0.071 |
thinks | -0.069 |
ks | -0.066 |
Token | back |
Token ID | 736 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
atmeal | +0.092 |
rolling | +0.087 |
ancer | +0.087 |
lifetime | +0.082 |
highlight | +0.081 |
Neg logit contributions | |
rs | -0.078 |
irk | -0.077 |
screams | -0.077 |
rum | -0.075 |
bites | -0.072 |
Token | on |
Token ID | 319 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
atmeal | +0.068 |
rolling | +0.064 |
ancer | +0.064 |
lifetime | +0.061 |
highlight | +0.060 |
Neg logit contributions | |
rs | -0.045 |
screams | -0.044 |
irk | -0.043 |
rum | -0.042 |
bites | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
atmeal | +0.000 |
ancer | +0.000 |
rolling | +0.000 |
igs | +0.000 |
nam | +0.000 |
Neg logit contributions | |
irk | -0.000 |
screams | -0.000 |
rum | -0.000 |
rs | -0.000 |
ks | -0.000 |
Token | First |
Token ID | 3274 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
atmeal | +0.014 |
rolling | +0.014 |
ancer | +0.013 |
Hatt | +0.013 |
highlight | +0.012 |
Neg logit contributions | |
rs | -0.011 |
screams | -0.011 |
irk | -0.011 |
rum | -0.011 |
bites | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | +2.72e+00 |
Pos logit contributions | |
atmeal | +0.073 |
rolling | +0.071 |
ancer | +0.070 |
highlight | +0.068 |
lifetime | +0.068 |
Neg logit contributions | |
screams | -0.038 |
rs | -0.036 |
bites | -0.036 |
and | -0.035 |
thinks | -0.035 |
Token | she |
Token ID | 673 |
Feature activation | +1.52e+00 |
Pos logit contributions | |
atmeal | +0.052 |
rolling | +0.049 |
lifetime | +0.048 |
ancer | +0.048 |
ital | +0.045 |
Neg logit contributions | |
screams | -0.073 |
bites | -0.071 |
rs | -0.070 |
ks | -0.070 |
thinks | -0.070 |
Token | put |
Token ID | 1234 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
atmeal | +0.038 |
ancer | +0.036 |
rolling | +0.035 |
highlight | +0.034 |
lifetime | +0.034 |
Neg logit contributions | |
screams | -0.032 |
rs | -0.032 |
bites | -0.031 |
irk | -0.031 |
thinks | -0.031 |
Token | her |
Token ID | 607 |
Feature activation | +3.97e+00 |
Pos logit contributions | |
rolling | +0.082 |
atmeal | +0.079 |
lifetime | +0.077 |
ancer | +0.075 |
inations | +0.073 |
Neg logit contributions | |
rs | -0.051 |
bites | -0.048 |
tant | -0.047 |
and | -0.047 |
irk | -0.047 |
Token | sunglasses |
Token ID | 36251 |
Feature activation | +5.70e+00 |
Pos logit contributions | |
atmeal | +0.095 |
rolling | +0.090 |
ancer | +0.087 |
lifetime | +0.083 |
Hatt | +0.081 |
Neg logit contributions | |
screams | -0.087 |
rs | -0.087 |
tant | -0.086 |
bites | -0.086 |
irk | -0.083 |
Token | into |
Token ID | 656 |
Feature activation | -6.74e-01 |
Pos logit contributions | |
atmeal | +0.162 |
rolling | +0.150 |
ancer | +0.148 |
lifetime | +0.147 |
pieces | +0.146 |
Neg logit contributions | |
and | -0.100 |
rs | -0.100 |
tant | -0.090 |
bites | -0.089 |
irk | -0.087 |
Token | her |
Token ID | 607 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
rs | +0.011 |
screams | +0.011 |
irk | +0.011 |
rum | +0.011 |
bites | +0.010 |
Neg logit contributions | |
atmeal | -0.020 |
rolling | -0.019 |
ancer | -0.019 |
lifetime | -0.018 |
highlight | -0.018 |
Token | bag |
Token ID | 6131 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
atmeal | +0.084 |
ancer | +0.080 |
rolling | +0.078 |
Hatt | +0.074 |
inations | +0.073 |
Neg logit contributions | |
screams | -0.061 |
rs | -0.061 |
bites | -0.061 |
tant | -0.059 |
irk | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | +1.05e-01 |
Pos logit contributions | |
atmeal | +0.100 |
rolling | +0.095 |
ancer | +0.095 |
lifetime | +0.092 |
ouses | +0.090 |
Neg logit contributions | |
screams | -0.033 |
rs | -0.032 |
irk | -0.031 |
rum | -0.029 |
bites | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
atmeal | +0.003 |
rolling | +0.003 |
ancer | +0.003 |
lifetime | +0.003 |
highlight | +0.003 |
Neg logit contributions | |
rs | -0.002 |
screams | -0.002 |
irk | -0.002 |
rum | -0.002 |
bites | -0.002 |
Token | park |
Token ID | 3952 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
atmeal | +0.041 |
inations | +0.041 |
ancer | +0.040 |
ouses | +0.038 |
pieces | +0.038 |
Neg logit contributions | |
screams | -0.017 |
irk | -0.016 |
dog | -0.016 |
word | -0.016 |
bites | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | +2.97e-01 |
Pos logit contributions | |
atmeal | +0.046 |
rolling | +0.044 |
ancer | +0.044 |
lifetime | +0.042 |
highlight | +0.042 |
Neg logit contributions | |
rs | -0.013 |
irk | -0.013 |
screams | -0.013 |
rum | -0.012 |
bites | -0.011 |
Token | She |
Token ID | 1375 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
atmeal | +0.010 |
ancer | +0.009 |
lifetime | +0.009 |
highlight | +0.009 |
rolling | +0.009 |
Neg logit contributions | |
screams | -0.004 |
rs | -0.004 |
irk | -0.004 |
bites | -0.004 |
thinks | -0.004 |
Token | put |
Token ID | 1234 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
atmeal | +0.037 |
highlight | +0.034 |
pieces | +0.034 |
ancer | +0.033 |
lifetime | +0.032 |
Neg logit contributions | |
thinks | -0.020 |
and | -0.019 |
screams | -0.019 |
bites | -0.019 |
ks | -0.019 |
Token | her |
Token ID | 607 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
rolling | +0.074 |
atmeal | +0.072 |
lifetime | +0.071 |
ancer | +0.068 |
inations | +0.068 |
Neg logit contributions | |
rs | -0.050 |
bites | -0.048 |
irk | -0.046 |
screams | -0.046 |
and | -0.045 |
Token | shoes |
Token ID | 10012 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
atmeal | +0.063 |
rolling | +0.059 |
ancer | +0.058 |
lifetime | +0.056 |
Hatt | +0.055 |
Neg logit contributions | |
screams | -0.055 |
rs | -0.054 |
irk | -0.053 |
bites | -0.052 |
tant | -0.051 |
Token | on |
Token ID | 319 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
atmeal | +0.195 |
lifetime | +0.182 |
pieces | +0.179 |
ancer | +0.177 |
rolling | +0.174 |
Neg logit contributions | |
and | -0.094 |
rs | -0.069 |
tant | -0.060 |
control | -0.060 |
. | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
Hatt | +0.003 |
rolling | +0.003 |
atmeal | +0.003 |
ancer | +0.003 |
nam | +0.003 |
Neg logit contributions | |
irk | -0.002 |
rum | -0.002 |
screams | -0.002 |
rs | -0.002 |
ks | -0.002 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
atmeal | +0.080 |
ancer | +0.079 |
lifetime | +0.076 |
highlight | +0.075 |
oming | +0.075 |
Neg logit contributions | |
screams | -0.052 |
bites | -0.051 |
and | -0.051 |
thinks | -0.050 |
ks | -0.047 |
Token | her |
Token ID | 607 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
atmeal | +0.012 |
rolling | +0.012 |
ancer | +0.012 |
lifetime | +0.011 |
highlight | +0.011 |
Neg logit contributions | |
rs | -0.007 |
screams | -0.006 |
irk | -0.006 |
bites | -0.006 |
rum | -0.006 |
Token | toy |
Token ID | 13373 |
Feature activation | +2.03e+00 |
Pos logit contributions | |
atmeal | +0.053 |
rolling | +0.049 |
ancer | +0.048 |
lifetime | +0.046 |
highlight | +0.046 |
Neg logit contributions | |
rs | -0.059 |
irk | -0.057 |
screams | -0.057 |
rum | -0.056 |
ks | -0.054 |
Token | " |
Token ID | 366 |
Feature activation | -7.17e-01 |
Pos logit contributions | |
ater | +0.058 |
rs | +0.055 |
irk | +0.053 |
ez | +0.053 |
rum | +0.051 |
Neg logit contributions | |
rolling | -0.057 |
Hatt | -0.055 |
ancer | -0.054 |
Kirst | -0.051 |
ouses | -0.050 |
Token | We |
Token ID | 1135 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
rs | +0.019 |
screams | +0.018 |
rum | +0.018 |
irk | +0.018 |
bites | +0.017 |
Neg logit contributions | |
atmeal | -0.015 |
ancer | -0.014 |
rolling | -0.014 |
highlight | -0.013 |
lifetime | -0.013 |
Token | can |
Token ID | 460 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
atmeal | +0.035 |
rolling | +0.034 |
ancer | +0.033 |
lifetime | +0.032 |
highlight | +0.031 |
Neg logit contributions | |
rs | -0.021 |
screams | -0.020 |
bites | -0.019 |
irk | -0.019 |
thinks | -0.019 |
Token | put |
Token ID | 1234 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
atmeal | +0.029 |
ancer | +0.028 |
lifetime | +0.028 |
rolling | +0.027 |
highlight | +0.027 |
Neg logit contributions | |
screams | -0.028 |
rs | -0.028 |
bites | -0.027 |
thinks | -0.027 |
rum | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
rolling | +0.086 |
atmeal | +0.084 |
lifetime | +0.082 |
ancer | +0.081 |
highlight | +0.077 |
Neg logit contributions | |
rs | -0.039 |
bites | -0.037 |
and | -0.035 |
words | -0.035 |
ks | -0.035 |
Token | boxes |
Token ID | 10559 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
atmeal | +0.065 |
rolling | +0.063 |
ancer | +0.060 |
lifetime | +0.060 |
ital | +0.058 |
Neg logit contributions | |
words | -0.037 |
word | -0.036 |
screams | -0.035 |
bites | -0.035 |
thinks | -0.034 |
Token | on |
Token ID | 319 |
Feature activation | +9.41e-01 |
Pos logit contributions | |
atmeal | +0.168 |
rolling | +0.160 |
lifetime | +0.154 |
ancer | +0.152 |
Hatt | +0.149 |
Neg logit contributions | |
rs | -0.101 |
and | -0.097 |
bites | -0.091 |
ks | -0.089 |
rum | -0.088 |
Token | top |
Token ID | 1353 |
Feature activation | +3.16e+00 |
Pos logit contributions | |
atmeal | +0.024 |
rolling | +0.022 |
ancer | +0.022 |
Hatt | +0.022 |
highlight | +0.021 |
Neg logit contributions | |
irk | -0.021 |
screams | -0.019 |
rs | -0.019 |
rum | -0.018 |
ks | -0.018 |
Token | of |
Token ID | 286 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
atmeal | +0.099 |
rolling | +0.095 |
ancer | +0.094 |
lifetime | +0.091 |
highlight | +0.089 |
Neg logit contributions | |
rs | -0.049 |
screams | -0.047 |
irk | -0.047 |
rum | -0.045 |
bites | -0.044 |
Token | each |
Token ID | 1123 |
Feature activation | +2.39e+00 |
Pos logit contributions | |
atmeal | +0.017 |
rolling | +0.016 |
ancer | +0.016 |
lifetime | +0.015 |
highlight | +0.015 |
Neg logit contributions | |
rs | -0.009 |
screams | -0.009 |
irk | -0.008 |
rum | -0.008 |
bites | -0.008 |
Token | other |
Token ID | 584 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
atmeal | +0.062 |
rolling | +0.058 |
ancer | +0.058 |
lifetime | +0.055 |
highlight | +0.054 |
Neg logit contributions | |
rs | -0.051 |
irk | -0.050 |
screams | -0.049 |
rum | -0.047 |
ks | -0.046 |
Token | She |
Token ID | 1375 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
atmeal | +0.015 |
rolling | +0.014 |
lifetime | +0.013 |
ancer | +0.013 |
inations | +0.013 |
Neg logit contributions | |
rs | -0.008 |
irk | -0.007 |
screams | -0.007 |
thinks | -0.007 |
bites | -0.007 |
Token | would |
Token ID | 561 |
Feature activation | +1.68e+00 |
Pos logit contributions | |
atmeal | +0.025 |
ancer | +0.025 |
rolling | +0.025 |
lifetime | +0.024 |
highlight | +0.023 |
Neg logit contributions | |
thinks | -0.024 |
screams | -0.023 |
rs | -0.023 |
bites | -0.023 |
ks | -0.023 |
Token | put |
Token ID | 1234 |
Feature activation | +2.77e+00 |
Pos logit contributions | |
atmeal | +0.038 |
rolling | +0.036 |
ancer | +0.035 |
lifetime | +0.033 |
highlight | +0.033 |
Neg logit contributions | |
rs | -0.041 |
screams | -0.040 |
irk | -0.040 |
rum | -0.039 |
ks | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | +2.62e+00 |
Pos logit contributions | |
rolling | +0.096 |
atmeal | +0.095 |
ancer | +0.091 |
lifetime | +0.091 |
ital | +0.089 |
Neg logit contributions | |
rs | -0.037 |
bites | -0.032 |
tant | -0.029 |
thinks | -0.029 |
screams | -0.029 |
Token | blue |
Token ID | 4171 |
Feature activation | +2.64e+00 |
Pos logit contributions | |
atmeal | +0.072 |
rolling | +0.070 |
ancer | +0.068 |
lifetime | +0.065 |
ital | +0.064 |
Neg logit contributions | |
rs | -0.051 |
screams | -0.049 |
bites | -0.048 |
irk | -0.047 |
thinks | -0.047 |
Token | berries |
Token ID | 20853 |
Feature activation | +5.69e+00 |
Pos logit contributions | |
atmeal | +0.058 |
rolling | +0.055 |
ancer | +0.053 |
lifetime | +0.052 |
ital | +0.050 |
Neg logit contributions | |
rs | -0.066 |
screams | -0.063 |
irk | -0.062 |
bites | -0.062 |
rum | -0.061 |
Token | in |
Token ID | 287 |
Feature activation | -1.68e-01 |
Pos logit contributions | |
atmeal | +0.162 |
rolling | +0.160 |
lifetime | +0.156 |
ancer | +0.156 |
ital | +0.152 |
Neg logit contributions | |
and | -0.098 |
rs | -0.097 |
bites | -0.091 |
irk | -0.086 |
ks | -0.086 |
Token | a |
Token ID | 257 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
irk | +0.004 |
screams | +0.004 |
rum | +0.004 |
ks | +0.004 |
rs | +0.004 |
Neg logit contributions | |
atmeal | -0.004 |
nam | -0.004 |
Hatt | -0.004 |
highlight | -0.004 |
rolling | -0.004 |
Token | bowl |
Token ID | 9396 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
ancer | +0.036 |
atmeal | +0.036 |
rolling | +0.035 |
Hatt | +0.032 |
highlight | +0.032 |
Neg logit contributions | |
bites | -0.024 |
rs | -0.024 |
screams | -0.023 |
irk | -0.023 |
tant | -0.023 |
Token | and |
Token ID | 290 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
atmeal | +0.079 |
ancer | +0.073 |
rolling | +0.071 |
lifetime | +0.069 |
highlight | +0.069 |
Neg logit contributions | |
screams | -0.041 |
rs | -0.038 |
rum | -0.038 |
irk | -0.038 |
Mine | -0.035 |
Token | eat |
Token ID | 4483 |
Feature activation | +8.69e-01 |
Pos logit contributions | |
ancer | +0.073 |
rolling | +0.071 |
atmeal | +0.070 |
lifetime | +0.070 |
ital | +0.066 |
Neg logit contributions | |
bites | -0.054 |
screams | -0.052 |
rs | -0.051 |
thinks | -0.051 |
and | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
atmeal | +0.021 |
ancer | +0.020 |
lifetime | +0.019 |
rolling | +0.019 |
ouses | +0.018 |
Neg logit contributions | |
tant | -0.012 |
irk | -0.011 |
screams | -0.011 |
rs | -0.011 |
Mine | -0.011 |
Token | I |
Token ID | 314 |
Feature activation | +5.41e-02 |
Pos logit contributions | |
atmeal | +0.079 |
inations | +0.071 |
rolling | +0.071 |
lifetime | +0.070 |
pieces | +0.070 |
Neg logit contributions | |
rs | -0.042 |
irk | -0.035 |
screams | -0.034 |
thinks | -0.034 |
Mine | -0.034 |
Token | will |
Token ID | 481 |
Feature activation | +5.16e-01 |
Pos logit contributions | |
atmeal | +0.002 |
rolling | +0.001 |
ancer | +0.001 |
lifetime | +0.001 |
highlight | +0.001 |
Neg logit contributions | |
rs | -0.001 |
irk | -0.001 |
screams | -0.001 |
rum | -0.001 |
bites | -0.001 |
Token | put |
Token ID | 1234 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
atmeal | +0.012 |
rolling | +0.012 |
ancer | +0.012 |
lifetime | +0.011 |
highlight | +0.011 |
Neg logit contributions | |
rs | -0.012 |
screams | -0.012 |
irk | -0.011 |
rum | -0.011 |
bites | -0.011 |
Token | my |
Token ID | 616 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
atmeal | +0.049 |
rolling | +0.049 |
ancer | +0.047 |
lifetime | +0.046 |
highlight | +0.044 |
Neg logit contributions | |
rs | -0.032 |
screams | -0.029 |
bites | -0.029 |
irk | -0.028 |
ks | -0.028 |
Token | dolls |
Token ID | 36062 |
Feature activation | +5.67e+00 |
Pos logit contributions | |
rolling | +0.060 |
atmeal | +0.056 |
ancer | +0.054 |
lifetime | +0.053 |
highlight | +0.050 |
Neg logit contributions | |
bites | -0.042 |
rs | -0.040 |
words | -0.040 |
screams | -0.040 |
thinks | -0.038 |
Token | in |
Token ID | 287 |
Feature activation | +6.00e-01 |
Pos logit contributions | |
rolling | +0.181 |
atmeal | +0.170 |
lifetime | +0.167 |
ancer | +0.164 |
Hatt | +0.162 |
Neg logit contributions | |
and | -0.092 |
rs | -0.090 |
ater | -0.078 |
bites | -0.076 |
tant | -0.074 |
Token | one |
Token ID | 530 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
atmeal | +0.016 |
rolling | +0.015 |
ancer | +0.015 |
lifetime | +0.015 |
Hatt | +0.015 |
Neg logit contributions | |
irk | -0.012 |
screams | -0.011 |
rs | -0.011 |
rum | -0.011 |
ks | -0.011 |
Token | box |
Token ID | 3091 |
Feature activation | +1.96e+00 |
Pos logit contributions | |
rolling | +0.093 |
atmeal | +0.091 |
ancer | +0.088 |
Hatt | +0.085 |
lifetime | +0.083 |
Neg logit contributions | |
rs | -0.058 |
bites | -0.055 |
irk | -0.055 |
screams | -0.054 |
word | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
atmeal | +0.061 |
ancer | +0.058 |
rolling | +0.056 |
lifetime | +0.055 |
highlight | +0.054 |
Neg logit contributions | |
screams | -0.031 |
irk | -0.031 |
rs | -0.030 |
rum | -0.029 |
bites | -0.027 |
Token | my |
Token ID | 616 |
Feature activation | +1.46e+00 |
Pos logit contributions | |
atmeal | +0.092 |
rolling | +0.092 |
ancer | +0.091 |
lifetime | +0.086 |
highlight | +0.084 |
Neg logit contributions | |
bites | -0.069 |
screams | -0.068 |
rs | -0.067 |
thinks | -0.067 |
and | -0.064 |
Token | when |
Token ID | 618 |
Feature activation | +7.64e-01 |
Pos logit contributions | |
atmeal | +0.010 |
rolling | +0.010 |
ancer | +0.009 |
lifetime | +0.009 |
exploring | +0.009 |
Neg logit contributions | |
rs | -0.012 |
irk | -0.012 |
rum | -0.012 |
Mine | -0.012 |
tant | -0.011 |
Token | suddenly |
Token ID | 6451 |
Feature activation | -6.27e-01 |
Pos logit contributions | |
atmeal | +0.023 |
ouses | +0.021 |
umes | +0.021 |
ancer | +0.020 |
pieces | +0.020 |
Neg logit contributions | |
screams | -0.015 |
bites | -0.013 |
ks | -0.013 |
blood | -0.013 |
its | -0.013 |
Token | he |
Token ID | 339 |
Feature activation | +9.53e-02 |
Pos logit contributions | |
rs | +0.012 |
screams | +0.012 |
irk | +0.011 |
rum | +0.011 |
bites | +0.011 |
Neg logit contributions | |
atmeal | -0.018 |
rolling | -0.017 |
ancer | -0.016 |
lifetime | -0.016 |
highlight | -0.016 |
Token | heard |
Token ID | 2982 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
atmeal | +0.003 |
ancer | +0.003 |
rolling | +0.003 |
Hatt | +0.003 |
lifetime | +0.003 |
Neg logit contributions | |
screams | -0.002 |
rs | -0.001 |
ks | -0.001 |
irk | -0.001 |
bites | -0.001 |
Token | a |
Token ID | 257 |
Feature activation | -5.02e+00 |
Pos logit contributions | |
rs | +0.056 |
irk | +0.055 |
rum | +0.053 |
tant | +0.050 |
screams | +0.050 |
Neg logit contributions | |
atmeal | -0.070 |
rolling | -0.067 |
ancer | -0.064 |
Hatt | -0.064 |
lifetime | -0.064 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.81e+00 |
Pos logit contributions | |
rs | +0.099 |
rum | +0.090 |
ud | +0.086 |
ases | +0.085 |
irk | +0.085 |
Neg logit contributions | |
rolling | -0.141 |
atmeal | -0.136 |
lifetime | -0.132 |
ancer | -0.127 |
Hatt | -0.127 |
Token | roar |
Token ID | 34532 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
ud | +0.157 |
irk | +0.150 |
Mine | +0.145 |
tant | +0.144 |
ases | +0.144 |
Neg logit contributions | |
rolling | -0.149 |
Hatt | -0.133 |
atmeal | -0.132 |
shining | -0.131 |
explore | -0.129 |
Token | . |
Token ID | 13 |
Feature activation | -2.21e+00 |
Pos logit contributions | |
Mine | +0.053 |
tant | +0.053 |
irk | +0.053 |
rs | +0.052 |
rum | +0.049 |
Neg logit contributions | |
rolling | -0.072 |
atmeal | -0.068 |
ancer | -0.067 |
oming | -0.064 |
ations | -0.063 |
Token | He |
Token ID | 679 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
rs | +0.036 |
irk | +0.034 |
rum | +0.033 |
screams | +0.032 |
tant | +0.032 |
Neg logit contributions | |
rolling | -0.068 |
atmeal | -0.067 |
ancer | -0.064 |
Hatt | -0.062 |
lifetime | -0.061 |
Token | was |
Token ID | 373 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
rs | +0.043 |
screams | +0.042 |
irk | +0.042 |
rum | +0.040 |
bites | +0.040 |
Neg logit contributions | |
atmeal | -0.053 |
rolling | -0.050 |
ancer | -0.049 |
lifetime | -0.047 |
highlight | -0.046 |
Token | scared |
Token ID | 12008 |
Feature activation | -2.54e+00 |
Pos logit contributions | |
irk | +0.036 |
rs | +0.035 |
tant | +0.034 |
Mine | +0.034 |
rum | +0.033 |
Neg logit contributions | |
rolling | -0.032 |
exploring | -0.028 |
atmeal | -0.027 |
highlight | -0.027 |
hiking | -0.027 |
Token | big |
Token ID | 1263 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
rs | +0.055 |
rum | +0.051 |
screams | +0.050 |
irk | +0.050 |
ks | +0.049 |
Neg logit contributions | |
atmeal | -0.073 |
rolling | -0.071 |
lifetime | -0.068 |
ancer | -0.068 |
Hatt | -0.065 |
Token | dog |
Token ID | 3290 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
rum | +0.084 |
rs | +0.083 |
ks | +0.082 |
ud | +0.078 |
ases | +0.078 |
Neg logit contributions | |
atmeal | -0.079 |
rolling | -0.075 |
forth | -0.074 |
ancer | -0.072 |
Hatt | -0.072 |
Token | appeared |
Token ID | 4120 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
irk | +0.064 |
tant | +0.062 |
rs | +0.061 |
rum | +0.060 |
aron | +0.058 |
Neg logit contributions | |
rolling | -0.042 |
atmeal | -0.040 |
Hatt | -0.038 |
cel | -0.036 |
exploring | -0.035 |
Token | with |
Token ID | 351 |
Feature activation | -2.95e+00 |
Pos logit contributions | |
tant | +0.025 |
Mine | +0.025 |
screams | +0.024 |
irk | +0.023 |
thinks | +0.023 |
Neg logit contributions | |
rolling | -0.029 |
ancer | -0.028 |
exploring | -0.027 |
atmeal | -0.027 |
oming | -0.026 |
Token | a |
Token ID | 257 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
aron | +0.089 |
irk | +0.084 |
ater | +0.084 |
ud | +0.081 |
rum | +0.078 |
Neg logit contributions | |
nam | -0.051 |
shining | -0.048 |
rolling | -0.044 |
exploring | -0.044 |
hiking | -0.042 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.66e+00 |
Pos logit contributions | |
rs | +0.105 |
ases | +0.101 |
ks | +0.094 |
ud | +0.093 |
irk | +0.093 |
Neg logit contributions | |
rolling | -0.096 |
lifetime | -0.088 |
atmeal | -0.083 |
nam | -0.080 |
highlight | -0.078 |
Token | bark |
Token ID | 21405 |
Feature activation | -2.91e+00 |
Pos logit contributions | |
ud | +0.147 |
ases | +0.142 |
ater | +0.129 |
ks | +0.129 |
Mine | +0.128 |
Neg logit contributions | |
rolling | -0.148 |
exploring | -0.135 |
explore | -0.128 |
shining | -0.128 |
cel | -0.125 |
Token | . |
Token ID | 13 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
tant | +0.059 |
Mine | +0.055 |
thinks | +0.054 |
irk | +0.053 |
screams | +0.052 |
Neg logit contributions | |
rolling | -0.070 |
ancer | -0.068 |
atmeal | -0.067 |
oming | -0.064 |
exploring | -0.063 |
Token | Peter |
Token ID | 5613 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
irk | +0.051 |
rs | +0.051 |
rum | +0.049 |
tant | +0.048 |
screams | +0.048 |
Neg logit contributions | |
rolling | -0.054 |
atmeal | -0.049 |
ancer | -0.049 |
Hatt | -0.049 |
lifetime | -0.048 |
Token | was |
Token ID | 373 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
irk | +0.075 |
rs | +0.072 |
ases | +0.069 |
rum | +0.069 |
tant | +0.068 |
Neg logit contributions | |
rolling | -0.056 |
atmeal | -0.048 |
Hatt | -0.047 |
lifetime | -0.046 |
ail | -0.046 |
Token | scared |
Token ID | 12008 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
irk | +0.040 |
tant | +0.040 |
rs | +0.039 |
ater | +0.039 |
Mine | +0.039 |
Neg logit contributions | |
rolling | -0.035 |
exploring | -0.030 |
highlight | -0.029 |
Hatt | -0.029 |
hiking | -0.029 |
Token | woods |
Token ID | 16479 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
atmeal | +0.011 |
ancer | +0.011 |
rolling | +0.011 |
Hatt | +0.010 |
lifetime | +0.010 |
Neg logit contributions | |
screams | -0.012 |
rs | -0.011 |
irk | -0.011 |
bites | -0.011 |
thinks | -0.011 |
Token | when |
Token ID | 618 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
atmeal | +0.021 |
rolling | +0.020 |
ancer | +0.020 |
lifetime | +0.019 |
highlight | +0.018 |
Neg logit contributions | |
rs | -0.019 |
irk | -0.018 |
screams | -0.018 |
rum | -0.018 |
tant | -0.017 |
Token | she |
Token ID | 673 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
atmeal | +0.033 |
ouses | +0.030 |
inations | +0.029 |
ancer | +0.029 |
rolling | +0.028 |
Neg logit contributions | |
screams | -0.031 |
its | -0.030 |
blood | -0.029 |
pain | -0.029 |
bites | -0.028 |
Token | heard |
Token ID | 2982 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
atmeal | +0.039 |
pieces | +0.038 |
ancer | +0.038 |
nam | +0.038 |
Hatt | +0.038 |
Neg logit contributions | |
screams | -0.014 |
ks | -0.014 |
bites | -0.013 |
and | -0.012 |
thinks | -0.012 |
Token | a |
Token ID | 257 |
Feature activation | -4.64e+00 |
Pos logit contributions | |
rs | +0.031 |
irk | +0.030 |
rum | +0.030 |
screams | +0.029 |
bites | +0.028 |
Neg logit contributions | |
atmeal | -0.051 |
rolling | -0.048 |
ancer | -0.047 |
Hatt | -0.046 |
lifetime | -0.046 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
rs | +0.080 |
rum | +0.074 |
irk | +0.070 |
ases | +0.067 |
screams | +0.066 |
Neg logit contributions | |
rolling | -0.138 |
atmeal | -0.137 |
lifetime | -0.132 |
ancer | -0.130 |
Hatt | -0.127 |
Token | sound |
Token ID | 2128 |
Feature activation | -3.44e+00 |
Pos logit contributions | |
ud | +0.139 |
irk | +0.132 |
ases | +0.131 |
Mine | +0.130 |
tant | +0.126 |
Neg logit contributions | |
rolling | -0.154 |
atmeal | -0.144 |
Hatt | -0.143 |
exploring | -0.135 |
shining | -0.135 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
rs | +0.051 |
irk | +0.049 |
rum | +0.048 |
Mine | +0.047 |
screams | +0.045 |
Neg logit contributions | |
atmeal | -0.107 |
rolling | -0.102 |
ancer | -0.102 |
highlight | -0.098 |
lifetime | -0.097 |
Token | She |
Token ID | 1375 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
rs | +0.020 |
screams | +0.019 |
irk | +0.019 |
rum | +0.018 |
bites | +0.018 |
Neg logit contributions | |
atmeal | -0.040 |
rolling | -0.038 |
ancer | -0.038 |
lifetime | -0.037 |
highlight | -0.036 |
Token | looked |
Token ID | 3114 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
screams | +0.039 |
rs | +0.038 |
irk | +0.037 |
ks | +0.036 |
bites | +0.036 |
Neg logit contributions | |
atmeal | -0.052 |
ancer | -0.048 |
rolling | -0.048 |
highlight | -0.046 |
lifetime | -0.046 |
Token | up |
Token ID | 510 |
Feature activation | +7.80e-01 |
Pos logit contributions | |
rs | +0.005 |
screams | +0.005 |
irk | +0.005 |
rum | +0.005 |
bites | +0.005 |
Neg logit contributions | |
atmeal | -0.005 |
rolling | -0.005 |
ancer | -0.005 |
lifetime | -0.004 |
highlight | -0.004 |
Token | when |
Token ID | 618 |
Feature activation | +7.13e-01 |
Pos logit contributions | |
atmeal | +0.026 |
rolling | +0.025 |
ancer | +0.024 |
highlight | +0.023 |
lifetime | +0.023 |
Neg logit contributions | |
rs | -0.023 |
irk | -0.023 |
rum | -0.022 |
screams | -0.022 |
tant | -0.021 |
Token | suddenly |
Token ID | 6451 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
atmeal | +0.022 |
pieces | +0.021 |
ital | +0.021 |
inations | +0.021 |
umes | +0.020 |
Neg logit contributions | |
screams | -0.013 |
bites | -0.011 |
its | -0.011 |
his | -0.011 |
blood | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
screams | +0.006 |
rs | +0.006 |
irk | +0.006 |
bites | +0.006 |
rum | +0.006 |
Neg logit contributions | |
atmeal | -0.011 |
rolling | -0.010 |
ancer | -0.010 |
lifetime | -0.010 |
highlight | -0.010 |
Token | heard |
Token ID | 2982 |
Feature activation | -2.94e+00 |
Pos logit contributions | |
atmeal | +0.003 |
ancer | +0.003 |
rolling | +0.003 |
lifetime | +0.003 |
Hatt | +0.003 |
Neg logit contributions | |
screams | -0.002 |
rs | -0.002 |
irk | -0.002 |
bites | -0.002 |
ks | -0.002 |
Token | a |
Token ID | 257 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
rs | +0.063 |
irk | +0.063 |
rum | +0.059 |
ater | +0.059 |
tant | +0.056 |
Neg logit contributions | |
atmeal | -0.071 |
rolling | -0.067 |
Hatt | -0.067 |
ancer | -0.064 |
lifetime | -0.061 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
rs | +0.091 |
rum | +0.084 |
ud | +0.080 |
ases | +0.078 |
irk | +0.078 |
Neg logit contributions | |
rolling | -0.139 |
atmeal | -0.134 |
lifetime | -0.129 |
Hatt | -0.126 |
ancer | -0.125 |
Token | noise |
Token ID | 7838 |
Feature activation | -3.37e+00 |
Pos logit contributions | |
ud | +0.152 |
irk | +0.141 |
tant | +0.138 |
fault | +0.138 |
ases | +0.137 |
Neg logit contributions | |
rolling | -0.141 |
atmeal | -0.129 |
Hatt | -0.128 |
shining | -0.127 |
explore | -0.123 |
Token | . |
Token ID | 13 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
tant | +0.066 |
Mine | +0.066 |
irk | +0.064 |
rs | +0.063 |
rum | +0.061 |
Neg logit contributions | |
atmeal | -0.086 |
rolling | -0.083 |
ancer | -0.080 |
exploring | -0.078 |
camping | -0.075 |
Token | He |
Token ID | 679 |
Feature activation | -1.99e+00 |
Pos logit contributions | |
rs | +0.037 |
irk | +0.036 |
rum | +0.033 |
screams | +0.033 |
tant | +0.032 |
Neg logit contributions | |
atmeal | -0.084 |
rolling | -0.082 |
ancer | -0.080 |
Hatt | -0.078 |
lifetime | -0.075 |
Token | was |
Token ID | 373 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
rs | +0.044 |
irk | +0.043 |
screams | +0.043 |
rum | +0.042 |
bites | +0.040 |
Neg logit contributions | |
atmeal | -0.049 |
rolling | -0.047 |
ancer | -0.046 |
lifetime | -0.044 |
Hatt | -0.043 |
Token | shocked |
Token ID | 11472 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
irk | +0.027 |
rs | +0.026 |
tant | +0.026 |
Mine | +0.025 |
rum | +0.025 |
Neg logit contributions | |
rolling | -0.026 |
atmeal | -0.023 |
exploring | -0.023 |
ancer | -0.023 |
highlight | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
irk | +0.028 |
Mine | +0.025 |
tant | +0.025 |
rs | +0.025 |
ases | +0.024 |
Neg logit contributions | |
atmeal | -0.048 |
rolling | -0.048 |
exploring | -0.045 |
ancer | -0.043 |
oming | -0.043 |
Token | terrifying |
Token ID | 17623 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
irk | +0.032 |
ases | +0.031 |
rs | +0.031 |
rum | +0.029 |
ud | +0.029 |
Neg logit contributions | |
atmeal | -0.037 |
rolling | -0.036 |
nam | -0.036 |
lifetime | -0.036 |
exploring | -0.035 |
Token | eyes |
Token ID | 2951 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
Mine | +0.090 |
tant | +0.077 |
irk | +0.076 |
ud | +0.076 |
rs | +0.074 |
Neg logit contributions | |
exploring | -0.091 |
rolling | -0.085 |
atmeal | -0.082 |
hiking | -0.080 |
wandering | -0.079 |
Token | and |
Token ID | 290 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
irk | +0.046 |
Mine | +0.041 |
ases | +0.040 |
rs | +0.038 |
tant | +0.037 |
Neg logit contributions | |
atmeal | -0.064 |
rolling | -0.064 |
shining | -0.060 |
oming | -0.059 |
cel | -0.059 |
Token | a |
Token ID | 257 |
Feature activation | -4.06e+00 |
Pos logit contributions | |
irk | +0.035 |
rs | +0.034 |
rum | +0.031 |
ases | +0.030 |
ud | +0.030 |
Neg logit contributions | |
atmeal | -0.036 |
rolling | -0.035 |
lifetime | -0.034 |
nam | -0.034 |
ancer | -0.033 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
rs | +0.098 |
ases | +0.094 |
irk | +0.088 |
ks | +0.085 |
rum | +0.085 |
Neg logit contributions | |
lifetime | -0.096 |
rolling | -0.096 |
atmeal | -0.092 |
highlight | -0.085 |
ancer | -0.083 |
Token | roar |
Token ID | 34532 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
ases | +0.148 |
ud | +0.140 |
irk | +0.139 |
Mine | +0.138 |
ks | +0.129 |
Neg logit contributions | |
rolling | -0.144 |
atmeal | -0.137 |
exploring | -0.132 |
cel | -0.131 |
shining | -0.130 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
irk | +0.049 |
Mine | +0.046 |
rs | +0.046 |
thinks | +0.043 |
tant | +0.043 |
Neg logit contributions | |
atmeal | -0.072 |
rolling | -0.072 |
ancer | -0.068 |
lifetime | -0.067 |
highlight | -0.065 |
Token |
|
Token ID | 198 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
rs | +0.033 |
irk | +0.032 |
screams | +0.031 |
rum | +0.031 |
ks | +0.030 |
Neg logit contributions | |
atmeal | -0.051 |
rolling | -0.049 |
ancer | -0.049 |
lifetime | -0.047 |
Hatt | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
rs | +0.052 |
irk | +0.049 |
screams | +0.049 |
bites | +0.047 |
rum | +0.046 |
Neg logit contributions | |
rolling | -0.072 |
atmeal | -0.070 |
ancer | -0.068 |
Hatt | -0.067 |
lifetime | -0.066 |
Token | The |
Token ID | 464 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
rs | +0.031 |
screams | +0.030 |
irk | +0.030 |
rum | +0.029 |
bites | +0.029 |
Neg logit contributions | |
atmeal | -0.033 |
rolling | -0.031 |
ancer | -0.031 |
lifetime | -0.029 |
highlight | -0.029 |
Token | but |
Token ID | 475 |
Feature activation | +8.39e-01 |
Pos logit contributions | |
irk | +0.004 |
rum | +0.004 |
rs | +0.004 |
ud | +0.003 |
tant | +0.003 |
Neg logit contributions | |
rolling | -0.003 |
atmeal | -0.003 |
nam | -0.003 |
ancer | -0.003 |
highlight | -0.003 |
Token | then |
Token ID | 788 |
Feature activation | -1.57e-01 |
Pos logit contributions | |
atmeal | +0.027 |
rolling | +0.026 |
lifetime | +0.025 |
ancer | +0.025 |
ital | +0.024 |
Neg logit contributions | |
screams | -0.013 |
rs | -0.012 |
irk | -0.012 |
ks | -0.012 |
bites | -0.012 |
Token | she |
Token ID | 673 |
Feature activation | -9.90e-01 |
Pos logit contributions | |
screams | +0.004 |
ks | +0.004 |
rs | +0.004 |
bites | +0.004 |
thinks | +0.004 |
Neg logit contributions | |
atmeal | -0.004 |
rolling | -0.003 |
ancer | -0.003 |
lifetime | -0.003 |
highlight | -0.003 |
Token | heard |
Token ID | 2982 |
Feature activation | -3.14e+00 |
Pos logit contributions | |
rs | +0.021 |
screams | +0.021 |
irk | +0.020 |
rum | +0.020 |
bites | +0.020 |
Neg logit contributions | |
atmeal | -0.025 |
rolling | -0.024 |
ancer | -0.024 |
lifetime | -0.023 |
highlight | -0.022 |
Token | a |
Token ID | 257 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
rum | +0.071 |
rs | +0.070 |
irk | +0.069 |
aron | +0.067 |
tant | +0.066 |
Neg logit contributions | |
atmeal | -0.069 |
Hatt | -0.066 |
rolling | -0.066 |
pieces | -0.066 |
ancer | -0.064 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
rs | +0.109 |
ases | +0.100 |
ud | +0.099 |
rum | +0.094 |
ez | +0.091 |
Neg logit contributions | |
rolling | -0.137 |
atmeal | -0.126 |
lifetime | -0.126 |
Hatt | -0.121 |
ancer | -0.117 |
Token | noise |
Token ID | 7838 |
Feature activation | -3.94e+00 |
Pos logit contributions | |
ud | +0.159 |
fault | +0.145 |
irk | +0.141 |
ases | +0.139 |
tant | +0.138 |
Neg logit contributions | |
rolling | -0.122 |
atmeal | -0.121 |
Hatt | -0.120 |
shining | -0.115 |
Kirst | -0.115 |
Token | . |
Token ID | 13 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
tant | +0.084 |
irk | +0.081 |
Mine | +0.080 |
fault | +0.075 |
rum | +0.075 |
Neg logit contributions | |
atmeal | -0.089 |
rolling | -0.084 |
exploring | -0.084 |
shining | -0.082 |
camping | -0.081 |
Token | " |
Token ID | 366 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
rum | +0.033 |
rs | +0.032 |
screams | +0.030 |
ks | +0.029 |
irk | +0.029 |
Neg logit contributions | |
atmeal | -0.042 |
rolling | -0.042 |
ancer | -0.041 |
Hatt | -0.039 |
ouses | -0.038 |
Token | Ro |
Token ID | 15450 |
Feature activation | +2.44e-01 |
Pos logit contributions | |
rs | +0.021 |
screams | +0.020 |
rum | +0.020 |
irk | +0.019 |
ks | +0.019 |
Neg logit contributions | |
atmeal | -0.024 |
highlight | -0.022 |
rolling | -0.022 |
ancer | -0.022 |
ital | -0.021 |
Token | ar |
Token ID | 283 |
Feature activation | +7.31e-01 |
Pos logit contributions | |
atmeal | +0.004 |
ancer | +0.004 |
rolling | +0.004 |
ital | +0.004 |
Hatt | +0.004 |
Neg logit contributions | |
screams | -0.007 |
irk | -0.007 |
rs | -0.007 |
tant | -0.007 |
rum | -0.007 |
Token | day |
Token ID | 1110 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
atmeal | +0.019 |
rolling | +0.018 |
ancer | +0.018 |
lifetime | +0.017 |
Hatt | +0.016 |
Neg logit contributions | |
rs | -0.027 |
irk | -0.026 |
screams | -0.026 |
rum | -0.026 |
bites | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
atmeal | +0.078 |
ancer | +0.071 |
rolling | +0.071 |
lifetime | +0.069 |
Hatt | +0.069 |
Neg logit contributions | |
screams | -0.034 |
rs | -0.034 |
irk | -0.033 |
ks | -0.032 |
bites | -0.031 |
Token | suddenly |
Token ID | 6451 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
atmeal | +0.045 |
ancer | +0.043 |
rolling | +0.043 |
lifetime | +0.041 |
ouses | +0.040 |
Neg logit contributions | |
screams | -0.036 |
thinks | -0.035 |
and | -0.034 |
ks | -0.033 |
rs | -0.033 |
Token | heard |
Token ID | 2982 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
atmeal | +0.033 |
ancer | +0.031 |
rolling | +0.030 |
lifetime | +0.030 |
highlight | +0.030 |
Neg logit contributions | |
screams | -0.017 |
ks | -0.015 |
bites | -0.015 |
rs | -0.015 |
and | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
rs | +0.024 |
screams | +0.023 |
irk | +0.023 |
rum | +0.022 |
bites | +0.021 |
Neg logit contributions | |
atmeal | -0.048 |
rolling | -0.046 |
ancer | -0.045 |
lifetime | -0.044 |
highlight | -0.043 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.53e+00 |
Pos logit contributions | |
rs | +0.070 |
rum | +0.065 |
irk | +0.064 |
screams | +0.062 |
ks | +0.061 |
Neg logit contributions | |
atmeal | -0.135 |
rolling | -0.133 |
ancer | -0.127 |
lifetime | -0.127 |
Hatt | -0.123 |
Token | roar |
Token ID | 34532 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
ud | +0.140 |
irk | +0.138 |
ases | +0.132 |
Mine | +0.127 |
tant | +0.125 |
Neg logit contributions | |
rolling | -0.154 |
atmeal | -0.141 |
Hatt | -0.139 |
shining | -0.134 |
exploring | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | -9.55e-01 |
Pos logit contributions | |
irk | +0.045 |
rs | +0.044 |
Mine | +0.043 |
tant | +0.042 |
rum | +0.041 |
Neg logit contributions | |
rolling | -0.069 |
atmeal | -0.068 |
ancer | -0.067 |
highlight | -0.063 |
pieces | -0.062 |
Token | Sarah |
Token ID | 10490 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
rs | +0.013 |
screams | +0.013 |
irk | +0.012 |
words | +0.012 |
thinks | +0.011 |
Neg logit contributions | |
atmeal | -0.033 |
ancer | -0.031 |
highlight | -0.030 |
lifetime | -0.030 |
rolling | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
rs | +0.037 |
irk | +0.036 |
screams | +0.035 |
rum | +0.035 |
bites | +0.034 |
Neg logit contributions | |
atmeal | -0.045 |
rolling | -0.043 |
ancer | -0.041 |
lifetime | -0.040 |
Hatt | -0.039 |
Token | scared |
Token ID | 12008 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
rs | +0.025 |
irk | +0.024 |
rum | +0.024 |
tant | +0.023 |
Mine | +0.023 |
Neg logit contributions | |
rolling | -0.029 |
atmeal | -0.027 |
ancer | -0.026 |
highlight | -0.026 |
Hatt | -0.025 |
Token | suddenly |
Token ID | 6451 |
Feature activation | -4.22e-01 |
Pos logit contributions | |
atmeal | +0.020 |
rolling | +0.019 |
ancer | +0.019 |
lifetime | +0.018 |
Hatt | +0.018 |
Neg logit contributions | |
rs | -0.015 |
irk | -0.015 |
screams | -0.014 |
rum | -0.014 |
bites | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +7.90e-01 |
Pos logit contributions | |
screams | +0.008 |
rs | +0.008 |
ks | +0.008 |
bites | +0.008 |
irk | +0.008 |
Neg logit contributions | |
atmeal | -0.012 |
ancer | -0.011 |
rolling | -0.011 |
highlight | -0.011 |
lifetime | -0.010 |
Token | he |
Token ID | 339 |
Feature activation | -2.40e-01 |
Pos logit contributions | |
atmeal | +0.021 |
rolling | +0.020 |
ancer | +0.019 |
lifetime | +0.019 |
highlight | +0.019 |
Neg logit contributions | |
screams | -0.016 |
rs | -0.016 |
irk | -0.015 |
bites | -0.015 |
ks | -0.015 |
Token | heard |
Token ID | 2982 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
screams | +0.004 |
rs | +0.004 |
irk | +0.004 |
ks | +0.004 |
bites | +0.004 |
Neg logit contributions | |
atmeal | -0.007 |
ancer | -0.007 |
rolling | -0.007 |
Hatt | -0.007 |
highlight | -0.007 |
Token | a |
Token ID | 257 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
rs | +0.059 |
irk | +0.058 |
rum | +0.057 |
ater | +0.052 |
tant | +0.052 |
Neg logit contributions | |
atmeal | -0.072 |
rolling | -0.071 |
lifetime | -0.067 |
ancer | -0.067 |
Hatt | -0.067 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.51e+00 |
Pos logit contributions | |
rs | +0.087 |
ases | +0.079 |
rum | +0.079 |
ud | +0.078 |
irk | +0.076 |
Neg logit contributions | |
rolling | -0.144 |
lifetime | -0.137 |
atmeal | -0.134 |
Hatt | -0.129 |
ancer | -0.127 |
Token | scream |
Token ID | 8196 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
ud | +0.148 |
irk | +0.137 |
ases | +0.135 |
tant | +0.135 |
fault | +0.134 |
Neg logit contributions | |
rolling | -0.143 |
Hatt | -0.135 |
atmeal | -0.128 |
shining | -0.128 |
exploring | -0.127 |
Token | . |
Token ID | 13 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
tant | +0.059 |
thinks | +0.058 |
rs | +0.058 |
Mine | +0.057 |
irk | +0.057 |
Neg logit contributions | |
rolling | -0.086 |
atmeal | -0.083 |
ancer | -0.082 |
Hatt | -0.077 |
exploring | -0.075 |
Token | Max |
Token ID | 5436 |
Feature activation | -1.95e+00 |
Pos logit contributions | |
rs | +0.045 |
irk | +0.043 |
rum | +0.042 |
screams | +0.040 |
ater | +0.039 |
Neg logit contributions | |
rolling | -0.074 |
atmeal | -0.071 |
ancer | -0.070 |
Hatt | -0.069 |
lifetime | -0.067 |
Token | was |
Token ID | 373 |
Feature activation | -1.46e+00 |
Pos logit contributions | |
rs | +0.046 |
irk | +0.045 |
rum | +0.043 |
tant | +0.042 |
screams | +0.041 |
Neg logit contributions | |
rolling | -0.046 |
atmeal | -0.045 |
ancer | -0.041 |
lifetime | -0.041 |
Hatt | -0.040 |
Token | very |
Token ID | 845 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
irk | +0.036 |
tant | +0.036 |
rs | +0.035 |
Mine | +0.035 |
rum | +0.033 |
Neg logit contributions | |
rolling | -0.033 |
exploring | -0.030 |
atmeal | -0.029 |
highlight | -0.028 |
hiking | -0.028 |
Token | at |
Token ID | 379 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
irk | +0.026 |
Mine | +0.022 |
tant | +0.022 |
rs | +0.021 |
rum | +0.020 |
Neg logit contributions | |
rolling | -0.039 |
oming | -0.036 |
umes | -0.035 |
highlight | -0.035 |
atmeal | -0.035 |
Token | them |
Token ID | 606 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
rum | +0.040 |
irk | +0.040 |
screams | +0.039 |
tant | +0.037 |
ez | +0.036 |
Neg logit contributions | |
ancer | -0.051 |
atmeal | -0.049 |
rolling | -0.048 |
Hatt | -0.048 |
nam | -0.047 |
Token | and |
Token ID | 290 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
irk | +0.028 |
tant | +0.025 |
Mine | +0.023 |
aron | +0.022 |
rs | +0.022 |
Neg logit contributions | |
rolling | -0.027 |
umes | -0.025 |
exploring | -0.025 |
oming | -0.024 |
mage | -0.024 |
Token | made |
Token ID | 925 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
irk | +0.035 |
rum | +0.034 |
rs | +0.032 |
ud | +0.032 |
ff | +0.031 |
Neg logit contributions | |
nam | -0.029 |
atmeal | -0.026 |
forth | -0.026 |
Hatt | -0.025 |
chard | -0.025 |
Token | a |
Token ID | 257 |
Feature activation | -4.66e+00 |
Pos logit contributions | |
aron | +0.056 |
irk | +0.055 |
rum | +0.055 |
rs | +0.054 |
ater | +0.052 |
Neg logit contributions | |
rolling | -0.050 |
pieces | -0.050 |
Hatt | -0.048 |
atmeal | -0.046 |
nam | -0.046 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.50e+00 |
Pos logit contributions | |
rs | +0.120 |
ases | +0.106 |
ud | +0.104 |
aron | +0.103 |
rum | +0.102 |
Neg logit contributions | |
rolling | -0.099 |
lifetime | -0.090 |
tallest | -0.083 |
mage | -0.082 |
roof | -0.081 |
Token | noise |
Token ID | 7838 |
Feature activation | -4.19e+00 |
Pos logit contributions | |
ud | +0.160 |
irk | +0.151 |
ases | +0.140 |
Mine | +0.138 |
fault | +0.138 |
Neg logit contributions | |
rolling | -0.113 |
atmeal | -0.108 |
forth | -0.107 |
shining | -0.105 |
mage | -0.104 |
Token | . |
Token ID | 13 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
irk | +0.103 |
Mine | +0.093 |
tant | +0.089 |
ff | +0.086 |
rs | +0.085 |
Neg logit contributions | |
atmeal | -0.081 |
shining | -0.077 |
oming | -0.077 |
forth | -0.075 |
mage | -0.074 |
Token | Lily |
Token ID | 20037 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
rum | +0.046 |
rs | +0.044 |
irk | +0.043 |
screams | +0.043 |
bites | +0.042 |
Neg logit contributions | |
Hatt | -0.060 |
ancer | -0.060 |
rolling | -0.059 |
atmeal | -0.055 |
ouses | -0.054 |
Token | and |
Token ID | 290 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
rs | +0.076 |
irk | +0.075 |
rum | +0.075 |
Mine | +0.074 |
fault | +0.072 |
Neg logit contributions | |
forgot | -0.072 |
rolling | -0.071 |
couldn | -0.067 |
wore | -0.067 |
ail | -0.066 |
Token | Tom |
Token ID | 4186 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
atmeal | +0.015 |
ancer | +0.014 |
nam | +0.014 |
Hatt | +0.014 |
rolling | +0.014 |
Neg logit contributions | |
rum | -0.010 |
rs | -0.010 |
irk | -0.009 |
aron | -0.009 |
ud | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
irk | +0.038 |
screams | +0.034 |
rs | +0.034 |
tant | +0.034 |
rum | +0.032 |
Neg logit contributions | |
atmeal | -0.089 |
ancer | -0.085 |
rolling | -0.080 |
highlight | -0.080 |
pieces | -0.079 |
Token | The |
Token ID | 383 |
Feature activation | -1.20e+00 |
Pos logit contributions | |
rum | +0.057 |
rs | +0.053 |
ater | +0.050 |
tant | +0.050 |
aron | +0.049 |
Neg logit contributions | |
atmeal | -0.042 |
ancer | -0.041 |
rolling | -0.040 |
angers | -0.038 |
Hatt | -0.036 |
Token | robot |
Token ID | 9379 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
irk | +0.030 |
rs | +0.029 |
aron | +0.029 |
ud | +0.028 |
ff | +0.028 |
Neg logit contributions | |
ancer | -0.024 |
Hatt | -0.024 |
rolling | -0.023 |
nam | -0.023 |
highlight | -0.023 |
Token | makes |
Token ID | 1838 |
Feature activation | -3.34e+00 |
Pos logit contributions | |
irk | +0.050 |
rum | +0.049 |
rs | +0.048 |
aron | +0.045 |
tant | +0.043 |
Neg logit contributions | |
atmeal | -0.063 |
rolling | -0.062 |
ancer | -0.059 |
highlight | -0.057 |
ital | -0.057 |
Token | a |
Token ID | 257 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
rum | +0.088 |
aron | +0.087 |
irk | +0.085 |
rs | +0.083 |
ater | +0.078 |
Neg logit contributions | |
pieces | -0.060 |
atmeal | -0.058 |
rolling | -0.056 |
ancer | -0.055 |
ail | -0.054 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.47e+00 |
Pos logit contributions | |
rs | +0.111 |
rum | +0.105 |
irk | +0.102 |
ases | +0.101 |
aron | +0.098 |
Neg logit contributions | |
rolling | -0.106 |
lifetime | -0.106 |
tallest | -0.098 |
atmeal | -0.097 |
highlight | -0.097 |
Token | noise |
Token ID | 7838 |
Feature activation | -4.14e+00 |
Pos logit contributions | |
ud | +0.163 |
irk | +0.162 |
fault | +0.146 |
ff | +0.143 |
ously | +0.142 |
Neg logit contributions | |
forth | -0.105 |
house | -0.102 |
atmeal | -0.100 |
shining | -0.100 |
cel | -0.099 |
Token | and |
Token ID | 290 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
irk | +0.098 |
Mine | +0.089 |
rum | +0.088 |
tant | +0.085 |
ff | +0.083 |
Neg logit contributions | |
atmeal | -0.081 |
she | -0.079 |
they | -0.078 |
forth | -0.078 |
oming | -0.077 |
Token | starts |
Token ID | 4940 |
Feature activation | -3.38e+00 |
Pos logit contributions | |
irk | +0.031 |
rum | +0.030 |
rs | +0.030 |
aron | +0.028 |
ud | +0.027 |
Neg logit contributions | |
atmeal | -0.042 |
rolling | -0.040 |
ancer | -0.039 |
highlight | -0.038 |
nam | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
aron | +0.087 |
irk | +0.085 |
rum | +0.079 |
rs | +0.078 |
Mine | +0.075 |
Neg logit contributions | |
rolling | -0.069 |
exploring | -0.065 |
oming | -0.058 |
planting | -0.057 |
nam | -0.057 |
Token | run |
Token ID | 1057 |
Feature activation | -2.49e+00 |
Pos logit contributions | |
irk | +0.096 |
rum | +0.090 |
ud | +0.087 |
ously | +0.086 |
rs | +0.086 |
Neg logit contributions | |
rolling | -0.065 |
atmeal | -0.061 |
Hatt | -0.059 |
highlight | -0.057 |
ancer | -0.057 |
Token | tunnel |
Token ID | 13275 |
Feature activation | +8.77e-01 |
Pos logit contributions | |
ancer | +0.025 |
atmeal | +0.024 |
rolling | +0.024 |
nam | +0.022 |
pieces | +0.022 |
Neg logit contributions | |
screams | -0.017 |
bites | -0.017 |
thinks | -0.017 |
animal | -0.016 |
word | -0.016 |
Token | when |
Token ID | 618 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
atmeal | +0.025 |
rolling | +0.024 |
ancer | +0.023 |
lifetime | +0.023 |
highlight | +0.023 |
Neg logit contributions | |
irk | -0.016 |
rum | -0.016 |
rs | -0.016 |
screams | -0.015 |
ez | -0.014 |
Token | they |
Token ID | 484 |
Feature activation | +9.26e-01 |
Pos logit contributions | |
atmeal | +0.038 |
ancer | +0.033 |
ital | +0.032 |
ouses | +0.032 |
lifetime | +0.031 |
Neg logit contributions | |
its | -0.025 |
screams | -0.025 |
ks | -0.025 |
blood | -0.024 |
bites | -0.024 |
Token | heard |
Token ID | 2982 |
Feature activation | -2.34e+00 |
Pos logit contributions | |
atmeal | +0.028 |
rolling | +0.027 |
ancer | +0.026 |
lifetime | +0.026 |
highlight | +0.025 |
Neg logit contributions | |
rs | -0.015 |
screams | -0.015 |
irk | -0.015 |
ks | -0.014 |
bites | -0.014 |
Token | a |
Token ID | 257 |
Feature activation | -4.56e+00 |
Pos logit contributions | |
rum | +0.054 |
irk | +0.053 |
rs | +0.052 |
ater | +0.050 |
aron | +0.050 |
Neg logit contributions | |
rolling | -0.050 |
pieces | -0.049 |
Hatt | -0.048 |
atmeal | -0.048 |
highlight | -0.046 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.44e+00 |
Pos logit contributions | |
rs | +0.080 |
rum | +0.074 |
irk | +0.072 |
ud | +0.070 |
ases | +0.067 |
Neg logit contributions | |
rolling | -0.136 |
atmeal | -0.132 |
lifetime | -0.128 |
ancer | -0.125 |
Hatt | -0.124 |
Token | noise |
Token ID | 7838 |
Feature activation | -3.62e+00 |
Pos logit contributions | |
ud | +0.153 |
irk | +0.146 |
fault | +0.138 |
tant | +0.135 |
ases | +0.135 |
Neg logit contributions | |
rolling | -0.136 |
Hatt | -0.125 |
atmeal | -0.123 |
shining | -0.122 |
explore | -0.120 |
Token | . |
Token ID | 13 |
Feature activation | -1.53e+00 |
Pos logit contributions | |
irk | +0.069 |
rs | +0.068 |
tant | +0.067 |
rum | +0.067 |
Mine | +0.065 |
Neg logit contributions | |
atmeal | -0.092 |
rolling | -0.090 |
ancer | -0.085 |
highlight | -0.082 |
shining | -0.080 |
Token | It |
Token ID | 632 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
rs | +0.026 |
irk | +0.026 |
rum | +0.025 |
screams | +0.025 |
tant | +0.023 |
Neg logit contributions | |
rolling | -0.044 |
atmeal | -0.044 |
ancer | -0.042 |
Hatt | -0.041 |
lifetime | -0.040 |
Token | was |
Token ID | 373 |
Feature activation | -2.69e+00 |
Pos logit contributions | |
irk | +0.049 |
rs | +0.049 |
rum | +0.046 |
tant | +0.045 |
ater | +0.044 |
Neg logit contributions | |
rolling | -0.050 |
atmeal | -0.049 |
ancer | -0.046 |
lifetime | -0.046 |
Hatt | -0.045 |
Token | a |
Token ID | 257 |
Feature activation | -3.27e+00 |
Pos logit contributions | |
irk | +0.068 |
rum | +0.066 |
rs | +0.064 |
ater | +0.062 |
tant | +0.062 |
Neg logit contributions | |
rolling | -0.054 |
highlight | -0.053 |
Hatt | -0.052 |
exploring | -0.052 |
camping | -0.052 |
Token | eating |
Token ID | 6600 |
Feature activation | +6.42e-01 |
Pos logit contributions | |
atmeal | +0.000 |
ancer | +0.000 |
rolling | +0.000 |
lifetime | +0.000 |
Hatt | +0.000 |
Neg logit contributions | |
rs | -0.000 |
screams | -0.000 |
irk | -0.000 |
rum | -0.000 |
bites | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +5.35e-01 |
Pos logit contributions | |
atmeal | +0.019 |
rolling | +0.018 |
ancer | +0.018 |
lifetime | +0.017 |
highlight | +0.017 |
Neg logit contributions | |
rs | -0.011 |
screams | -0.011 |
irk | -0.010 |
rum | -0.010 |
bites | -0.010 |
Token | he |
Token ID | 339 |
Feature activation | -6.50e-01 |
Pos logit contributions | |
atmeal | +0.019 |
ouses | +0.018 |
ital | +0.018 |
rolling | +0.018 |
ancer | +0.018 |
Neg logit contributions | |
its | -0.007 |
blood | -0.006 |
his | -0.006 |
words | -0.006 |
pain | -0.006 |
Token | heard |
Token ID | 2982 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
screams | +0.012 |
bites | +0.012 |
ks | +0.012 |
rs | +0.012 |
irk | +0.012 |
Neg logit contributions | |
atmeal | -0.018 |
ancer | -0.017 |
rolling | -0.017 |
Hatt | -0.017 |
highlight | -0.016 |
Token | a |
Token ID | 257 |
Feature activation | -4.79e+00 |
Pos logit contributions | |
rs | +0.049 |
irk | +0.049 |
rum | +0.047 |
screams | +0.046 |
bites | +0.044 |
Neg logit contributions | |
atmeal | -0.069 |
rolling | -0.067 |
Hatt | -0.064 |
ancer | -0.063 |
lifetime | -0.063 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.43e+00 |
Pos logit contributions | |
rs | +0.091 |
rum | +0.081 |
ud | +0.080 |
ases | +0.079 |
irk | +0.078 |
Neg logit contributions | |
rolling | -0.138 |
atmeal | -0.131 |
lifetime | -0.129 |
Hatt | -0.123 |
ancer | -0.123 |
Token | noise |
Token ID | 7838 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
ud | +0.151 |
irk | +0.140 |
ases | +0.136 |
fault | +0.136 |
tant | +0.135 |
Neg logit contributions | |
rolling | -0.134 |
atmeal | -0.122 |
Hatt | -0.120 |
shining | -0.119 |
exploring | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
tant | +0.077 |
irk | +0.076 |
rum | +0.076 |
Mine | +0.075 |
rs | +0.075 |
Neg logit contributions | |
atmeal | -0.087 |
rolling | -0.087 |
ancer | -0.082 |
shining | -0.079 |
exploring | -0.079 |
Token | It |
Token ID | 632 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
rs | +0.028 |
irk | +0.026 |
screams | +0.026 |
rum | +0.025 |
ks | +0.025 |
Neg logit contributions | |
atmeal | -0.056 |
rolling | -0.056 |
ancer | -0.054 |
lifetime | -0.052 |
Hatt | -0.052 |
Token | was |
Token ID | 373 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
irk | +0.042 |
rs | +0.041 |
rum | +0.039 |
tant | +0.038 |
screams | +0.038 |
Neg logit contributions | |
atmeal | -0.043 |
rolling | -0.043 |
ancer | -0.040 |
lifetime | -0.039 |
Hatt | -0.039 |
Token | a |
Token ID | 257 |
Feature activation | -3.06e+00 |
Pos logit contributions | |
irk | +0.067 |
ater | +0.064 |
tant | +0.062 |
rum | +0.062 |
rs | +0.060 |
Neg logit contributions | |
exploring | -0.050 |
camping | -0.050 |
rolling | -0.049 |
highlight | -0.048 |
hiking | -0.048 |
Token | it |
Token ID | 340 |
Feature activation | -5.52e-01 |
Pos logit contributions | |
atmeal | +0.011 |
rolling | +0.010 |
ancer | +0.010 |
highlight | +0.010 |
nam | +0.010 |
Neg logit contributions | |
rs | -0.012 |
irk | -0.012 |
rum | -0.012 |
screams | -0.011 |
aron | -0.011 |
Token | fell |
Token ID | 3214 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
rs | +0.014 |
irk | +0.014 |
rum | +0.013 |
aron | +0.013 |
screams | +0.013 |
Neg logit contributions | |
atmeal | -0.012 |
rolling | -0.011 |
ancer | -0.010 |
highlight | -0.010 |
lifetime | -0.010 |
Token | down |
Token ID | 866 |
Feature activation | -2.25e+00 |
Pos logit contributions | |
irk | +0.035 |
gging | +0.033 |
rs | +0.032 |
rum | +0.031 |
aron | +0.031 |
Neg logit contributions | |
rolling | -0.018 |
ancer | -0.016 |
oming | -0.016 |
atmeal | -0.016 |
shining | -0.015 |
Token | with |
Token ID | 351 |
Feature activation | -2.85e+00 |
Pos logit contributions | |
irk | +0.054 |
gging | +0.048 |
ater | +0.046 |
ff | +0.046 |
una | +0.046 |
Neg logit contributions | |
Hatt | -0.044 |
darker | -0.044 |
exploring | -0.043 |
oming | -0.042 |
she | -0.042 |
Token | a |
Token ID | 257 |
Feature activation | -4.23e+00 |
Pos logit contributions | |
aron | +0.078 |
irk | +0.076 |
rs | +0.073 |
ater | +0.072 |
rum | +0.071 |
Neg logit contributions | |
nam | -0.055 |
highlight | -0.047 |
atmeal | -0.046 |
tallest | -0.046 |
Hatt | -0.046 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.43e+00 |
Pos logit contributions | |
rs | +0.117 |
ases | +0.106 |
red | +0.101 |
irk | +0.100 |
ks | +0.099 |
Neg logit contributions | |
rolling | -0.079 |
lifetime | -0.073 |
oming | -0.071 |
tallest | -0.071 |
atmeal | -0.070 |
Token | crash |
Token ID | 7014 |
Feature activation | -2.03e+00 |
Pos logit contributions | |
irk | +0.164 |
ud | +0.162 |
ases | +0.152 |
ks | +0.151 |
ater | +0.150 |
Neg logit contributions | |
rolling | -0.092 |
atmeal | -0.092 |
roof | -0.089 |
cel | -0.087 |
shining | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
irk | +0.042 |
rs | +0.037 |
Mine | +0.037 |
tant | +0.036 |
gging | +0.036 |
Neg logit contributions | |
atmeal | -0.048 |
rolling | -0.047 |
cases | -0.045 |
belt | -0.045 |
forth | -0.044 |
Token | All |
Token ID | 1439 |
Feature activation | -8.59e-01 |
Pos logit contributions | |
rs | +0.048 |
irk | +0.045 |
ater | +0.044 |
ks | +0.043 |
screams | +0.043 |
Neg logit contributions | |
atmeal | -0.056 |
ancer | -0.053 |
rolling | -0.053 |
Hatt | -0.053 |
nam | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | +4.36e-02 |
Pos logit contributions | |
rs | +0.021 |
aron | +0.021 |
irk | +0.020 |
ater | +0.020 |
gging | +0.020 |
Neg logit contributions | |
atmeal | -0.018 |
highlight | -0.016 |
ancer | -0.016 |
nights | -0.016 |
rolling | -0.016 |
Token | blocks |
Token ID | 7021 |
Feature activation | +2.63e-01 |
Pos logit contributions | |
atmeal | +0.001 |
rolling | +0.001 |
ancer | +0.001 |
lifetime | +0.001 |
highlight | +0.001 |
Neg logit contributions | |
rs | -0.001 |
irk | -0.001 |
screams | -0.001 |
rum | -0.001 |
ks | -0.001 |
Token | had |
Token ID | 550 |
Feature activation | -2.22e+00 |
Pos logit contributions | |
rs | +0.061 |
irk | +0.060 |
rum | +0.059 |
ases | +0.056 |
tant | +0.056 |
Neg logit contributions | |
atmeal | -0.058 |
rolling | -0.058 |
Hatt | -0.053 |
ancer | -0.052 |
lifetime | -0.051 |
Token | sharp |
Token ID | 7786 |
Feature activation | -4.05e+00 |
Pos logit contributions | |
rs | +0.060 |
rum | +0.059 |
irk | +0.059 |
aron | +0.056 |
ater | +0.056 |
Neg logit contributions | |
rolling | -0.042 |
exploring | -0.040 |
nam | -0.040 |
hiking | -0.039 |
highlight | -0.038 |
Token | teeth |
Token ID | 9941 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
irk | +0.064 |
rs | +0.062 |
Mine | +0.056 |
ud | +0.053 |
aron | +0.053 |
Neg logit contributions | |
rolling | -0.112 |
atmeal | -0.110 |
igs | -0.106 |
ouses | -0.103 |
exploring | -0.103 |
Token | and |
Token ID | 290 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
irk | +0.035 |
tant | +0.032 |
Mine | +0.031 |
ff | +0.029 |
rs | +0.028 |
Neg logit contributions | |
atmeal | -0.036 |
exploring | -0.035 |
rolling | -0.034 |
cases | -0.032 |
shining | -0.032 |
Token | a |
Token ID | 257 |
Feature activation | -4.48e+00 |
Pos logit contributions | |
rs | +0.028 |
irk | +0.028 |
rum | +0.026 |
ud | +0.025 |
ater | +0.025 |
Neg logit contributions | |
atmeal | -0.028 |
nam | -0.027 |
rolling | -0.026 |
belt | -0.025 |
ancer | -0.025 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.43e+00 |
Pos logit contributions | |
rs | +0.123 |
ases | +0.117 |
ud | +0.107 |
rum | +0.106 |
irk | +0.104 |
Neg logit contributions | |
rolling | -0.092 |
lifetime | -0.083 |
atmeal | -0.081 |
nam | -0.077 |
belt | -0.077 |
Token | bark |
Token ID | 21405 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
ud | +0.143 |
irk | +0.129 |
ases | +0.128 |
rs | +0.124 |
Mine | +0.121 |
Neg logit contributions | |
atmeal | -0.139 |
rolling | -0.138 |
forth | -0.123 |
cel | -0.121 |
exploring | -0.118 |
Token | . |
Token ID | 13 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
tant | +0.057 |
irk | +0.057 |
Mine | +0.056 |
thinks | +0.051 |
rs | +0.050 |
Neg logit contributions | |
atmeal | -0.064 |
rolling | -0.061 |
ancer | -0.058 |
exploring | -0.055 |
hiking | -0.054 |
Token | It |
Token ID | 632 |
Feature activation | -1.92e+00 |
Pos logit contributions | |
rum | +0.052 |
rs | +0.051 |
ater | +0.048 |
ez | +0.048 |
control | +0.048 |
Neg logit contributions | |
atmeal | -0.047 |
ancer | -0.045 |
rolling | -0.045 |
ouses | -0.042 |
oming | -0.041 |
Token | looked |
Token ID | 3114 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
irk | +0.045 |
rs | +0.044 |
rum | +0.043 |
ater | +0.040 |
ases | +0.040 |
Neg logit contributions | |
atmeal | -0.043 |
rolling | -0.042 |
Hatt | -0.039 |
nam | -0.039 |
ancer | -0.038 |
Token | fierce |
Token ID | 14800 |
Feature activation | -2.38e+00 |
Pos logit contributions | |
rs | +0.022 |
irk | +0.022 |
rum | +0.022 |
screams | +0.021 |
ud | +0.021 |
Neg logit contributions | |
atmeal | -0.024 |
rolling | -0.024 |
ancer | -0.023 |
highlight | -0.023 |
nam | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -6.90e-01 |
Pos logit contributions | |
rs | +0.032 |
irk | +0.031 |
rum | +0.030 |
tant | +0.030 |
screams | +0.030 |
Neg logit contributions | |
rolling | -0.037 |
atmeal | -0.036 |
ancer | -0.035 |
Hatt | -0.034 |
ail | -0.033 |
Token | The |
Token ID | 464 |
Feature activation | -7.38e-01 |
Pos logit contributions | |
rs | +0.013 |
screams | +0.013 |
irk | +0.013 |
rum | +0.012 |
bites | +0.012 |
Neg logit contributions | |
atmeal | -0.019 |
rolling | -0.018 |
ancer | -0.018 |
lifetime | -0.017 |
highlight | -0.017 |
Token | gun |
Token ID | 2485 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
rs | +0.016 |
rum | +0.016 |
ff | +0.016 |
irk | +0.015 |
ud | +0.015 |
Neg logit contributions | |
atmeal | -0.017 |
ancer | -0.017 |
highlight | -0.017 |
rolling | -0.016 |
lifetime | -0.016 |
Token | makes |
Token ID | 1838 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
irk | +0.076 |
rum | +0.071 |
aron | +0.070 |
ously | +0.065 |
rs | +0.065 |
Neg logit contributions | |
atmeal | -0.053 |
rolling | -0.051 |
oming | -0.049 |
irl | -0.048 |
forth | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | -4.90e+00 |
Pos logit contributions | |
rum | +0.084 |
aron | +0.084 |
irk | +0.083 |
ater | +0.079 |
rs | +0.078 |
Neg logit contributions | |
pieces | -0.046 |
rolling | -0.046 |
atmeal | -0.045 |
warmer | -0.043 |
highlight | -0.041 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.43e+00 |
Pos logit contributions | |
rs | +0.115 |
rum | +0.110 |
irk | +0.104 |
ez | +0.102 |
ases | +0.102 |
Neg logit contributions | |
rolling | -0.110 |
lifetime | -0.107 |
oming | -0.096 |
highlight | -0.095 |
roof | -0.094 |
Token | noise |
Token ID | 7838 |
Feature activation | -3.84e+00 |
Pos logit contributions | |
irk | +0.168 |
ud | +0.164 |
fault | +0.158 |
ff | +0.152 |
ously | +0.147 |
Neg logit contributions | |
forth | -0.095 |
atmeal | -0.095 |
shining | -0.092 |
we | -0.089 |
house | -0.089 |
Token | . |
Token ID | 13 |
Feature activation | -2.76e+00 |
Pos logit contributions | |
irk | +0.102 |
tant | +0.091 |
Mine | +0.090 |
ff | +0.089 |
disapproval | +0.087 |
Neg logit contributions | |
atmeal | -0.066 |
they | -0.066 |
forth | -0.064 |
we | -0.064 |
soon | -0.060 |
Token | Ben |
Token ID | 3932 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
rum | +0.066 |
ously | +0.065 |
irk | +0.063 |
ater | +0.061 |
rs | +0.060 |
Neg logit contributions | |
ancer | -0.051 |
atmeal | -0.051 |
mm | -0.046 |
rolling | -0.045 |
maybe | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | -4.01e-02 |
Pos logit contributions | |
irk | +0.075 |
rum | +0.070 |
ously | +0.066 |
ff | +0.065 |
rs | +0.064 |
Neg logit contributions | |
rolling | -0.067 |
atmeal | -0.064 |
rains | -0.063 |
oming | -0.063 |
mage | -0.062 |
Token | Tom |
Token ID | 4186 |
Feature activation | -2.80e+00 |
Pos logit contributions | |
rs | +0.001 |
rum | +0.001 |
irk | +0.001 |
aron | +0.001 |
screams | +0.001 |
Neg logit contributions | |
atmeal | -0.001 |
ancer | -0.001 |
rolling | -0.001 |
Hatt | -0.001 |
nam | -0.001 |
Token | he |
Token ID | 339 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
atmeal | +0.027 |
rolling | +0.025 |
pieces | +0.024 |
ouses | +0.024 |
ital | +0.024 |
Neg logit contributions | |
screams | -0.017 |
bites | -0.016 |
blood | -0.016 |
ks | -0.015 |
pain | -0.015 |
Token | heard |
Token ID | 2982 |
Feature activation | -2.77e+00 |
Pos logit contributions | |
screams | +0.002 |
ks | +0.002 |
irk | +0.002 |
rs | +0.002 |
bites | +0.002 |
Neg logit contributions | |
atmeal | -0.006 |
ancer | -0.005 |
rolling | -0.005 |
highlight | -0.005 |
Hatt | -0.005 |
Token | a |
Token ID | 257 |
Feature activation | -4.58e+00 |
Pos logit contributions | |
rs | +0.054 |
irk | +0.053 |
rum | +0.051 |
tant | +0.048 |
Mine | +0.048 |
Neg logit contributions | |
atmeal | -0.073 |
rolling | -0.071 |
ancer | -0.068 |
lifetime | -0.067 |
Hatt | -0.067 |
Token | terrible |
Token ID | 7818 |
Feature activation | -5.40e+00 |
Pos logit contributions | |
rs | +0.083 |
rum | +0.075 |
ases | +0.074 |
ud | +0.072 |
irk | +0.071 |
Neg logit contributions | |
rolling | -0.134 |
lifetime | -0.129 |
atmeal | -0.127 |
Hatt | -0.122 |
ancer | -0.121 |
Token | , |
Token ID | 11 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
rs | +0.099 |
Mine | +0.094 |
ud | +0.094 |
rum | +0.093 |
ases | +0.092 |
Neg logit contributions | |
atmeal | -0.144 |
rolling | -0.138 |
Hatt | -0.131 |
ancer | -0.130 |
ital | -0.130 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.42e+00 |
Pos logit contributions | |
rs | +0.038 |
rum | +0.037 |
ases | +0.037 |
ud | +0.036 |
irk | +0.036 |
Neg logit contributions | |
rolling | -0.037 |
nam | -0.036 |
atmeal | -0.035 |
lifetime | -0.035 |
ancer | -0.034 |
Token | squ |
Token ID | 2809 |
Feature activation | -1.65e+00 |
Pos logit contributions | |
ud | +0.143 |
ases | +0.139 |
irk | +0.135 |
Mine | +0.134 |
tant | +0.133 |
Neg logit contributions | |
rolling | -0.133 |
Hatt | -0.126 |
exploring | -0.123 |
Kirst | -0.122 |
atmeal | -0.122 |
Token | eal |
Token ID | 2287 |
Feature activation | -2.28e+00 |
Pos logit contributions | |
rs | +0.026 |
Mine | +0.025 |
rum | +0.025 |
screams | +0.024 |
words | +0.023 |
Neg logit contributions | |
atmeal | -0.050 |
rolling | -0.046 |
ancer | -0.045 |
oming | -0.043 |
igs | -0.043 |
Token | ! |
Token ID | 0 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
rs | +0.053 |
Mine | +0.051 |
tant | +0.051 |
screams | +0.050 |
bites | +0.050 |
Neg logit contributions | |
atmeal | -0.051 |
ancer | -0.049 |
rolling | -0.049 |
oming | -0.043 |
exploring | -0.043 |
Token | Start |
Token ID | 7253 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
rs | +0.036 |
rum | +0.033 |
irk | +0.033 |
tant | +0.033 |
screams | +0.032 |
Neg logit contributions | |
rolling | -0.062 |
atmeal | -0.061 |
ancer | -0.059 |
Hatt | -0.057 |
lifetime | -0.055 |
Token | led |
Token ID | 992 |
Feature activation | -1.58e+00 |
Pos logit contributions | |
rs | +0.034 |
screams | +0.033 |
irk | +0.033 |
rum | +0.032 |
bites | +0.031 |
Neg logit contributions | |
atmeal | -0.034 |
rolling | -0.032 |
ancer | -0.032 |
lifetime | -0.030 |
highlight | -0.030 |
Token | something |
Token ID | 1223 |
Feature activation | -2.70e+00 |
Pos logit contributions | |
rs | +0.053 |
rum | +0.052 |
irk | +0.052 |
ater | +0.049 |
aron | +0.048 |
Neg logit contributions | |
atmeal | -0.052 |
nam | -0.051 |
Hatt | -0.050 |
ancer | -0.048 |
highlight | -0.047 |
Token | move |
Token ID | 1445 |
Feature activation | -2.58e+00 |
Pos logit contributions | |
rs | +0.069 |
rum | +0.066 |
irk | +0.065 |
screams | +0.063 |
ff | +0.062 |
Neg logit contributions | |
atmeal | -0.057 |
rolling | -0.053 |
ancer | -0.051 |
highlight | -0.050 |
lifetime | -0.050 |
Token | and |
Token ID | 290 |
Feature activation | -1.33e-01 |
Pos logit contributions | |
rum | +0.063 |
irk | +0.063 |
rs | +0.060 |
aron | +0.060 |
screams | +0.060 |
Neg logit contributions | |
belt | -0.046 |
ancer | -0.045 |
atmeal | -0.045 |
rolling | -0.045 |
ations | -0.043 |
Token | heard |
Token ID | 2982 |
Feature activation | -3.35e+00 |
Pos logit contributions | |
screams | +0.003 |
rs | +0.002 |
ks | +0.002 |
irk | +0.002 |
bites | +0.002 |
Neg logit contributions | |
atmeal | -0.004 |
ancer | -0.004 |
rolling | -0.004 |
lifetime | -0.003 |
highlight | -0.003 |
Token | a |
Token ID | 257 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
irk | +0.076 |
rs | +0.076 |
rum | +0.076 |
ater | +0.073 |
aron | +0.070 |
Neg logit contributions | |
Hatt | -0.069 |
atmeal | -0.068 |
pieces | -0.067 |
nam | -0.066 |
rolling | -0.066 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
rs | +0.089 |
rum | +0.083 |
irk | +0.079 |
ases | +0.079 |
ud | +0.078 |
Neg logit contributions | |
rolling | -0.123 |
lifetime | -0.119 |
atmeal | -0.119 |
ancer | -0.113 |
Hatt | -0.112 |
Token | his |
Token ID | 465 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
ud | +0.158 |
irk | +0.152 |
fault | +0.150 |
ases | +0.144 |
tant | +0.141 |
Neg logit contributions | |
rolling | -0.114 |
Hatt | -0.113 |
shining | -0.112 |
explore | -0.109 |
cel | -0.107 |
Token | s |
Token ID | 82 |
Feature activation | -3.52e+00 |
Pos logit contributions | |
rs | +0.063 |
rum | +0.060 |
ud | +0.058 |
Mine | +0.058 |
aback | +0.057 |
Neg logit contributions | |
rolling | -0.048 |
tallest | -0.042 |
atmeal | -0.042 |
ancer | -0.042 |
lifetime | -0.042 |
Token | . |
Token ID | 13 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
Mine | +0.083 |
aback | +0.078 |
ud | +0.075 |
tant | +0.074 |
rs | +0.074 |
Neg logit contributions | |
rolling | -0.068 |
roof | -0.064 |
shining | -0.064 |
belt | -0.064 |
ail | -0.064 |
Token | He |
Token ID | 679 |
Feature activation | -2.41e+00 |
Pos logit contributions | |
rs | +0.047 |
ater | +0.046 |
screams | +0.044 |
rum | +0.043 |
tant | +0.043 |
Neg logit contributions | |
atmeal | -0.061 |
Hatt | -0.059 |
rolling | -0.058 |
ancer | -0.057 |
nam | -0.054 |
Token | felt |
Token ID | 2936 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
rs | +0.059 |
rum | +0.059 |
irk | +0.057 |
tant | +0.053 |
screams | +0.052 |
Neg logit contributions | |
rolling | -0.051 |
atmeal | -0.050 |
lifetime | -0.046 |
ancer | -0.046 |
Hatt | -0.046 |
Token | But |
Token ID | 1537 |
Feature activation | +8.97e-01 |
Pos logit contributions | |
rs | +0.006 |
screams | +0.006 |
rum | +0.006 |
irk | +0.006 |
ks | +0.006 |
Neg logit contributions | |
atmeal | -0.015 |
ancer | -0.014 |
rolling | -0.014 |
highlight | -0.014 |
lifetime | -0.014 |
Token | then |
Token ID | 788 |
Feature activation | -3.17e-01 |
Pos logit contributions | |
atmeal | +0.031 |
rolling | +0.031 |
lifetime | +0.030 |
ancer | +0.029 |
ouses | +0.029 |
Neg logit contributions | |
and | -0.013 |
its | -0.012 |
blood | -0.012 |
his | -0.012 |
screams | -0.011 |
Token | he |
Token ID | 339 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
screams | +0.005 |
bites | +0.005 |
ks | +0.005 |
rs | +0.005 |
thinks | +0.005 |
Neg logit contributions | |
atmeal | -0.010 |
rolling | -0.010 |
ancer | -0.010 |
highlight | -0.010 |
lifetime | -0.009 |
Token | heard |
Token ID | 2982 |
Feature activation | -3.43e+00 |
Pos logit contributions | |
rs | +0.025 |
screams | +0.024 |
irk | +0.024 |
rum | +0.023 |
bites | +0.023 |
Neg logit contributions | |
atmeal | -0.039 |
rolling | -0.037 |
ancer | -0.037 |
lifetime | -0.036 |
highlight | -0.035 |
Token | a |
Token ID | 257 |
Feature activation | -5.11e+00 |
Pos logit contributions | |
rs | +0.074 |
irk | +0.073 |
rum | +0.073 |
screams | +0.068 |
ater | +0.068 |
Neg logit contributions | |
atmeal | -0.080 |
Hatt | -0.076 |
rolling | -0.073 |
ancer | -0.072 |
pieces | -0.070 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
rs | +0.109 |
ud | +0.102 |
ases | +0.098 |
fault | +0.097 |
ez | +0.097 |
Neg logit contributions | |
rolling | -0.127 |
atmeal | -0.118 |
lifetime | -0.115 |
Hatt | -0.112 |
ancer | -0.108 |
Token | crack |
Token ID | 8469 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
fault | +0.154 |
ud | +0.154 |
irk | +0.143 |
tant | +0.142 |
Mine | +0.139 |
Neg logit contributions | |
Hatt | -0.115 |
atmeal | -0.115 |
rolling | -0.112 |
Kirst | -0.111 |
Tri | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | -2.50e+00 |
Pos logit contributions | |
Mine | +0.077 |
irk | +0.074 |
tant | +0.073 |
fault | +0.071 |
rs | +0.069 |
Neg logit contributions | |
atmeal | -0.065 |
ations | -0.061 |
mage | -0.056 |
house | -0.055 |
forth | -0.054 |
Token | The |
Token ID | 383 |
Feature activation | -1.79e+00 |
Pos logit contributions | |
rs | +0.048 |
rum | +0.047 |
screams | +0.046 |
irk | +0.046 |
ks | +0.044 |
Neg logit contributions | |
atmeal | -0.064 |
ancer | -0.061 |
Hatt | -0.060 |
rolling | -0.059 |
nam | -0.056 |
Token | branch |
Token ID | 8478 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
rs | +0.033 |
irk | +0.031 |
rum | +0.030 |
tant | +0.029 |
ks | +0.028 |
Neg logit contributions | |
atmeal | -0.052 |
rolling | -0.048 |
ancer | -0.048 |
lifetime | -0.047 |
highlight | -0.046 |
Token | he |
Token ID | 339 |
Feature activation | -2.00e+00 |
Pos logit contributions | |
irk | +0.039 |
rs | +0.038 |
rum | +0.037 |
tant | +0.035 |
Mine | +0.034 |
Neg logit contributions | |
atmeal | -0.032 |
rolling | -0.030 |
ancer | -0.027 |
belt | -0.027 |
ail | -0.027 |
Token | Then |
Token ID | 3244 |
Feature activation | +4.37e-01 |
Pos logit contributions | |
rs | +0.016 |
screams | +0.016 |
irk | +0.016 |
rum | +0.015 |
bites | +0.015 |
Neg logit contributions | |
atmeal | -0.030 |
rolling | -0.028 |
ancer | -0.028 |
lifetime | -0.027 |
highlight | -0.027 |
Token | suddenly |
Token ID | 6451 |
Feature activation | -4.29e-01 |
Pos logit contributions | |
atmeal | +0.015 |
ancer | +0.015 |
rolling | +0.015 |
ital | +0.014 |
inations | +0.014 |
Neg logit contributions | |
and | -0.006 |
his | -0.006 |
screams | -0.006 |
bites | -0.006 |
its | -0.006 |
Token | he |
Token ID | 339 |
Feature activation | -2.93e-01 |
Pos logit contributions | |
screams | +0.007 |
ks | +0.007 |
bites | +0.007 |
rs | +0.006 |
thinks | +0.006 |
Neg logit contributions | |
atmeal | -0.014 |
ancer | -0.013 |
rolling | -0.013 |
highlight | -0.012 |
lifetime | -0.012 |
Token | heard |
Token ID | 2982 |
Feature activation | -3.05e+00 |
Pos logit contributions | |
rs | +0.005 |
screams | +0.005 |
irk | +0.005 |
bites | +0.005 |
ks | +0.005 |
Neg logit contributions | |
atmeal | -0.009 |
ancer | -0.008 |
rolling | -0.008 |
lifetime | -0.008 |
highlight | -0.008 |
Token | a |
Token ID | 257 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
rs | +0.061 |
irk | +0.059 |
rum | +0.057 |
screams | +0.054 |
Mine | +0.053 |
Neg logit contributions | |
atmeal | -0.079 |
rolling | -0.077 |
ancer | -0.074 |
Hatt | -0.074 |
lifetime | -0.073 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
rs | +0.080 |
rum | +0.073 |
ud | +0.072 |
irk | +0.071 |
ases | +0.070 |
Neg logit contributions | |
rolling | -0.137 |
atmeal | -0.132 |
lifetime | -0.131 |
ancer | -0.125 |
Hatt | -0.125 |
Token | noise |
Token ID | 7838 |
Feature activation | -3.67e+00 |
Pos logit contributions | |
ud | +0.146 |
irk | +0.135 |
ases | +0.132 |
Mine | +0.131 |
tant | +0.131 |
Neg logit contributions | |
rolling | -0.142 |
Hatt | -0.130 |
atmeal | -0.129 |
exploring | -0.126 |
explore | -0.126 |
Token | . |
Token ID | 13 |
Feature activation | -2.14e+00 |
Pos logit contributions | |
tant | +0.078 |
Mine | +0.077 |
irk | +0.076 |
rum | +0.074 |
rs | +0.072 |
Neg logit contributions | |
rolling | -0.084 |
atmeal | -0.083 |
exploring | -0.081 |
shining | -0.079 |
ancer | -0.078 |
Token | He |
Token ID | 679 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
rs | +0.033 |
irk | +0.031 |
rum | +0.030 |
screams | +0.030 |
tant | +0.029 |
Neg logit contributions | |
atmeal | -0.066 |
rolling | -0.066 |
ancer | -0.063 |
Hatt | -0.061 |
lifetime | -0.060 |
Token | dropped |
Token ID | 5710 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
rs | +0.045 |
irk | +0.044 |
screams | +0.044 |
rum | +0.043 |
bites | +0.042 |
Neg logit contributions | |
atmeal | -0.051 |
rolling | -0.048 |
ancer | -0.047 |
lifetime | -0.045 |
highlight | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -8.08e-01 |
Pos logit contributions | |
irk | +0.076 |
aron | +0.074 |
ater | +0.071 |
rs | +0.071 |
ud | +0.071 |
Neg logit contributions | |
exploring | -0.032 |
Hatt | -0.031 |
Tri | -0.030 |
forth | -0.029 |
nam | -0.028 |
Token | The |
Token ID | 383 |
Feature activation | -9.89e-01 |
Pos logit contributions | |
rum | +0.029 |
rs | +0.027 |
irk | +0.026 |
screams | +0.026 |
ater | +0.025 |
Neg logit contributions | |
rolling | -0.037 |
ancer | -0.037 |
atmeal | -0.036 |
Hatt | -0.034 |
angers | -0.033 |
Token | toy |
Token ID | 13373 |
Feature activation | -1.04e+00 |
Pos logit contributions | |
rs | +0.022 |
rum | +0.021 |
ff | +0.021 |
irk | +0.020 |
aron | +0.020 |
Neg logit contributions | |
atmeal | -0.024 |
ancer | -0.022 |
rolling | -0.022 |
belt | -0.021 |
highlight | -0.021 |
Token | gun |
Token ID | 2485 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
rs | +0.022 |
irk | +0.021 |
rum | +0.021 |
aron | +0.019 |
ff | +0.019 |
Neg logit contributions | |
atmeal | -0.027 |
rolling | -0.025 |
ancer | -0.025 |
Hatt | -0.024 |
lifetime | -0.024 |
Token | made |
Token ID | 925 |
Feature activation | -2.67e+00 |
Pos logit contributions | |
irk | +0.065 |
rs | +0.059 |
rum | +0.059 |
aron | +0.058 |
ff | +0.055 |
Neg logit contributions | |
rolling | -0.036 |
atmeal | -0.032 |
cases | -0.032 |
oming | -0.029 |
highlight | -0.029 |
Token | a |
Token ID | 257 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
rum | +0.065 |
irk | +0.064 |
rs | +0.062 |
aron | +0.061 |
ater | +0.059 |
Neg logit contributions | |
Hatt | -0.054 |
atmeal | -0.053 |
ancer | -0.051 |
pieces | -0.051 |
rolling | -0.051 |
Token | loud |
Token ID | 7812 |
Feature activation | -6.40e+00 |
Pos logit contributions | |
rs | +0.111 |
irk | +0.102 |
rum | +0.101 |
ases | +0.100 |
ez | +0.094 |
Neg logit contributions | |
rolling | -0.112 |
lifetime | -0.110 |
highlight | -0.097 |
tallest | -0.097 |
atmeal | -0.095 |
Token | noise |
Token ID | 7838 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
irk | +0.172 |
ud | +0.163 |
fault | +0.152 |
ff | +0.148 |
oco | +0.146 |
Neg logit contributions | |
forth | -0.102 |
shining | -0.097 |
house | -0.095 |
oming | -0.094 |
rolling | -0.094 |
Token | and |
Token ID | 290 |
Feature activation | -1.00e+00 |
Pos logit contributions | |
irk | +0.095 |
rum | +0.082 |
Mine | +0.082 |
ff | +0.080 |
tant | +0.077 |
Neg logit contributions | |
they | -0.075 |
atmeal | -0.074 |
shining | -0.074 |
exploring | -0.070 |
before | -0.070 |
Token | a |
Token ID | 257 |
Feature activation | -4.55e+00 |
Pos logit contributions | |
irk | +0.023 |
rs | +0.022 |
rum | +0.022 |
ff | +0.020 |
aron | +0.020 |
Neg logit contributions | |
atmeal | -0.023 |
rolling | -0.022 |
ancer | -0.022 |
Hatt | -0.021 |
nam | -0.021 |
Token | plastic |
Token ID | 7309 |
Feature activation | -4.17e+00 |
Pos logit contributions | |
rs | +0.106 |
ases | +0.097 |
rum | +0.096 |
irk | +0.093 |
ff | +0.087 |
Neg logit contributions | |
lifetime | -0.110 |
rolling | -0.109 |
atmeal | -0.099 |
highlight | -0.097 |
ancer | -0.095 |
Token | bullet |
Token ID | 10492 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
rs | +0.100 |
rum | +0.094 |
irk | +0.093 |
ff | +0.090 |
aron | +0.088 |
Neg logit contributions | |
rolling | -0.087 |
atmeal | -0.086 |
lifetime | -0.083 |
belt | -0.080 |
ancer | -0.080 |
Token | and |
Token ID | 290 |
Feature activation | +2.14e+00 |
Pos logit contributions | |
atmeal | +0.055 |
ancer | +0.053 |
Hatt | +0.050 |
highlight | +0.050 |
lifetime | +0.050 |
Neg logit contributions | |
irk | -0.025 |
rum | -0.024 |
screams | -0.024 |
rs | -0.022 |
ff | -0.021 |
Token | books |
Token ID | 3835 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
atmeal | +0.060 |
rolling | +0.059 |
ancer | +0.058 |
oming | +0.055 |
lifetime | +0.055 |
Neg logit contributions | |
screams | -0.041 |
bites | -0.041 |
words | -0.041 |
rs | -0.041 |
thinks | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | +5.58e-01 |
Pos logit contributions | |
atmeal | +0.061 |
ancer | +0.058 |
rolling | +0.055 |
lifetime | +0.055 |
ouses | +0.055 |
Neg logit contributions | |
screams | -0.028 |
irk | -0.027 |
rum | -0.027 |
rs | -0.025 |
Mine | -0.024 |
Token | One |
Token ID | 1881 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
atmeal | +0.014 |
rolling | +0.013 |
ancer | +0.013 |
lifetime | +0.013 |
ital | +0.012 |
Neg logit contributions | |
rs | -0.013 |
screams | -0.012 |
irk | -0.012 |
bites | -0.012 |
ks | -0.012 |
Token | day |
Token ID | 1110 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
atmeal | +0.013 |
rolling | +0.013 |
ancer | +0.012 |
lifetime | +0.012 |
Hatt | +0.011 |
Neg logit contributions | |
screams | -0.017 |
rs | -0.017 |
irk | -0.017 |
bites | -0.016 |
rum | -0.016 |
Token | , |
Token ID | 11 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
atmeal | +0.103 |
rolling | +0.097 |
lifetime | +0.097 |
ital | +0.096 |
pieces | +0.096 |
Neg logit contributions | |
screams | -0.038 |
rs | -0.038 |
bites | -0.037 |
ks | -0.037 |
rum | -0.034 |
Token | they |
Token ID | 484 |
Feature activation | +1.45e+00 |
Pos logit contributions | |
atmeal | +0.069 |
rolling | +0.065 |
lifetime | +0.062 |
ancer | +0.059 |
ital | +0.059 |
Neg logit contributions | |
screams | -0.097 |
rs | -0.096 |
bites | -0.096 |
ks | -0.094 |
thinks | -0.094 |
Token | found |
Token ID | 1043 |
Feature activation | -1.99e-01 |
Pos logit contributions | |
atmeal | +0.039 |
rolling | +0.037 |
ancer | +0.036 |
lifetime | +0.036 |
highlight | +0.034 |
Neg logit contributions | |
rs | -0.029 |
irk | -0.029 |
screams | -0.028 |
ks | -0.027 |
bites | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
rum | +0.004 |
rs | +0.004 |
irk | +0.004 |
aron | +0.004 |
screams | +0.004 |
Neg logit contributions | |
atmeal | -0.005 |
ancer | -0.005 |
Hatt | -0.005 |
highlight | -0.005 |
rolling | -0.004 |
Token | big |
Token ID | 1263 |
Feature activation | -2.30e+00 |
Pos logit contributions | |
screams | +0.023 |
rs | +0.023 |
irk | +0.023 |
bites | +0.022 |
word | +0.022 |
Neg logit contributions | |
atmeal | -0.040 |
rolling | -0.038 |
ancer | -0.038 |
highlight | -0.036 |
lifetime | -0.036 |
Token | box |
Token ID | 3091 |
Feature activation | +6.87e-01 |
Pos logit contributions | |
rs | +0.047 |
irk | +0.045 |
screams | +0.045 |
rum | +0.044 |
ks | +0.043 |
Neg logit contributions | |
atmeal | -0.061 |
rolling | -0.057 |
ancer | -0.056 |
lifetime | -0.054 |
Hatt | -0.053 |
Token | Lily |
Token ID | 20037 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
atmeal | +0.086 |
rolling | +0.083 |
lifetime | +0.079 |
ancer | +0.077 |
inations | +0.075 |
Neg logit contributions | |
and | -0.069 |
rs | -0.069 |
screams | -0.069 |
bites | -0.066 |
tant | -0.066 |
Token | and |
Token ID | 290 |
Feature activation | +2.89e+00 |
Pos logit contributions | |
atmeal | +0.022 |
rolling | +0.021 |
ancer | +0.021 |
lifetime | +0.020 |
highlight | +0.020 |
Neg logit contributions | |
rs | -0.005 |
irk | -0.005 |
screams | -0.005 |
rum | -0.004 |
ks | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | +1.83e+00 |
Pos logit contributions | |
atmeal | +0.079 |
rolling | +0.074 |
ancer | +0.073 |
Hatt | +0.070 |
highlight | +0.069 |
Neg logit contributions | |
rs | -0.057 |
irk | -0.055 |
rum | -0.054 |
screams | -0.054 |
ks | -0.052 |
Token | mom |
Token ID | 1995 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
atmeal | +0.041 |
rolling | +0.039 |
ancer | +0.038 |
lifetime | +0.036 |
highlight | +0.035 |
Neg logit contributions | |
rs | -0.045 |
screams | -0.044 |
irk | -0.044 |
rum | -0.043 |
ks | -0.042 |
Token | sailed |
Token ID | 33835 |
Feature activation | +2.30e+00 |
Pos logit contributions | |
atmeal | +0.030 |
rolling | +0.028 |
ancer | +0.028 |
lifetime | +0.028 |
Hatt | +0.027 |
Neg logit contributions | |
rs | -0.029 |
screams | -0.028 |
irk | -0.028 |
bites | -0.028 |
ks | -0.028 |
Token | their |
Token ID | 511 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
rolling | +0.049 |
ancer | +0.046 |
lifetime | +0.045 |
atmeal | +0.045 |
highlight | +0.044 |
Neg logit contributions | |
rum | -0.057 |
screams | -0.055 |
irk | -0.055 |
rs | -0.053 |
ez | -0.053 |
Token | boats |
Token ID | 16659 |
Feature activation | +4.71e+00 |
Pos logit contributions | |
atmeal | +0.091 |
ancer | +0.084 |
rolling | +0.080 |
Hatt | +0.079 |
highlight | +0.076 |
Neg logit contributions | |
screams | -0.080 |
bites | -0.077 |
rs | -0.074 |
thinks | -0.073 |
tant | -0.073 |
Token | together |
Token ID | 1978 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
atmeal | +0.109 |
rolling | +0.105 |
ancer | +0.103 |
lifetime | +0.098 |
highlight | +0.096 |
Neg logit contributions | |
rs | -0.110 |
irk | -0.109 |
screams | -0.108 |
rum | -0.106 |
bites | -0.102 |
Token | and |
Token ID | 290 |
Feature activation | +3.65e+00 |
Pos logit contributions | |
rolling | +0.050 |
exploring | +0.047 |
lifetime | +0.046 |
highlight | +0.045 |
atmeal | +0.044 |
Neg logit contributions | |
irk | -0.041 |
rum | -0.041 |
screams | -0.037 |
ez | -0.037 |
tant | -0.036 |
Token | had |
Token ID | 550 |
Feature activation | +5.12e-01 |
Pos logit contributions | |
atmeal | +0.104 |
rolling | +0.096 |
ancer | +0.096 |
lifetime | +0.091 |
highlight | +0.090 |
Neg logit contributions | |
ks | -0.070 |
screams | -0.070 |
rs | -0.070 |
bites | -0.068 |
thinks | -0.066 |
Token | a |
Token ID | 257 |
Feature activation | +5.97e-01 |
Pos logit contributions | |
atmeal | +0.012 |
rolling | +0.011 |
lifetime | +0.011 |
highlight | +0.011 |
ancer | +0.011 |
Neg logit contributions | |
irk | -0.012 |
rum | -0.012 |
rs | -0.012 |
screams | -0.011 |
tant | -0.011 |
Token | we |
Token ID | 356 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
rolling | +0.095 |
atmeal | +0.092 |
ouses | +0.089 |
lifetime | +0.085 |
pieces | +0.083 |
Neg logit contributions | |
and | -0.061 |
thinks | -0.057 |
rs | -0.056 |
word | -0.055 |
bites | -0.053 |
Token | have |
Token ID | 423 |
Feature activation | +5.41e-01 |
Pos logit contributions | |
atmeal | +0.029 |
rolling | +0.028 |
lifetime | +0.027 |
ancer | +0.027 |
highlight | +0.026 |
Neg logit contributions | |
rs | -0.024 |
screams | -0.023 |
thinks | -0.023 |
bites | -0.023 |
irk | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
atmeal | +0.018 |
rolling | +0.017 |
ancer | +0.017 |
lifetime | +0.017 |
highlight | +0.016 |
Neg logit contributions | |
rs | -0.007 |
irk | -0.007 |
screams | -0.007 |
rum | -0.007 |
ks | -0.006 |
Token | hurry |
Token ID | 23290 |
Feature activation | +2.05e+00 |
Pos logit contributions | |
atmeal | +0.010 |
rolling | +0.009 |
ancer | +0.009 |
lifetime | +0.009 |
highlight | +0.008 |
Neg logit contributions | |
rs | -0.010 |
screams | -0.010 |
irk | -0.010 |
rum | -0.010 |
bites | -0.010 |
Token | , |
Token ID | 11 |
Feature activation | +2.78e+00 |
Pos logit contributions | |
atmeal | +0.068 |
rolling | +0.065 |
ancer | +0.065 |
lifetime | +0.063 |
highlight | +0.062 |
Neg logit contributions | |
rs | -0.028 |
screams | -0.027 |
irk | -0.026 |
rum | -0.025 |
bites | -0.024 |
Token | because |
Token ID | 780 |
Feature activation | +3.67e+00 |
Pos logit contributions | |
atmeal | +0.076 |
rolling | +0.072 |
ancer | +0.071 |
lifetime | +0.069 |
highlight | +0.067 |
Neg logit contributions | |
rs | -0.054 |
screams | -0.053 |
irk | -0.052 |
rum | -0.050 |
bites | -0.050 |
Token | mom |
Token ID | 1995 |
Feature activation | +6.11e-01 |
Pos logit contributions | |
rolling | +0.110 |
atmeal | +0.108 |
ouses | +0.100 |
lifetime | +0.100 |
ital | +0.097 |
Neg logit contributions | |
and | -0.065 |
its | -0.062 |
word | -0.061 |
words | -0.061 |
blood | -0.060 |
Token | will |
Token ID | 481 |
Feature activation | +3.35e-01 |
Pos logit contributions | |
atmeal | +0.015 |
ancer | +0.014 |
rolling | +0.014 |
lifetime | +0.013 |
highlight | +0.013 |
Neg logit contributions | |
rs | -0.014 |
screams | -0.014 |
irk | -0.014 |
rum | -0.013 |
ks | -0.013 |
Token | be |
Token ID | 307 |
Feature activation | +8.02e-01 |
Pos logit contributions | |
atmeal | +0.008 |
rolling | +0.008 |
ancer | +0.007 |
lifetime | +0.007 |
highlight | +0.007 |
Neg logit contributions | |
rs | -0.008 |
screams | -0.007 |
irk | -0.007 |
rum | -0.007 |
bites | -0.007 |
Token | home |
Token ID | 1363 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
atmeal | +0.022 |
ancer | +0.021 |
rolling | +0.021 |
lifetime | +0.020 |
Hatt | +0.019 |
Neg logit contributions | |
rs | -0.016 |
screams | -0.015 |
irk | -0.015 |
ks | -0.015 |
rum | -0.015 |
Token | soon |
Token ID | 2582 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
atmeal | +0.040 |
rolling | +0.039 |
ancer | +0.038 |
lifetime | +0.037 |
highlight | +0.036 |
Neg logit contributions | |
rs | -0.021 |
screams | -0.019 |
rum | -0.019 |
irk | -0.018 |
ks | -0.018 |
Token | her |
Token ID | 607 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
rs | +0.012 |
screams | +0.012 |
irk | +0.012 |
rum | +0.012 |
bites | +0.011 |
Neg logit contributions | |
atmeal | -0.016 |
rolling | -0.015 |
ancer | -0.015 |
lifetime | -0.014 |
highlight | -0.014 |
Token | special |
Token ID | 2041 |
Feature activation | +4.02e-01 |
Pos logit contributions | |
atmeal | +0.048 |
rolling | +0.045 |
ancer | +0.045 |
lifetime | +0.041 |
Hatt | +0.041 |
Neg logit contributions | |
rs | -0.046 |
screams | -0.045 |
irk | -0.044 |
bites | -0.043 |
rum | -0.043 |
Token | prize |
Token ID | 11596 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
atmeal | +0.009 |
rolling | +0.009 |
ancer | +0.008 |
lifetime | +0.008 |
highlight | +0.008 |
Neg logit contributions | |
rs | -0.010 |
screams | -0.010 |
irk | -0.009 |
rum | -0.009 |
ks | -0.009 |
Token | ! |
Token ID | 0 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
atmeal | +0.049 |
rolling | +0.047 |
ancer | +0.046 |
lifetime | +0.046 |
Hatt | +0.045 |
Neg logit contributions | |
rs | -0.017 |
screams | -0.017 |
irk | -0.017 |
rum | -0.016 |
bites | -0.015 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +8.09e-01 |
Pos logit contributions | |
atmeal | +0.056 |
rolling | +0.055 |
ancer | +0.054 |
Hatt | +0.052 |
lifetime | +0.051 |
Neg logit contributions | |
rs | -0.044 |
screams | -0.044 |
bites | -0.043 |
rum | -0.042 |
ks | -0.042 |
Token | Once |
Token ID | 7454 |
Feature activation | +3.12e+00 |
Pos logit contributions | |
atmeal | +0.018 |
ancer | +0.018 |
rolling | +0.017 |
lifetime | +0.016 |
Hatt | +0.016 |
Neg logit contributions | |
screams | -0.019 |
rs | -0.019 |
rum | -0.019 |
irk | -0.018 |
tant | -0.018 |
Token | upon |
Token ID | 2402 |
Feature activation | -7.61e-01 |
Pos logit contributions | |
atmeal | +0.060 |
rolling | +0.053 |
lifetime | +0.050 |
ancer | +0.050 |
highlight | +0.049 |
Neg logit contributions | |
irk | -0.087 |
rs | -0.087 |
screams | -0.086 |
rum | -0.084 |
ks | -0.083 |
Token | a |
Token ID | 257 |
Feature activation | +6.41e-01 |
Pos logit contributions | |
rs | +0.015 |
irk | +0.015 |
rum | +0.014 |
screams | +0.014 |
tant | +0.013 |
Neg logit contributions | |
atmeal | -0.021 |
rolling | -0.020 |
ancer | -0.019 |
highlight | -0.019 |
lifetime | -0.019 |
Token | time |
Token ID | 640 |
Feature activation | +1.51e+00 |
Pos logit contributions | |
atmeal | +0.014 |
rolling | +0.013 |
ital | +0.012 |
lifetime | +0.012 |
highlight | +0.012 |
Neg logit contributions | |
rs | -0.016 |
rum | -0.016 |
screams | -0.016 |
irk | -0.015 |
ases | -0.015 |
Token | there |
Token ID | 612 |
Feature activation | -4.38e-01 |
Pos logit contributions | |
atmeal | +0.048 |
rolling | +0.044 |
ancer | +0.044 |
lifetime | +0.043 |
highlight | +0.043 |
Neg logit contributions | |
rs | -0.024 |
screams | -0.023 |
irk | -0.022 |
rum | -0.022 |
ks | -0.021 |
Token | was |
Token ID | 373 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
rs | +0.010 |
irk | +0.010 |
screams | +0.010 |
rum | +0.010 |
tant | +0.009 |
Neg logit contributions | |
atmeal | -0.010 |
rolling | -0.009 |
ancer | -0.009 |
Hatt | -0.009 |
lifetime | -0.009 |
Token | |
Token ID | 220 |
Feature activation | +1.13e+00 |
Pos logit contributions | |
atmeal | +0.043 |
ancer | +0.040 |
rolling | +0.039 |
lifetime | +0.039 |
highlight | +0.039 |
Neg logit contributions | |
rs | -0.021 |
irk | -0.019 |
screams | -0.019 |
Mine | -0.018 |
thinks | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +5.47e-01 |
Pos logit contributions | |
atmeal | +0.039 |
rolling | +0.037 |
ancer | +0.037 |
lifetime | +0.036 |
highlight | +0.035 |
Neg logit contributions | |
rs | -0.014 |
screams | -0.013 |
irk | -0.013 |
rum | -0.013 |
ks | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
atmeal | +0.018 |
rolling | +0.017 |
ancer | +0.017 |
lifetime | +0.016 |
highlight | +0.016 |
Neg logit contributions | |
rs | -0.008 |
screams | -0.007 |
irk | -0.007 |
rum | -0.007 |
bites | -0.007 |
Token | When |
Token ID | 2215 |
Feature activation | +3.54e+00 |
Pos logit contributions | |
atmeal | +0.045 |
ancer | +0.042 |
rolling | +0.039 |
Hatt | +0.037 |
lifetime | +0.037 |
Neg logit contributions | |
rs | -0.043 |
Mine | -0.042 |
rum | -0.042 |
irk | -0.041 |
screams | -0.041 |
Token | they |
Token ID | 484 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
atmeal | +0.101 |
rolling | +0.100 |
inations | +0.099 |
ancer | +0.096 |
ouses | +0.095 |
Neg logit contributions | |
its | -0.067 |
and | -0.064 |
Tom | -0.060 |
his | -0.060 |
dog | -0.060 |
Token | arrived |
Token ID | 5284 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
atmeal | +0.067 |
rolling | +0.063 |
ancer | +0.062 |
lifetime | +0.061 |
Hatt | +0.059 |
Neg logit contributions | |
rs | -0.060 |
screams | -0.058 |
irk | -0.058 |
bites | -0.058 |
ks | -0.056 |
Token | , |
Token ID | 11 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
atmeal | +0.116 |
ancer | +0.107 |
inations | +0.105 |
lifetime | +0.104 |
highlight | +0.104 |
Neg logit contributions | |
and | -0.034 |
screams | -0.032 |
rs | -0.031 |
irk | -0.030 |
ks | -0.030 |
Token | the |
Token ID | 262 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
atmeal | +0.094 |
rolling | +0.085 |
lifetime | +0.082 |
inations | +0.081 |
ancer | +0.081 |
Neg logit contributions | |
rs | -0.055 |
screams | -0.054 |
and | -0.054 |
its | -0.053 |
tant | -0.053 |
Token | little |
Token ID | 1310 |
Feature activation | +1.27e+00 |
Pos logit contributions | |
atmeal | +0.052 |
rolling | +0.048 |
ancer | +0.048 |
pieces | +0.047 |
ital | +0.046 |
Neg logit contributions | |
screams | -0.027 |
dog | -0.026 |
words | -0.025 |
bites | -0.025 |
thinks | -0.025 |
Token | girl |
Token ID | 2576 |
Feature activation | +3.63e-01 |
Pos logit contributions | |
atmeal | +0.040 |
rolling | +0.037 |
lifetime | +0.036 |
inations | +0.036 |
ancer | +0.035 |
Neg logit contributions | |
screams | -0.020 |
bites | -0.019 |
irk | -0.019 |
rs | -0.019 |
thinks | -0.019 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.07e+00 |
Pos logit contributions | |
atmeal | +0.010 |
ancer | +0.010 |
rolling | +0.009 |
highlight | +0.009 |
lifetime | +0.009 |
Neg logit contributions | |
screams | -0.007 |
rs | -0.006 |
bites | -0.006 |
ks | -0.006 |
irk | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
irk | +0.015 |
rum | +0.013 |
rs | +0.013 |
tant | +0.013 |
gging | +0.012 |
Neg logit contributions | |
atmeal | -0.015 |
oming | -0.014 |
rolling | -0.014 |
ancer | -0.014 |
cases | -0.013 |
Token | She |
Token ID | 1375 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
rum | +0.032 |
rs | +0.031 |
screams | +0.030 |
ks | +0.030 |
irk | +0.029 |
Neg logit contributions | |
atmeal | -0.031 |
rolling | -0.031 |
Hatt | -0.030 |
ancer | -0.030 |
angers | -0.027 |
Token | also |
Token ID | 635 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
rs | +0.050 |
rum | +0.048 |
irk | +0.048 |
tant | +0.044 |
screams | +0.044 |
Neg logit contributions | |
atmeal | -0.045 |
rolling | -0.043 |
nam | -0.040 |
Hatt | -0.039 |
lifetime | -0.038 |
Token | saw |
Token ID | 2497 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
rum | +0.040 |
rs | +0.040 |
irk | +0.039 |
screams | +0.038 |
tant | +0.037 |
Neg logit contributions | |
atmeal | -0.033 |
rolling | -0.031 |
nam | -0.029 |
lifetime | -0.029 |
Hatt | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | -2.92e+00 |
Pos logit contributions | |
rum | +0.042 |
irk | +0.042 |
rs | +0.042 |
aron | +0.041 |
ater | +0.040 |
Neg logit contributions | |
atmeal | -0.037 |
nam | -0.037 |
Hatt | -0.035 |
pieces | -0.034 |
ancer | -0.032 |
Token | bag |
Token ID | 6131 |
Feature activation | +6.36e-01 |
Pos logit contributions | |
rs | +0.067 |
rum | +0.063 |
irk | +0.061 |
ases | +0.060 |
ks | +0.060 |
Neg logit contributions | |
atmeal | -0.071 |
rolling | -0.068 |
lifetime | -0.066 |
ancer | -0.065 |
highlight | -0.063 |
Token | in |
Token ID | 287 |
Feature activation | -2.56e+00 |
Pos logit contributions | |
atmeal | +0.017 |
rolling | +0.016 |
ancer | +0.015 |
lifetime | +0.015 |
highlight | +0.015 |
Neg logit contributions | |
rs | -0.013 |
screams | -0.013 |
irk | -0.013 |
rum | -0.012 |
bites | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | +3.75e-01 |
Pos logit contributions | |
irk | +0.073 |
rum | +0.070 |
screams | +0.069 |
rs | +0.068 |
ez | +0.067 |
Neg logit contributions | |
nam | -0.048 |
Hatt | -0.045 |
chard | -0.037 |
Grac | -0.037 |
Kirst | -0.036 |
Token | trash |
Token ID | 13913 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
atmeal | +0.008 |
rolling | +0.007 |
highlight | +0.007 |
lifetime | +0.007 |
ancer | +0.007 |
Neg logit contributions | |
rs | -0.010 |
rum | -0.010 |
irk | -0.010 |
screams | -0.010 |
ks | -0.009 |
Token | can |
Token ID | 460 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
rum | +0.020 |
ez | +0.018 |
tant | +0.018 |
irk | +0.018 |
gging | +0.018 |
Neg logit contributions | |
atmeal | -0.015 |
ancer | -0.015 |
Hatt | -0.014 |
oming | -0.014 |
umes | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e+00 |
Pos logit contributions | |
irk | +0.038 |
rs | +0.036 |
tant | +0.036 |
screams | +0.035 |
gging | +0.034 |
Neg logit contributions | |
atmeal | -0.044 |
rolling | -0.040 |
ancer | -0.038 |
Hatt | -0.037 |
belt | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
atmeal | +0.025 |
rolling | +0.025 |
ancer | +0.024 |
lifetime | +0.024 |
Hatt | +0.024 |
Neg logit contributions | |
rs | -0.008 |
screams | -0.008 |
irk | -0.008 |
rum | -0.008 |
bites | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +1.97e+00 |
Pos logit contributions | |
atmeal | +0.035 |
rolling | +0.034 |
ancer | +0.033 |
lifetime | +0.032 |
highlight | +0.032 |
Neg logit contributions | |
rs | -0.020 |
irk | -0.019 |
rum | -0.019 |
screams | -0.019 |
ks | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | +3.00e-01 |
Pos logit contributions | |
atmeal | +0.060 |
ancer | +0.058 |
rolling | +0.058 |
ouses | +0.054 |
lifetime | +0.053 |
Neg logit contributions | |
screams | -0.036 |
rs | -0.035 |
bites | -0.034 |
ks | -0.034 |
blood | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
atmeal | +0.009 |
ancer | +0.008 |
rolling | +0.008 |
lifetime | +0.008 |
pieces | +0.007 |
Neg logit contributions | |
screams | -0.006 |
rs | -0.006 |
bites | -0.005 |
irk | -0.005 |
thinks | -0.005 |
Token | dark |
Token ID | 3223 |
Feature activation | -1.64e+00 |
Pos logit contributions | |
rs | +0.002 |
screams | +0.002 |
rum | +0.002 |
irk | +0.002 |
bites | +0.002 |
Neg logit contributions | |
atmeal | -0.003 |
ancer | -0.003 |
rolling | -0.002 |
lifetime | -0.002 |
Hatt | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -2.65e-01 |
Pos logit contributions | |
irk | +0.023 |
screams | +0.022 |
rum | +0.022 |
rs | +0.021 |
tant | +0.020 |
Neg logit contributions | |
atmeal | -0.053 |
rolling | -0.051 |
ancer | -0.050 |
lifetime | -0.049 |
Hatt | -0.049 |
Token | Sue |
Token ID | 26089 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
rs | +0.006 |
rum | +0.006 |
irk | +0.006 |
screams | +0.006 |
tant | +0.005 |
Neg logit contributions | |
atmeal | -0.006 |
rolling | -0.006 |
ancer | -0.006 |
highlight | -0.006 |
lifetime | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +3.55e-01 |
Pos logit contributions | |
rs | +0.025 |
irk | +0.024 |
rum | +0.024 |
tant | +0.023 |
screams | +0.023 |
Neg logit contributions | |
atmeal | -0.026 |
rolling | -0.025 |
ancer | -0.023 |
lifetime | -0.023 |
Hatt | -0.023 |
Token | still |
Token ID | 991 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
atmeal | +0.010 |
ancer | +0.009 |
rolling | +0.009 |
lifetime | +0.008 |
highlight | +0.008 |
Neg logit contributions | |
rs | -0.007 |
screams | -0.007 |
irk | -0.007 |
rum | -0.007 |
ks | -0.007 |
Token | lost |
Token ID | 2626 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
rs | +0.024 |
Mine | +0.023 |
rum | +0.023 |
irk | +0.023 |
screams | +0.023 |
Neg logit contributions | |
rolling | -0.024 |
atmeal | -0.023 |
ancer | -0.023 |
highlight | -0.022 |
lifetime | -0.022 |
Token | and |
Token ID | 290 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
irk | +0.033 |
screams | +0.032 |
rum | +0.030 |
Mine | +0.030 |
ases | +0.029 |
Neg logit contributions | |
Hatt | -0.049 |
nam | -0.048 |
exploring | -0.048 |
atmeal | -0.047 |
ancer | -0.046 |
Token | send |
Token ID | 3758 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
rs | +0.013 |
screams | +0.012 |
rum | +0.012 |
irk | +0.012 |
thinks | +0.011 |
Neg logit contributions | |
atmeal | -0.017 |
ancer | -0.016 |
rolling | -0.016 |
lifetime | -0.015 |
highlight | -0.015 |
Token | things |
Token ID | 1243 |
Feature activation | +9.02e-01 |
Pos logit contributions | |
irk | +0.019 |
rs | +0.019 |
screams | +0.019 |
rum | +0.018 |
bites | +0.017 |
Neg logit contributions | |
atmeal | -0.024 |
ancer | -0.023 |
rolling | -0.023 |
lifetime | -0.022 |
Hatt | -0.022 |
Token | away |
Token ID | 1497 |
Feature activation | -8.94e-01 |
Pos logit contributions | |
atmeal | +0.027 |
rolling | +0.026 |
ancer | +0.026 |
lifetime | +0.025 |
highlight | +0.024 |
Neg logit contributions | |
rs | -0.015 |
screams | -0.015 |
irk | -0.014 |
rum | -0.014 |
bites | -0.014 |
Token | to |
Token ID | 284 |
Feature activation | -1.17e+00 |
Pos logit contributions | |
irk | +0.012 |
screams | +0.012 |
rs | +0.012 |
rum | +0.011 |
bites | +0.010 |
Neg logit contributions | |
atmeal | -0.029 |
ancer | -0.028 |
rolling | -0.028 |
lifetime | -0.027 |
highlight | -0.027 |
Token | keep |
Token ID | 1394 |
Feature activation | -1.56e-01 |
Pos logit contributions | |
rs | +0.025 |
irk | +0.024 |
screams | +0.024 |
rum | +0.024 |
bites | +0.023 |
Neg logit contributions | |
atmeal | -0.030 |
rolling | -0.028 |
ancer | -0.028 |
lifetime | -0.027 |
highlight | -0.026 |
Token | them |
Token ID | 606 |
Feature activation | +2.45e+00 |
Pos logit contributions | |
rs | +0.003 |
screams | +0.003 |
irk | +0.003 |
rum | +0.003 |
bites | +0.003 |
Neg logit contributions | |
atmeal | -0.004 |
rolling | -0.004 |
ancer | -0.004 |
lifetime | -0.004 |
highlight | -0.004 |
Token | safe |
Token ID | 3338 |
Feature activation | -4.08e-01 |
Pos logit contributions | |
atmeal | +0.062 |
ancer | +0.056 |
rolling | +0.056 |
Hatt | +0.052 |
pieces | +0.052 |
Neg logit contributions | |
rs | -0.052 |
and | -0.051 |
screams | -0.051 |
bites | -0.049 |
rum | -0.049 |
Token | and |
Token ID | 290 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
irk | +0.005 |
screams | +0.005 |
rs | +0.005 |
rum | +0.004 |
bites | +0.004 |
Neg logit contributions | |
atmeal | -0.014 |
ancer | -0.013 |
rolling | -0.013 |
lifetime | -0.013 |
highlight | -0.013 |
Token | that |
Token ID | 326 |
Feature activation | +1.41e+00 |
Pos logit contributions | |
atmeal | +0.059 |
ancer | +0.055 |
rolling | +0.055 |
angers | +0.052 |
Hatt | +0.051 |
Neg logit contributions | |
screams | -0.037 |
words | -0.036 |
thinks | -0.036 |
rs | -0.035 |
bites | -0.035 |
Token | it |
Token ID | 340 |
Feature activation | +5.25e-01 |
Pos logit contributions | |
atmeal | +0.039 |
rolling | +0.038 |
ancer | +0.037 |
ital | +0.034 |
ouses | +0.034 |
Neg logit contributions | |
screams | -0.028 |
rs | -0.027 |
thinks | -0.026 |
bites | -0.026 |
words | -0.026 |
Token | 's |
Token ID | 338 |
Feature activation | -7.40e-03 |
Pos logit contributions | |
atmeal | +0.018 |
rolling | +0.017 |
lifetime | +0.016 |
ancer | +0.016 |
belt | +0.016 |
Neg logit contributions | |
thinks | -0.008 |
screams | -0.008 |
bites | -0.007 |
rs | -0.007 |
words | -0.007 |
Token | to |
Token ID | 284 |
Feature activation | -1.57e+00 |
Pos logit contributions | |
rs | +0.002 |
rum | +0.002 |
irk | +0.002 |
screams | +0.002 |
ez | +0.002 |
Neg logit contributions | |
rolling | -0.003 |
atmeal | -0.003 |
ancer | -0.003 |
Hatt | -0.003 |
lifetime | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | +5.68e-01 |
Pos logit contributions | |
rs | +0.036 |
screams | +0.035 |
rum | +0.035 |
irk | +0.035 |
ks | +0.034 |
Neg logit contributions | |
atmeal | -0.037 |
rolling | -0.034 |
ancer | -0.034 |
Hatt | -0.033 |
highlight | -0.032 |
Token | and |
Token ID | 290 |
Feature activation | -1.50e-01 |
Pos logit contributions | |
rolling | +0.017 |
atmeal | +0.017 |
ancer | +0.016 |
lifetime | +0.016 |
highlight | +0.015 |
Neg logit contributions | |
rs | -0.009 |
irk | -0.009 |
rum | -0.009 |
screams | -0.008 |
bites | -0.008 |
Token | said |
Token ID | 531 |
Feature activation | +1.33e-01 |
Pos logit contributions | |
rs | +0.003 |
screams | +0.003 |
irk | +0.003 |
bites | +0.002 |
ks | +0.002 |
Neg logit contributions | |
atmeal | -0.004 |
ancer | -0.004 |
rolling | -0.004 |
lifetime | -0.004 |
highlight | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +1.87e-01 |
Pos logit contributions | |
atmeal | +0.004 |
rolling | +0.003 |
ancer | +0.003 |
Hatt | +0.003 |
lifetime | +0.003 |
Neg logit contributions | |
rs | -0.003 |
irk | -0.003 |
screams | -0.003 |
rum | -0.002 |
bites | -0.002 |
Token | � |
Token ID | 6184 |
Feature activation | +5.43e-01 |
Pos logit contributions | |
rolling | +0.005 |
atmeal | +0.005 |
ancer | +0.005 |
lifetime | +0.005 |
Hatt | +0.005 |
Neg logit contributions | |
rs | -0.004 |
irk | -0.004 |
screams | -0.004 |
rum | -0.003 |
bites | -0.003 |
Token | � |
Token ID | 95 |
Feature activation | +6.27e-02 |
Pos logit contributions | |
atmeal | +0.013 |
ancer | +0.012 |
rolling | +0.012 |
lifetime | +0.011 |
highlight | +0.011 |
Neg logit contributions | |
rs | -0.013 |
screams | -0.012 |
irk | -0.012 |
rum | -0.012 |
ks | -0.012 |
Token | € |
Token ID | 26391 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
atmeal | +0.002 |
rolling | +0.001 |
ancer | +0.001 |
ital | +0.001 |
lifetime | +0.001 |
Neg logit contributions | |
screams | -0.001 |
rs | -0.001 |
irk | -0.001 |
tant | -0.001 |
rum | -0.001 |
Token | � |
Token ID | 129 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
atmeal | +0.042 |
rolling | +0.039 |
ancer | +0.038 |
lifetime | +0.037 |
highlight | +0.036 |
Neg logit contributions | |
rs | -0.046 |
screams | -0.044 |
irk | -0.044 |
rum | -0.043 |
bites | -0.042 |
Token | � |
Token ID | 241 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
tant | +0.035 |
irk | +0.034 |
rs | +0.032 |
ously | +0.032 |
blood | +0.031 |
Neg logit contributions | |
rolling | -0.033 |
atmeal | -0.031 |
ital | -0.027 |
Hatt | -0.027 |
belt | -0.026 |
Token | The |
Token ID | 464 |
Feature activation | +3.39e-01 |
Pos logit contributions | |
rs | +0.047 |
screams | +0.045 |
bites | +0.045 |
rum | +0.044 |
tant | +0.043 |
Neg logit contributions | |
ancer | -0.049 |
atmeal | -0.047 |
rolling | -0.046 |
lifetime | -0.045 |
highlight | -0.043 |
Token | playing |
Token ID | 2712 |
Feature activation | +5.89e-01 |
Pos logit contributions | |
atmeal | +0.088 |
lifetime | +0.083 |
rolling | +0.082 |
ancer | +0.082 |
Hatt | +0.081 |
Neg logit contributions | |
screams | -0.072 |
rs | -0.069 |
irk | -0.069 |
ks | -0.069 |
bites | -0.068 |
Token | in |
Token ID | 287 |
Feature activation | +3.81e-02 |
Pos logit contributions | |
atmeal | +0.012 |
ancer | +0.011 |
rolling | +0.011 |
highlight | +0.010 |
ital | +0.010 |
Neg logit contributions | |
irk | -0.016 |
screams | -0.016 |
rum | -0.016 |
rs | -0.015 |
ff | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
atmeal | +0.001 |
rolling | +0.001 |
ancer | +0.001 |
Hatt | +0.001 |
lifetime | +0.001 |
Neg logit contributions | |
rs | -0.001 |
irk | -0.001 |
screams | -0.001 |
rum | -0.001 |
tant | -0.001 |
Token | garden |
Token ID | 11376 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
atmeal | +0.037 |
ancer | +0.037 |
rolling | +0.035 |
lifetime | +0.034 |
Hatt | +0.034 |
Neg logit contributions | |
screams | -0.029 |
rs | -0.028 |
bites | -0.028 |
irk | -0.027 |
thinks | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +6.50e-01 |
Pos logit contributions | |
atmeal | +0.041 |
rolling | +0.039 |
ancer | +0.038 |
highlight | +0.037 |
lifetime | +0.037 |
Neg logit contributions | |
irk | -0.021 |
rs | -0.020 |
rum | -0.020 |
screams | -0.020 |
tant | -0.019 |
Token | They |
Token ID | 1119 |
Feature activation | +9.22e-01 |
Pos logit contributions | |
atmeal | +0.019 |
rolling | +0.018 |
ancer | +0.017 |
highlight | +0.017 |
Hatt | +0.017 |
Neg logit contributions | |
screams | -0.011 |
rs | -0.011 |
rum | -0.011 |
irk | -0.011 |
ez | -0.010 |
Token | liked |
Token ID | 8288 |
Feature activation | +5.61e-01 |
Pos logit contributions | |
atmeal | +0.028 |
ancer | +0.026 |
rolling | +0.026 |
lifetime | +0.026 |
highlight | +0.025 |
Neg logit contributions | |
rs | -0.016 |
screams | -0.016 |
thinks | -0.015 |
irk | -0.015 |
ks | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +4.32e-01 |
Pos logit contributions | |
atmeal | +0.018 |
rolling | +0.017 |
ancer | +0.016 |
highlight | +0.016 |
nam | +0.016 |
Neg logit contributions | |
rs | -0.009 |
irk | -0.009 |
rum | -0.009 |
screams | -0.009 |
aron | -0.008 |
Token | dig |
Token ID | 3100 |
Feature activation | -1.58e-01 |
Pos logit contributions | |
ancer | +0.011 |
atmeal | +0.011 |
lifetime | +0.011 |
rolling | +0.010 |
Hatt | +0.010 |
Neg logit contributions | |
rs | -0.009 |
screams | -0.009 |
bites | -0.009 |
thinks | -0.009 |
Mine | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
irk | +0.003 |
rs | +0.003 |
rum | +0.003 |
screams | +0.003 |
ez | +0.003 |
Neg logit contributions | |
atmeal | -0.004 |
rolling | -0.004 |
ancer | -0.004 |
highlight | -0.004 |
Hatt | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | +9.97e-01 |
Pos logit contributions | |
rs | +0.013 |
screams | +0.012 |
irk | +0.012 |
rum | +0.012 |
bites | +0.011 |
Neg logit contributions | |
atmeal | -0.020 |
rolling | -0.019 |
ancer | -0.019 |
lifetime | -0.018 |
highlight | -0.018 |
Token | boy |
Token ID | 2933 |
Feature activation | -1.11e-01 |
Pos logit contributions | |
atmeal | +0.014 |
rolling | +0.013 |
ancer | +0.013 |
lifetime | +0.013 |
highlight | +0.013 |
Neg logit contributions | |
rs | -0.007 |
screams | -0.006 |
irk | -0.006 |
rum | -0.006 |
ks | -0.006 |
Token | put |
Token ID | 1234 |
Feature activation | +5.11e-01 |
Pos logit contributions | |
screams | +0.002 |
rs | +0.002 |
bites | +0.002 |
ks | +0.002 |
thinks | +0.002 |
Neg logit contributions | |
atmeal | -0.003 |
ancer | -0.003 |
rolling | -0.003 |
highlight | -0.003 |
lifetime | -0.003 |
Token | his |
Token ID | 465 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
atmeal | +0.016 |
rolling | +0.016 |
ancer | +0.015 |
lifetime | +0.015 |
highlight | +0.015 |
Neg logit contributions | |
rs | -0.008 |
screams | -0.008 |
irk | -0.007 |
rum | -0.007 |
bites | -0.007 |
Token | hoop |
Token ID | 44792 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
atmeal | +0.042 |
rolling | +0.039 |
ancer | +0.039 |
lifetime | +0.038 |
Hatt | +0.037 |
Neg logit contributions | |
screams | -0.031 |
rs | -0.031 |
irk | -0.030 |
bites | -0.029 |
rum | -0.029 |
Token | down |
Token ID | 866 |
Feature activation | +1.13e-01 |
Pos logit contributions | |
atmeal | +0.099 |
ancer | +0.096 |
rolling | +0.091 |
lifetime | +0.090 |
Hatt | +0.089 |
Neg logit contributions | |
rs | -0.059 |
and | -0.058 |
bites | -0.057 |
ks | -0.054 |
screams | -0.054 |
Token | on |
Token ID | 319 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
atmeal | +0.003 |
rolling | +0.003 |
ancer | +0.003 |
lifetime | +0.003 |
belt | +0.003 |
Neg logit contributions | |
screams | -0.002 |
irk | -0.002 |
rs | -0.002 |
rum | -0.002 |
bites | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -2.27e-01 |
Pos logit contributions | |
irk | +0.051 |
screams | +0.045 |
ff | +0.044 |
rum | +0.044 |
rs | +0.044 |
Neg logit contributions | |
exploring | -0.028 |
nights | -0.027 |
belt | -0.026 |
atmeal | -0.025 |
Hatt | -0.025 |
Token | ground |
Token ID | 2323 |
Feature activation | -6.26e-01 |
Pos logit contributions | |
rs | +0.005 |
irk | +0.005 |
screams | +0.005 |
rum | +0.005 |
ks | +0.005 |
Neg logit contributions | |
atmeal | -0.005 |
rolling | -0.005 |
ancer | -0.005 |
lifetime | -0.005 |
highlight | -0.005 |
Token | and |
Token ID | 290 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
irk | +0.011 |
Mine | +0.011 |
rum | +0.011 |
screams | +0.010 |
rs | +0.010 |
Neg logit contributions | |
rolling | -0.017 |
atmeal | -0.017 |
exploring | -0.017 |
lifetime | -0.017 |
belt | -0.016 |
Token | started |
Token ID | 2067 |
Feature activation | -5.83e-01 |
Pos logit contributions | |
atmeal | +0.043 |
ancer | +0.042 |
rolling | +0.041 |
highlight | +0.040 |
lifetime | +0.039 |
Neg logit contributions | |
screams | -0.034 |
bites | -0.032 |
thinks | -0.031 |
ks | -0.031 |
rs | -0.031 |
Token | spinning |
Token ID | 19493 |
Feature activation | -7.16e-01 |
Pos logit contributions | |
rs | +0.012 |
irk | +0.012 |
screams | +0.011 |
rum | +0.011 |
aron | +0.011 |
Neg logit contributions | |
atmeal | -0.015 |
rolling | -0.015 |
ancer | -0.014 |
lifetime | -0.014 |
highlight | -0.013 |
Token | a |
Token ID | 257 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
rum | +0.007 |
rs | +0.007 |
irk | +0.007 |
screams | +0.006 |
aron | +0.006 |
Neg logit contributions | |
atmeal | -0.010 |
rolling | -0.009 |
ancer | -0.009 |
highlight | -0.009 |
Hatt | -0.009 |
Token | big |
Token ID | 1263 |
Feature activation | -2.88e+00 |
Pos logit contributions | |
screams | +0.042 |
rs | +0.042 |
irk | +0.041 |
bites | +0.039 |
tant | +0.038 |
Neg logit contributions | |
atmeal | -0.073 |
rolling | -0.069 |
ancer | -0.069 |
highlight | -0.065 |
lifetime | -0.065 |
Token | wreck |
Token ID | 15228 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
rs | +0.057 |
irk | +0.055 |
screams | +0.055 |
rum | +0.054 |
ks | +0.053 |
Neg logit contributions | |
atmeal | -0.077 |
rolling | -0.073 |
ancer | -0.072 |
lifetime | -0.069 |
Hatt | -0.068 |
Token | on |
Token ID | 319 |
Feature activation | -2.15e+00 |
Pos logit contributions | |
rs | +0.008 |
irk | +0.008 |
screams | +0.007 |
rum | +0.007 |
bites | +0.007 |
Neg logit contributions | |
atmeal | -0.010 |
rolling | -0.010 |
ancer | -0.010 |
lifetime | -0.009 |
highlight | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
irk | +0.060 |
rum | +0.057 |
screams | +0.054 |
ks | +0.054 |
rs | +0.053 |
Neg logit contributions | |
Hatt | -0.041 |
nam | -0.039 |
rolling | -0.037 |
highlight | -0.036 |
chard | -0.036 |
Token | road |
Token ID | 2975 |
Feature activation | -5.66e-01 |
Pos logit contributions | |
rs | +0.007 |
irk | +0.007 |
rum | +0.007 |
ks | +0.007 |
ez | +0.006 |
Neg logit contributions | |
atmeal | -0.006 |
rolling | -0.005 |
ancer | -0.005 |
highlight | -0.005 |
lifetime | -0.005 |
Token | . |
Token ID | 13 |
Feature activation | -7.71e-01 |
Pos logit contributions | |
irk | +0.009 |
rs | +0.009 |
rum | +0.009 |
ez | +0.009 |
screams | +0.009 |
Neg logit contributions | |
rolling | -0.016 |
atmeal | -0.016 |
belt | -0.015 |
lifetime | -0.015 |
ancer | -0.015 |
Token | It |
Token ID | 632 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
rs | +0.011 |
screams | +0.010 |
irk | +0.010 |
bites | +0.010 |
words | +0.009 |
Neg logit contributions | |
atmeal | -0.026 |
ancer | -0.024 |
rolling | -0.024 |
highlight | -0.023 |
lifetime | -0.023 |
Token | was |
Token ID | 373 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
rs | +0.014 |
screams | +0.014 |
irk | +0.014 |
rum | +0.013 |
bites | +0.013 |
Neg logit contributions | |
atmeal | -0.022 |
rolling | -0.021 |
ancer | -0.020 |
lifetime | -0.020 |
highlight | -0.019 |
Token | a |
Token ID | 257 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
irk | +0.029 |
rs | +0.028 |
rum | +0.027 |
screams | +0.027 |
tant | +0.025 |
Neg logit contributions | |
rolling | -0.030 |
atmeal | -0.029 |
highlight | -0.028 |
ancer | -0.027 |
Hatt | -0.027 |
Token | mess |
Token ID | 2085 |
Feature activation | -1.61e+00 |
Pos logit contributions | |
rs | +0.047 |
irk | +0.045 |
screams | +0.045 |
rum | +0.045 |
ks | +0.043 |
Neg logit contributions | |
atmeal | -0.058 |
rolling | -0.056 |
ancer | -0.054 |
lifetime | -0.053 |
highlight | -0.052 |
Token | steal |
Token ID | 8711 |
Feature activation | -2.40e+00 |
Pos logit contributions | |
rs | +0.055 |
irk | +0.054 |
screams | +0.053 |
rum | +0.052 |
ks | +0.050 |
Neg logit contributions | |
atmeal | -0.052 |
rolling | -0.049 |
Hatt | -0.047 |
ancer | -0.046 |
nam | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
irk | +0.057 |
rum | +0.055 |
ez | +0.054 |
aron | +0.052 |
ud | +0.051 |
Neg logit contributions | |
nam | -0.047 |
highlight | -0.043 |
anywhere | -0.042 |
pieces | -0.042 |
best | -0.041 |
Token | They |
Token ID | 1119 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
rum | +0.025 |
rs | +0.025 |
irk | +0.024 |
screams | +0.024 |
bites | +0.024 |
Neg logit contributions | |
rolling | -0.031 |
Hatt | -0.030 |
ancer | -0.030 |
lifetime | -0.028 |
highlight | -0.028 |
Token | just |
Token ID | 655 |
Feature activation | -8.97e-01 |
Pos logit contributions | |
rum | +0.043 |
rs | +0.042 |
irk | +0.041 |
ff | +0.037 |
screams | +0.037 |
Neg logit contributions | |
atmeal | -0.031 |
Hatt | -0.029 |
nam | -0.029 |
rolling | -0.028 |
highlight | -0.027 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
rs | +0.018 |
rum | +0.018 |
irk | +0.018 |
screams | +0.017 |
tant | +0.016 |
Neg logit contributions | |
atmeal | -0.023 |
rolling | -0.021 |
nam | -0.021 |
ancer | -0.021 |
lifetime | -0.020 |
Token | to |
Token ID | 284 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
rum | +0.023 |
irk | +0.023 |
rs | +0.022 |
screams | +0.021 |
aron | +0.021 |
Neg logit contributions | |
atmeal | -0.031 |
highlight | -0.029 |
nam | -0.029 |
Hatt | -0.029 |
rolling | -0.029 |
Token | play |
Token ID | 711 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
irk | +0.035 |
rs | +0.035 |
rum | +0.034 |
screams | +0.033 |
ks | +0.033 |
Neg logit contributions | |
atmeal | -0.024 |
rolling | -0.022 |
Hatt | -0.020 |
highlight | -0.020 |
lifetime | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
screams | +0.023 |
irk | +0.023 |
rum | +0.022 |
ff | +0.022 |
ud | +0.021 |
Neg logit contributions | |
atmeal | -0.026 |
pieces | -0.024 |
highlight | -0.023 |
nam | -0.023 |
ancer | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -2.37e-01 |
Pos logit contributions | |
rum | +0.021 |
rs | +0.020 |
screams | +0.020 |
irk | +0.020 |
bites | +0.019 |
Neg logit contributions | |
rolling | -0.029 |
ancer | -0.029 |
Hatt | -0.028 |
atmeal | -0.028 |
lifetime | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +5.03e-01 |
Pos logit contributions | |
rs | +0.004 |
irk | +0.004 |
screams | +0.004 |
rum | +0.004 |
bites | +0.004 |
Neg logit contributions | |
rolling | -0.007 |
atmeal | -0.007 |
ancer | -0.006 |
lifetime | -0.006 |
Hatt | -0.006 |
Token | " |
Token ID | 1 |
Feature activation | -8.64e-02 |
Pos logit contributions | |
atmeal | +0.015 |
ancer | +0.014 |
rolling | +0.013 |
highlight | +0.013 |
lifetime | +0.013 |
Neg logit contributions | |
screams | -0.009 |
rs | -0.009 |
ks | -0.009 |
irk | -0.009 |
rum | -0.009 |
Token | You |
Token ID | 1639 |
Feature activation | +1.69e-01 |
Pos logit contributions | |
irk | +0.070 |
rs | +0.069 |
ases | +0.064 |
rum | +0.063 |
tant | +0.062 |
Neg logit contributions | |
rolling | -0.050 |
atmeal | -0.047 |
ail | -0.044 |
lifetime | -0.042 |
ital | -0.039 |
Token | 're |
Token ID | 821 |
Feature activation | +1.03e-01 |
Pos logit contributions | |
atmeal | +0.004 |
ancer | +0.004 |
rolling | +0.004 |
lifetime | +0.004 |
highlight | +0.004 |
Neg logit contributions | |
rs | -0.004 |
irk | -0.004 |
screams | -0.004 |
rum | -0.004 |
bites | -0.003 |
Token | welcome |
Token ID | 7062 |
Feature activation | +6.02e-02 |
Pos logit contributions | |
atmeal | +0.003 |
rolling | +0.003 |
ancer | +0.003 |
lifetime | +0.003 |
Hatt | +0.003 |
Neg logit contributions | |
rs | -0.002 |
screams | -0.002 |
irk | -0.002 |
rum | -0.002 |
ks | -0.002 |
Token | ! |
Token ID | 0 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
atmeal | +0.002 |
ancer | +0.002 |
rolling | +0.002 |
lifetime | +0.002 |
Hatt | +0.002 |
Neg logit contributions | |
screams | -0.001 |
rum | -0.001 |
irk | -0.001 |
rs | -0.001 |
tant | -0.001 |
Token | I |
Token ID | 314 |
Feature activation | +4.27e-01 |
Pos logit contributions | |
atmeal | +0.064 |
rolling | +0.057 |
lifetime | +0.055 |
ancer | +0.054 |
highlight | +0.054 |
Neg logit contributions | |
rs | -0.042 |
irk | -0.038 |
rum | -0.038 |
screams | -0.037 |
thinks | -0.037 |
Token | had |
Token ID | 550 |
Feature activation | -4.60e-01 |
Pos logit contributions | |
atmeal | +0.010 |
rolling | +0.010 |
ancer | +0.009 |
lifetime | +0.009 |
highlight | +0.009 |
Neg logit contributions | |
rs | -0.010 |
screams | -0.010 |
irk | -0.010 |
rum | -0.009 |
bites | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -4.53e-01 |
Pos logit contributions | |
irk | +0.009 |
rs | +0.009 |
rum | +0.009 |
screams | +0.008 |
ks | +0.008 |
Neg logit contributions | |
atmeal | -0.013 |
rolling | -0.012 |
lifetime | -0.012 |
ancer | -0.011 |
highlight | -0.011 |
Token | great |
Token ID | 1049 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
rs | +0.010 |
screams | +0.010 |
rum | +0.010 |
irk | +0.010 |
ks | +0.010 |
Neg logit contributions | |
atmeal | -0.011 |
rolling | -0.010 |
lifetime | -0.010 |
ancer | -0.010 |
highlight | -0.010 |
Token | time |
Token ID | 640 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
rs | +0.024 |
rum | +0.023 |
screams | +0.023 |
irk | +0.023 |
ks | +0.023 |
Neg logit contributions | |
atmeal | -0.020 |
lifetime | -0.019 |
rolling | -0.019 |
ancer | -0.017 |
highlight | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | +1.86e+00 |
Pos logit contributions | |
atmeal | +0.042 |
rolling | +0.039 |
ancer | +0.039 |
Hatt | +0.038 |
highlight | +0.037 |
Neg logit contributions | |
rs | -0.026 |
screams | -0.025 |
rum | -0.024 |
irk | -0.024 |
ks | -0.024 |
Token | Let |
Token ID | 3914 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
atmeal | +0.056 |
rolling | +0.052 |
lifetime | +0.050 |
ancer | +0.050 |
highlight | +0.049 |
Neg logit contributions | |
rs | -0.035 |
irk | -0.031 |
rum | -0.031 |
screams | -0.030 |
thinks | -0.030 |
Token | very |
Token ID | 845 |
Feature activation | +1.24e+00 |
Pos logit contributions | |
rs | +0.000 |
irk | +0.000 |
screams | +0.000 |
rum | +0.000 |
ks | +0.000 |
Neg logit contributions | |
atmeal | -0.000 |
rolling | -0.000 |
ancer | -0.000 |
lifetime | -0.000 |
pieces | -0.000 |
Token | restless |
Token ID | 42537 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
atmeal | +0.036 |
pieces | +0.036 |
lifetime | +0.034 |
rolling | +0.034 |
highlight | +0.033 |
Neg logit contributions | |
screams | -0.022 |
irk | -0.021 |
ks | -0.021 |
bites | -0.020 |
thinks | -0.020 |
Token | and |
Token ID | 290 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
irk | +0.027 |
screams | +0.027 |
rs | +0.026 |
rum | +0.026 |
Mine | +0.026 |
Neg logit contributions | |
atmeal | -0.038 |
ancer | -0.037 |
exploring | -0.036 |
rolling | -0.035 |
lifetime | -0.035 |
Token | never |
Token ID | 1239 |
Feature activation | -2.16e-01 |
Pos logit contributions | |
atmeal | +0.044 |
rolling | +0.043 |
ancer | +0.042 |
pieces | +0.040 |
lifetime | +0.040 |
Neg logit contributions | |
thinks | -0.023 |
screams | -0.023 |
rs | -0.022 |
ks | -0.021 |
bites | -0.021 |
Token | stayed |
Token ID | 9658 |
Feature activation | -1.72e-01 |
Pos logit contributions | |
rs | +0.004 |
screams | +0.004 |
irk | +0.004 |
ks | +0.004 |
bites | +0.003 |
Neg logit contributions | |
atmeal | -0.006 |
rolling | -0.006 |
ancer | -0.006 |
lifetime | -0.006 |
Hatt | -0.006 |
Token | still |
Token ID | 991 |
Feature activation | -3.62e-01 |
Pos logit contributions | |
rs | +0.003 |
ks | +0.003 |
screams | +0.003 |
and | +0.003 |
bites | +0.003 |
Neg logit contributions | |
atmeal | -0.005 |
ancer | -0.005 |
rolling | -0.005 |
lifetime | -0.005 |
pieces | -0.004 |
Token | for |
Token ID | 329 |
Feature activation | -7.62e-01 |
Pos logit contributions | |
irk | +0.006 |
screams | +0.006 |
rs | +0.006 |
rum | +0.005 |
bites | +0.005 |
Neg logit contributions | |
atmeal | -0.011 |
rolling | -0.011 |
ancer | -0.011 |
lifetime | -0.010 |
highlight | -0.010 |
Token | too |
Token ID | 1165 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
rs | +0.012 |
screams | +0.012 |
irk | +0.011 |
bites | +0.011 |
ks | +0.011 |
Neg logit contributions | |
atmeal | -0.024 |
rolling | -0.023 |
ancer | -0.022 |
lifetime | -0.021 |
highlight | -0.021 |
Token | long |
Token ID | 890 |
Feature activation | -4.15e-01 |
Pos logit contributions | |
atmeal | +0.000 |
rolling | +0.000 |
ancer | +0.000 |
lifetime | +0.000 |
highlight | +0.000 |
Neg logit contributions | |
rs | -0.000 |
irk | -0.000 |
screams | -0.000 |
rum | -0.000 |
bites | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -2.32e-01 |
Pos logit contributions | |
irk | +0.006 |
rs | +0.005 |
screams | +0.005 |
Mine | +0.005 |
rum | +0.005 |
Neg logit contributions | |
atmeal | -0.014 |
rolling | -0.013 |
ancer | -0.013 |
lifetime | -0.013 |
Hatt | -0.012 |
Token | One |
Token ID | 1881 |
Feature activation | +5.63e-01 |
Pos logit contributions | |
rs | +0.004 |
irk | +0.004 |
screams | +0.004 |
thinks | +0.004 |
words | +0.004 |
Neg logit contributions | |
atmeal | -0.007 |
rolling | -0.007 |
ancer | -0.006 |
lifetime | -0.006 |
highlight | -0.006 |
Token | pulls |
Token ID | 16194 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
irk | +0.044 |
rum | +0.043 |
rs | +0.042 |
tant | +0.038 |
aron | +0.037 |
Neg logit contributions | |
atmeal | -0.066 |
rolling | -0.064 |
ancer | -0.060 |
Hatt | -0.060 |
highlight | -0.058 |
Token | his |
Token ID | 465 |
Feature activation | -7.23e-01 |
Pos logit contributions | |
rum | +0.041 |
irk | +0.041 |
ater | +0.040 |
gging | +0.038 |
rs | +0.038 |
Neg logit contributions | |
Hatt | -0.036 |
ancer | -0.035 |
forth | -0.033 |
nam | -0.032 |
atmeal | -0.032 |
Token | toe |
Token ID | 21189 |
Feature activation | -6.76e-01 |
Pos logit contributions | |
rs | +0.018 |
ud | +0.016 |
aron | +0.016 |
irk | +0.016 |
ff | +0.016 |
Neg logit contributions | |
nam | -0.015 |
belt | -0.015 |
forth | -0.014 |
atmeal | -0.014 |
best | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
irk | +0.017 |
rs | +0.016 |
Mine | +0.015 |
screams | +0.015 |
unts | +0.015 |
Neg logit contributions | |
atmeal | -0.014 |
belt | -0.013 |
forth | -0.013 |
rolling | -0.012 |
mage | -0.012 |
Token | The |
Token ID | 383 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
ater | +0.046 |
irk | +0.045 |
rs | +0.044 |
screams | +0.044 |
rum | +0.043 |
Neg logit contributions | |
ancer | -0.048 |
Hatt | -0.047 |
rolling | -0.047 |
atmeal | -0.045 |
angers | -0.043 |
Token | dog |
Token ID | 3290 |
Feature activation | -3.75e+00 |
Pos logit contributions | |
rs | +0.030 |
rum | +0.028 |
aron | +0.027 |
ff | +0.027 |
ks | +0.026 |
Neg logit contributions | |
atmeal | -0.037 |
ancer | -0.035 |
rolling | -0.034 |
highlight | -0.033 |
nam | -0.033 |
Token | lets |
Token ID | 8781 |
Feature activation | -5.22e-01 |
Pos logit contributions | |
irk | +0.087 |
rum | +0.083 |
aron | +0.078 |
rs | +0.075 |
ously | +0.075 |
Neg logit contributions | |
atmeal | -0.079 |
rolling | -0.072 |
hiking | -0.071 |
forth | -0.070 |
mage | -0.070 |
Token | go |
Token ID | 467 |
Feature activation | -2.51e-01 |
Pos logit contributions | |
irk | +0.013 |
rum | +0.013 |
rs | +0.013 |
screams | +0.012 |
aron | +0.012 |
Neg logit contributions | |
atmeal | -0.011 |
ancer | -0.010 |
rolling | -0.010 |
Hatt | -0.009 |
pieces | -0.009 |
Token | . |
Token ID | 13 |
Feature activation | -2.32e+00 |
Pos logit contributions | |
screams | +0.004 |
irk | +0.004 |
gging | +0.004 |
rs | +0.004 |
rum | +0.004 |
Neg logit contributions | |
atmeal | -0.007 |
ancer | -0.007 |
rolling | -0.007 |
Hatt | -0.006 |
ital | -0.006 |
Token | Tom |
Token ID | 4186 |
Feature activation | -3.20e+00 |
Pos logit contributions | |
ater | +0.058 |
rum | +0.056 |
irk | +0.055 |
rs | +0.054 |
ously | +0.053 |
Neg logit contributions | |
Hatt | -0.042 |
ancer | -0.042 |
rolling | -0.042 |
atmeal | -0.040 |
maybe | -0.039 |
Token | looks |
Token ID | 3073 |
Feature activation | -9.56e-01 |
Pos logit contributions | |
irk | +0.077 |
rum | +0.072 |
keeping | +0.069 |
ff | +0.067 |
iger | +0.067 |
Neg logit contributions | |
atmeal | -0.061 |
rolling | -0.057 |
rains | -0.055 |
mage | -0.054 |
igs | -0.053 |
Token | be |
Token ID | 307 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
irk | +0.040 |
rum | +0.039 |
rs | +0.039 |
screams | +0.038 |
ud | +0.037 |
Neg logit contributions | |
atmeal | -0.035 |
rolling | -0.033 |
ancer | -0.032 |
highlight | -0.032 |
Hatt | -0.032 |
Token | shy |
Token ID | 15800 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
rs | +0.010 |
irk | +0.010 |
screams | +0.010 |
rum | +0.010 |
bites | +0.010 |
Neg logit contributions | |
atmeal | -0.012 |
rolling | -0.012 |
ancer | -0.011 |
lifetime | -0.011 |
highlight | -0.011 |
Token | at |
Token ID | 379 |
Feature activation | -6.55e-01 |
Pos logit contributions | |
irk | +0.028 |
Mine | +0.027 |
screams | +0.027 |
rum | +0.027 |
rs | +0.025 |
Neg logit contributions | |
ancer | -0.051 |
atmeal | -0.048 |
highlight | -0.045 |
rolling | -0.045 |
lifetime | -0.044 |
Token | first |
Token ID | 717 |
Feature activation | -7.89e-01 |
Pos logit contributions | |
irk | +0.017 |
rum | +0.016 |
rs | +0.016 |
aron | +0.016 |
screams | +0.016 |
Neg logit contributions | |
atmeal | -0.013 |
ancer | -0.013 |
Hatt | -0.012 |
lifetime | -0.012 |
highlight | -0.012 |
Token | ." |
Token ID | 526 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
irk | +0.014 |
screams | +0.013 |
Mine | +0.012 |
rum | +0.012 |
rs | +0.012 |
Neg logit contributions | |
atmeal | -0.022 |
ancer | -0.022 |
rolling | -0.020 |
lifetime | -0.020 |
highlight | -0.020 |
Token | Tom |
Token ID | 4186 |
Feature activation | -3.60e+00 |
Pos logit contributions | |
rs | +0.029 |
rum | +0.028 |
irk | +0.027 |
screams | +0.027 |
tant | +0.026 |
Neg logit contributions | |
atmeal | -0.058 |
ancer | -0.056 |
rolling | -0.056 |
Hatt | -0.055 |
lifetime | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | +4.74e-01 |
Pos logit contributions | |
rum | +0.070 |
tant | +0.063 |
Mine | +0.060 |
control | +0.057 |
irk | +0.057 |
Neg logit contributions | |
atmeal | -0.086 |
ail | -0.080 |
ancer | -0.080 |
Hatt | -0.078 |
rolling | -0.078 |
Token | Sam |
Token ID | 3409 |
Feature activation | -2.10e+00 |
Pos logit contributions | |
atmeal | +0.014 |
rolling | +0.013 |
ancer | +0.013 |
Hatt | +0.013 |
highlight | +0.013 |
Neg logit contributions | |
rs | -0.008 |
irk | -0.008 |
rum | -0.008 |
screams | -0.007 |
tant | -0.007 |
Token | go |
Token ID | 467 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
rum | +0.048 |
ud | +0.045 |
irk | +0.045 |
rs | +0.045 |
tant | +0.043 |
Neg logit contributions | |
atmeal | -0.049 |
rolling | -0.047 |
highlight | -0.045 |
ancer | -0.045 |
Hatt | -0.044 |
Token | to |
Token ID | 284 |
Feature activation | -6.14e-01 |
Pos logit contributions | |
atmeal | +0.042 |
highlight | +0.039 |
ancer | +0.039 |
lifetime | +0.039 |
rolling | +0.039 |
Neg logit contributions | |
rs | -0.014 |
ks | -0.013 |
bites | -0.012 |
screams | -0.012 |
irk | -0.012 |
Token | Brown |
Token ID | 4373 |
Feature activation | +9.95e-01 |
Pos logit contributions | |
irk | +0.013 |
rs | +0.013 |
rum | +0.012 |
screams | +0.012 |
ks | +0.012 |
Neg logit contributions | |
atmeal | -0.015 |
rolling | -0.015 |
ancer | -0.015 |
Hatt | -0.014 |
lifetime | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
rum | +0.061 |
rs | +0.060 |
ater | +0.059 |
screams | +0.057 |
ez | +0.056 |
Neg logit contributions | |
rolling | -0.053 |
ancer | -0.052 |
Hatt | -0.052 |
Early | -0.047 |
Grac | -0.046 |
Token |
|
Token ID | 198 |
Feature activation | -4.12e-01 |
Pos logit contributions | |
rs | +0.028 |
irk | +0.026 |
screams | +0.026 |
bites | +0.026 |
tant | +0.026 |
Neg logit contributions | |
rolling | -0.035 |
ancer | -0.033 |
atmeal | -0.033 |
Hatt | -0.032 |
ail | -0.031 |
Token | L |
Token ID | 43 |
Feature activation | -5.44e-01 |
Pos logit contributions | |
rs | +0.009 |
screams | +0.009 |
irk | +0.009 |
rum | +0.008 |
bites | +0.008 |
Neg logit contributions | |
atmeal | -0.010 |
rolling | -0.010 |
ancer | -0.010 |
lifetime | -0.009 |
ital | -0.009 |
Token | ily |
Token ID | 813 |
Feature activation | -3.51e+00 |
Pos logit contributions | |
screams | +0.015 |
tant | +0.014 |
rs | +0.014 |
bites | +0.014 |
Mine | +0.014 |
Neg logit contributions | |
atmeal | -0.011 |
ancer | -0.010 |
ital | -0.009 |
ail | -0.009 |
angers | -0.009 |
Token | did |
Token ID | 750 |
Feature activation | -2.04e+00 |
Pos logit contributions | |
rum | +0.090 |
rs | +0.086 |
irk | +0.084 |
ases | +0.082 |
tant | +0.081 |
Neg logit contributions | |
rolling | -0.071 |
atmeal | -0.069 |
ail | -0.061 |
Hatt | -0.060 |
ancer | -0.059 |
Token | not |
Token ID | 407 |
Feature activation | -3.88e+00 |
Pos logit contributions | |
irk | +0.057 |
rs | +0.055 |
ud | +0.054 |
rum | +0.053 |
screams | +0.052 |
Neg logit contributions | |
atmeal | -0.037 |
rolling | -0.036 |
ancer | -0.033 |
nam | -0.033 |
Hatt | -0.033 |
Token | know |
Token ID | 760 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
screams | +0.081 |
ud | +0.080 |
rs | +0.078 |
Mine | +0.077 |
rum | +0.076 |
Neg logit contributions | |
atmeal | -0.093 |
ancer | -0.092 |
Hatt | -0.084 |
inations | -0.083 |
rolling | -0.082 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
rs | +0.031 |
irk | +0.031 |
screams | +0.030 |
rum | +0.030 |
bites | +0.029 |
Neg logit contributions | |
atmeal | -0.034 |
ancer | -0.031 |
rolling | -0.031 |
lifetime | -0.029 |
Hatt | -0.029 |
Token | She |
Token ID | 1375 |
Feature activation | -2.51e+00 |
Pos logit contributions | |
rum | +0.045 |
ez | +0.044 |
rs | +0.043 |
tant | +0.042 |
bites | +0.041 |
Neg logit contributions | |
ancer | -0.030 |
rolling | -0.029 |
Hatt | -0.027 |
angers | -0.026 |
atmeal | -0.026 |
Token | wanted |
Token ID | 2227 |
Feature activation | -1.83e+00 |
Pos logit contributions | |
rs | +0.059 |
rum | +0.059 |
irk | +0.056 |
tant | +0.053 |
screams | +0.053 |
Neg logit contributions | |
atmeal | -0.058 |
rolling | -0.054 |
ancer | -0.053 |
Hatt | -0.051 |
lifetime | -0.049 |
Token | to |
Token ID | 284 |
Feature activation | -2.27e+00 |
Pos logit contributions | |
rum | +0.037 |
irk | +0.036 |
rs | +0.036 |
aron | +0.035 |
screams | +0.032 |
Neg logit contributions | |
atmeal | -0.047 |
highlight | -0.044 |
ancer | -0.044 |
rolling | -0.042 |
nam | -0.042 |
Token | for |
Token ID | 329 |
Feature activation | -9.54e-01 |
Pos logit contributions | |
rs | +0.014 |
irk | +0.013 |
screams | +0.013 |
rum | +0.013 |
ks | +0.013 |
Neg logit contributions | |
atmeal | -0.018 |
rolling | -0.017 |
ancer | -0.017 |
lifetime | -0.017 |
Hatt | -0.016 |
Token | breaking |
Token ID | 7163 |
Feature activation | -1.84e+00 |
Pos logit contributions | |
irk | +0.020 |
rs | +0.020 |
screams | +0.019 |
rum | +0.019 |
tant | +0.018 |
Neg logit contributions | |
atmeal | -0.024 |
rolling | -0.023 |
ancer | -0.023 |
lifetime | -0.022 |
Hatt | -0.022 |
Token | our |
Token ID | 674 |
Feature activation | -1.32e-01 |
Pos logit contributions | |
irk | +0.046 |
rs | +0.040 |
screams | +0.040 |
unts | +0.038 |
ks | +0.037 |
Neg logit contributions | |
nam | -0.039 |
atmeal | -0.038 |
pieces | -0.036 |
Hatt | -0.035 |
ations | -0.035 |
Token | castle |
Token ID | 16669 |
Feature activation | +3.82e-01 |
Pos logit contributions | |
irk | +0.003 |
rs | +0.003 |
rum | +0.003 |
aron | +0.003 |
ks | +0.003 |
Neg logit contributions | |
atmeal | -0.003 |
rolling | -0.003 |
lifetime | -0.003 |
highlight | -0.003 |
nam | -0.003 |
Token | ," |
Token ID | 553 |
Feature activation | -4.07e-01 |
Pos logit contributions | |
atmeal | +0.011 |
rolling | +0.010 |
ancer | +0.010 |
lifetime | +0.010 |
ital | +0.009 |
Neg logit contributions | |
irk | -0.007 |
rs | -0.007 |
screams | -0.007 |
rum | -0.007 |
ks | -0.006 |
Token | Ben |
Token ID | 3932 |
Feature activation | -3.76e+00 |
Pos logit contributions | |
rs | +0.008 |
irk | +0.008 |
rum | +0.008 |
screams | +0.008 |
bites | +0.007 |
Neg logit contributions | |
atmeal | -0.011 |
ancer | -0.010 |
rolling | -0.010 |
Hatt | -0.010 |
lifetime | -0.010 |
Token | says |
Token ID | 1139 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
rum | +0.098 |
ud | +0.096 |
Mine | +0.096 |
ater | +0.092 |
rs | +0.091 |
Neg logit contributions | |
Hatt | -0.062 |
atmeal | -0.057 |
cases | -0.057 |
rolling | -0.057 |
pieces | -0.056 |
Token | . |
Token ID | 13 |
Feature activation | -2.26e+00 |
Pos logit contributions | |
Mine | +0.020 |
irk | +0.019 |
rs | +0.018 |
ud | +0.018 |
thinks | +0.017 |
Neg logit contributions | |
rolling | -0.036 |
atmeal | -0.036 |
ancer | -0.035 |
Hatt | -0.034 |
ail | -0.033 |
Token | " |
Token ID | 366 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
ater | +0.059 |
rum | +0.057 |
tant | +0.055 |
screams | +0.055 |
irk | +0.055 |
Neg logit contributions | |
rolling | -0.041 |
Hatt | -0.040 |
ancer | -0.039 |
Kirst | -0.036 |
they | -0.036 |
Token | Maybe |
Token ID | 13300 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
rs | +0.057 |
screams | +0.056 |
irk | +0.055 |
rum | +0.055 |
bites | +0.054 |
Neg logit contributions | |
atmeal | -0.041 |
ancer | -0.040 |
rolling | -0.038 |
highlight | -0.037 |
nam | -0.036 |
Token | he |
Token ID | 339 |
Feature activation | -1.39e+00 |
Pos logit contributions | |
atmeal | +0.047 |
rolling | +0.046 |
ancer | +0.042 |
ouses | +0.041 |
highlight | +0.041 |
Neg logit contributions | |
and | -0.033 |
words | -0.033 |
word | -0.032 |
its | -0.032 |
screams | -0.031 |
Token | dropped |
Token ID | 5710 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
irk | +0.027 |
rs | +0.027 |
screams | +0.025 |
rum | +0.025 |
tant | +0.024 |
Neg logit contributions | |
atmeal | -0.028 |
rolling | -0.026 |
ancer | -0.025 |
lifetime | -0.024 |
highlight | -0.024 |
Token | his |
Token ID | 465 |
Feature activation | +9.35e-01 |
Pos logit contributions | |
irk | +0.066 |
aron | +0.064 |
unts | +0.060 |
rs | +0.060 |
rum | +0.058 |
Neg logit contributions | |
nam | -0.034 |
forth | -0.032 |
exploring | -0.029 |
shining | -0.029 |
Hatt | -0.027 |
Token | pe |
Token ID | 613 |
Feature activation | +7.39e-01 |
Pos logit contributions | |
atmeal | +0.023 |
rolling | +0.022 |
ancer | +0.021 |
lifetime | +0.021 |
highlight | +0.020 |
Neg logit contributions | |
rs | -0.021 |
irk | -0.020 |
screams | -0.020 |
rum | -0.020 |
ks | -0.019 |
Token | b |
Token ID | 65 |
Feature activation | +7.04e-01 |
Pos logit contributions | |
atmeal | +0.015 |
ancer | +0.014 |
rolling | +0.014 |
lifetime | +0.013 |
Hatt | +0.013 |
Neg logit contributions | |
screams | -0.019 |
rum | -0.019 |
rs | -0.019 |
irk | -0.019 |
ks | -0.019 |
Token | ble |
Token ID | 903 |
Feature activation | +4.05e-01 |
Pos logit contributions | |
atmeal | +0.012 |
rolling | +0.011 |
ancer | +0.010 |
highlight | +0.009 |
lifetime | +0.009 |
Neg logit contributions | |
rs | -0.022 |
screams | -0.021 |
irk | -0.021 |
bites | -0.021 |
Mine | -0.020 |
Token | in |
Token ID | 287 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
atmeal | +0.011 |
rolling | +0.010 |
ancer | +0.010 |
highlight | +0.010 |
belt | +0.010 |
Neg logit contributions | |
rs | -0.008 |
irk | -0.008 |
screams | -0.007 |
ks | -0.007 |
Mine | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | +2.30e-01 |
Pos logit contributions | |
affe | +0.122 |
irk | +0.116 |
aron | +0.112 |
gging | +0.110 |
una | +0.109 |
Neg logit contributions | |
there | -0.040 |
suddenly | -0.039 |
exploring | -0.037 |
Grac | -0.036 |
mummy | -0.036 |
Token | water |
Token ID | 1660 |
Feature activation | -7.28e-01 |
Pos logit contributions | |
atmeal | +0.006 |
rolling | +0.005 |
highlight | +0.005 |
lifetime | +0.005 |
ancer | +0.005 |
Neg logit contributions | |
rs | -0.005 |
rum | -0.005 |
irk | -0.005 |
ks | -0.005 |
screams | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -1.67e+00 |
Pos logit contributions | |
rum | +0.015 |
irk | +0.015 |
Mine | +0.015 |
screams | +0.014 |
rs | +0.014 |
Neg logit contributions | |
atmeal | -0.018 |
oming | -0.016 |
ancer | -0.016 |
highlight | -0.015 |
ail | -0.015 |
Token | He |
Token ID | 679 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
rs | +0.034 |
irk | +0.032 |
ks | +0.031 |
rum | +0.031 |
aron | +0.030 |
Neg logit contributions | |
atmeal | -0.044 |
rolling | -0.044 |
ancer | -0.039 |
Hatt | -0.038 |
angers | -0.037 |
Token | was |
Token ID | 373 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
rs | +0.030 |
irk | +0.030 |
rum | +0.029 |
screams | +0.027 |
aron | +0.027 |
Neg logit contributions | |
atmeal | -0.027 |
rolling | -0.026 |
lifetime | -0.024 |
ancer | -0.024 |
Hatt | -0.024 |