Token | to |
Token ID | 284 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
can | +0.001 |
has | +0.000 |
is | +0.000 |
that | +0.000 |
lic | +0.000 |
Neg logit contributions | |
argue | -0.001 |
elbows | -0.001 |
cle | -0.001 |
iver | -0.001 |
afar | -0.001 |
Token | never |
Token ID | 1239 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
argue | +0.051 |
elbows | +0.048 |
cle | +0.046 |
gy | +0.045 |
weep | +0.044 |
Neg logit contributions | |
can | -0.050 |
has | -0.047 |
lic | -0.047 |
is | -0.045 |
boards | -0.045 |
Token | try |
Token ID | 1949 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
elbows | +0.073 |
argue | +0.072 |
cle | +0.070 |
afar | +0.066 |
gy | +0.066 |
Neg logit contributions | |
can | -0.070 |
has | -0.065 |
is | -0.063 |
lic | -0.061 |
makes | -0.060 |
Token | to |
Token ID | 284 |
Feature activation | +6.60e+00 |
Pos logit contributions | |
cle | +0.042 |
argue | +0.042 |
elbows | +0.042 |
iver | +0.039 |
ieties | +0.038 |
Neg logit contributions | |
can | -0.024 |
has | -0.022 |
is | -0.022 |
that | -0.021 |
makes | -0.020 |
Token | catch |
Token ID | 4929 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
elbows | +0.146 |
cle | +0.140 |
argue | +0.131 |
bie | +0.130 |
ieties | +0.127 |
Neg logit contributions | |
can | -0.129 |
is | -0.115 |
that | -0.111 |
of | -0.110 |
has | -0.109 |
Token | Twe |
Token ID | 24205 |
Feature activation | +1.13e+01 |
Pos logit contributions | |
argue | +0.003 |
elbows | +0.002 |
cle | +0.002 |
ge | +0.002 |
ree | +0.002 |
Neg logit contributions | |
can | -0.005 |
is | -0.005 |
has | -0.005 |
that | -0.005 |
helps | -0.005 |
Token | ety |
Token ID | 2963 |
Feature activation | +4.58e+00 |
Pos logit contributions | |
argue | +0.169 |
elbows | +0.169 |
mischief | +0.157 |
weep | +0.147 |
aster | +0.147 |
Neg logit contributions | |
can | -0.285 |
lic | -0.280 |
ing | -0.279 |
is | -0.269 |
has | -0.263 |
Token | again |
Token ID | 757 |
Feature activation | +4.91e+00 |
Pos logit contributions | |
elbows | +0.128 |
cle | +0.128 |
argue | +0.122 |
afar | +0.115 |
ieties | +0.113 |
Neg logit contributions | |
can | -0.064 |
is | -0.058 |
that | -0.056 |
of | -0.054 |
has | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -3.44e-02 |
Pos logit contributions | |
elbows | +0.131 |
argue | +0.131 |
cle | +0.125 |
gy | +0.119 |
ree | +0.119 |
Neg logit contributions | |
can | -0.068 |
has | -0.061 |
is | -0.059 |
that | -0.055 |
of | -0.055 |
Token | From |
Token ID | 3574 |
Feature activation | -2.08e+00 |
Pos logit contributions | |
can | +0.001 |
lic | +0.001 |
br | +0.001 |
has | +0.001 |
boards | +0.001 |
Neg logit contributions | |
argue | -0.001 |
gy | -0.001 |
elbows | -0.001 |
cle | -0.001 |
ree | -0.001 |
Token | that |
Token ID | 326 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
can | +0.014 |
lic | +0.012 |
has | +0.011 |
boards | +0.010 |
br | +0.010 |
Neg logit contributions | |
argue | -0.068 |
elbows | -0.067 |
cle | -0.066 |
afar | -0.065 |
gy | -0.064 |
Token | dare |
Token ID | 16498 |
Feature activation | +2.52e+00 |
Pos logit contributions | |
elbows | +0.062 |
cle | +0.058 |
argue | +0.058 |
afar | +0.053 |
ieties | +0.052 |
Neg logit contributions | |
can | -0.077 |
has | -0.070 |
is | -0.068 |
lic | -0.067 |
br | -0.067 |
Token | to |
Token ID | 284 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
elbows | +0.068 |
cle | +0.066 |
iver | +0.066 |
argue | +0.065 |
days | +0.064 |
Neg logit contributions | |
can | -0.034 |
that | -0.031 |
is | -0.029 |
has | -0.028 |
of | -0.027 |
Token | climb |
Token ID | 12080 |
Feature activation | +3.27e+00 |
Pos logit contributions | |
cle | +0.148 |
elbows | +0.146 |
bie | +0.139 |
ieties | +0.135 |
keeping | +0.134 |
Neg logit contributions | |
can | -0.103 |
that | -0.090 |
is | -0.088 |
of | -0.086 |
makes | -0.082 |
Token | up |
Token ID | 510 |
Feature activation | +2.57e+00 |
Pos logit contributions | |
cle | +0.095 |
argue | +0.093 |
iver | +0.090 |
elbows | +0.090 |
hr | +0.088 |
Neg logit contributions | |
can | -0.042 |
that | -0.038 |
is | -0.037 |
has | -0.036 |
all | -0.032 |
Token | to |
Token ID | 284 |
Feature activation | +4.03e+00 |
Pos logit contributions | |
cle | +0.073 |
elbows | +0.071 |
argue | +0.070 |
iver | +0.068 |
bie | +0.066 |
Neg logit contributions | |
can | -0.034 |
that | -0.030 |
is | -0.029 |
of | -0.029 |
has | -0.028 |
Token | Twe |
Token ID | 24205 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
elbows | +0.104 |
cle | +0.102 |
argue | +0.099 |
ge | +0.097 |
ree | +0.095 |
Neg logit contributions | |
can | -0.064 |
is | -0.058 |
that | -0.056 |
has | -0.054 |
helps | -0.051 |
Token | ety |
Token ID | 2963 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
argue | +0.170 |
elbows | +0.156 |
mischief | +0.152 |
footing | +0.152 |
weep | +0.149 |
Neg logit contributions | |
lic | -0.249 |
can | -0.247 |
ing | -0.246 |
is | -0.243 |
has | -0.239 |
Token | 's |
Token ID | 338 |
Feature activation | +2.12e+00 |
Pos logit contributions | |
cle | +0.120 |
elbows | +0.120 |
argue | +0.116 |
afar | +0.111 |
ieties | +0.107 |
Neg logit contributions | |
can | -0.048 |
is | -0.041 |
that | -0.040 |
has | -0.039 |
of | -0.038 |
Token | nest |
Token ID | 16343 |
Feature activation | +3.18e-01 |
Pos logit contributions | |
cle | +0.043 |
argue | +0.043 |
elbows | +0.042 |
ge | +0.041 |
aster | +0.039 |
Neg logit contributions | |
can | -0.042 |
is | -0.039 |
has | -0.039 |
living | -0.037 |
box | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | +7.88e-01 |
Pos logit contributions | |
argue | +0.007 |
elbows | +0.007 |
cle | +0.007 |
gy | +0.007 |
ge | +0.007 |
Neg logit contributions | |
can | -0.005 |
has | -0.005 |
lic | -0.005 |
is | -0.005 |
br | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | +2.86e-01 |
Pos logit contributions | |
argue | +0.020 |
elbows | +0.020 |
cle | +0.019 |
ge | +0.019 |
weep | +0.018 |
Neg logit contributions | |
can | -0.012 |
has | -0.011 |
is | -0.011 |
lic | -0.010 |
helps | -0.010 |
Token | who |
Token ID | 508 |
Feature activation | -2.15e-01 |
Pos logit contributions | |
argue | +0.040 |
elbows | +0.039 |
cle | +0.039 |
ge | +0.036 |
afar | +0.036 |
Neg logit contributions | |
can | -0.025 |
has | -0.023 |
is | -0.023 |
that | -0.022 |
of | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
can | +0.003 |
has | +0.002 |
lic | +0.002 |
is | +0.002 |
br | +0.002 |
Neg logit contributions | |
argue | -0.006 |
elbows | -0.006 |
cle | -0.006 |
gy | -0.006 |
ge | -0.006 |
Token | trying |
Token ID | 2111 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
can | +0.030 |
has | +0.029 |
is | +0.028 |
lic | +0.028 |
living | +0.027 |
Neg logit contributions | |
argue | -0.031 |
elbows | -0.031 |
cle | -0.030 |
ge | -0.028 |
ree | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
can | +0.014 |
is | +0.012 |
that | +0.012 |
has | +0.011 |
living | +0.011 |
Neg logit contributions | |
elbows | -0.037 |
cle | -0.037 |
argue | -0.036 |
iver | -0.035 |
gy | -0.034 |
Token | take |
Token ID | 1011 |
Feature activation | -9.51e-01 |
Pos logit contributions | |
elbows | +0.104 |
cle | +0.104 |
bie | +0.098 |
argue | +0.096 |
gy | +0.091 |
Neg logit contributions | |
can | -0.091 |
of | -0.084 |
is | -0.082 |
that | -0.081 |
makes | -0.078 |
Token | Twe |
Token ID | 24205 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
can | +0.014 |
is | +0.012 |
that | +0.012 |
br | +0.012 |
has | +0.011 |
Neg logit contributions | |
argue | -0.026 |
elbows | -0.026 |
cle | -0.025 |
ge | -0.025 |
sing | -0.024 |
Token | ety |
Token ID | 2963 |
Feature activation | +4.26e+00 |
Pos logit contributions | |
argue | +0.167 |
elbows | +0.154 |
mischief | +0.140 |
weep | +0.138 |
afar | +0.136 |
Neg logit contributions | |
can | -0.249 |
lic | -0.246 |
ing | -0.246 |
br | -0.233 |
of | -0.232 |
Token | 's |
Token ID | 338 |
Feature activation | +3.00e+00 |
Pos logit contributions | |
elbows | +0.127 |
cle | +0.124 |
argue | +0.122 |
afar | +0.119 |
ieties | +0.117 |
Neg logit contributions | |
can | -0.051 |
that | -0.044 |
of | -0.044 |
is | -0.043 |
living | -0.041 |
Token | nest |
Token ID | 16343 |
Feature activation | +5.28e-01 |
Pos logit contributions | |
argue | +0.069 |
elbows | +0.068 |
cle | +0.068 |
ge | +0.068 |
afar | +0.063 |
Neg logit contributions | |
can | -0.056 |
is | -0.049 |
has | -0.048 |
that | -0.047 |
of | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +8.84e-01 |
Pos logit contributions | |
argue | +0.013 |
elbows | +0.013 |
cle | +0.012 |
ge | +0.012 |
gy | +0.012 |
Neg logit contributions | |
can | -0.008 |
has | -0.007 |
lic | -0.007 |
is | -0.007 |
helps | -0.007 |
Token | Twe |
Token ID | 24205 |
Feature activation | +6.10e+00 |
Pos logit contributions | |
argue | +0.017 |
elbows | +0.017 |
cle | +0.016 |
ge | +0.015 |
afar | +0.015 |
Neg logit contributions | |
can | -0.019 |
has | -0.018 |
is | -0.018 |
lic | -0.017 |
helps | -0.017 |
Token | Lucy |
Token ID | 22162 |
Feature activation | +2.18e+00 |
Pos logit contributions | |
argue | +0.045 |
elbows | +0.044 |
cle | +0.043 |
ree | +0.042 |
ge | +0.042 |
Neg logit contributions | |
can | -0.033 |
that | -0.030 |
is | -0.030 |
has | -0.030 |
of | -0.028 |
Token | noticed |
Token ID | 6810 |
Feature activation | -2.79e+00 |
Pos logit contributions | |
argue | +0.060 |
elbows | +0.058 |
cle | +0.058 |
ge | +0.056 |
afar | +0.054 |
Neg logit contributions | |
can | -0.032 |
has | -0.029 |
is | -0.029 |
living | -0.026 |
could | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | -2.60e+00 |
Pos logit contributions | |
can | +0.044 |
has | +0.040 |
lic | +0.039 |
is | +0.039 |
helps | +0.036 |
Neg logit contributions | |
argue | -0.069 |
elbows | -0.067 |
cle | -0.064 |
ge | -0.062 |
gy | -0.062 |
Token | weather |
Token ID | 6193 |
Feature activation | +1.25e+00 |
Pos logit contributions | |
can | +0.038 |
lic | +0.035 |
has | +0.035 |
is | +0.033 |
br | +0.032 |
Neg logit contributions | |
argue | -0.065 |
elbows | -0.064 |
cle | -0.060 |
afar | -0.060 |
weep | -0.059 |
Token | was |
Token ID | 373 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
argue | +0.027 |
elbows | +0.025 |
gy | +0.024 |
iver | +0.024 |
ge | +0.024 |
Neg logit contributions | |
can | -0.021 |
lic | -0.020 |
ye | -0.020 |
has | -0.019 |
helps | -0.019 |
Token | uncom |
Token ID | 8820 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
can | +0.042 |
has | +0.039 |
lic | +0.038 |
is | +0.038 |
br | +0.037 |
Neg logit contributions | |
argue | -0.043 |
elbows | -0.041 |
cle | -0.038 |
gy | -0.038 |
weep | -0.037 |
Token | fort |
Token ID | 3319 |
Feature activation | +3.10e+00 |
Pos logit contributions | |
elbows | +0.207 |
mischief | +0.195 |
argue | +0.175 |
packs | +0.166 |
weep | +0.164 |
Neg logit contributions | |
can | -0.201 |
lic | -0.198 |
has | -0.179 |
br | -0.178 |
boards | -0.174 |
Token | ably |
Token ID | 1346 |
Feature activation | +2.20e+00 |
Pos logit contributions | |
elbows | +0.059 |
argue | +0.058 |
afar | +0.052 |
cle | +0.051 |
weep | +0.051 |
Neg logit contributions | |
can | -0.062 |
lic | -0.061 |
that | -0.061 |
of | -0.060 |
is | -0.060 |
Token | hot |
Token ID | 3024 |
Feature activation | +1.65e+00 |
Pos logit contributions | |
argue | +0.051 |
elbows | +0.048 |
ge | +0.046 |
worry | +0.045 |
weep | +0.045 |
Neg logit contributions | |
can | -0.037 |
lic | -0.036 |
has | -0.034 |
boards | -0.033 |
br | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e-01 |
Pos logit contributions | |
elbows | +0.029 |
argue | +0.028 |
keeping | +0.027 |
gy | +0.026 |
Johnson | +0.026 |
Neg logit contributions | |
lic | -0.034 |
can | -0.033 |
has | -0.032 |
br | -0.031 |
teaches | -0.031 |
Token | She |
Token ID | 1375 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
can | +0.002 |
has | +0.001 |
lic | +0.001 |
is | +0.001 |
helps | +0.001 |
Neg logit contributions | |
argue | -0.004 |
elbows | -0.004 |
cle | -0.004 |
ge | -0.004 |
gy | -0.004 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.02e+00 |
Pos logit contributions | |
can | +0.032 |
has | +0.030 |
is | +0.029 |
living | +0.029 |
lic | +0.029 |
Neg logit contributions | |
argue | -0.037 |
elbows | -0.036 |
cle | -0.036 |
ge | -0.034 |
gy | -0.033 |
Token | that |
Token ID | 326 |
Feature activation | -1.60e+00 |
Pos logit contributions | |
argue | +0.028 |
elbows | +0.027 |
cle | +0.026 |
gy | +0.026 |
ge | +0.026 |
Neg logit contributions | |
can | -0.013 |
has | -0.012 |
lic | -0.012 |
is | -0.011 |
br | -0.011 |
Token | she |
Token ID | 673 |
Feature activation | -2.30e-01 |
Pos logit contributions | |
can | +0.025 |
has | +0.023 |
lic | +0.023 |
is | +0.022 |
br | +0.021 |
Neg logit contributions | |
argue | -0.039 |
elbows | -0.038 |
cle | -0.036 |
gy | -0.035 |
ge | -0.035 |
Token | could |
Token ID | 714 |
Feature activation | +1.84e+00 |
Pos logit contributions | |
can | +0.003 |
lic | +0.003 |
boards | +0.003 |
br | +0.003 |
der | +0.003 |
Neg logit contributions | |
argue | -0.005 |
weep | -0.005 |
gy | -0.005 |
elbows | -0.005 |
cle | -0.005 |
Token | help |
Token ID | 1037 |
Feature activation | +9.18e-02 |
Pos logit contributions | |
argue | +0.035 |
elbows | +0.033 |
cle | +0.032 |
gy | +0.031 |
weep | +0.031 |
Neg logit contributions | |
can | -0.039 |
has | -0.037 |
lic | -0.037 |
is | -0.035 |
boards | -0.035 |
Token | Twe |
Token ID | 24205 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
argue | +0.002 |
elbows | +0.002 |
cle | +0.002 |
gy | +0.002 |
afar | +0.002 |
Neg logit contributions | |
can | -0.002 |
is | -0.002 |
has | -0.002 |
of | -0.002 |
that | -0.002 |
Token | ety |
Token ID | 2963 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
elbows | +0.148 |
mischief | +0.145 |
argue | +0.144 |
afar | +0.134 |
footing | +0.131 |
Neg logit contributions | |
can | -0.241 |
ing | -0.236 |
of | -0.231 |
lic | -0.230 |
has | -0.220 |
Token | and |
Token ID | 290 |
Feature activation | +2.83e+00 |
Pos logit contributions | |
elbows | +0.099 |
argue | +0.097 |
cle | +0.095 |
afar | +0.089 |
ree | +0.086 |
Neg logit contributions | |
can | -0.094 |
is | -0.084 |
has | -0.084 |
that | -0.082 |
of | -0.082 |
Token | learned |
Token ID | 4499 |
Feature activation | -3.18e+00 |
Pos logit contributions | |
argue | +0.058 |
elbows | +0.053 |
gy | +0.053 |
worry | +0.052 |
weep | +0.052 |
Neg logit contributions | |
lic | -0.054 |
boards | -0.053 |
can | -0.051 |
br | -0.050 |
has | -0.049 |
Token | that |
Token ID | 326 |
Feature activation | -2.17e+00 |
Pos logit contributions | |
has | +0.047 |
can | +0.047 |
lic | +0.046 |
br | +0.042 |
boards | +0.041 |
Neg logit contributions | |
argue | -0.077 |
elbows | -0.071 |
afar | -0.071 |
ree | -0.070 |
ge | -0.070 |
Token | it |
Token ID | 340 |
Feature activation | -3.40e+00 |
Pos logit contributions | |
can | +0.032 |
is | +0.028 |
that | +0.028 |
has | +0.027 |
living | +0.027 |
Neg logit contributions | |
elbows | -0.057 |
argue | -0.056 |
cle | -0.055 |
ighed | -0.055 |
gy | -0.054 |
Token | The |
Token ID | 383 |
Feature activation | -3.85e+00 |
Pos logit contributions | |
argue | +0.012 |
elbows | +0.012 |
cle | +0.011 |
ge | +0.011 |
afar | +0.011 |
Neg logit contributions | |
can | -0.010 |
has | -0.009 |
is | -0.009 |
lic | -0.008 |
that | -0.008 |
Token | cat |
Token ID | 3797 |
Feature activation | -7.95e-01 |
Pos logit contributions | |
can | +0.072 |
has | +0.067 |
is | +0.066 |
lic | +0.062 |
living | +0.062 |
Neg logit contributions | |
argue | -0.086 |
elbows | -0.083 |
ge | -0.081 |
cle | -0.080 |
afar | -0.076 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
can | +0.011 |
has | +0.010 |
lic | +0.009 |
is | +0.009 |
br | +0.009 |
Neg logit contributions | |
argue | -0.021 |
elbows | -0.021 |
cle | -0.020 |
gy | -0.020 |
weep | -0.019 |
Token | to |
Token ID | 284 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
can | +0.029 |
that | +0.025 |
is | +0.025 |
has | +0.025 |
of | +0.024 |
Neg logit contributions | |
argue | -0.064 |
elbows | -0.063 |
ge | -0.060 |
cle | -0.060 |
iver | -0.060 |
Token | eat |
Token ID | 4483 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
cle | +0.110 |
elbows | +0.109 |
ge | +0.109 |
bie | +0.105 |
packs | +0.103 |
Neg logit contributions | |
can | -0.072 |
that | -0.068 |
is | -0.067 |
of | -0.064 |
big | -0.063 |
Token | Twe |
Token ID | 24205 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
can | +0.027 |
is | +0.025 |
has | +0.024 |
that | +0.024 |
helps | +0.023 |
Neg logit contributions | |
argue | -0.023 |
elbows | -0.022 |
cle | -0.021 |
ge | -0.020 |
ree | -0.020 |
Token | ety |
Token ID | 2963 |
Feature activation | +4.19e+00 |
Pos logit contributions | |
argue | +0.165 |
elbows | +0.153 |
mischief | +0.139 |
footing | +0.136 |
weep | +0.133 |
Neg logit contributions | |
lic | -0.242 |
can | -0.241 |
ing | -0.239 |
is | -0.230 |
has | -0.229 |
Token | ! |
Token ID | 0 |
Feature activation | +5.15e-01 |
Pos logit contributions | |
elbows | +0.124 |
cle | +0.123 |
argue | +0.118 |
afar | +0.115 |
ree | +0.112 |
Neg logit contributions | |
can | -0.054 |
is | -0.052 |
that | -0.051 |
of | -0.047 |
has | -0.045 |
Token |
|
Token ID | 198 |
Feature activation | +4.79e-01 |
Pos logit contributions | |
argue | +0.012 |
elbows | +0.012 |
cle | +0.011 |
ge | +0.011 |
afar | +0.011 |
Neg logit contributions | |
can | -0.009 |
has | -0.008 |
is | -0.008 |
lic | -0.008 |
helps | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +7.07e-01 |
Pos logit contributions | |
elbows | +0.013 |
argue | +0.013 |
cle | +0.012 |
afar | +0.012 |
gy | +0.012 |
Neg logit contributions | |
can | -0.006 |
is | -0.006 |
lic | -0.006 |
has | -0.006 |
of | -0.005 |
Token | Twe |
Token ID | 32665 |
Feature activation | +7.79e+00 |
Pos logit contributions | |
argue | +0.009 |
elbows | +0.009 |
cle | +0.008 |
afar | +0.007 |
weep | +0.007 |
Neg logit contributions | |
can | -0.020 |
has | -0.019 |
is | -0.018 |
lic | -0.018 |
br | -0.018 |
Token | Tom |
Token ID | 4186 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
elbows | +0.010 |
argue | +0.010 |
cle | +0.010 |
ge | +0.009 |
afar | +0.009 |
Neg logit contributions | |
can | -0.006 |
has | -0.005 |
is | -0.005 |
lic | -0.005 |
helps | -0.005 |
Token | was |
Token ID | 373 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
elbows | +0.021 |
argue | +0.021 |
cle | +0.020 |
ge | +0.019 |
afar | +0.019 |
Neg logit contributions | |
can | -0.010 |
has | -0.009 |
is | -0.009 |
lic | -0.008 |
helps | -0.008 |
Token | trying |
Token ID | 2111 |
Feature activation | -1.25e+00 |
Pos logit contributions | |
can | +0.042 |
has | +0.040 |
is | +0.039 |
living | +0.039 |
lic | +0.038 |
Neg logit contributions | |
argue | -0.056 |
cle | -0.055 |
elbows | -0.054 |
ge | -0.052 |
aster | -0.050 |
Token | to |
Token ID | 284 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
can | +0.013 |
that | +0.012 |
is | +0.011 |
has | +0.011 |
living | +0.010 |
Neg logit contributions | |
elbows | -0.039 |
cle | -0.039 |
argue | -0.038 |
iver | -0.038 |
keeping | -0.037 |
Token | catch |
Token ID | 4929 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
elbows | +0.090 |
cle | +0.089 |
bie | +0.088 |
packs | +0.082 |
ge | +0.080 |
Neg logit contributions | |
can | -0.084 |
that | -0.079 |
of | -0.078 |
is | -0.075 |
big | -0.075 |
Token | Twe |
Token ID | 24205 |
Feature activation | +9.92e+00 |
Pos logit contributions | |
can | +0.017 |
that | +0.016 |
is | +0.016 |
of | +0.015 |
has | +0.014 |
Neg logit contributions | |
cle | -0.028 |
argue | -0.028 |
elbows | -0.027 |
ge | -0.026 |
days | -0.025 |
Token | ety |
Token ID | 2963 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
argue | +0.162 |
elbows | +0.156 |
mischief | +0.149 |
footing | +0.135 |
afar | +0.134 |
Neg logit contributions | |
lic | -0.238 |
can | -0.233 |
ing | -0.231 |
of | -0.223 |
is | -0.221 |
Token | , |
Token ID | 11 |
Feature activation | +2.93e+00 |
Pos logit contributions | |
cle | +0.093 |
elbows | +0.092 |
argue | +0.090 |
afar | +0.085 |
ree | +0.083 |
Neg logit contributions | |
can | -0.046 |
is | -0.041 |
that | -0.039 |
has | -0.039 |
of | -0.037 |
Token | but |
Token ID | 475 |
Feature activation | +5.52e-01 |
Pos logit contributions | |
argue | +0.062 |
elbows | +0.061 |
cle | +0.059 |
gy | +0.056 |
ge | +0.056 |
Neg logit contributions | |
can | -0.057 |
has | -0.053 |
is | -0.051 |
lic | -0.050 |
helps | -0.049 |
Token | Twe |
Token ID | 24205 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
argue | +0.017 |
elbows | +0.016 |
cle | +0.016 |
iver | +0.015 |
ree | +0.015 |
Neg logit contributions | |
can | -0.006 |
has | -0.005 |
is | -0.005 |
that | -0.005 |
makes | -0.004 |
Token | ety |
Token ID | 2963 |
Feature activation | -1.07e-01 |
Pos logit contributions | |
argue | +0.112 |
mischief | +0.106 |
elbows | +0.105 |
weep | +0.096 |
aster | +0.094 |
Neg logit contributions | |
can | -0.166 |
has | -0.158 |
is | -0.157 |
lic | -0.154 |
ing | -0.152 |
Token | like |
Token ID | 588 |
Feature activation | +1.31e-01 |
Pos logit contributions | |
argue | +0.033 |
elbows | +0.032 |
cle | +0.030 |
gy | +0.030 |
weep | +0.029 |
Neg logit contributions | |
can | -0.033 |
lic | -0.031 |
has | -0.031 |
is | -0.030 |
boards | -0.030 |
Token | to |
Token ID | 284 |
Feature activation | +5.03e+00 |
Pos logit contributions | |
argue | +0.003 |
elbows | +0.003 |
cle | +0.003 |
afar | +0.003 |
weep | +0.003 |
Neg logit contributions | |
can | -0.002 |
lic | -0.002 |
has | -0.002 |
boards | -0.002 |
is | -0.002 |
Token | pick |
Token ID | 2298 |
Feature activation | -2.23e+00 |
Pos logit contributions | |
elbows | +0.091 |
argue | +0.090 |
cle | +0.085 |
ge | +0.084 |
gy | +0.081 |
Neg logit contributions | |
can | -0.112 |
has | -0.103 |
is | -0.102 |
lic | -0.098 |
makes | -0.097 |
Token | flowers |
Token ID | 12734 |
Feature activation | +1.94e+00 |
Pos logit contributions | |
lic | +0.042 |
can | +0.039 |
has | +0.039 |
teaches | +0.036 |
lessly | +0.036 |
Neg logit contributions | |
afar | -0.043 |
elbows | -0.041 |
argue | -0.041 |
ree | -0.039 |
gy | -0.039 |
Token | on |
Token ID | 319 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
argue | +0.037 |
gy | +0.033 |
ree | +0.033 |
cle | +0.033 |
elbows | +0.033 |
Neg logit contributions | |
lic | -0.037 |
can | -0.034 |
has | -0.034 |
boards | -0.033 |
helps | -0.032 |
Token | Tues |
Token ID | 48496 |
Feature activation | +9.87e+00 |
Pos logit contributions | |
argue | +0.066 |
elbows | +0.064 |
cle | +0.061 |
afar | +0.060 |
gy | +0.059 |
Neg logit contributions | |
can | -0.053 |
lic | -0.051 |
has | -0.050 |
is | -0.047 |
helps | -0.047 |
Token | days |
Token ID | 12545 |
Feature activation | +1.37e+00 |
Pos logit contributions | |
elbows | +0.098 |
mischief | +0.096 |
argue | +0.093 |
worry | +0.088 |
panic | +0.086 |
Neg logit contributions | |
can | -0.279 |
is | -0.272 |
has | -0.269 |
living | -0.266 |
will | -0.248 |
Token | ." |
Token ID | 526 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
argue | +0.025 |
cle | +0.023 |
days | +0.023 |
gy | +0.022 |
elbows | +0.022 |
Neg logit contributions | |
lic | -0.026 |
can | -0.025 |
has | -0.024 |
br | -0.024 |
helps | -0.023 |
Token | |
Token ID | 220 |
Feature activation | +6.53e-01 |
Pos logit contributions | |
argue | +0.037 |
elbows | +0.036 |
ge | +0.035 |
footing | +0.034 |
iver | +0.034 |
Neg logit contributions | |
can | -0.017 |
has | -0.016 |
is | -0.015 |
that | -0.014 |
helps | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +2.91e-01 |
Pos logit contributions | |
argue | +0.017 |
elbows | +0.016 |
cle | +0.015 |
ge | +0.015 |
gy | +0.015 |
Neg logit contributions | |
can | -0.010 |
has | -0.009 |
is | -0.009 |
lic | -0.009 |
helps | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
argue | +0.009 |
elbows | +0.008 |
ge | +0.008 |
afar | +0.008 |
worry | +0.008 |
Neg logit contributions | |
can | -0.003 |
is | -0.003 |
lic | -0.003 |
has | -0.003 |
living | -0.003 |
Token | world |
Token ID | 995 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
can | +0.023 |
lic | +0.022 |
has | +0.022 |
is | +0.021 |
boards | +0.021 |
Neg logit contributions | |
argue | -0.028 |
elbows | -0.027 |
cle | -0.026 |
gy | -0.026 |
afar | -0.025 |
Token | from |
Token ID | 422 |
Feature activation | +1.59e+00 |
Pos logit contributions | |
argue | +0.042 |
ge | +0.038 |
weep | +0.038 |
gy | +0.037 |
worry | +0.037 |
Neg logit contributions | |
lic | -0.034 |
can | -0.031 |
has | -0.030 |
boards | -0.029 |
br | -0.029 |
Token | up |
Token ID | 510 |
Feature activation | +2.37e+00 |
Pos logit contributions | |
argue | +0.042 |
elbows | +0.041 |
cle | +0.041 |
ree | +0.040 |
iver | +0.040 |
Neg logit contributions | |
can | -0.023 |
that | -0.022 |
is | -0.021 |
has | -0.021 |
living | -0.020 |
Token | high |
Token ID | 1029 |
Feature activation | +4.42e+00 |
Pos logit contributions | |
elbows | +0.059 |
argue | +0.058 |
cle | +0.056 |
gy | +0.053 |
iver | +0.053 |
Neg logit contributions | |
can | -0.039 |
has | -0.035 |
is | -0.033 |
of | -0.033 |
that | -0.032 |
Token | like |
Token ID | 588 |
Feature activation | +1.79e-01 |
Pos logit contributions | |
argue | +0.103 |
elbows | +0.101 |
cle | +0.095 |
gy | +0.095 |
ge | +0.094 |
Neg logit contributions | |
can | -0.073 |
lic | -0.067 |
has | -0.067 |
is | -0.064 |
helps | -0.062 |
Token | Twe |
Token ID | 24205 |
Feature activation | +9.83e+00 |
Pos logit contributions | |
argue | +0.004 |
elbows | +0.004 |
afar | +0.003 |
cle | +0.003 |
gy | +0.003 |
Neg logit contributions | |
can | -0.003 |
lic | -0.003 |
has | -0.003 |
is | -0.003 |
br | -0.003 |
Token | ety |
Token ID | 2963 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
argue | +0.161 |
elbows | +0.147 |
weep | +0.133 |
mischief | +0.132 |
footing | +0.126 |
Neg logit contributions | |
ing | -0.239 |
lic | -0.239 |
can | -0.238 |
has | -0.230 |
br | -0.224 |
Token | , |
Token ID | 11 |
Feature activation | +3.60e+00 |
Pos logit contributions | |
argue | +0.093 |
elbows | +0.092 |
cle | +0.089 |
ree | +0.084 |
ge | +0.084 |
Neg logit contributions | |
can | -0.058 |
has | -0.052 |
is | -0.051 |
lic | -0.048 |
helps | -0.047 |
Token | but |
Token ID | 475 |
Feature activation | +7.56e-01 |
Pos logit contributions | |
argue | +0.078 |
elbows | +0.075 |
cle | +0.070 |
afar | +0.069 |
weep | +0.069 |
Neg logit contributions | |
can | -0.065 |
lic | -0.063 |
has | -0.061 |
is | -0.059 |
br | -0.059 |
Token | he |
Token ID | 339 |
Feature activation | -1.76e+00 |
Pos logit contributions | |
argue | +0.020 |
elbows | +0.019 |
cle | +0.019 |
gy | +0.018 |
ge | +0.018 |
Neg logit contributions | |
can | -0.010 |
has | -0.009 |
lic | -0.009 |
is | -0.009 |
br | -0.009 |
Token | was |
Token ID | 373 |
Feature activation | -2.37e+00 |
Pos logit contributions | |
can | +0.028 |
has | +0.026 |
is | +0.025 |
lic | +0.024 |
helps | +0.023 |
Neg logit contributions | |
argue | -0.044 |
elbows | -0.044 |
cle | -0.041 |
ge | -0.040 |
afar | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | +2.27e+00 |
Pos logit contributions | |
can | +0.004 |
that | +0.004 |
all | +0.003 |
is | +0.003 |
of | +0.003 |
Neg logit contributions | |
argue | -0.005 |
bie | -0.004 |
elbows | -0.004 |
ree | -0.004 |
cle | -0.004 |
Token | little |
Token ID | 1310 |
Feature activation | +4.41e+00 |
Pos logit contributions | |
elbows | +0.057 |
argue | +0.053 |
cle | +0.051 |
iver | +0.051 |
gy | +0.050 |
Neg logit contributions | |
can | -0.040 |
br | -0.034 |
has | -0.034 |
is | -0.033 |
lic | -0.032 |
Token | bird |
Token ID | 6512 |
Feature activation | +3.15e+00 |
Pos logit contributions | |
elbows | +0.094 |
argue | +0.090 |
cle | +0.090 |
iver | +0.085 |
afar | +0.083 |
Neg logit contributions | |
can | -0.088 |
has | -0.078 |
is | -0.077 |
that | -0.074 |
of | -0.074 |
Token | ie |
Token ID | 494 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
elbows | +0.090 |
argue | +0.088 |
cle | +0.087 |
mischief | +0.082 |
afar | +0.082 |
Neg logit contributions | |
can | -0.043 |
that | -0.037 |
of | -0.037 |
is | -0.035 |
has | -0.034 |
Token | like |
Token ID | 588 |
Feature activation | +3.34e-01 |
Pos logit contributions | |
elbows | +0.096 |
argue | +0.096 |
cle | +0.092 |
afar | +0.088 |
iver | +0.087 |
Neg logit contributions | |
can | -0.055 |
has | -0.048 |
is | -0.046 |
that | -0.043 |
of | -0.042 |
Token | Twe |
Token ID | 24205 |
Feature activation | +9.78e+00 |
Pos logit contributions | |
argue | +0.008 |
elbows | +0.008 |
cle | +0.007 |
gy | +0.007 |
ge | +0.007 |
Neg logit contributions | |
can | -0.006 |
has | -0.005 |
is | -0.005 |
lic | -0.005 |
helps | -0.005 |
Token | ety |
Token ID | 2963 |
Feature activation | +4.11e+00 |
Pos logit contributions | |
argue | +0.176 |
elbows | +0.163 |
mischief | +0.158 |
weep | +0.148 |
footing | +0.146 |
Neg logit contributions | |
can | -0.215 |
ing | -0.210 |
lic | -0.198 |
has | -0.197 |
is | -0.195 |
Token | . |
Token ID | 13 |
Feature activation | +7.58e-01 |
Pos logit contributions | |
argue | +0.113 |
elbows | +0.113 |
cle | +0.110 |
afar | +0.104 |
ree | +0.103 |
Neg logit contributions | |
can | -0.060 |
is | -0.052 |
has | -0.052 |
that | -0.047 |
of | -0.046 |
Token | So |
Token ID | 1406 |
Feature activation | +1.52e-01 |
Pos logit contributions | |
argue | +0.021 |
elbows | +0.021 |
cle | +0.020 |
ge | +0.020 |
iver | +0.019 |
Neg logit contributions | |
can | -0.011 |
has | -0.010 |
is | -0.010 |
that | -0.008 |
lic | -0.008 |
Token | , |
Token ID | 11 |
Feature activation | -4.58e-01 |
Pos logit contributions | |
argue | +0.004 |
elbows | +0.004 |
cle | +0.004 |
ge | +0.004 |
afar | +0.003 |
Neg logit contributions | |
can | -0.002 |
has | -0.002 |
is | -0.002 |
that | -0.002 |
lic | -0.002 |
Token | Twe |
Token ID | 24205 |
Feature activation | +5.93e+00 |
Pos logit contributions | |
can | +0.010 |
that | +0.010 |
has | +0.009 |
of | +0.009 |
is | +0.009 |
Neg logit contributions | |
elbows | -0.010 |
argue | -0.009 |
iver | -0.009 |
cle | -0.009 |
ree | -0.009 |
Token | ! |
Token ID | 0 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
lic | +0.056 |
can | +0.055 |
br | +0.053 |
has | +0.051 |
helps | +0.049 |
Neg logit contributions | |
argue | -0.055 |
gy | -0.053 |
elbows | -0.052 |
ge | -0.051 |
weep | -0.050 |
Token | Tom |
Token ID | 4186 |
Feature activation | +3.76e-01 |
Pos logit contributions | |
can | +0.014 |
has | +0.013 |
is | +0.013 |
lic | +0.013 |
helps | +0.012 |
Neg logit contributions | |
argue | -0.011 |
elbows | -0.010 |
cle | -0.010 |
ge | -0.009 |
gy | -0.009 |
Token | wanted |
Token ID | 2227 |
Feature activation | -2.63e+00 |
Pos logit contributions | |
argue | +0.010 |
elbows | +0.010 |
cle | +0.009 |
ge | +0.009 |
afar | +0.009 |
Neg logit contributions | |
can | -0.005 |
has | -0.005 |
is | -0.005 |
lic | -0.004 |
helps | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +4.33e+00 |
Pos logit contributions | |
can | +0.038 |
has | +0.034 |
is | +0.033 |
that | +0.032 |
helps | +0.031 |
Neg logit contributions | |
argue | -0.070 |
elbows | -0.069 |
cle | -0.066 |
ge | -0.064 |
iver | -0.064 |
Token | catch |
Token ID | 4929 |
Feature activation | -1.23e+00 |
Pos logit contributions | |
elbows | +0.112 |
cle | +0.107 |
ge | +0.106 |
bie | +0.103 |
packs | +0.101 |
Neg logit contributions | |
can | -0.073 |
that | -0.067 |
is | -0.064 |
of | -0.064 |
big | -0.062 |
Token | Twe |
Token ID | 24205 |
Feature activation | +9.77e+00 |
Pos logit contributions | |
can | +0.026 |
that | +0.024 |
is | +0.024 |
has | +0.023 |
of | +0.023 |
Neg logit contributions | |
argue | -0.025 |
elbows | -0.025 |
cle | -0.025 |
ge | -0.023 |
sing | -0.022 |
Token | ety |
Token ID | 2963 |
Feature activation | +3.43e+00 |
Pos logit contributions | |
argue | +0.154 |
elbows | +0.148 |
mischief | +0.135 |
afar | +0.124 |
weep | +0.123 |
Neg logit contributions | |
can | -0.240 |
lic | -0.239 |
ing | -0.234 |
of | -0.227 |
is | -0.225 |
Token | and |
Token ID | 290 |
Feature activation | +3.06e+00 |
Pos logit contributions | |
cle | +0.098 |
elbows | +0.097 |
argue | +0.094 |
afar | +0.089 |
ree | +0.088 |
Neg logit contributions | |
can | -0.048 |
is | -0.043 |
that | -0.041 |
has | -0.040 |
of | -0.039 |
Token | eat |
Token ID | 4483 |
Feature activation | -2.43e+00 |
Pos logit contributions | |
argue | +0.063 |
elbows | +0.062 |
cle | +0.058 |
ge | +0.056 |
gy | +0.056 |
Neg logit contributions | |
can | -0.060 |
has | -0.056 |
lic | -0.054 |
is | -0.054 |
helps | -0.052 |
Token | her |
Token ID | 607 |
Feature activation | +2.26e+00 |
Pos logit contributions | |
can | +0.050 |
lic | +0.048 |
has | +0.048 |
br | +0.045 |
is | +0.045 |
Neg logit contributions | |
argue | -0.046 |
elbows | -0.045 |
cle | -0.041 |
afar | -0.041 |
ge | -0.041 |
Token | for |
Token ID | 329 |
Feature activation | +1.73e-01 |
Pos logit contributions | |
cle | +0.063 |
elbows | +0.062 |
argue | +0.062 |
ge | +0.059 |
ree | +0.058 |
Neg logit contributions | |
can | -0.033 |
is | -0.032 |
has | -0.028 |
that | -0.028 |
of | -0.027 |
Token | 's |
Token ID | 338 |
Feature activation | +7.41e-01 |
Pos logit contributions | |
lic | +0.040 |
lessly | +0.035 |
boards | +0.033 |
der | +0.031 |
br | +0.029 |
Neg logit contributions | |
argue | -0.084 |
worry | -0.079 |
cle | -0.078 |
elbows | -0.076 |
weep | -0.075 |
Token | so |
Token ID | 523 |
Feature activation | +1.58e+00 |
Pos logit contributions | |
argue | +0.019 |
elbows | +0.019 |
cle | +0.018 |
afar | +0.018 |
gy | +0.018 |
Neg logit contributions | |
can | -0.010 |
lic | -0.010 |
has | -0.009 |
is | -0.009 |
boards | -0.009 |
Token | special |
Token ID | 2041 |
Feature activation | -4.26e-01 |
Pos logit contributions | |
argue | +0.035 |
worry | +0.033 |
afar | +0.033 |
cle | +0.032 |
weep | +0.032 |
Neg logit contributions | |
boards | -0.024 |
der | -0.024 |
als | -0.021 |
has | -0.021 |
can | -0.021 |
Token | about |
Token ID | 546 |
Feature activation | +1.42e+00 |
Pos logit contributions | |
lic | +0.010 |
boards | +0.010 |
lessly | +0.009 |
der | +0.009 |
lid | +0.009 |
Neg logit contributions | |
argue | -0.006 |
worry | -0.005 |
reason | -0.005 |
cle | -0.005 |
gy | -0.005 |
Token | Wed |
Token ID | 3300 |
Feature activation | +6.52e+00 |
Pos logit contributions | |
argue | +0.030 |
gy | +0.028 |
afar | +0.028 |
elbows | +0.028 |
cle | +0.028 |
Neg logit contributions | |
lic | -0.026 |
boards | -0.025 |
can | -0.024 |
lessly | -0.023 |
has | -0.023 |
Token | nes |
Token ID | 2516 |
Feature activation | +9.55e+00 |
Pos logit contributions | |
elbows | +0.109 |
argue | +0.103 |
cle | +0.094 |
gy | +0.093 |
afar | +0.090 |
Neg logit contributions | |
can | -0.154 |
lic | -0.149 |
has | -0.145 |
br | -0.141 |
is | -0.139 |
Token | days |
Token ID | 12545 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
elbows | +0.211 |
argue | +0.186 |
afar | +0.178 |
cle | +0.174 |
ieties | +0.166 |
Neg logit contributions | |
can | -0.198 |
of | -0.188 |
has | -0.186 |
lic | -0.181 |
is | -0.180 |
Token | ?" |
Token ID | 1701 |
Feature activation | +7.15e-01 |
Pos logit contributions | |
argue | +0.026 |
days | +0.023 |
worry | +0.022 |
iver | +0.022 |
cle | +0.021 |
Neg logit contributions | |
lid | -0.037 |
br | -0.036 |
can | -0.036 |
lic | -0.036 |
der | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | +4.16e-01 |
Pos logit contributions | |
argue | +0.020 |
elbows | +0.020 |
ge | +0.019 |
cle | +0.019 |
gy | +0.018 |
Neg logit contributions | |
can | -0.010 |
has | -0.008 |
is | -0.008 |
lic | -0.008 |
living | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +2.73e-01 |
Pos logit contributions | |
argue | +0.011 |
elbows | +0.010 |
cle | +0.010 |
ge | +0.010 |
gy | +0.010 |
Neg logit contributions | |
can | -0.006 |
has | -0.006 |
is | -0.006 |
lic | -0.006 |
br | -0.005 |
Token | Max |
Token ID | 11518 |
Feature activation | +8.57e-01 |
Pos logit contributions | |
argue | +0.006 |
elbows | +0.006 |
cle | +0.006 |
gy | +0.005 |
ge | +0.005 |
Neg logit contributions | |
can | -0.005 |
has | -0.005 |
lic | -0.005 |
is | -0.005 |
br | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +9.30e-01 |
Pos logit contributions | |
can | +0.011 |
lic | +0.011 |
has | +0.010 |
is | +0.010 |
boards | +0.010 |
Neg logit contributions | |
argue | -0.014 |
elbows | -0.014 |
gy | -0.013 |
cle | -0.013 |
weep | -0.012 |
Token | Bugs |
Token ID | 44991 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
argue | +0.016 |
elbows | +0.015 |
cle | +0.014 |
iver | +0.014 |
ge | +0.014 |
Neg logit contributions | |
can | -0.023 |
has | -0.021 |
is | -0.021 |
that | -0.021 |
lic | -0.020 |
Token | said |
Token ID | 531 |
Feature activation | -3.55e+00 |
Pos logit contributions | |
can | +0.026 |
has | +0.024 |
is | +0.023 |
lic | +0.023 |
br | +0.022 |
Neg logit contributions | |
argue | -0.041 |
elbows | -0.040 |
cle | -0.038 |
gy | -0.038 |
ge | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +5.17e-01 |
Pos logit contributions | |
can | +0.062 |
has | +0.059 |
lic | +0.058 |
is | +0.056 |
helps | +0.055 |
Neg logit contributions | |
argue | -0.078 |
elbows | -0.073 |
gy | -0.071 |
worry | -0.069 |
cle | -0.069 |
Token | " |
Token ID | 366 |
Feature activation | +2.55e-01 |
Pos logit contributions | |
argue | +0.016 |
elbows | +0.015 |
cle | +0.015 |
gy | +0.015 |
ree | +0.014 |
Neg logit contributions | |
can | -0.005 |
has | -0.004 |
is | -0.004 |
lic | -0.004 |
br | -0.004 |
Token | Twe |
Token ID | 32665 |
Feature activation | +9.47e+00 |
Pos logit contributions | |
argue | +0.006 |
elbows | +0.006 |
sing | +0.005 |
ge | +0.005 |
cle | +0.005 |
Neg logit contributions | |
can | -0.005 |
is | -0.004 |
has | -0.004 |
lic | -0.004 |
br | -0.004 |
Token | ety |
Token ID | 2963 |
Feature activation | +1.93e+00 |
Pos logit contributions | |
argue | +0.155 |
elbows | +0.149 |
mischief | +0.147 |
weep | +0.136 |
panic | +0.132 |
Neg logit contributions | |
can | -0.220 |
has | -0.206 |
lic | -0.203 |
ing | -0.203 |
is | -0.196 |
Token | , |
Token ID | 11 |
Feature activation | +7.29e-01 |
Pos logit contributions | |
argue | +0.046 |
elbows | +0.045 |
cle | +0.043 |
ge | +0.042 |
gy | +0.041 |
Neg logit contributions | |
can | -0.032 |
has | -0.029 |
is | -0.028 |
lic | -0.028 |
helps | -0.027 |
Token | I |
Token ID | 314 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
argue | +0.016 |
worry | +0.016 |
weep | +0.015 |
afar | +0.015 |
panic | +0.015 |
Neg logit contributions | |
lic | -0.012 |
boards | -0.012 |
br | -0.011 |
has | -0.011 |
lessly | -0.010 |
Token | have |
Token ID | 423 |
Feature activation | -1.44e+00 |
Pos logit contributions | |
elbows | +0.056 |
argue | +0.054 |
cle | +0.053 |
ge | +0.051 |
ieties | +0.049 |
Neg logit contributions | |
can | -0.047 |
has | -0.042 |
is | -0.041 |
helps | -0.037 |
makes | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | +8.20e-01 |
Pos logit contributions | |
can | +0.025 |
has | +0.023 |
lic | +0.023 |
is | +0.022 |
helps | +0.022 |
Neg logit contributions | |
argue | -0.032 |
elbows | -0.032 |
cle | -0.030 |
gy | -0.029 |
afar | -0.029 |
Token | and |
Token ID | 290 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
argue | +0.030 |
elbows | +0.029 |
ge | +0.027 |
weep | +0.027 |
afar | +0.026 |
Neg logit contributions | |
lic | -0.032 |
can | -0.028 |
br | -0.028 |
has | -0.028 |
boards | -0.028 |
Token | he |
Token ID | 339 |
Feature activation | -1.90e+00 |
Pos logit contributions | |
argue | +0.036 |
elbows | +0.035 |
afar | +0.033 |
gy | +0.033 |
weep | +0.033 |
Neg logit contributions | |
lic | -0.030 |
can | -0.030 |
boards | -0.029 |
br | -0.028 |
has | -0.028 |
Token | accidentally |
Token ID | 14716 |
Feature activation | +1.12e+00 |
Pos logit contributions | |
can | +0.031 |
has | +0.028 |
is | +0.027 |
lic | +0.027 |
makes | +0.026 |
Neg logit contributions | |
argue | -0.046 |
elbows | -0.046 |
cle | -0.044 |
ge | -0.042 |
gy | -0.042 |
Token | stepped |
Token ID | 10764 |
Feature activation | +1.77e-01 |
Pos logit contributions | |
argue | +0.023 |
cle | +0.023 |
elbows | +0.023 |
ge | +0.021 |
gy | +0.021 |
Neg logit contributions | |
can | -0.023 |
has | -0.021 |
is | -0.020 |
makes | -0.020 |
lic | -0.019 |
Token | on |
Token ID | 319 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
argue | +0.005 |
elbows | +0.005 |
cle | +0.004 |
gy | +0.004 |
ge | +0.004 |
Neg logit contributions | |
can | -0.003 |
has | -0.002 |
lic | -0.002 |
is | -0.002 |
helps | -0.002 |
Token | Twe |
Token ID | 24205 |
Feature activation | +9.39e+00 |
Pos logit contributions | |
argue | +0.051 |
cle | +0.050 |
iver | +0.050 |
elbows | +0.050 |
ge | +0.048 |
Neg logit contributions | |
can | -0.025 |
that | -0.023 |
is | -0.022 |
all | -0.020 |
has | -0.020 |
Token | ety |
Token ID | 2963 |
Feature activation | +3.20e+00 |
Pos logit contributions | |
argue | +0.183 |
elbows | +0.166 |
weep | +0.160 |
afar | +0.157 |
mischief | +0.154 |
Neg logit contributions | |
lic | -0.199 |
can | -0.197 |
ing | -0.186 |
br | -0.186 |
is | -0.185 |
Token | 's |
Token ID | 338 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
cle | +0.100 |
elbows | +0.099 |
argue | +0.097 |
afar | +0.094 |
mischief | +0.092 |
Neg logit contributions | |
can | -0.033 |
that | -0.028 |
is | -0.028 |
of | -0.027 |
living | -0.026 |
Token | foot |
Token ID | 2366 |
Feature activation | +7.18e-01 |
Pos logit contributions | |
argue | +0.050 |
elbows | +0.048 |
cle | +0.048 |
ge | +0.047 |
afar | +0.045 |
Neg logit contributions | |
can | -0.051 |
has | -0.047 |
is | -0.047 |
living | -0.045 |
makes | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
argue | +0.018 |
elbows | +0.018 |
cle | +0.018 |
gy | +0.017 |
afar | +0.017 |
Neg logit contributions | |
can | -0.011 |
has | -0.009 |
is | -0.009 |
lic | -0.009 |
of | -0.009 |
Token | " |
Token ID | 366 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
can | +0.010 |
has | +0.009 |
lic | +0.009 |
br | +0.009 |
is | +0.009 |
Neg logit contributions | |
argue | -0.010 |
gy | -0.009 |
elbows | -0.009 |
cle | -0.009 |
ree | -0.009 |
Token | and |
Token ID | 290 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
argue | +0.031 |
elbows | +0.030 |
gy | +0.029 |
cle | +0.029 |
ge | +0.029 |
Neg logit contributions | |
can | -0.025 |
has | -0.023 |
lic | -0.023 |
br | -0.022 |
is | -0.022 |
Token | created |
Token ID | 2727 |
Feature activation | -4.00e+00 |
Pos logit contributions | |
argue | +0.038 |
elbows | +0.037 |
gy | +0.035 |
weep | +0.034 |
cle | +0.033 |
Neg logit contributions | |
can | -0.044 |
lic | -0.042 |
has | -0.041 |
br | -0.040 |
is | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | +3.03e-01 |
Pos logit contributions | |
can | +0.076 |
has | +0.073 |
lic | +0.072 |
helps | +0.068 |
boards | +0.067 |
Neg logit contributions | |
elbows | -0.080 |
argue | -0.078 |
gy | -0.076 |
afar | -0.074 |
mischief | -0.072 |
Token | shelter |
Token ID | 11772 |
Feature activation | -9.97e-02 |
Pos logit contributions | |
argue | +0.008 |
elbows | +0.007 |
worry | +0.007 |
weep | +0.007 |
cle | +0.007 |
Neg logit contributions | |
can | -0.004 |
has | -0.004 |
lic | -0.004 |
boards | -0.004 |
is | -0.004 |
Token | for |
Token ID | 329 |
Feature activation | -4.65e-01 |
Pos logit contributions | |
can | +0.002 |
lic | +0.002 |
br | +0.002 |
boards | +0.002 |
helps | +0.002 |
Neg logit contributions | |
gy | -0.002 |
argue | -0.002 |
ge | -0.002 |
keeping | -0.002 |
weep | -0.002 |
Token | Twe |
Token ID | 24205 |
Feature activation | +9.33e+00 |
Pos logit contributions | |
that | +0.012 |
can | +0.012 |
all | +0.011 |
is | +0.011 |
of | +0.011 |
Neg logit contributions | |
argue | -0.007 |
elbows | -0.007 |
ree | -0.007 |
cle | -0.007 |
iver | -0.006 |
Token | ety |
Token ID | 2963 |
Feature activation | +3.21e+00 |
Pos logit contributions | |
argue | +0.160 |
elbows | +0.143 |
aster | +0.127 |
mischief | +0.127 |
weep | +0.125 |
Neg logit contributions | |
can | -0.221 |
ing | -0.213 |
lic | -0.207 |
of | -0.206 |
is | -0.201 |
Token | . |
Token ID | 13 |
Feature activation | -2.11e-01 |
Pos logit contributions | |
elbows | +0.091 |
argue | +0.091 |
cle | +0.089 |
afar | +0.086 |
ieties | +0.082 |
Neg logit contributions | |
can | -0.043 |
has | -0.037 |
is | -0.037 |
of | -0.036 |
that | -0.036 |
Token | Twe |
Token ID | 24205 |
Feature activation | +5.83e+00 |
Pos logit contributions | |
can | +0.007 |
has | +0.006 |
lic | +0.006 |
br | +0.006 |
is | +0.006 |
Neg logit contributions | |
argue | -0.002 |
elbows | -0.002 |
gy | -0.002 |
cle | -0.001 |
weep | -0.001 |
Token | ety |
Token ID | 2963 |
Feature activation | -4.75e-01 |
Pos logit contributions | |
argue | +0.094 |
elbows | +0.085 |
aster | +0.078 |
mischief | +0.074 |
cle | +0.071 |
Neg logit contributions | |
can | -0.149 |
lic | -0.141 |
has | -0.140 |
ing | -0.139 |
is | -0.138 |
Token | felt |
Token ID | 2936 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
can | +0.006 |
has | +0.006 |
lic | +0.006 |
is | +0.006 |
helps | +0.005 |
Neg logit contributions | |
argue | -0.013 |
elbows | -0.012 |
cle | -0.012 |
ge | -0.012 |
gy | -0.012 |
Token | rock |
Token ID | 3881 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
can | +0.096 |
lic | +0.094 |
has | +0.091 |
is | +0.088 |
br | +0.088 |
Neg logit contributions | |
argue | -0.084 |
elbows | -0.083 |
worry | -0.075 |
weep | -0.074 |
gy | -0.074 |
Token | was |
Token ID | 373 |
Feature activation | -2.82e+00 |
Pos logit contributions | |
can | +0.033 |
has | +0.029 |
is | +0.029 |
makes | +0.024 |
that | +0.024 |
Neg logit contributions | |
argue | -0.087 |
elbows | -0.087 |
cle | -0.084 |
ge | -0.081 |
afar | -0.081 |
Token | too |
Token ID | 1165 |
Feature activation | +1.64e+00 |
Pos logit contributions | |
can | +0.044 |
has | +0.040 |
is | +0.038 |
lic | +0.038 |
helps | +0.036 |
Neg logit contributions | |
argue | -0.071 |
elbows | -0.070 |
cle | -0.067 |
ge | -0.064 |
gy | -0.064 |
Token | heavy |
Token ID | 4334 |
Feature activation | +2.24e+00 |
Pos logit contributions | |
argue | +0.044 |
elbows | +0.044 |
cle | +0.041 |
ieties | +0.040 |
ge | +0.040 |
Neg logit contributions | |
can | -0.024 |
has | -0.021 |
is | -0.020 |
lic | -0.020 |
that | -0.019 |
Token | for |
Token ID | 329 |
Feature activation | -8.16e-01 |
Pos logit contributions | |
ge | +0.047 |
argue | +0.046 |
gy | +0.046 |
elbows | +0.044 |
owing | +0.043 |
Neg logit contributions | |
lic | -0.041 |
teaches | -0.035 |
br | -0.035 |
can | -0.034 |
has | -0.033 |
Token | Twe |
Token ID | 24205 |
Feature activation | +9.22e+00 |
Pos logit contributions | |
can | +0.020 |
that | +0.020 |
is | +0.019 |
all | +0.018 |
of | +0.018 |
Neg logit contributions | |
argue | -0.014 |
elbows | -0.012 |
ree | -0.012 |
cle | -0.012 |
bie | -0.012 |
Token | ety |
Token ID | 2963 |
Feature activation | +3.44e+00 |
Pos logit contributions | |
argue | +0.161 |
elbows | +0.143 |
mischief | +0.129 |
weep | +0.127 |
whine | +0.121 |
Neg logit contributions | |
can | -0.221 |
ing | -0.211 |
lic | -0.202 |
has | -0.202 |
of | -0.202 |
Token | to |
Token ID | 284 |
Feature activation | +5.18e+00 |
Pos logit contributions | |
elbows | +0.097 |
argue | +0.097 |
cle | +0.095 |
afar | +0.092 |
iver | +0.088 |
Neg logit contributions | |
can | -0.048 |
is | -0.039 |
has | -0.039 |
that | -0.039 |
of | -0.038 |
Token | move |
Token ID | 1445 |
Feature activation | +2.78e-01 |
Pos logit contributions | |
elbows | +0.119 |
cle | +0.117 |
argue | +0.110 |
afar | +0.110 |
bie | +0.108 |
Neg logit contributions | |
can | -0.099 |
of | -0.083 |
that | -0.083 |
is | -0.083 |
all | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
argue | +0.007 |
elbows | +0.007 |
cle | +0.006 |
ge | +0.006 |
gy | +0.006 |
Neg logit contributions | |
can | -0.004 |
has | -0.004 |
is | -0.004 |
lic | -0.004 |
helps | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
argue | +0.003 |
elbows | +0.003 |
cle | +0.003 |
ge | +0.003 |
gy | +0.003 |
Neg logit contributions | |
can | -0.005 |
has | -0.005 |
is | -0.005 |
lic | -0.005 |
helps | -0.005 |
Token | regretted |
Token ID | 44652 |
Feature activation | -9.49e-01 |
Pos logit contributions | |
can | +0.032 |
lic | +0.029 |
has | +0.029 |
br | +0.028 |
is | +0.028 |
Neg logit contributions | |
argue | -0.038 |
elbows | -0.037 |
cle | -0.035 |
gy | -0.035 |
weep | -0.034 |
Token | getting |
Token ID | 1972 |
Feature activation | -2.08e-01 |
Pos logit contributions | |
can | +0.018 |
has | +0.016 |
that | +0.016 |
is | +0.016 |
living | +0.016 |
Neg logit contributions | |
argue | -0.020 |
elbows | -0.020 |
cle | -0.019 |
ree | -0.018 |
iver | -0.018 |
Token | close |
Token ID | 1969 |
Feature activation | +2.09e+00 |
Pos logit contributions | |
can | +0.004 |
has | +0.004 |
lic | +0.004 |
is | +0.004 |
br | +0.004 |
Neg logit contributions | |
argue | -0.004 |
elbows | -0.004 |
cle | -0.004 |
afar | -0.004 |
ge | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +2.91e+00 |
Pos logit contributions | |
argue | +0.043 |
elbows | +0.042 |
ge | +0.042 |
gy | +0.041 |
cle | +0.040 |
Neg logit contributions | |
can | -0.039 |
lic | -0.038 |
br | -0.037 |
has | -0.036 |
is | -0.035 |
Token | the |
Token ID | 262 |
Feature activation | -1.88e+00 |
Pos logit contributions | |
argue | +0.069 |
elbows | +0.068 |
cle | +0.065 |
ge | +0.063 |
gy | +0.063 |
Neg logit contributions | |
can | -0.049 |
has | -0.045 |
is | -0.044 |
helps | -0.041 |
that | -0.041 |
Token | Gor |
Token ID | 19097 |
Feature activation | +9.13e+00 |
Pos logit contributions | |
lic | +0.039 |
can | +0.038 |
br | +0.037 |
boards | +0.036 |
has | +0.034 |
Neg logit contributions | |
argue | -0.035 |
afar | -0.034 |
worry | -0.033 |
cle | -0.032 |
weep | -0.032 |
Token | illa |
Token ID | 5049 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
elbows | +0.139 |
argue | +0.134 |
weep | +0.121 |
mischief | +0.121 |
ree | +0.116 |
Neg logit contributions | |
can | -0.225 |
is | -0.220 |
has | -0.216 |
living | -0.209 |
that | -0.206 |
Token | and |
Token ID | 290 |
Feature activation | +2.97e+00 |
Pos logit contributions | |
argue | +0.084 |
elbows | +0.080 |
ge | +0.078 |
cle | +0.078 |
gy | +0.077 |
Neg logit contributions | |
can | -0.063 |
lic | -0.060 |
has | -0.058 |
br | -0.056 |
is | -0.055 |
Token | not |
Token ID | 407 |
Feature activation | +1.56e+00 |
Pos logit contributions | |
argue | +0.063 |
elbows | +0.060 |
weep | +0.057 |
worry | +0.056 |
cle | +0.056 |
Neg logit contributions | |
lic | -0.055 |
can | -0.055 |
br | -0.053 |
has | -0.051 |
boards | -0.051 |
Token | listening |
Token ID | 8680 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
argue | +0.026 |
elbows | +0.025 |
cle | +0.023 |
ge | +0.023 |
gy | +0.023 |
Neg logit contributions | |
can | -0.037 |
has | -0.035 |
lic | -0.034 |
is | -0.034 |
br | -0.033 |
Token | to |
Token ID | 284 |
Feature activation | +2.79e+00 |
Pos logit contributions | |
can | +0.001 |
has | +0.001 |
lic | +0.001 |
br | +0.001 |
helps | +0.001 |
Neg logit contributions | |
argue | -0.001 |
elbows | -0.001 |
ge | -0.001 |
worry | -0.001 |
cle | -0.001 |
Token | " |
Token ID | 366 |
Feature activation | +4.28e-01 |
Pos logit contributions | |
argue | +0.047 |
elbows | +0.045 |
cle | +0.044 |
gy | +0.043 |
ge | +0.043 |
Neg logit contributions | |
can | -0.016 |
lic | -0.015 |
has | -0.014 |
br | -0.014 |
is | -0.014 |
Token | Don |
Token ID | 3987 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
argue | +0.010 |
elbows | +0.010 |
sing | +0.009 |
gy | +0.009 |
cle | +0.009 |
Neg logit contributions | |
can | -0.008 |
has | -0.007 |
is | -0.007 |
lic | -0.007 |
helps | -0.007 |
Token | 't |
Token ID | 470 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
argue | +0.002 |
gy | +0.002 |
cle | +0.002 |
worry | +0.001 |
ree | +0.001 |
Neg logit contributions | |
can | -0.002 |
living | -0.002 |
boards | -0.002 |
der | -0.002 |
has | -0.002 |
Token | worry |
Token ID | 5490 |
Feature activation | +4.01e-01 |
Pos logit contributions | |
elbows | +0.030 |
cle | +0.029 |
afar | +0.026 |
packs | +0.026 |
argue | +0.025 |
Neg logit contributions | |
can | -0.057 |
is | -0.051 |
that | -0.051 |
of | -0.050 |
has | -0.050 |
Token | little |
Token ID | 1310 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
argue | +0.008 |
gy | +0.008 |
elbows | +0.008 |
cle | +0.008 |
worry | +0.008 |
Neg logit contributions | |
can | -0.007 |
lic | -0.007 |
has | -0.007 |
teaches | -0.007 |
br | -0.007 |
Token | Twe |
Token ID | 24205 |
Feature activation | +9.13e+00 |
Pos logit contributions | |
argue | +0.051 |
elbows | +0.050 |
cle | +0.047 |
ge | +0.045 |
gy | +0.045 |
Neg logit contributions | |
can | -0.049 |
has | -0.045 |
is | -0.044 |
lic | -0.044 |
helps | -0.042 |
Token | ety |
Token ID | 2963 |
Feature activation | +4.05e+00 |
Pos logit contributions | |
argue | +0.132 |
elbows | +0.124 |
mischief | +0.110 |
weep | +0.104 |
afar | +0.099 |
Neg logit contributions | |
can | -0.247 |
has | -0.231 |
ing | -0.231 |
lic | -0.229 |
is | -0.225 |
Token | , |
Token ID | 11 |
Feature activation | +1.48e+00 |
Pos logit contributions | |
argue | +0.096 |
elbows | +0.094 |
cle | +0.090 |
gy | +0.087 |
ge | +0.087 |
Neg logit contributions | |
can | -0.066 |
has | -0.061 |
lic | -0.060 |
is | -0.058 |
br | -0.056 |
Token | I |
Token ID | 314 |
Feature activation | +2.68e+00 |
Pos logit contributions | |
worry | +0.032 |
argue | +0.030 |
weep | +0.029 |
cle | +0.028 |
ge | +0.028 |
Neg logit contributions | |
lic | -0.027 |
boards | -0.025 |
br | -0.024 |
has | -0.023 |
teaches | -0.023 |
Token | can |
Token ID | 460 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
argue | +0.076 |
gy | +0.071 |
weep | +0.071 |
elbows | +0.070 |
worry | +0.070 |
Neg logit contributions | |
lic | -0.027 |
boards | -0.027 |
can | -0.026 |
has | -0.026 |
br | -0.026 |
Token | help |
Token ID | 1037 |
Feature activation | +6.02e-01 |
Pos logit contributions | |
argue | +0.048 |
elbows | +0.044 |
weep | +0.043 |
gy | +0.043 |
iver | +0.043 |
Neg logit contributions | |
lic | -0.050 |
can | -0.050 |
has | -0.049 |
boards | -0.048 |
br | -0.046 |
Token | I |
Token ID | 314 |
Feature activation | +1.81e+00 |
Pos logit contributions | |
argue | +0.005 |
worry | +0.005 |
afar | +0.004 |
elbows | +0.004 |
cle | +0.004 |
Neg logit contributions | |
lic | -0.006 |
boards | -0.005 |
br | -0.005 |
lessly | -0.005 |
ative | -0.004 |
Token | don |
Token ID | 836 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
argue | +0.038 |
elbows | +0.036 |
cle | +0.035 |
gy | +0.034 |
ge | +0.033 |
Neg logit contributions | |
can | -0.034 |
lic | -0.032 |
has | -0.032 |
is | -0.031 |
br | -0.030 |
Token | 't |
Token ID | 470 |
Feature activation | +3.34e+00 |
Pos logit contributions | |
argue | +0.032 |
elbows | +0.029 |
cle | +0.028 |
ge | +0.027 |
iver | +0.027 |
Neg logit contributions | |
can | -0.035 |
lic | -0.033 |
has | -0.033 |
living | -0.031 |
boards | -0.031 |
Token | like |
Token ID | 588 |
Feature activation | +1.72e+00 |
Pos logit contributions | |
argue | +0.065 |
elbows | +0.063 |
cle | +0.059 |
gy | +0.057 |
ge | +0.057 |
Neg logit contributions | |
can | -0.070 |
has | -0.065 |
lic | -0.064 |
is | -0.064 |
helps | -0.061 |
Token | rac |
Token ID | 3444 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
argue | +0.042 |
elbows | +0.041 |
cle | +0.039 |
gy | +0.038 |
ge | +0.038 |
Neg logit contributions | |
can | -0.028 |
has | -0.025 |
lic | -0.025 |
is | -0.025 |
helps | -0.023 |
Token | co |
Token ID | 1073 |
Feature activation | +9.07e+00 |
Pos logit contributions | |
argue | +0.075 |
elbows | +0.073 |
cle | +0.067 |
ge | +0.067 |
iver | +0.066 |
Neg logit contributions | |
can | -0.070 |
has | -0.066 |
lic | -0.063 |
is | -0.062 |
makes | -0.060 |
Token | ons |
Token ID | 684 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
elbows | +0.196 |
weep | +0.171 |
gy | +0.170 |
worry | +0.168 |
afar | +0.166 |
Neg logit contributions | |
is | -0.182 |
can | -0.177 |
has | -0.170 |
that | -0.170 |
makes | -0.165 |
Token | . |
Token ID | 13 |
Feature activation | -1.51e-02 |
Pos logit contributions | |
argue | +0.027 |
elbows | +0.026 |
ge | +0.024 |
weep | +0.024 |
worry | +0.023 |
Neg logit contributions | |
lic | -0.026 |
can | -0.024 |
has | -0.023 |
boards | -0.022 |
helps | -0.021 |
Token | They |
Token ID | 1119 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
can | +0.000 |
lic | +0.000 |
living | +0.000 |
boards | +0.000 |
has | +0.000 |
Neg logit contributions | |
argue | -0.000 |
elbows | -0.000 |
cle | -0.000 |
ree | -0.000 |
gy | -0.000 |
Token | are |
Token ID | 389 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
lic | +0.026 |
boards | +0.021 |
br | +0.021 |
der | +0.019 |
lessly | +0.019 |
Neg logit contributions | |
argue | -0.049 |
worry | -0.044 |
weep | -0.044 |
elbows | -0.042 |
panic | -0.042 |
Token | mean |
Token ID | 1612 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
boards | +0.038 |
lic | +0.036 |
can | +0.034 |
br | +0.033 |
ing | +0.031 |
Neg logit contributions | |
argue | -0.044 |
elbows | -0.041 |
worry | -0.039 |
afar | -0.039 |
weep | -0.039 |
Token | want |
Token ID | 765 |
Feature activation | -8.54e-01 |
Pos logit contributions | |
elbows | +0.094 |
cle | +0.087 |
gy | +0.082 |
ge | +0.082 |
argue | +0.082 |
Neg logit contributions | |
can | -0.088 |
has | -0.078 |
is | -0.075 |
of | -0.071 |
makes | -0.069 |
Token | to |
Token ID | 284 |
Feature activation | +5.48e+00 |
Pos logit contributions | |
lic | +0.015 |
can | +0.015 |
has | +0.015 |
br | +0.014 |
lessly | +0.014 |
Neg logit contributions | |
argue | -0.018 |
elbows | -0.017 |
cle | -0.016 |
weep | -0.016 |
afar | -0.016 |
Token | share |
Token ID | 2648 |
Feature activation | +1.09e-01 |
Pos logit contributions | |
argue | +0.099 |
elbows | +0.098 |
cle | +0.092 |
ge | +0.089 |
gy | +0.088 |
Neg logit contributions | |
can | -0.122 |
has | -0.113 |
is | -0.111 |
lic | -0.110 |
helps | -0.106 |
Token | my |
Token ID | 616 |
Feature activation | +5.02e+00 |
Pos logit contributions | |
argue | +0.002 |
elbows | +0.002 |
cle | +0.002 |
gy | +0.002 |
afar | +0.002 |
Neg logit contributions | |
can | -0.002 |
lic | -0.002 |
has | -0.002 |
is | -0.002 |
br | -0.002 |
Token | ice |
Token ID | 4771 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
ree | +0.139 |
argue | +0.138 |
elbows | +0.138 |
cle | +0.130 |
ge | +0.130 |
Neg logit contributions | |
can | -0.072 |
is | -0.068 |
has | -0.063 |
box | -0.060 |
living | -0.059 |
Token | - |
Token ID | 12 |
Feature activation | +9.04e+00 |
Pos logit contributions | |
argue | +0.112 |
elbows | +0.111 |
afar | +0.101 |
weep | +0.101 |
cle | +0.100 |
Neg logit contributions | |
can | -0.081 |
is | -0.075 |
has | -0.073 |
lic | -0.070 |
makes | -0.068 |
Token | cream |
Token ID | 36277 |
Feature activation | +8.50e-01 |
Pos logit contributions | |
argue | +0.203 |
elbows | +0.202 |
weep | +0.181 |
cle | +0.179 |
worry | +0.178 |
Neg logit contributions | |
can | -0.164 |
lic | -0.151 |
is | -0.151 |
has | -0.150 |
br | -0.145 |
Token | with |
Token ID | 351 |
Feature activation | +7.43e-01 |
Pos logit contributions | |
argue | +0.019 |
elbows | +0.018 |
cle | +0.018 |
gy | +0.017 |
ge | +0.017 |
Neg logit contributions | |
can | -0.015 |
has | -0.014 |
lic | -0.014 |
br | -0.013 |
is | -0.013 |
Token | me |
Token ID | 502 |
Feature activation | +5.11e+00 |
Pos logit contributions | |
argue | +0.017 |
elbows | +0.017 |
cle | +0.017 |
afar | +0.016 |
ree | +0.016 |
Neg logit contributions | |
can | -0.012 |
lic | -0.011 |
has | -0.011 |
br | -0.010 |
boards | -0.010 |
Token | ?" |
Token ID | 1701 |
Feature activation | +1.26e+00 |
Pos logit contributions | |
argue | +0.111 |
elbows | +0.108 |
cle | +0.102 |
ge | +0.099 |
gy | +0.099 |
Neg logit contributions | |
can | -0.096 |
has | -0.089 |
is | -0.086 |
lic | -0.085 |
helps | -0.082 |
Token |
|
Token ID | 198 |
Feature activation | +2.52e-01 |
Pos logit contributions | |
argue | +0.028 |
elbows | +0.027 |
cle | +0.026 |
ree | +0.025 |
ge | +0.025 |
Neg logit contributions | |
can | -0.022 |
lic | -0.020 |
has | -0.020 |
is | -0.019 |
br | -0.019 |
Token | started |
Token ID | 2067 |
Feature activation | -7.86e-01 |
Pos logit contributions | |
lic | +0.070 |
can | +0.070 |
has | +0.068 |
br | +0.066 |
helps | +0.065 |
Neg logit contributions | |
argue | -0.045 |
elbows | -0.041 |
cle | -0.039 |
weep | -0.039 |
reason | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | +3.63e+00 |
Pos logit contributions | |
can | +0.011 |
has | +0.010 |
is | +0.010 |
of | +0.010 |
makes | +0.009 |
Neg logit contributions | |
argue | -0.021 |
elbows | -0.020 |
cle | -0.020 |
afar | -0.019 |
iver | -0.019 |
Token | happen |
Token ID | 1645 |
Feature activation | -7.31e-01 |
Pos logit contributions | |
argue | +0.072 |
worry | +0.065 |
weep | +0.065 |
elbows | +0.064 |
aster | +0.062 |
Neg logit contributions | |
lic | -0.074 |
can | -0.072 |
boards | -0.070 |
has | -0.070 |
br | -0.066 |
Token | . |
Token ID | 13 |
Feature activation | -6.86e-01 |
Pos logit contributions | |
can | +0.014 |
lic | +0.013 |
has | +0.013 |
br | +0.013 |
helps | +0.012 |
Neg logit contributions | |
argue | -0.015 |
elbows | -0.014 |
ge | -0.014 |
cle | -0.013 |
gy | -0.013 |
Token | The |
Token ID | 383 |
Feature activation | -4.36e+00 |
Pos logit contributions | |
can | +0.010 |
has | +0.009 |
lic | +0.009 |
is | +0.009 |
br | +0.009 |
Neg logit contributions | |
argue | -0.017 |
elbows | -0.016 |
cle | -0.016 |
gy | -0.015 |
ree | -0.015 |
Token | print |
Token ID | 3601 |
Feature activation | -7.97e+00 |
Pos logit contributions | |
can | +0.076 |
lic | +0.074 |
has | +0.071 |
br | +0.069 |
is | +0.068 |
Neg logit contributions | |
argue | -0.095 |
elbows | -0.091 |
cle | -0.086 |
weep | -0.085 |
afar | -0.084 |
Token | started |
Token ID | 2067 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
lic | +0.122 |
can | +0.107 |
arl | +0.107 |
lessly | +0.105 |
boards | +0.102 |
Neg logit contributions | |
argue | -0.173 |
weep | -0.165 |
worry | -0.157 |
elbows | -0.157 |
reason | -0.156 |
Token | to |
Token ID | 284 |
Feature activation | +2.99e+00 |
Pos logit contributions | |
can | +0.018 |
has | +0.016 |
is | +0.016 |
lic | +0.016 |
helps | +0.015 |
Neg logit contributions | |
argue | -0.027 |
elbows | -0.027 |
cle | -0.026 |
ge | -0.025 |
gy | -0.025 |
Token | shine |
Token ID | 18340 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
argue | +0.066 |
elbows | +0.063 |
cle | +0.059 |
weep | +0.058 |
gy | +0.058 |
Neg logit contributions | |
can | -0.055 |
has | -0.051 |
lic | -0.051 |
is | -0.049 |
boards | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
lic | +0.020 |
teaches | +0.019 |
can | +0.019 |
helps | +0.019 |
boards | +0.019 |
Neg logit contributions | |
gy | -0.019 |
argue | -0.018 |
worry | -0.018 |
elbows | -0.018 |
ge | -0.017 |
Token | spark |
Token ID | 9009 |
Feature activation | -1.13e+00 |
Pos logit contributions | |
argue | +0.044 |
elbows | +0.042 |
worry | +0.041 |
weep | +0.040 |
afar | +0.039 |
Neg logit contributions | |
lic | -0.040 |
boards | -0.038 |
ative | -0.036 |
br | -0.035 |
oke | -0.035 |
Token | ! |
Token ID | 0 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
lic | +0.021 |
can | +0.021 |
has | +0.020 |
br | +0.019 |
boards | +0.019 |
Neg logit contributions | |
argue | -0.026 |
elbows | -0.025 |
gy | -0.024 |
ge | -0.024 |
worry | -0.024 |
Token | |
Token ID | 220 |
Feature activation | -2.51e-02 |
Pos logit contributions | |
can | +0.017 |
lic | +0.017 |
br | +0.017 |
has | +0.016 |
helps | +0.016 |
Neg logit contributions | |
elbows | -0.021 |
argue | -0.021 |
cle | -0.021 |
gy | -0.021 |
ree | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -8.48e-01 |
Pos logit contributions | |
can | +0.000 |
has | +0.000 |
lic | +0.000 |
is | +0.000 |
br | +0.000 |
Neg logit contributions | |
argue | -0.001 |
elbows | -0.001 |
cle | -0.001 |
gy | -0.001 |
ge | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -8.52e-01 |
Pos logit contributions | |
can | +0.015 |
has | +0.014 |
lic | +0.013 |
is | +0.013 |
helps | +0.013 |
Neg logit contributions | |
argue | -0.019 |
elbows | -0.018 |
cle | -0.018 |
ge | -0.017 |
gy | -0.017 |
Token | The |
Token ID | 464 |
Feature activation | -4.47e+00 |
Pos logit contributions | |
can | +0.017 |
has | +0.016 |
is | +0.016 |
lic | +0.015 |
helps | +0.015 |
Neg logit contributions | |
argue | -0.017 |
elbows | -0.016 |
cle | -0.016 |
ge | -0.015 |
ree | -0.015 |
Token | print |
Token ID | 3601 |
Feature activation | -7.97e+00 |
Pos logit contributions | |
can | +0.070 |
has | +0.064 |
is | +0.061 |
lic | +0.057 |
living | +0.056 |
Neg logit contributions | |
argue | -0.114 |
elbows | -0.113 |
cle | -0.109 |
ge | -0.107 |
gy | -0.105 |
Token | was |
Token ID | 373 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
lic | +0.110 |
can | +0.105 |
has | +0.095 |
br | +0.094 |
boards | +0.093 |
Neg logit contributions | |
argue | -0.197 |
elbows | -0.184 |
weep | -0.183 |
cle | -0.180 |
gy | -0.179 |
Token | the |
Token ID | 262 |
Feature activation | -3.31e+00 |
Pos logit contributions | |
can | +0.046 |
has | +0.042 |
lic | +0.041 |
boards | +0.041 |
is | +0.040 |
Neg logit contributions | |
argue | -0.069 |
elbows | -0.067 |
cle | -0.064 |
gy | -0.063 |
afar | -0.063 |
Token | bug |
Token ID | 5434 |
Feature activation | -1.94e+00 |
Pos logit contributions | |
can | +0.048 |
has | +0.042 |
is | +0.040 |
living | +0.037 |
makes | +0.036 |
Neg logit contributions | |
elbows | -0.090 |
argue | -0.090 |
cle | -0.086 |
ge | -0.085 |
ree | -0.084 |
Token | 's |
Token ID | 338 |
Feature activation | -7.54e-01 |
Pos logit contributions | |
can | +0.031 |
lic | +0.029 |
has | +0.028 |
boards | +0.027 |
br | +0.027 |
Neg logit contributions | |
argue | -0.045 |
elbows | -0.043 |
gy | -0.042 |
cle | -0.042 |
weep | -0.041 |
Token | new |
Token ID | 649 |
Feature activation | -8.78e-01 |
Pos logit contributions | |
can | +0.014 |
has | +0.013 |
is | +0.013 |
living | +0.012 |
that | +0.012 |
Neg logit contributions | |
argue | -0.017 |
elbows | -0.016 |
ge | -0.015 |
cle | -0.015 |
ree | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
argue | +0.032 |
elbows | +0.032 |
cle | +0.030 |
gy | +0.030 |
ge | +0.029 |
Neg logit contributions | |
can | -0.021 |
has | -0.019 |
is | -0.018 |
lic | -0.018 |
helps | -0.017 |
Token | saw |
Token ID | 2497 |
Feature activation | -3.47e+00 |
Pos logit contributions | |
argue | +0.039 |
elbows | +0.038 |
cle | +0.036 |
gy | +0.035 |
ge | +0.035 |
Neg logit contributions | |
can | -0.034 |
has | -0.031 |
lic | -0.031 |
is | -0.030 |
br | -0.030 |
Token | that |
Token ID | 326 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
lic | +0.061 |
br | +0.059 |
has | +0.056 |
can | +0.054 |
boards | +0.054 |
Neg logit contributions | |
afar | -0.077 |
argue | -0.075 |
elbows | -0.074 |
worry | -0.070 |
hr | -0.067 |
Token | the |
Token ID | 262 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
can | +0.027 |
lic | +0.027 |
has | +0.025 |
br | +0.025 |
boards | +0.024 |
Neg logit contributions | |
argue | -0.035 |
elbows | -0.033 |
cle | -0.032 |
afar | -0.031 |
ge | -0.031 |
Token | purple |
Token ID | 14032 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
lic | +0.061 |
can | +0.061 |
has | +0.056 |
br | +0.056 |
boards | +0.055 |
Neg logit contributions | |
argue | -0.074 |
elbows | -0.071 |
cle | -0.068 |
afar | -0.067 |
weep | -0.065 |
Token | print |
Token ID | 3601 |
Feature activation | -7.78e+00 |
Pos logit contributions | |
can | +0.035 |
lic | +0.034 |
has | +0.032 |
helps | +0.032 |
br | +0.031 |
Neg logit contributions | |
argue | -0.042 |
elbows | -0.040 |
cle | -0.039 |
gy | -0.039 |
afar | -0.038 |
Token | had |
Token ID | 550 |
Feature activation | -3.02e+00 |
Pos logit contributions | |
lic | +0.121 |
lessly | +0.096 |
br | +0.095 |
arl | +0.095 |
der | +0.095 |
Neg logit contributions | |
argue | -0.174 |
elbows | -0.161 |
weep | -0.160 |
reason | -0.158 |
worry | -0.157 |
Token | been |
Token ID | 587 |
Feature activation | -2.33e+00 |
Pos logit contributions | |
can | +0.056 |
lic | +0.053 |
has | +0.053 |
helps | +0.051 |
is | +0.050 |
Neg logit contributions | |
argue | -0.061 |
elbows | -0.057 |
ge | -0.054 |
gy | -0.054 |
worry | -0.054 |
Token | ruined |
Token ID | 20484 |
Feature activation | -2.78e+00 |
Pos logit contributions | |
can | +0.042 |
has | +0.039 |
lic | +0.038 |
is | +0.038 |
helps | +0.037 |
Neg logit contributions | |
argue | -0.051 |
elbows | -0.050 |
cle | -0.047 |
ge | -0.047 |
gy | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | -5.82e-01 |
Pos logit contributions | |
lic | +0.052 |
can | +0.050 |
has | +0.048 |
br | +0.048 |
helps | +0.047 |
Neg logit contributions | |
argue | -0.057 |
elbows | -0.054 |
ge | -0.053 |
gy | -0.053 |
cle | -0.051 |
Token | They |
Token ID | 1119 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
br | +0.011 |
can | +0.011 |
lic | +0.011 |
has | +0.010 |
helps | +0.010 |
Neg logit contributions | |
argue | -0.011 |
afar | -0.010 |
gy | -0.010 |
mischief | -0.010 |
elbows | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -9.72e-01 |
Pos logit contributions | |
argue | +0.002 |
elbows | +0.002 |
cle | +0.002 |
gy | +0.002 |
ge | +0.002 |
Neg logit contributions | |
can | -0.002 |
has | -0.002 |
lic | -0.001 |
is | -0.001 |
br | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
can | +0.019 |
boards | +0.018 |
has | +0.018 |
helps | +0.017 |
lic | +0.017 |
Neg logit contributions | |
argue | -0.017 |
elbows | -0.017 |
ree | -0.016 |
cle | -0.016 |
weep | -0.016 |
Token | Suddenly |
Token ID | 38582 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
can | +0.024 |
boards | +0.024 |
lic | +0.023 |
has | +0.023 |
helps | +0.022 |
Neg logit contributions | |
argue | -0.016 |
elbows | -0.015 |
ree | -0.015 |
iver | -0.014 |
cle | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +4.98e-02 |
Pos logit contributions | |
lic | +0.006 |
can | +0.006 |
boards | +0.006 |
has | +0.005 |
living | +0.005 |
Neg logit contributions | |
argue | -0.006 |
elbows | -0.006 |
gy | -0.006 |
weep | -0.005 |
worry | -0.005 |
Token | the |
Token ID | 262 |
Feature activation | -4.02e+00 |
Pos logit contributions | |
argue | +0.001 |
elbows | +0.001 |
weep | +0.001 |
afar | +0.001 |
worry | +0.001 |
Neg logit contributions | |
can | -0.001 |
lic | -0.001 |
boards | -0.001 |
has | -0.001 |
is | -0.001 |
Token | print |
Token ID | 3601 |
Feature activation | -7.71e+00 |
Pos logit contributions | |
can | +0.069 |
lic | +0.067 |
has | +0.062 |
br | +0.062 |
boards | +0.061 |
Neg logit contributions | |
argue | -0.090 |
elbows | -0.087 |
cle | -0.083 |
afar | -0.081 |
weep | -0.081 |
Token | began |
Token ID | 2540 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
can | +0.121 |
lic | +0.120 |
helps | +0.114 |
has | +0.113 |
boards | +0.109 |
Neg logit contributions | |
argue | -0.163 |
weep | -0.151 |
elbows | -0.151 |
worry | -0.148 |
gy | -0.147 |
Token | to |
Token ID | 284 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
can | +0.018 |
has | +0.016 |
is | +0.015 |
lic | +0.015 |
makes | +0.014 |
Neg logit contributions | |
argue | -0.030 |
elbows | -0.030 |
cle | -0.029 |
afar | -0.028 |
ge | -0.027 |
Token | move |
Token ID | 1445 |
Feature activation | -5.38e-01 |
Pos logit contributions | |
argue | +0.078 |
elbows | +0.076 |
cle | +0.072 |
gy | +0.070 |
ge | +0.070 |
Neg logit contributions | |
can | -0.068 |
has | -0.063 |
lic | -0.061 |
is | -0.061 |
br | -0.058 |
Token | around |
Token ID | 1088 |
Feature activation | +1.60e+00 |
Pos logit contributions | |
can | +0.010 |
lic | +0.010 |
has | +0.009 |
br | +0.009 |
helps | +0.009 |
Neg logit contributions | |
argue | -0.011 |
elbows | -0.011 |
gy | -0.010 |
ge | -0.010 |
afar | -0.010 |
Token | the |
Token ID | 262 |
Feature activation | -1.06e+00 |
Pos logit contributions | |
argue | +0.035 |
elbows | +0.034 |
gy | +0.032 |
afar | +0.032 |
cle | +0.032 |
Neg logit contributions | |
can | -0.028 |
lic | -0.027 |
has | -0.026 |
br | -0.025 |
boards | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -2.30e-02 |
Pos logit contributions | |
argue | +0.119 |
elbows | +0.119 |
cle | +0.113 |
afar | +0.108 |
gy | +0.108 |
Neg logit contributions | |
can | -0.076 |
has | -0.069 |
is | -0.067 |
lic | -0.065 |
helps | -0.063 |
Token | |
Token ID | 220 |
Feature activation | -1.98e-01 |
Pos logit contributions | |
can | +0.000 |
has | +0.000 |
is | +0.000 |
lic | +0.000 |
of | +0.000 |
Neg logit contributions | |
argue | -0.001 |
elbows | -0.001 |
cle | -0.001 |
ge | -0.001 |
weep | -0.000 |
Token |
|
Token ID | 198 |
Feature activation | -4.42e-01 |
Pos logit contributions | |
can | +0.003 |
has | +0.003 |
lic | +0.003 |
is | +0.003 |
br | +0.003 |
Neg logit contributions | |
argue | -0.004 |
elbows | -0.004 |
cle | -0.004 |
gy | -0.004 |
ge | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -5.08e-01 |
Pos logit contributions | |
can | +0.007 |
lic | +0.006 |
is | +0.006 |
has | +0.006 |
of | +0.006 |
Neg logit contributions | |
argue | -0.011 |
elbows | -0.011 |
weep | -0.010 |
gy | -0.010 |
cle | -0.010 |
Token | The |
Token ID | 464 |
Feature activation | -4.73e+00 |
Pos logit contributions | |
can | +0.012 |
lic | +0.011 |
is | +0.011 |
has | +0.011 |
of | +0.011 |
Neg logit contributions | |
elbows | -0.009 |
argue | -0.009 |
weep | -0.008 |
gy | -0.008 |
ge | -0.008 |
Token | card |
Token ID | 2657 |
Feature activation | -7.66e+00 |
Pos logit contributions | |
can | +0.081 |
lic | +0.075 |
has | +0.075 |
is | +0.073 |
br | +0.071 |
Neg logit contributions | |
argue | -0.107 |
elbows | -0.104 |
cle | -0.100 |
afar | -0.097 |
gy | -0.096 |
Token | was |
Token ID | 373 |
Feature activation | -3.25e+00 |
Pos logit contributions | |
lic | +0.121 |
can | +0.118 |
br | +0.108 |
boards | +0.108 |
helps | +0.105 |
Neg logit contributions | |
argue | -0.167 |
weep | -0.154 |
elbows | -0.153 |
gy | -0.152 |
worry | -0.152 |
Token | incredible |
Token ID | 8082 |
Feature activation | -2.69e-01 |
Pos logit contributions | |
can | +0.052 |
boards | +0.050 |
has | +0.048 |
helps | +0.048 |
lic | +0.047 |
Neg logit contributions | |
argue | -0.074 |
elbows | -0.070 |
worry | -0.069 |
cle | -0.069 |
gy | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e+00 |
Pos logit contributions | |
lic | +0.006 |
can | +0.005 |
br | +0.005 |
has | +0.005 |
teaches | +0.005 |
Neg logit contributions | |
argue | -0.004 |
gy | -0.004 |
ge | -0.004 |
afar | -0.004 |
elbows | -0.004 |
Token | It |
Token ID | 632 |
Feature activation | -4.30e+00 |
Pos logit contributions | |
can | +0.018 |
br | +0.017 |
has | +0.017 |
lic | +0.016 |
living | +0.016 |
Neg logit contributions | |
argue | -0.022 |
cle | -0.021 |
afar | -0.021 |
ree | -0.021 |
elbows | -0.021 |
Token | had |
Token ID | 550 |
Feature activation | -3.04e+00 |
Pos logit contributions | |
boards | +0.070 |
lic | +0.066 |
arl | +0.063 |
br | +0.062 |
der | +0.061 |
Neg logit contributions | |
gy | -0.091 |
argue | -0.090 |
cker | -0.086 |
weep | -0.084 |
worry | -0.083 |
Token | proudly |
Token ID | 23017 |
Feature activation | +2.14e-01 |
Pos logit contributions | |
lic | +0.035 |
br | +0.034 |
can | +0.033 |
boards | +0.033 |
lessly | +0.033 |
Neg logit contributions | |
argue | -0.047 |
weep | -0.042 |
elbows | -0.042 |
worry | -0.039 |
gy | -0.039 |
Token | showed |
Token ID | 3751 |
Feature activation | -4.99e+00 |
Pos logit contributions | |
argue | +0.004 |
elbows | +0.004 |
weep | +0.004 |
ge | +0.004 |
gy | +0.004 |
Neg logit contributions | |
can | -0.004 |
lic | -0.004 |
lessly | -0.004 |
br | -0.004 |
has | -0.004 |
Token | her |
Token ID | 607 |
Feature activation | -4.90e-01 |
Pos logit contributions | |
can | +0.117 |
has | +0.113 |
lic | +0.111 |
br | +0.106 |
is | +0.105 |
Neg logit contributions | |
argue | -0.082 |
elbows | -0.078 |
afar | -0.072 |
ree | -0.072 |
weep | -0.070 |
Token | teacher |
Token ID | 4701 |
Feature activation | +1.33e+00 |
Pos logit contributions | |
can | +0.009 |
has | +0.009 |
is | +0.008 |
makes | +0.008 |
helps | +0.008 |
Neg logit contributions | |
elbows | -0.011 |
argue | -0.011 |
cle | -0.010 |
ge | -0.010 |
gy | -0.010 |
Token | her |
Token ID | 607 |
Feature activation | -9.04e-02 |
Pos logit contributions | |
argue | +0.029 |
elbows | +0.028 |
cle | +0.027 |
gy | +0.026 |
ge | +0.026 |
Neg logit contributions | |
can | -0.024 |
has | -0.022 |
lic | -0.022 |
is | -0.021 |
br | -0.021 |
Token | print |
Token ID | 3601 |
Feature activation | -7.65e+00 |
Pos logit contributions | |
can | +0.002 |
has | +0.001 |
is | +0.001 |
lic | +0.001 |
helps | +0.001 |
Neg logit contributions | |
argue | -0.002 |
elbows | -0.002 |
cle | -0.002 |
ge | -0.002 |
gy | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -1.45e+00 |
Pos logit contributions | |
lic | +0.135 |
has | +0.125 |
can | +0.122 |
ye | +0.118 |
helps | +0.116 |
Neg logit contributions | |
argue | -0.135 |
elbows | -0.132 |
reason | -0.128 |
aster | -0.125 |
ree | -0.123 |
Token | The |
Token ID | 383 |
Feature activation | -5.12e+00 |
Pos logit contributions | |
can | +0.023 |
has | +0.021 |
br | +0.020 |
is | +0.020 |
lic | +0.020 |
Neg logit contributions | |
argue | -0.033 |
ree | -0.032 |
elbows | -0.031 |
cle | -0.030 |
gy | -0.030 |
Token | teacher |
Token ID | 4701 |
Feature activation | -8.95e-01 |
Pos logit contributions | |
can | +0.101 |
lic | +0.098 |
has | +0.094 |
br | +0.092 |
boards | +0.091 |
Neg logit contributions | |
argue | -0.101 |
elbows | -0.096 |
cle | -0.090 |
weep | -0.089 |
worry | -0.087 |
Token | smiled |
Token ID | 13541 |
Feature activation | -2.64e+00 |
Pos logit contributions | |
lic | +0.016 |
can | +0.016 |
br | +0.016 |
boards | +0.016 |
lessly | +0.016 |
Neg logit contributions | |
argue | -0.017 |
weep | -0.015 |
worry | -0.014 |
hr | -0.014 |
cle | -0.014 |
Token | . |
Token ID | 13 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
can | +0.055 |
lic | +0.054 |
br | +0.053 |
boards | +0.053 |
has | +0.053 |
Neg logit contributions | |
argue | -0.044 |
worry | -0.043 |
gy | -0.042 |
afar | -0.041 |
cle | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -9.88e-01 |
Pos logit contributions | |
argue | +0.059 |
elbows | +0.057 |
cle | +0.054 |
ge | +0.053 |
gy | +0.053 |
Neg logit contributions | |
can | -0.041 |
has | -0.038 |
lic | -0.037 |
is | -0.036 |
br | -0.035 |
Token | |
Token ID | 220 |
Feature activation | -8.83e-01 |
Pos logit contributions | |
can | +0.015 |
has | +0.014 |
lic | +0.014 |
is | +0.014 |
helps | +0.013 |
Neg logit contributions | |
argue | -0.025 |
elbows | -0.024 |
cle | -0.023 |
ge | -0.023 |
gy | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
can | +0.015 |
has | +0.014 |
lic | +0.013 |
is | +0.013 |
helps | +0.013 |
Neg logit contributions | |
argue | -0.020 |
elbows | -0.020 |
cle | -0.019 |
gy | -0.019 |
ree | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -1.14e+00 |
Pos logit contributions | |
can | +0.016 |
has | +0.014 |
lic | +0.014 |
is | +0.014 |
living | +0.013 |
Neg logit contributions | |
argue | -0.028 |
elbows | -0.028 |
cle | -0.026 |
gy | -0.026 |
ge | -0.026 |
Token | The |
Token ID | 464 |
Feature activation | -5.35e+00 |
Pos logit contributions | |
can | +0.020 |
lic | +0.019 |
has | +0.019 |
is | +0.018 |
br | +0.018 |
Neg logit contributions | |
argue | -0.026 |
elbows | -0.025 |
cle | -0.024 |
gy | -0.023 |
afar | -0.023 |
Token | symbol |
Token ID | 6194 |
Feature activation | -7.61e+00 |
Pos logit contributions | |
can | +0.095 |
lic | +0.089 |
has | +0.088 |
is | +0.085 |
br | +0.084 |
Neg logit contributions | |
argue | -0.118 |
elbows | -0.114 |
cle | -0.108 |
afar | -0.106 |
gy | -0.105 |
Token | said |
Token ID | 531 |
Feature activation | -4.60e+00 |
Pos logit contributions | |
can | +0.118 |
lic | +0.113 |
boards | +0.107 |
has | +0.105 |
helps | +0.101 |
Neg logit contributions | |
argue | -0.162 |
cle | -0.155 |
cker | -0.154 |
weep | -0.154 |
elbows | -0.153 |
Token | goodbye |
Token ID | 24829 |
Feature activation | +3.54e-01 |
Pos logit contributions | |
has | +0.080 |
can | +0.078 |
boards | +0.076 |
helps | +0.075 |
makes | +0.074 |
Neg logit contributions | |
argue | -0.087 |
ree | -0.085 |
worry | -0.084 |
gy | -0.082 |
weep | -0.081 |
Token | and |
Token ID | 290 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
argue | +0.008 |
elbows | +0.007 |
gy | +0.007 |
cle | +0.007 |
ree | +0.007 |
Neg logit contributions | |
can | -0.006 |
lic | -0.006 |
has | -0.006 |
is | -0.006 |
br | -0.006 |
Token | took |
Token ID | 1718 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
boards | +0.001 |
can | +0.001 |
lic | +0.001 |
has | +0.001 |
br | +0.001 |
Neg logit contributions | |
argue | -0.001 |
elbows | -0.001 |
gy | -0.001 |
worry | -0.001 |
weep | -0.001 |
Token | off |
Token ID | 572 |
Feature activation | +2.54e+00 |
Pos logit contributions | |
can | +0.081 |
has | +0.077 |
lic | +0.076 |
boards | +0.075 |
living | +0.072 |
Neg logit contributions | |
elbows | -0.074 |
argue | -0.073 |
gy | -0.069 |
ree | -0.069 |
cle | -0.067 |
Token | . |
Token ID | 13 |
Feature activation | -9.28e-01 |
Pos logit contributions | |
can | +0.026 |
has | +0.023 |
is | +0.023 |
lic | +0.022 |
helps | +0.021 |
Neg logit contributions | |
argue | -0.042 |
elbows | -0.041 |
cle | -0.039 |
gy | -0.039 |
ge | -0.038 |
Token | |
Token ID | 220 |
Feature activation | -1.48e-01 |
Pos logit contributions | |
can | +0.017 |
has | +0.016 |
lic | +0.015 |
is | +0.015 |
br | +0.015 |
Neg logit contributions | |
argue | -0.020 |
elbows | -0.020 |
cle | -0.019 |
gy | -0.018 |
ge | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -7.40e-01 |
Pos logit contributions | |
can | +0.002 |
has | +0.002 |
lic | +0.002 |
is | +0.002 |
helps | +0.002 |
Neg logit contributions | |
argue | -0.004 |
elbows | -0.004 |
cle | -0.004 |
ge | -0.003 |
afar | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -7.00e-01 |
Pos logit contributions | |
can | +0.009 |
lic | +0.008 |
is | +0.008 |
has | +0.008 |
of | +0.008 |
Neg logit contributions | |
argue | -0.022 |
elbows | -0.022 |
afar | -0.020 |
cle | -0.020 |
ge | -0.020 |
Token | The |
Token ID | 464 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
can | +0.013 |
lic | +0.012 |
of | +0.012 |
is | +0.012 |
has | +0.012 |
Neg logit contributions | |
argue | -0.016 |
elbows | -0.016 |
afar | -0.015 |
cle | -0.014 |
ge | -0.014 |
Token | card |
Token ID | 2657 |
Feature activation | -7.60e+00 |
Pos logit contributions | |
can | +0.078 |
has | +0.071 |
lic | +0.070 |
is | +0.069 |
br | +0.066 |
Neg logit contributions | |
argue | -0.118 |
elbows | -0.115 |
cle | -0.111 |
gy | -0.107 |
ge | -0.107 |
Token | was |
Token ID | 373 |
Feature activation | -3.21e+00 |
Pos logit contributions | |
can | +0.112 |
lic | +0.104 |
has | +0.101 |
is | +0.096 |
br | +0.095 |
Neg logit contributions | |
argue | -0.190 |
elbows | -0.184 |
cle | -0.175 |
gy | -0.173 |
weep | -0.173 |
Token | very |
Token ID | 845 |
Feature activation | -5.74e-01 |
Pos logit contributions | |
can | +0.054 |
has | +0.049 |
lic | +0.049 |
is | +0.048 |
br | +0.046 |
Neg logit contributions | |
argue | -0.075 |
elbows | -0.073 |
cle | -0.069 |
gy | -0.068 |
ge | -0.068 |
Token | cheap |
Token ID | 7026 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
can | +0.012 |
has | +0.011 |
lic | +0.011 |
is | +0.011 |
boards | +0.011 |
Neg logit contributions | |
argue | -0.011 |
elbows | -0.011 |
cle | -0.010 |
ge | -0.010 |
weep | -0.010 |
Token | . |
Token ID | 13 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
lic | +0.028 |
can | +0.027 |
has | +0.025 |
br | +0.025 |
helps | +0.024 |
Neg logit contributions | |
argue | -0.031 |
elbows | -0.029 |
ge | -0.028 |
gy | -0.028 |
worry | -0.027 |
Token | It |
Token ID | 632 |
Feature activation | -4.15e+00 |
Pos logit contributions | |
can | +0.033 |
has | +0.032 |
br | +0.031 |
lic | +0.031 |
is | +0.031 |
Neg logit contributions | |
argue | -0.021 |
elbows | -0.020 |
gy | -0.019 |
ree | -0.019 |
cle | -0.019 |
Token | bed |
Token ID | 3996 |
Feature activation | +4.03e-01 |
Pos logit contributions | |
can | +0.005 |
that | +0.005 |
is | +0.005 |
of | +0.004 |
has | +0.004 |
Neg logit contributions | |
argue | -0.006 |
ge | -0.006 |
elbows | -0.006 |
cker | -0.006 |
cle | -0.006 |
Token | . |
Token ID | 13 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
argue | +0.008 |
gy | +0.007 |
cle | +0.007 |
elbows | +0.007 |
ge | +0.007 |
Neg logit contributions | |
can | -0.008 |
has | -0.008 |
lic | -0.007 |
helps | -0.007 |
br | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | -8.82e-01 |
Pos logit contributions | |
can | +0.022 |
has | +0.020 |
lic | +0.020 |
is | +0.020 |
helps | +0.019 |
Neg logit contributions | |
argue | -0.030 |
elbows | -0.030 |
cle | -0.028 |
ge | -0.028 |
gy | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | -8.39e-01 |
Pos logit contributions | |
can | +0.010 |
lic | +0.010 |
is | +0.009 |
of | +0.009 |
has | +0.009 |
Neg logit contributions | |
elbows | -0.026 |
argue | -0.026 |
gy | -0.024 |
afar | -0.024 |
ge | -0.024 |
Token | The |
Token ID | 464 |
Feature activation | -4.38e+00 |
Pos logit contributions | |
can | +0.014 |
lic | +0.013 |
has | +0.013 |
is | +0.013 |
br | +0.013 |
Neg logit contributions | |
elbows | -0.020 |
argue | -0.019 |
gy | -0.018 |
cle | -0.018 |
ge | -0.018 |
Token | cube |
Token ID | 40296 |
Feature activation | -7.54e+00 |
Pos logit contributions | |
can | +0.071 |
has | +0.065 |
lic | +0.065 |
is | +0.063 |
br | +0.062 |
Neg logit contributions | |
argue | -0.104 |
elbows | -0.101 |
cle | -0.097 |
ge | -0.094 |
gy | -0.094 |
Token | was |
Token ID | 373 |
Feature activation | -3.11e+00 |
Pos logit contributions | |
can | +0.109 |
lic | +0.099 |
has | +0.099 |
is | +0.094 |
br | +0.093 |
Neg logit contributions | |
argue | -0.190 |
elbows | -0.184 |
cle | -0.179 |
gy | -0.175 |
weep | -0.172 |
Token | so |
Token ID | 523 |
Feature activation | -2.75e-01 |
Pos logit contributions | |
can | +0.052 |
has | +0.048 |
is | +0.046 |
lic | +0.046 |
living | +0.044 |
Neg logit contributions | |
argue | -0.074 |
elbows | -0.072 |
cle | -0.069 |
ge | -0.067 |
ree | -0.066 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.17e-01 |
Pos logit contributions | |
can | +0.007 |
br | +0.006 |
boards | +0.006 |
has | +0.006 |
lic | +0.006 |
Neg logit contributions | |
argue | -0.004 |
elbows | -0.004 |
worry | -0.004 |
weep | -0.004 |
cle | -0.004 |
Token | to |
Token ID | 284 |
Feature activation | +1.70e+00 |
Pos logit contributions | |
argue | +0.003 |
elbows | +0.003 |
cle | +0.003 |
gy | +0.003 |
ge | +0.003 |
Neg logit contributions | |
can | -0.002 |
lic | -0.002 |
has | -0.002 |
br | -0.001 |
is | -0.001 |
Token | have |
Token ID | 423 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
elbows | +0.039 |
argue | +0.038 |
cle | +0.037 |
ge | +0.037 |
afar | +0.036 |
Neg logit contributions | |
can | -0.030 |
has | -0.028 |
is | -0.027 |
of | -0.025 |
makes | -0.025 |
Token | get |
Token ID | 651 |
Feature activation | -3.32e-01 |
Pos logit contributions | |
elbows | +0.093 |
argue | +0.091 |
cle | +0.088 |
ge | +0.084 |
gy | +0.083 |
Neg logit contributions | |
can | -0.088 |
has | -0.079 |
is | -0.079 |
lic | -0.077 |
helps | -0.075 |
Token | it |
Token ID | 340 |
Feature activation | -5.70e-01 |
Pos logit contributions | |
can | +0.006 |
lic | +0.006 |
has | +0.005 |
boards | +0.005 |
br | +0.005 |
Neg logit contributions | |
argue | -0.007 |
elbows | -0.007 |
cle | -0.007 |
afar | -0.007 |
weep | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -9.26e-02 |
Pos logit contributions | |
can | +0.009 |
has | +0.008 |
lic | +0.008 |
is | +0.008 |
helps | +0.007 |
Neg logit contributions | |
argue | -0.014 |
elbows | -0.014 |
cle | -0.013 |
ge | -0.013 |
gy | -0.013 |
Token | But |
Token ID | 887 |
Feature activation | +2.01e-01 |
Pos logit contributions | |
can | +0.002 |
has | +0.001 |
lic | +0.001 |
is | +0.001 |
br | +0.001 |
Neg logit contributions | |
argue | -0.002 |
elbows | -0.002 |
cle | -0.002 |
gy | -0.002 |
ge | -0.002 |
Token | the |
Token ID | 262 |
Feature activation | -4.34e+00 |
Pos logit contributions | |
argue | +0.005 |
elbows | +0.005 |
cle | +0.005 |
ge | +0.005 |
ree | +0.004 |
Neg logit contributions | |
can | -0.003 |
has | -0.003 |
is | -0.003 |
lic | -0.003 |
makes | -0.003 |
Token | print |
Token ID | 3601 |
Feature activation | -7.53e+00 |
Pos logit contributions | |
lic | +0.082 |
can | +0.080 |
br | +0.078 |
has | +0.078 |
boards | +0.076 |
Neg logit contributions | |
argue | -0.089 |
elbows | -0.083 |
worry | -0.080 |
afar | -0.079 |
weep | -0.079 |
Token | was |
Token ID | 373 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
lic | +0.097 |
can | +0.095 |
has | +0.088 |
br | +0.084 |
helps | +0.081 |
Neg logit contributions | |
argue | -0.194 |
elbows | -0.185 |
weep | -0.180 |
gy | -0.178 |
cle | -0.178 |
Token | surrounded |
Token ID | 11191 |
Feature activation | -3.91e+00 |
Pos logit contributions | |
can | +0.045 |
boards | +0.044 |
lic | +0.044 |
br | +0.042 |
has | +0.042 |
Neg logit contributions | |
argue | -0.059 |
elbows | -0.055 |
ge | -0.053 |
worry | -0.053 |
afar | -0.053 |
Token | by |
Token ID | 416 |
Feature activation | +7.23e-01 |
Pos logit contributions | |
can | +0.069 |
has | +0.063 |
lic | +0.061 |
is | +0.061 |
helps | +0.058 |
Neg logit contributions | |
argue | -0.090 |
elbows | -0.087 |
cle | -0.083 |
ge | -0.081 |
gy | -0.081 |
Token | a |
Token ID | 257 |
Feature activation | -8.92e-01 |
Pos logit contributions | |
argue | +0.016 |
elbows | +0.015 |
afar | +0.015 |
worry | +0.015 |
ge | +0.015 |
Neg logit contributions | |
can | -0.012 |
lic | -0.012 |
has | -0.012 |
br | -0.011 |
boards | -0.011 |
Token | big |
Token ID | 1263 |
Feature activation | +1.28e+00 |
Pos logit contributions | |
can | +0.013 |
has | +0.012 |
lic | +0.012 |
boards | +0.012 |
helps | +0.012 |
Neg logit contributions | |
argue | -0.022 |
elbows | -0.021 |
worry | -0.020 |
cle | -0.020 |
weep | -0.020 |
Token | gently |
Token ID | 15165 |
Feature activation | +3.52e+00 |
Pos logit contributions | |
lic | +0.038 |
can | +0.035 |
br | +0.035 |
has | +0.035 |
boards | +0.034 |
Neg logit contributions | |
argue | -0.037 |
gy | -0.034 |
elbows | -0.034 |
ge | -0.033 |
worry | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -1.32e-02 |
Pos logit contributions | |
argue | +0.084 |
elbows | +0.082 |
cle | +0.077 |
ge | +0.076 |
gy | +0.076 |
Neg logit contributions | |
can | -0.058 |
has | -0.053 |
lic | -0.052 |
is | -0.051 |
br | -0.049 |
Token | Suddenly |
Token ID | 24975 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
can | +0.000 |
has | +0.000 |
lic | +0.000 |
is | +0.000 |
br | +0.000 |
Neg logit contributions | |
argue | -0.000 |
elbows | -0.000 |
cle | -0.000 |
gy | -0.000 |
ge | -0.000 |
Token | , |
Token ID | 11 |
Feature activation | +6.43e-01 |
Pos logit contributions | |
can | +0.001 |
has | +0.001 |
lic | +0.001 |
is | +0.001 |
helps | +0.001 |
Neg logit contributions | |
argue | -0.001 |
elbows | -0.001 |
cle | -0.001 |
gy | -0.001 |
ge | -0.001 |
Token | the |
Token ID | 262 |
Feature activation | -4.08e+00 |
Pos logit contributions | |
argue | +0.016 |
elbows | +0.015 |
cle | +0.015 |
gy | +0.014 |
ge | +0.014 |
Neg logit contributions | |
can | -0.010 |
has | -0.009 |
lic | -0.009 |
is | -0.009 |
br | -0.008 |
Token | print |
Token ID | 3601 |
Feature activation | -7.52e+00 |
Pos logit contributions | |
can | +0.077 |
lic | +0.073 |
has | +0.072 |
br | +0.071 |
boards | +0.071 |
Neg logit contributions | |
argue | -0.081 |
elbows | -0.078 |
cle | -0.075 |
gy | -0.074 |
afar | -0.072 |
Token | began |
Token ID | 2540 |
Feature activation | -9.40e-01 |
Pos logit contributions | |
can | +0.124 |
lic | +0.123 |
helps | +0.119 |
has | +0.117 |
living | +0.114 |
Neg logit contributions | |
argue | -0.148 |
elbows | -0.141 |
weep | -0.139 |
gy | -0.136 |
cker | -0.135 |
Token | to |
Token ID | 284 |
Feature activation | +3.86e+00 |
Pos logit contributions | |
can | +0.014 |
has | +0.012 |
is | +0.012 |
lic | +0.012 |
of | +0.011 |
Neg logit contributions | |
argue | -0.024 |
elbows | -0.024 |
cle | -0.023 |
afar | -0.022 |
iver | -0.022 |
Token | melt |
Token ID | 16867 |
Feature activation | +2.24e-01 |
Pos logit contributions | |
argue | +0.082 |
elbows | +0.080 |
cle | +0.076 |
gy | +0.073 |
ge | +0.073 |
Neg logit contributions | |
can | -0.074 |
has | -0.068 |
lic | -0.067 |
is | -0.066 |
br | -0.064 |
Token | ! |
Token ID | 0 |
Feature activation | -4.68e-01 |
Pos logit contributions | |
elbows | +0.004 |
argue | +0.004 |
gy | +0.004 |
ge | +0.004 |
cle | +0.004 |
Neg logit contributions | |
lic | -0.004 |
can | -0.004 |
has | -0.004 |
br | -0.004 |
teaches | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -1.63e-01 |
Pos logit contributions | |
can | +0.009 |
has | +0.009 |
lic | +0.008 |
is | +0.008 |
br | +0.008 |
Neg logit contributions | |
argue | -0.009 |
elbows | -0.009 |
cle | -0.009 |
gy | -0.008 |
ge | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
lic | +0.000 |
can | +0.000 |
has | +0.000 |
br | +0.000 |
boards | +0.000 |
Neg logit contributions | |
argue | -0.000 |
gy | -0.000 |
ge | -0.000 |
worry | -0.000 |
cle | -0.000 |
Token | sugar |
Token ID | 7543 |
Feature activation | -1.24e+00 |
Pos logit contributions | |
argue | +0.032 |
elbows | +0.032 |
worry | +0.031 |
afar | +0.031 |
weep | +0.030 |
Neg logit contributions | |
lic | -0.029 |
boards | -0.026 |
br | -0.025 |
can | -0.024 |
has | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | -1.47e+00 |
Pos logit contributions | |
lic | +0.024 |
can | +0.023 |
has | +0.022 |
boards | +0.021 |
br | +0.021 |
Neg logit contributions | |
argue | -0.023 |
gy | -0.022 |
ge | -0.021 |
elbows | -0.021 |
cle | -0.021 |
Token | The |
Token ID | 383 |
Feature activation | -5.01e+00 |
Pos logit contributions | |
can | +0.024 |
lic | +0.023 |
has | +0.023 |
boards | +0.022 |
is | +0.022 |
Neg logit contributions | |
argue | -0.032 |
cle | -0.031 |
elbows | -0.031 |
gy | -0.030 |
afar | -0.030 |
Token | secret |
Token ID | 3200 |
Feature activation | -5.22e+00 |
Pos logit contributions | |
can | +0.083 |
has | +0.076 |
lic | +0.075 |
is | +0.073 |
br | +0.071 |
Neg logit contributions | |
argue | -0.118 |
elbows | -0.116 |
cle | -0.110 |
gy | -0.107 |
afar | -0.107 |
Token | mixture |
Token ID | 11710 |
Feature activation | -7.50e+00 |
Pos logit contributions | |
lic | +0.074 |
can | +0.065 |
boards | +0.065 |
br | +0.064 |
has | +0.060 |
Neg logit contributions | |
argue | -0.125 |
worry | -0.119 |
elbows | -0.119 |
weep | -0.117 |
reason | -0.117 |
Token | was |
Token ID | 373 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
lic | +0.104 |
br | +0.087 |
boards | +0.085 |
der | +0.079 |
ative | +0.079 |
Neg logit contributions | |
argue | -0.178 |
weep | -0.168 |
worry | -0.168 |
gy | -0.166 |
cker | -0.164 |
Token | so |
Token ID | 523 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
boards | +0.057 |
lic | +0.056 |
can | +0.054 |
br | +0.052 |
has | +0.051 |
Neg logit contributions | |
argue | -0.074 |
worry | -0.069 |
afar | -0.068 |
cle | -0.068 |
gy | -0.067 |
Token | good |
Token ID | 922 |
Feature activation | +4.17e-01 |
Pos logit contributions | |
boards | +0.015 |
br | +0.014 |
lic | +0.014 |
der | +0.012 |
can | +0.012 |
Neg logit contributions | |
worry | -0.016 |
argue | -0.015 |
panic | -0.015 |
afar | -0.015 |
cle | -0.014 |
Token | that |
Token ID | 326 |
Feature activation | -2.87e+00 |
Pos logit contributions | |
argue | +0.007 |
ge | +0.007 |
gy | +0.007 |
cle | +0.007 |
keeping | +0.007 |
Neg logit contributions | |
lic | -0.008 |
can | -0.008 |
br | -0.008 |
boards | -0.007 |
has | -0.007 |
Token | it |
Token ID | 340 |
Feature activation | -4.61e+00 |
Pos logit contributions | |
lic | +0.054 |
boards | +0.046 |
can | +0.045 |
br | +0.044 |
has | +0.043 |
Neg logit contributions | |
argue | -0.060 |
cle | -0.058 |
worry | -0.058 |
elbows | -0.056 |
afar | -0.054 |
Token | . |
Token ID | 13 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
lic | +0.023 |
can | +0.021 |
boards | +0.021 |
br | +0.021 |
has | +0.021 |
Neg logit contributions | |
argue | -0.022 |
ge | -0.020 |
gy | -0.020 |
worry | -0.020 |
cle | -0.020 |
Token | |
Token ID | 220 |
Feature activation | -7.99e-01 |
Pos logit contributions | |
can | +0.023 |
has | +0.021 |
lic | +0.020 |
is | +0.020 |
helps | +0.019 |
Neg logit contributions | |
argue | -0.034 |
elbows | -0.034 |
cle | -0.032 |
ge | -0.031 |
gy | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
can | +0.013 |
has | +0.012 |
lic | +0.012 |
is | +0.012 |
br | +0.011 |
Neg logit contributions | |
argue | -0.019 |
elbows | -0.018 |
cle | -0.017 |
gy | -0.017 |
ge | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | -1.35e+00 |
Pos logit contributions | |
can | +0.023 |
has | +0.021 |
lic | +0.020 |
is | +0.020 |
helps | +0.019 |
Neg logit contributions | |
argue | -0.034 |
elbows | -0.034 |
cle | -0.032 |
gy | -0.031 |
ge | -0.031 |
Token | The |
Token ID | 464 |
Feature activation | -5.26e+00 |
Pos logit contributions | |
can | +0.027 |
has | +0.025 |
lic | +0.024 |
is | +0.024 |
helps | +0.023 |
Neg logit contributions | |
argue | -0.028 |
elbows | -0.027 |
cle | -0.025 |
gy | -0.025 |
ge | -0.025 |
Token | symbol |
Token ID | 6194 |
Feature activation | -7.49e+00 |
Pos logit contributions | |
can | +0.086 |
has | +0.079 |
is | +0.076 |
lic | +0.075 |
helps | +0.072 |
Neg logit contributions | |
argue | -0.127 |
elbows | -0.125 |
cle | -0.119 |
ge | -0.116 |
gy | -0.116 |
Token | worked |
Token ID | 3111 |
Feature activation | -4.27e+00 |
Pos logit contributions | |
lic | +0.104 |
can | +0.102 |
boards | +0.100 |
arl | +0.089 |
has | +0.088 |
Neg logit contributions | |
argue | -0.168 |
cker | -0.160 |
cle | -0.159 |
worry | -0.157 |
weep | -0.157 |
Token | ! |
Token ID | 0 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
lic | +0.078 |
can | +0.077 |
boards | +0.074 |
has | +0.073 |
living | +0.073 |
Neg logit contributions | |
ge | -0.081 |
argue | -0.081 |
gy | -0.078 |
worry | -0.073 |
cle | -0.072 |
Token | Every |
Token ID | 3887 |
Feature activation | -3.70e+00 |
Pos logit contributions | |
can | +0.040 |
has | +0.037 |
lic | +0.036 |
is | +0.036 |
br | +0.035 |
Neg logit contributions | |
argue | -0.048 |
elbows | -0.046 |
cle | -0.046 |
gy | -0.045 |
ree | -0.044 |
Token | time |
Token ID | 640 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
can | +0.082 |
lic | +0.082 |
boards | +0.079 |
has | +0.078 |
br | +0.076 |
Neg logit contributions | |
argue | -0.062 |
elbows | -0.055 |
cle | -0.055 |
worry | -0.054 |
weep | -0.054 |
Token | Andy |
Token ID | 12382 |
Feature activation | +1.61e+00 |
Pos logit contributions | |
argue | +0.009 |
elbows | +0.008 |
gy | +0.008 |
ge | +0.008 |
worry | +0.008 |
Neg logit contributions | |
lic | -0.006 |
can | -0.006 |
has | -0.006 |
boards | -0.006 |
is | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
argue | +0.017 |
elbows | +0.016 |
cle | +0.016 |
gy | +0.015 |
ge | +0.015 |
Neg logit contributions | |
can | -0.010 |
has | -0.009 |
is | -0.009 |
lic | -0.008 |
living | -0.008 |
Token | found |
Token ID | 1043 |
Feature activation | -3.98e+00 |
Pos logit contributions | |
argue | +0.025 |
elbows | +0.025 |
cle | +0.023 |
gy | +0.023 |
ge | +0.023 |
Neg logit contributions | |
can | -0.021 |
has | -0.020 |
lic | -0.019 |
is | -0.019 |
br | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
lic | +0.096 |
br | +0.093 |
boards | +0.092 |
has | +0.091 |
can | +0.088 |
Neg logit contributions | |
afar | -0.055 |
elbows | -0.050 |
gy | -0.050 |
argue | -0.050 |
Su | -0.048 |
Token | pretty |
Token ID | 2495 |
Feature activation | -1.01e+00 |
Pos logit contributions | |
can | +0.014 |
lic | +0.013 |
has | +0.013 |
boards | +0.013 |
helps | +0.012 |
Neg logit contributions | |
argue | -0.031 |
elbows | -0.030 |
cle | -0.029 |
gy | -0.028 |
worry | -0.028 |
Token | purple |
Token ID | 14032 |
Feature activation | -1.28e+00 |
Pos logit contributions | |
can | +0.016 |
lic | +0.015 |
has | +0.015 |
helps | +0.014 |
is | +0.014 |
Neg logit contributions | |
argue | -0.024 |
elbows | -0.023 |
cle | -0.022 |
gy | -0.022 |
afar | -0.021 |
Token | print |
Token ID | 3601 |
Feature activation | -7.34e+00 |
Pos logit contributions | |
can | +0.023 |
lic | +0.022 |
has | +0.021 |
helps | +0.020 |
is | +0.020 |
Neg logit contributions | |
argue | -0.028 |
elbows | -0.026 |
cle | -0.026 |
gy | -0.025 |
afar | -0.025 |
Token | . |
Token ID | 13 |
Feature activation | -7.42e-01 |
Pos logit contributions | |
lic | +0.135 |
helps | +0.125 |
can | +0.124 |
has | +0.121 |
stals | +0.115 |
Neg logit contributions | |
argue | -0.124 |
elbows | -0.116 |
reason | -0.113 |
cle | -0.113 |
aster | -0.111 |
Token | N |
Token ID | 399 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
br | +0.014 |
can | +0.013 |
has | +0.013 |
lic | +0.012 |
teaches | +0.012 |
Neg logit contributions | |
argue | -0.014 |
foot | -0.013 |
Samantha | -0.013 |
Su | -0.013 |
gy | -0.013 |
Token | ee |
Token ID | 1453 |
Feature activation | -3.54e-01 |
Pos logit contributions | |
argue | +0.040 |
elbows | +0.038 |
cle | +0.035 |
gy | +0.035 |
weep | +0.034 |
Neg logit contributions | |
can | -0.039 |
is | -0.036 |
has | -0.035 |
lic | -0.035 |
br | -0.034 |
Token | N |
Token ID | 45 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
can | +0.006 |
has | +0.005 |
lic | +0.005 |
is | +0.005 |
br | +0.005 |
Neg logit contributions | |
elbows | -0.008 |
argue | -0.008 |
cle | -0.008 |
ge | -0.008 |
afar | -0.008 |
Token | ee |
Token ID | 1453 |
Feature activation | -5.32e-01 |
Pos logit contributions | |
argue | +0.024 |
elbows | +0.023 |
cle | +0.021 |
weep | +0.021 |
afar | +0.020 |
Neg logit contributions | |
can | -0.025 |
has | -0.023 |
is | -0.023 |
lic | -0.023 |
br | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | -7.37e-01 |
Pos logit contributions | |
lic | +0.031 |
teaches | +0.028 |
ye | +0.027 |
helps | +0.027 |
has | +0.026 |
Neg logit contributions | |
ge | -0.022 |
argue | -0.021 |
gy | -0.019 |
worry | -0.019 |
owing | -0.018 |
Token | Now |
Token ID | 2735 |
Feature activation | -5.11e-01 |
Pos logit contributions | |
can | +0.011 |
lic | +0.010 |
has | +0.010 |
is | +0.009 |
br | +0.009 |
Neg logit contributions | |
argue | -0.018 |
elbows | -0.018 |
cle | -0.017 |
gy | -0.017 |
ree | -0.017 |
Token | , |
Token ID | 11 |
Feature activation | +7.45e-01 |
Pos logit contributions | |
lic | +0.010 |
can | +0.009 |
boards | +0.009 |
has | +0.009 |
br | +0.009 |
Neg logit contributions | |
argue | -0.010 |
worry | -0.009 |
elbows | -0.009 |
gy | -0.009 |
weep | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
argue | +0.017 |
elbows | +0.016 |
cle | +0.015 |
worry | +0.015 |
gy | +0.015 |
Neg logit contributions | |
can | -0.012 |
lic | -0.012 |
has | -0.012 |
boards | -0.011 |
br | -0.011 |
Token | herb |
Token ID | 21047 |
Feature activation | -3.53e+00 |
Pos logit contributions | |
lic | +0.063 |
can | +0.061 |
has | +0.058 |
br | +0.057 |
boards | +0.057 |
Neg logit contributions | |
argue | -0.081 |
elbows | -0.076 |
worry | -0.074 |
reason | -0.074 |
cle | -0.074 |
Token | print |
Token ID | 3601 |
Feature activation | -7.33e+00 |
Pos logit contributions | |
lic | +0.056 |
lessly | +0.047 |
boards | +0.045 |
br | +0.044 |
der | +0.044 |
Neg logit contributions | |
argue | -0.082 |
gy | -0.077 |
weep | -0.077 |
worry | -0.076 |
elbows | -0.075 |
Token | hangs |
Token ID | 28087 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
lic | +0.108 |
der | +0.091 |
can | +0.087 |
lessly | +0.087 |
boards | +0.086 |
Neg logit contributions | |
argue | -0.154 |
worry | -0.149 |
elbows | -0.148 |
reason | -0.148 |
weep | -0.146 |
Token | in |
Token ID | 287 |
Feature activation | +2.29e+00 |
Pos logit contributions | |
lic | +0.029 |
has | +0.028 |
can | +0.028 |
helps | +0.028 |
living | +0.027 |
Neg logit contributions | |
gy | -0.033 |
argue | -0.031 |
ree | -0.030 |
ge | -0.029 |
worry | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | -1.26e+00 |
Pos logit contributions | |
argue | +0.051 |
elbows | +0.050 |
cle | +0.047 |
ge | +0.046 |
gy | +0.046 |
Neg logit contributions | |
can | -0.041 |
has | -0.038 |
lic | -0.038 |
is | -0.036 |
br | -0.035 |
Token | kitchen |
Token ID | 9592 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
lic | +0.022 |
can | +0.021 |
boards | +0.019 |
has | +0.019 |
der | +0.019 |
Neg logit contributions | |
argue | -0.027 |
elbows | -0.027 |
cle | -0.026 |
afar | -0.026 |
aster | -0.025 |
Token | and |
Token ID | 290 |
Feature activation | +9.03e-01 |
Pos logit contributions | |
lic | +0.042 |
br | +0.038 |
lessly | +0.038 |
can | +0.037 |
has | +0.037 |
Neg logit contributions | |
argue | -0.034 |
worry | -0.031 |
gy | -0.030 |
elbows | -0.030 |
ieties | -0.029 |
Token | year |
Token ID | 614 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
argue | +0.019 |
elbows | +0.019 |
cle | +0.017 |
gy | +0.017 |
ge | +0.017 |
Neg logit contributions | |
can | -0.020 |
has | -0.019 |
is | -0.019 |
lic | -0.019 |
of | -0.018 |
Token | old |
Token ID | 1468 |
Feature activation | +2.43e-02 |
Pos logit contributions | |
cle | +0.004 |
argue | +0.004 |
ree | +0.004 |
ge | +0.003 |
gy | +0.003 |
Neg logit contributions | |
can | -0.002 |
has | -0.001 |
is | -0.001 |
makes | -0.001 |
lic | -0.001 |
Token | child |
Token ID | 1200 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
argue | +0.000 |
elbows | +0.000 |
cle | +0.000 |
gy | +0.000 |
ge | +0.000 |
Neg logit contributions | |
can | -0.001 |
has | -0.000 |
lic | -0.000 |
is | -0.000 |
br | -0.000 |
Token | . |
Token ID | 13 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
argue | +0.026 |
elbows | +0.025 |
cle | +0.024 |
gy | +0.023 |
ge | +0.023 |
Neg logit contributions | |
can | -0.018 |
has | -0.017 |
lic | -0.016 |
is | -0.016 |
helps | -0.015 |
Token | The |
Token ID | 383 |
Feature activation | -3.45e+00 |
Pos logit contributions | |
can | +0.002 |
has | +0.002 |
is | +0.002 |
lic | +0.002 |
helps | +0.001 |
Neg logit contributions | |
argue | -0.003 |
elbows | -0.003 |
cle | -0.002 |
ge | -0.002 |
gy | -0.002 |
Token | card |
Token ID | 2657 |
Feature activation | -7.28e+00 |
Pos logit contributions | |
can | +0.075 |
has | +0.070 |
is | +0.069 |
lic | +0.068 |
living | +0.066 |
Neg logit contributions | |
argue | -0.065 |
elbows | -0.064 |
cle | -0.059 |
ge | -0.058 |
gy | -0.058 |
Token | had |
Token ID | 550 |
Feature activation | -2.61e+00 |
Pos logit contributions | |
lic | +0.112 |
can | +0.105 |
lessly | +0.103 |
br | +0.100 |
arl | +0.099 |
Neg logit contributions | |
argue | -0.159 |
weep | -0.151 |
gy | -0.150 |
cle | -0.149 |
worry | -0.145 |
Token | a |
Token ID | 257 |
Feature activation | -6.35e-01 |
Pos logit contributions | |
can | +0.049 |
lic | +0.046 |
boards | +0.046 |
helps | +0.045 |
rooms | +0.044 |
Neg logit contributions | |
argue | -0.046 |
keeping | -0.044 |
elbows | -0.043 |
gy | -0.043 |
seen | -0.043 |
Token | picture |
Token ID | 4286 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
boards | +0.010 |
lic | +0.010 |
can | +0.010 |
helps | +0.010 |
has | +0.009 |
Neg logit contributions | |
argue | -0.014 |
weep | -0.013 |
cle | -0.013 |
worry | -0.013 |
elbows | -0.013 |
Token | of |
Token ID | 286 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
can | +0.066 |
lic | +0.062 |
helps | +0.059 |
rooms | +0.058 |
stals | +0.058 |
Neg logit contributions | |
aster | -0.134 |
cle | -0.132 |
Johnson | -0.131 |
gy | -0.131 |
ree | -0.127 |
Token | an |
Token ID | 281 |
Feature activation | +5.39e-01 |
Pos logit contributions | |
can | +0.020 |
has | +0.019 |
lic | +0.019 |
is | +0.018 |
br | +0.018 |
Neg logit contributions | |
argue | -0.023 |
elbows | -0.022 |
cle | -0.021 |
afar | -0.021 |
gy | -0.020 |
Token | buy |
Token ID | 2822 |
Feature activation | -3.19e+00 |
Pos logit contributions | |
elbows | +0.071 |
cle | +0.066 |
argue | +0.065 |
ree | +0.063 |
cker | +0.062 |
Neg logit contributions | |
can | -0.070 |
is | -0.063 |
has | -0.062 |
that | -0.061 |
of | -0.059 |
Token | something |
Token ID | 1223 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
can | +0.055 |
lic | +0.052 |
has | +0.052 |
br | +0.048 |
is | +0.048 |
Neg logit contributions | |
argue | -0.071 |
elbows | -0.069 |
cle | -0.065 |
afar | -0.064 |
gy | -0.064 |
Token | special |
Token ID | 2041 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
lic | +0.035 |
can | +0.034 |
has | +0.034 |
br | +0.031 |
boards | +0.030 |
Neg logit contributions | |
argue | -0.054 |
elbows | -0.050 |
worry | -0.050 |
reason | -0.050 |
ge | -0.050 |
Token | - |
Token ID | 532 |
Feature activation | +1.06e+00 |
Pos logit contributions | |
lic | +0.021 |
can | +0.019 |
has | +0.019 |
br | +0.018 |
boards | +0.018 |
Neg logit contributions | |
argue | -0.022 |
cle | -0.021 |
elbows | -0.020 |
ge | -0.020 |
gy | -0.020 |
Token | a |
Token ID | 257 |
Feature activation | -9.21e-01 |
Pos logit contributions | |
argue | +0.023 |
elbows | +0.022 |
afar | +0.021 |
worry | +0.021 |
cle | +0.021 |
Neg logit contributions | |
lic | -0.019 |
can | -0.018 |
has | -0.017 |
br | -0.017 |
is | -0.016 |
Token | print |
Token ID | 3601 |
Feature activation | -7.28e+00 |
Pos logit contributions | |
can | +0.013 |
lic | +0.012 |
has | +0.012 |
is | +0.011 |
helps | +0.011 |
Neg logit contributions | |
argue | -0.023 |
elbows | -0.022 |
cle | -0.022 |
weep | -0.021 |
worry | -0.021 |
Token | ! |
Token ID | 0 |
Feature activation | -1.28e-01 |
Pos logit contributions | |
lic | +0.105 |
can | +0.096 |
helps | +0.092 |
has | +0.091 |
der | +0.090 |
Neg logit contributions | |
argue | -0.151 |
aster | -0.150 |
cle | -0.150 |
reason | -0.145 |
elbows | -0.141 |
Token |
|
Token ID | 198 |
Feature activation | +1.48e-01 |
Pos logit contributions | |
can | +0.002 |
has | +0.002 |
is | +0.002 |
lic | +0.002 |
helps | +0.002 |
Neg logit contributions | |
argue | -0.003 |
elbows | -0.003 |
ge | -0.003 |
cle | -0.003 |
afar | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | +3.11e-01 |
Pos logit contributions | |
argue | +0.004 |
elbows | +0.004 |
cle | +0.003 |
gy | +0.003 |
ge | +0.003 |
Neg logit contributions | |
can | -0.002 |
has | -0.002 |
lic | -0.002 |
is | -0.002 |
br | -0.002 |
Token | Billy |
Token ID | 49640 |
Feature activation | +1.20e+00 |
Pos logit contributions | |
argue | +0.006 |
elbows | +0.006 |
weep | +0.005 |
afar | +0.005 |
gy | +0.005 |
Neg logit contributions | |
can | -0.007 |
lic | -0.007 |
has | -0.007 |
is | -0.006 |
of | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -2.55e+00 |
Pos logit contributions | |
argue | +0.030 |
elbows | +0.030 |
cle | +0.028 |
ge | +0.027 |
gy | +0.027 |
Neg logit contributions | |
can | -0.019 |
has | -0.017 |
is | -0.016 |
lic | -0.016 |
helps | -0.015 |
Token | . |
Token ID | 13 |
Feature activation | -1.92e-01 |
Pos logit contributions | |
argue | +0.078 |
elbows | +0.077 |
cle | +0.074 |
ge | +0.071 |
gy | +0.071 |
Neg logit contributions | |
can | -0.052 |
has | -0.048 |
is | -0.046 |
lic | -0.043 |
makes | -0.043 |
Token | He |
Token ID | 679 |
Feature activation | -2.48e+00 |
Pos logit contributions | |
can | +0.003 |
has | +0.002 |
is | +0.002 |
lic | +0.002 |
helps | +0.002 |
Neg logit contributions | |
argue | -0.005 |
elbows | -0.005 |
cle | -0.005 |
ge | -0.005 |
gy | -0.005 |
Token | noticed |
Token ID | 6810 |
Feature activation | -2.97e+00 |
Pos logit contributions | |
lic | +0.042 |
br | +0.038 |
can | +0.038 |
boards | +0.037 |
living | +0.034 |
Neg logit contributions | |
argue | -0.057 |
elbows | -0.053 |
weep | -0.052 |
afar | -0.051 |
gy | -0.050 |
Token | that |
Token ID | 326 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
can | +0.041 |
has | +0.038 |
lic | +0.037 |
is | +0.035 |
br | +0.035 |
Neg logit contributions | |
argue | -0.076 |
elbows | -0.075 |
afar | -0.072 |
cle | -0.072 |
gy | -0.071 |
Token | the |
Token ID | 262 |
Feature activation | -3.30e+00 |
Pos logit contributions | |
can | +0.030 |
lic | +0.029 |
has | +0.028 |
br | +0.027 |
is | +0.027 |
Neg logit contributions | |
argue | -0.040 |
elbows | -0.039 |
cle | -0.037 |
afar | -0.036 |
weep | -0.036 |
Token | print |
Token ID | 3601 |
Feature activation | -7.25e+00 |
Pos logit contributions | |
can | +0.056 |
lic | +0.052 |
has | +0.052 |
is | +0.050 |
br | +0.049 |
Neg logit contributions | |
argue | -0.075 |
elbows | -0.073 |
cle | -0.069 |
afar | -0.068 |
gy | -0.067 |
Token | in |
Token ID | 287 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
lic | +0.110 |
can | +0.090 |
br | +0.089 |
helps | +0.084 |
arl | +0.084 |
Neg logit contributions | |
argue | -0.166 |
weep | -0.157 |
elbows | -0.155 |
worry | -0.154 |
gy | -0.149 |
Token | his |
Token ID | 465 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
argue | +0.023 |
elbows | +0.022 |
cle | +0.021 |
afar | +0.020 |
ge | +0.020 |
Neg logit contributions | |
can | -0.019 |
lic | -0.018 |
has | -0.018 |
is | -0.017 |
br | -0.017 |
Token | new |
Token ID | 649 |
Feature activation | +6.05e-01 |
Pos logit contributions | |
argue | +0.024 |
elbows | +0.023 |
cle | +0.022 |
ge | +0.021 |
gy | +0.021 |
Neg logit contributions | |
can | -0.023 |
has | -0.021 |
is | -0.020 |
lic | -0.020 |
helps | -0.019 |
Token | coloring |
Token ID | 33988 |
Feature activation | -4.72e+00 |
Pos logit contributions | |
argue | +0.013 |
elbows | +0.013 |
cle | +0.012 |
ge | +0.012 |
gy | +0.012 |
Neg logit contributions | |
can | -0.011 |
has | -0.010 |
is | -0.010 |
lic | -0.010 |
living | -0.010 |
Token | book |
Token ID | 1492 |
Feature activation | -3.69e+00 |
Pos logit contributions | |
lic | +0.076 |
can | +0.071 |
has | +0.067 |
helps | +0.067 |
lessly | +0.062 |
Neg logit contributions | |
argue | -0.101 |
elbows | -0.099 |
cle | -0.095 |
gy | -0.094 |
aster | -0.092 |
Token | . |
Token ID | 13 |
Feature activation | +2.89e-01 |
Pos logit contributions | |
can | +0.004 |
lic | +0.004 |
has | +0.004 |
br | +0.004 |
helps | +0.004 |
Neg logit contributions | |
argue | -0.005 |
elbows | -0.005 |
ge | -0.005 |
gy | -0.005 |
weep | -0.005 |
Token |
|
Token ID | 198 |
Feature activation | -6.11e-01 |
Pos logit contributions | |
argue | +0.008 |
elbows | +0.008 |
cle | +0.008 |
ge | +0.008 |
weep | +0.007 |
Neg logit contributions | |
can | -0.004 |
has | -0.003 |
is | -0.003 |
lic | -0.003 |
helps | -0.003 |
Token |
|
Token ID | 198 |
Feature activation | -5.45e-01 |
Pos logit contributions | |
can | +0.008 |
lic | +0.007 |
is | +0.007 |
has | +0.007 |
of | +0.007 |
Neg logit contributions | |
argue | -0.017 |
elbows | -0.017 |
gy | -0.016 |
weep | -0.016 |
cle | -0.015 |
Token | When |
Token ID | 2215 |
Feature activation | -5.31e-01 |
Pos logit contributions | |
can | +0.009 |
lic | +0.008 |
of | +0.008 |
has | +0.008 |
is | +0.008 |
Neg logit contributions | |
argue | -0.013 |
elbows | -0.013 |
gy | -0.013 |
weep | -0.012 |
afar | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -3.61e+00 |
Pos logit contributions | |
can | +0.008 |
has | +0.007 |
lic | +0.007 |
is | +0.007 |
helps | +0.006 |
Neg logit contributions | |
argue | -0.014 |
elbows | -0.013 |
cle | -0.013 |
gy | -0.013 |
ge | -0.013 |
Token | print |
Token ID | 3601 |
Feature activation | -7.24e+00 |
Pos logit contributions | |
can | +0.060 |
lic | +0.056 |
has | +0.056 |
is | +0.054 |
br | +0.051 |
Neg logit contributions | |
argue | -0.083 |
elbows | -0.081 |
cle | -0.078 |
worry | -0.074 |
weep | -0.074 |
Token | was |
Token ID | 373 |
Feature activation | -1.74e+00 |
Pos logit contributions | |
lic | +0.099 |
can | +0.097 |
has | +0.089 |
living | +0.085 |
helps | +0.085 |
Neg logit contributions | |
argue | -0.173 |
elbows | -0.162 |
gy | -0.161 |
weep | -0.159 |
worry | -0.159 |
Token | full |
Token ID | 1336 |
Feature activation | -4.70e+00 |
Pos logit contributions | |
can | +0.035 |
has | +0.033 |
is | +0.033 |
helps | +0.032 |
boards | +0.031 |
Neg logit contributions | |
argue | -0.034 |
elbows | -0.030 |
ge | -0.029 |
cle | -0.029 |
aster | -0.029 |
Token | , |
Token ID | 11 |
Feature activation | +2.13e-01 |
Pos logit contributions | |
has | +0.084 |
lic | +0.084 |
can | +0.082 |
br | +0.077 |
is | +0.076 |
Neg logit contributions | |
argue | -0.092 |
worry | -0.090 |
cle | -0.086 |
elbows | -0.086 |
reason | -0.084 |
Token | Daddy |
Token ID | 26926 |
Feature activation | +6.96e-01 |
Pos logit contributions | |
argue | +0.004 |
elbows | +0.004 |
cle | +0.004 |
worry | +0.004 |
gy | +0.004 |
Neg logit contributions | |
can | -0.004 |
has | -0.004 |
lic | -0.004 |
is | -0.003 |
br | -0.003 |
Token | showed |
Token ID | 3751 |
Feature activation | -5.32e+00 |
Pos logit contributions | |
argue | +0.015 |
gy | +0.014 |
cle | +0.014 |
ge | +0.014 |
bie | +0.013 |
Neg logit contributions | |
can | -0.012 |
br | -0.012 |
has | -0.011 |
boards | -0.011 |
lic | -0.011 |
Token | to |
Token ID | 284 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
argue | +0.072 |
gy | +0.065 |
ge | +0.064 |
cle | +0.062 |
weep | +0.062 |
Neg logit contributions | |
lic | -0.058 |
can | -0.056 |
br | -0.056 |
has | -0.054 |
boards | -0.053 |
Token | go |
Token ID | 467 |
Feature activation | +3.39e+00 |
Pos logit contributions | |
argue | +0.050 |
elbows | +0.047 |
cle | +0.046 |
gy | +0.044 |
weep | +0.044 |
Neg logit contributions | |
can | -0.050 |
has | -0.047 |
lic | -0.047 |
is | -0.045 |
br | -0.044 |
Token | and |
Token ID | 290 |
Feature activation | +2.59e+00 |
Pos logit contributions | |
argue | +0.085 |
elbows | +0.083 |
cle | +0.080 |
gy | +0.078 |
ge | +0.078 |
Neg logit contributions | |
can | -0.052 |
has | -0.047 |
lic | -0.045 |
is | -0.045 |
helps | -0.043 |
Token | find |
Token ID | 1064 |
Feature activation | -4.33e+00 |
Pos logit contributions | |
argue | +0.050 |
elbows | +0.050 |
cle | +0.047 |
ge | +0.045 |
gy | +0.045 |
Neg logit contributions | |
can | -0.054 |
has | -0.050 |
is | -0.049 |
lic | -0.048 |
helps | -0.047 |
Token | a |
Token ID | 257 |
Feature activation | -1.15e+00 |
Pos logit contributions | |
lic | +0.098 |
has | +0.097 |
can | +0.094 |
br | +0.090 |
der | +0.088 |
Neg logit contributions | |
afar | -0.066 |
elbows | -0.065 |
cle | -0.064 |
mischief | -0.063 |
aster | -0.063 |
Token | print |
Token ID | 3601 |
Feature activation | -7.22e+00 |
Pos logit contributions | |
can | +0.019 |
has | +0.017 |
lic | +0.017 |
is | +0.017 |
helps | +0.016 |
Neg logit contributions | |
argue | -0.027 |
elbows | -0.027 |
cle | -0.025 |
gy | -0.025 |
ge | -0.025 |
Token | in |
Token ID | 287 |
Feature activation | +2.02e+00 |
Pos logit contributions | |
lic | +0.114 |
has | +0.107 |
can | +0.106 |
is | +0.095 |
helps | +0.094 |
Neg logit contributions | |
argue | -0.154 |
cle | -0.148 |
aster | -0.147 |
elbows | -0.147 |
reason | -0.142 |
Token | the |
Token ID | 262 |
Feature activation | -6.62e-01 |
Pos logit contributions | |
argue | +0.046 |
elbows | +0.045 |
cle | +0.043 |
ge | +0.042 |
gy | +0.041 |
Neg logit contributions | |
can | -0.035 |
has | -0.033 |
lic | -0.032 |
is | -0.032 |
br | -0.030 |
Token | me |
Token ID | 502 |
Feature activation | +3.30e+00 |
Pos logit contributions | |
can | +0.012 |
lic | +0.011 |
has | +0.011 |
br | +0.011 |
is | +0.010 |
Neg logit contributions | |
argue | -0.014 |
elbows | -0.014 |
cle | -0.013 |
afar | -0.013 |
gy | -0.013 |
Token | adow |
Token ID | 4584 |
Feature activation | -3.28e-01 |
Pos logit contributions | |
argue | +0.033 |
elbows | +0.031 |
cle | +0.026 |
ge | +0.026 |
gy | +0.025 |
Neg logit contributions | |
can | -0.102 |
has | -0.097 |
is | -0.096 |
lic | -0.094 |
living | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | -7.84e-01 |
Pos logit contributions | |
can | +0.006 |
lic | +0.006 |
br | +0.006 |
has | +0.005 |
helps | +0.005 |
Neg logit contributions | |
argue | -0.007 |
elbows | -0.006 |
gy | -0.006 |
cle | -0.006 |
ge | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
lic | +0.050 |
can | +0.046 |
br | +0.044 |
has | +0.043 |
helps | +0.039 |
Neg logit contributions | |
argue | -0.102 |
elbows | -0.100 |
weep | -0.094 |
worry | -0.093 |
gy | -0.093 |
Token | nothing |
Token ID | 2147 |
Feature activation | -1.59e+00 |
Pos logit contributions | |
can | +0.041 |
has | +0.037 |
is | +0.036 |
lic | +0.034 |
helps | +0.034 |
Neg logit contributions | |
argue | -0.059 |
elbows | -0.058 |
cle | -0.056 |
ge | -0.054 |
ree | -0.054 |
Token | she |
Token ID | 673 |
Feature activation | -4.48e-01 |
Pos logit contributions | |
lic | +0.025 |
can | +0.023 |
boards | +0.023 |
teaches | +0.022 |
has | +0.022 |
Neg logit contributions | |
ge | -0.035 |
argue | -0.033 |
elbows | -0.033 |
gy | -0.032 |
worry | -0.032 |
Token | could |
Token ID | 714 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
lic | +0.006 |
can | +0.006 |
br | +0.006 |
boards | +0.006 |
has | +0.006 |
Neg logit contributions | |
argue | -0.011 |
elbows | -0.010 |
cle | -0.010 |
gy | -0.010 |
afar | -0.010 |
Token | do |
Token ID | 466 |
Feature activation | -5.51e-01 |
Pos logit contributions | |
elbows | +0.060 |
argue | +0.058 |
cle | +0.057 |
afar | +0.054 |
ree | +0.054 |
Neg logit contributions | |
can | -0.045 |
is | -0.039 |
has | -0.039 |
that | -0.038 |
of | -0.037 |
Token | to |
Token ID | 284 |
Feature activation | +7.31e+00 |
Pos logit contributions | |
can | +0.009 |
lic | +0.009 |
has | +0.008 |
br | +0.008 |
is | +0.008 |
Neg logit contributions | |
argue | -0.013 |
elbows | -0.012 |
ge | -0.012 |
cle | -0.012 |
gy | -0.012 |
Token | fix |
Token ID | 4259 |
Feature activation | -6.10e-01 |
Pos logit contributions | |
elbows | +0.164 |
cle | +0.159 |
ree | +0.155 |
argue | +0.153 |
bie | +0.152 |
Neg logit contributions | |
can | -0.129 |
is | -0.116 |
that | -0.116 |
of | -0.110 |
has | -0.109 |
Token | his |
Token ID | 465 |
Feature activation | +3.48e+00 |
Pos logit contributions | |
can | +0.011 |
has | +0.010 |
is | +0.010 |
lic | +0.009 |
helps | +0.009 |
Neg logit contributions | |
argue | -0.014 |
elbows | -0.014 |
cle | -0.013 |
ge | -0.013 |
gy | -0.013 |
Token | special |
Token ID | 2041 |
Feature activation | +1.47e+00 |
Pos logit contributions | |
argue | +0.068 |
cle | +0.066 |
ree | +0.065 |
aster | +0.064 |
elbows | +0.063 |
Neg logit contributions | |
can | -0.073 |
is | -0.068 |
has | -0.067 |
makes | -0.062 |
living | -0.062 |
Token | jacket |
Token ID | 15224 |
Feature activation | +1.43e+00 |
Pos logit contributions | |
argue | +0.025 |
elbows | +0.024 |
cle | +0.023 |
ree | +0.022 |
gy | +0.022 |
Neg logit contributions | |
can | -0.035 |
has | -0.032 |
is | -0.032 |
helps | -0.030 |
makes | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -8.38e-01 |
Pos logit contributions | |
argue | +0.035 |
elbows | +0.034 |
cle | +0.033 |
ge | +0.032 |
gy | +0.032 |
Neg logit contributions | |
can | -0.023 |
has | -0.021 |
lic | -0.020 |
is | -0.020 |
helps | -0.019 |
Token | sun |
Token ID | 4252 |
Feature activation | +6.69e-01 |
Pos logit contributions | |
can | +0.036 |
has | +0.033 |
lic | +0.033 |
is | +0.032 |
helps | +0.031 |
Neg logit contributions | |
argue | -0.043 |
elbows | -0.042 |
cle | -0.039 |
gy | -0.038 |
afar | -0.038 |
Token | sets |
Token ID | 5621 |
Feature activation | -6.58e-01 |
Pos logit contributions | |
argue | +0.020 |
elbows | +0.019 |
gy | +0.019 |
cle | +0.019 |
weep | +0.018 |
Neg logit contributions | |
can | -0.006 |
lic | -0.006 |
boards | -0.005 |
has | -0.005 |
br | -0.005 |
Token | ." |
Token ID | 526 |
Feature activation | +3.47e-01 |
Pos logit contributions | |
can | +0.012 |
lic | +0.012 |
has | +0.011 |
br | +0.011 |
boards | +0.011 |
Neg logit contributions | |
argue | -0.013 |
elbows | -0.013 |
cle | -0.013 |
gy | -0.013 |
ge | -0.012 |
Token |
|
Token ID | 198 |
Feature activation | +1.96e-01 |
Pos logit contributions | |
argue | +0.006 |
elbows | +0.006 |
cle | +0.006 |
ge | +0.005 |
afar | +0.005 |
Neg logit contributions | |
can | -0.008 |
is | -0.008 |
has | -0.008 |
that | -0.007 |
lic | -0.007 |
Token |
|
Token ID | 198 |
Feature activation | +2.38e-01 |
Pos logit contributions | |
argue | +0.006 |
elbows | +0.006 |
cle | +0.005 |
afar | +0.005 |
ge | +0.005 |
Neg logit contributions | |
can | -0.002 |
is | -0.002 |
has | -0.002 |
lic | -0.002 |
of | -0.002 |
Token | Twe |
Token ID | 32665 |
Feature activation | +7.59e+00 |
Pos logit contributions | |
elbows | +0.004 |
argue | +0.004 |
sing | +0.004 |
cle | +0.004 |
bie | +0.004 |
Neg logit contributions | |
can | -0.005 |
is | -0.005 |
has | -0.005 |
lic | -0.005 |
that | -0.005 |
Token | ety |
Token ID | 2963 |
Feature activation | -7.29e-01 |
Pos logit contributions | |
argue | +0.122 |
elbows | +0.121 |
mischief | +0.120 |
panic | +0.108 |
weep | +0.102 |
Neg logit contributions | |
can | -0.186 |
has | -0.176 |
is | -0.172 |
ing | -0.168 |
lic | -0.167 |
Token | was |
Token ID | 373 |
Feature activation | -2.74e+00 |
Pos logit contributions | |
can | +0.011 |
has | +0.010 |
is | +0.010 |
lic | +0.009 |
helps | +0.009 |
Neg logit contributions | |
argue | -0.019 |
elbows | -0.019 |
cle | -0.018 |
ge | -0.017 |
afar | -0.017 |
Token | very |
Token ID | 845 |
Feature activation | +3.84e-01 |
Pos logit contributions | |
can | +0.040 |
has | +0.039 |
is | +0.038 |
that | +0.037 |
living | +0.037 |
Neg logit contributions | |
cle | -0.070 |
elbows | -0.069 |
argue | -0.069 |
ge | -0.067 |
ree | -0.066 |
Token | happy |
Token ID | 3772 |
Feature activation | +1.10e+00 |
Pos logit contributions | |
argue | +0.008 |
elbows | +0.008 |
cle | +0.007 |
ge | +0.007 |
gy | +0.007 |
Neg logit contributions | |
can | -0.008 |
has | -0.008 |
is | -0.007 |
lic | -0.007 |
helps | -0.007 |
Token | and |
Token ID | 290 |
Feature activation | +7.63e-01 |
Pos logit contributions | |
argue | +0.025 |
elbows | +0.025 |
cle | +0.023 |
ge | +0.023 |
gy | +0.023 |
Neg logit contributions | |
can | -0.019 |
has | -0.018 |
lic | -0.017 |
is | -0.017 |
br | -0.016 |
Token | the |
Token ID | 262 |
Feature activation | -6.38e-01 |
Pos logit contributions | |
argue | +0.048 |
elbows | +0.047 |
cle | +0.045 |
ge | +0.043 |
gy | +0.043 |
Neg logit contributions | |
can | -0.043 |
has | -0.039 |
lic | -0.039 |
is | -0.038 |
helps | -0.037 |
Token | floor |
Token ID | 4314 |
Feature activation | -1.18e+00 |
Pos logit contributions | |
can | +0.011 |
lic | +0.011 |
has | +0.010 |
br | +0.010 |
is | +0.010 |
Neg logit contributions | |
argue | -0.014 |
elbows | -0.014 |
weep | -0.013 |
cle | -0.013 |
afar | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +2.13e+00 |
Pos logit contributions | |
lic | +0.023 |
can | +0.022 |
br | +0.022 |
has | +0.021 |
helps | +0.020 |
Neg logit contributions | |
argue | -0.023 |
elbows | -0.022 |
ge | -0.022 |
gy | -0.021 |
worry | -0.021 |
Token | not |
Token ID | 407 |
Feature activation | +1.76e+00 |
Pos logit contributions | |
argue | +0.044 |
elbows | +0.043 |
cle | +0.040 |
ge | +0.039 |
gy | +0.039 |
Neg logit contributions | |
can | -0.042 |
lic | -0.039 |
has | -0.039 |
is | -0.038 |
br | -0.037 |
Token | wanting |
Token ID | 10291 |
Feature activation | -1.37e+00 |
Pos logit contributions | |
argue | +0.033 |
elbows | +0.032 |
cle | +0.030 |
ge | +0.029 |
gy | +0.029 |
Neg logit contributions | |
can | -0.038 |
has | -0.035 |
lic | -0.035 |
is | -0.035 |
br | -0.034 |
Token | to |
Token ID | 284 |
Feature activation | +6.77e+00 |
Pos logit contributions | |
can | +0.023 |
has | +0.021 |
lic | +0.021 |
is | +0.020 |
br | +0.019 |
Neg logit contributions | |
argue | -0.032 |
elbows | -0.032 |
cle | -0.030 |
ge | -0.029 |
gy | -0.029 |
Token | see |
Token ID | 766 |
Feature activation | -1.26e-01 |
Pos logit contributions | |
elbows | +0.146 |
cle | +0.141 |
ree | +0.134 |
afar | +0.133 |
ighed | +0.131 |
Neg logit contributions | |
can | -0.127 |
that | -0.120 |
is | -0.115 |
of | -0.114 |
has | -0.110 |
Token | anyone |
Token ID | 2687 |
Feature activation | +3.89e+00 |
Pos logit contributions | |
can | +0.002 |
lic | +0.002 |
has | +0.002 |
br | +0.002 |
boards | +0.002 |
Neg logit contributions | |
argue | -0.003 |
elbows | -0.003 |
cle | -0.002 |
ge | -0.002 |
afar | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | -3.88e-01 |
Pos logit contributions | |
argue | +0.089 |
elbows | +0.086 |
ge | +0.081 |
cle | +0.081 |
weep | +0.080 |
Neg logit contributions | |
can | -0.067 |
has | -0.062 |
lic | -0.062 |
is | -0.060 |
br | -0.058 |
Token |
|
Token ID | 198 |
Feature activation | -8.73e-01 |
Pos logit contributions | |
can | +0.006 |
has | +0.006 |
lic | +0.006 |
is | +0.006 |
br | +0.005 |
Neg logit contributions | |
argue | -0.009 |
elbows | -0.009 |
cle | -0.009 |
gy | -0.008 |
ge | -0.008 |
Token |
|
Token ID | 198 |
Feature activation | -9.39e-01 |
Pos logit contributions | |
can | +0.014 |
is | +0.013 |
has | +0.013 |
lic | +0.013 |
of | +0.013 |
Neg logit contributions | |
argue | -0.021 |
elbows | -0.021 |
cle | -0.019 |
gy | -0.019 |
afar | -0.019 |
Token | plant |
Token ID | 4618 |
Feature activation | -3.71e+00 |
Pos logit contributions | |
can | +0.010 |
lic | +0.010 |
has | +0.009 |
boards | +0.009 |
is | +0.009 |
Neg logit contributions | |
argue | -0.014 |
elbows | -0.013 |
cle | -0.013 |
weep | -0.013 |
afar | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -4.82e-02 |
Pos logit contributions | |
lic | +0.070 |
boards | +0.066 |
can | +0.063 |
lessly | +0.062 |
has | +0.062 |
Neg logit contributions | |
gy | -0.067 |
argue | -0.066 |
cle | -0.062 |
cker | -0.061 |
ree | -0.061 |
Token | Would |
Token ID | 10928 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
br | +0.001 |
boards | +0.001 |
lic | +0.001 |
can | +0.001 |
has | +0.001 |
Neg logit contributions | |
argue | -0.001 |
gy | -0.001 |
ree | -0.001 |
cle | -0.001 |
afar | -0.001 |
Token | you |
Token ID | 345 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
argue | +0.003 |
elbows | +0.002 |
cle | +0.002 |
afar | +0.002 |
gy | +0.002 |
Neg logit contributions | |
can | -0.002 |
has | -0.002 |
lic | -0.001 |
is | -0.001 |
helps | -0.001 |
Token | like |
Token ID | 588 |
Feature activation | +2.23e+00 |
Pos logit contributions | |
argue | +0.115 |
elbows | +0.111 |
cle | +0.106 |
gy | +0.103 |
ge | +0.103 |
Neg logit contributions | |
can | -0.085 |
has | -0.079 |
lic | -0.077 |
is | -0.076 |
helps | -0.073 |
Token | to |
Token ID | 284 |
Feature activation | +7.03e+00 |
Pos logit contributions | |
argue | +0.052 |
elbows | +0.049 |
cle | +0.048 |
afar | +0.047 |
ree | +0.047 |
Neg logit contributions | |
can | -0.035 |
has | -0.034 |
lic | -0.034 |
boards | -0.031 |
br | -0.031 |
Token | learn |
Token ID | 2193 |
Feature activation | -9.47e-01 |
Pos logit contributions | |
elbows | +0.141 |
argue | +0.139 |
cle | +0.132 |
ge | +0.129 |
gy | +0.127 |
Neg logit contributions | |
can | -0.144 |
has | -0.131 |
is | -0.129 |
lic | -0.127 |
helps | -0.123 |
Token | about |
Token ID | 546 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
has | +0.015 |
lic | +0.015 |
can | +0.014 |
boards | +0.014 |
lessly | +0.013 |
Neg logit contributions | |
argue | -0.020 |
afar | -0.019 |
ree | -0.019 |
elbows | -0.018 |
cle | -0.018 |
Token | it |
Token ID | 340 |
Feature activation | +1.16e+00 |
Pos logit contributions | |
argue | +0.059 |
elbows | +0.056 |
cle | +0.054 |
afar | +0.054 |
gy | +0.053 |
Neg logit contributions | |
can | -0.042 |
lic | -0.040 |
has | -0.040 |
boards | -0.037 |
is | -0.037 |
Token | ?" |
Token ID | 1701 |
Feature activation | +9.60e-01 |
Pos logit contributions | |
argue | +0.020 |
cle | +0.018 |
iver | +0.018 |
ree | +0.017 |
afar | +0.017 |
Neg logit contributions | |
can | -0.023 |
lic | -0.023 |
has | -0.023 |
boards | -0.022 |
br | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +2.43e-01 |
Pos logit contributions | |
argue | +0.023 |
elbows | +0.023 |
cle | +0.022 |
ge | +0.021 |
gy | +0.021 |
Neg logit contributions | |
can | -0.016 |
has | -0.014 |
is | -0.014 |
lic | -0.014 |
helps | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | +9.89e-01 |
Pos logit contributions | |
argue | +0.037 |
elbows | +0.034 |
cle | +0.034 |
gy | +0.034 |
worry | +0.033 |
Neg logit contributions | |
can | -0.026 |
lic | -0.026 |
br | -0.024 |
boards | -0.024 |
has | -0.024 |
Token | I |
Token ID | 314 |
Feature activation | +1.71e+00 |
Pos logit contributions | |
argue | +0.023 |
worry | +0.022 |
cle | +0.020 |
elbows | +0.020 |
weep | +0.020 |
Neg logit contributions | |
lic | -0.017 |
br | -0.015 |
boards | -0.015 |
has | -0.014 |
can | -0.014 |
Token | don |
Token ID | 836 |
Feature activation | +1.55e+00 |
Pos logit contributions | |
argue | +0.035 |
elbows | +0.034 |
cle | +0.032 |
gy | +0.031 |
ge | +0.031 |
Neg logit contributions | |
can | -0.033 |
has | -0.031 |
lic | -0.030 |
is | -0.030 |
br | -0.029 |
Token | 't |
Token ID | 470 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
argue | +0.028 |
elbows | +0.025 |
ge | +0.024 |
cle | +0.024 |
iver | +0.024 |
Neg logit contributions | |
can | -0.033 |
lic | -0.032 |
has | -0.031 |
boards | -0.031 |
living | -0.030 |
Token | want |
Token ID | 765 |
Feature activation | -3.84e-01 |
Pos logit contributions | |
elbows | +0.080 |
argue | +0.077 |
cle | +0.075 |
gy | +0.072 |
afar | +0.072 |
Neg logit contributions | |
can | -0.077 |
has | -0.069 |
is | -0.068 |
of | -0.066 |
lic | -0.066 |
Token | to |
Token ID | 284 |
Feature activation | +6.61e+00 |
Pos logit contributions | |
can | +0.006 |
has | +0.005 |
is | +0.005 |
lic | +0.005 |
helps | +0.005 |
Neg logit contributions | |
argue | -0.010 |
elbows | -0.009 |
cle | -0.009 |
gy | -0.009 |
ge | -0.009 |
Token | tidy |
Token ID | 43044 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
elbows | +0.152 |
cle | +0.142 |
afar | +0.135 |
ge | +0.134 |
ighed | +0.133 |
Neg logit contributions | |
can | -0.120 |
that | -0.111 |
is | -0.107 |
of | -0.104 |
has | -0.099 |
Token | my |
Token ID | 616 |
Feature activation | +2.08e+00 |
Pos logit contributions | |
argue | +0.063 |
elbows | +0.062 |
cle | +0.059 |
gy | +0.057 |
ge | +0.057 |
Neg logit contributions | |
can | -0.047 |
has | -0.043 |
lic | -0.042 |
is | -0.042 |
helps | -0.040 |
Token | room |
Token ID | 2119 |
Feature activation | -5.73e-01 |
Pos logit contributions | |
argue | +0.049 |
elbows | +0.048 |
cle | +0.048 |
ge | +0.046 |
ree | +0.045 |
Neg logit contributions | |
can | -0.035 |
is | -0.032 |
has | -0.032 |
living | -0.031 |
box | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +6.08e-01 |
Pos logit contributions | |
can | +0.010 |
lic | +0.010 |
has | +0.010 |
br | +0.010 |
helps | +0.009 |
Neg logit contributions | |
argue | -0.012 |
elbows | -0.011 |
ge | -0.011 |
gy | -0.011 |
cle | -0.011 |
Token | I |
Token ID | 314 |
Feature activation | +1.99e+00 |
Pos logit contributions | |
argue | +0.015 |
elbows | +0.015 |
cle | +0.015 |
gy | +0.014 |
weep | +0.014 |
Neg logit contributions | |
lic | -0.008 |
can | -0.008 |
br | -0.007 |
has | -0.007 |
boards | -0.007 |
Token | Hey |
Token ID | 10814 |
Feature activation | +1.44e+00 |
Pos logit contributions | |
argue | +0.005 |
elbows | +0.005 |
cle | +0.004 |
afar | +0.004 |
gy | +0.004 |
Neg logit contributions | |
can | -0.005 |
has | -0.005 |
lic | -0.005 |
is | -0.004 |
br | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +2.47e+00 |
Pos logit contributions | |
argue | +0.037 |
elbows | +0.036 |
cle | +0.035 |
ge | +0.034 |
afar | +0.033 |
Neg logit contributions | |
can | -0.023 |
has | -0.020 |
is | -0.020 |
lic | -0.018 |
br | -0.018 |
Token | kids |
Token ID | 3988 |
Feature activation | +1.74e+00 |
Pos logit contributions | |
argue | +0.051 |
worry | +0.049 |
weep | +0.046 |
elbows | +0.045 |
reason | +0.045 |
Neg logit contributions | |
lic | -0.045 |
boards | -0.044 |
br | -0.042 |
has | -0.042 |
teaches | -0.041 |
Token | ! |
Token ID | 0 |
Feature activation | +4.69e-01 |
Pos logit contributions | |
argue | +0.043 |
elbows | +0.043 |
cle | +0.041 |
afar | +0.040 |
gy | +0.039 |
Neg logit contributions | |
can | -0.028 |
has | -0.025 |
is | -0.025 |
lic | -0.023 |
that | -0.023 |
Token | Don |
Token ID | 2094 |
Feature activation | -1.10e+00 |
Pos logit contributions | |
argue | +0.012 |
elbows | +0.012 |
cle | +0.012 |
ge | +0.012 |
afar | +0.011 |
Neg logit contributions | |
can | -0.007 |
has | -0.006 |
is | -0.006 |
lic | -0.006 |
helps | -0.006 |
Token | 't |
Token ID | 470 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
can | +0.022 |
lic | +0.021 |
has | +0.021 |
living | +0.020 |
der | +0.020 |
Neg logit contributions | |
argue | -0.021 |
elbows | -0.019 |
cle | -0.018 |
gy | -0.018 |
weep | -0.018 |
Token | worry |
Token ID | 5490 |
Feature activation | +4.63e-01 |
Pos logit contributions | |
elbows | +0.075 |
cle | +0.074 |
afar | +0.072 |
ge | +0.070 |
ieties | +0.069 |
Neg logit contributions | |
can | -0.059 |
is | -0.051 |
that | -0.049 |
has | -0.049 |
of | -0.049 |
Token | ! |
Token ID | 0 |
Feature activation | +1.31e+00 |
Pos logit contributions | |
argue | +0.008 |
worry | +0.008 |
elbows | +0.008 |
cle | +0.007 |
gy | +0.007 |
Neg logit contributions | |
lic | -0.009 |
can | -0.009 |
has | -0.009 |
boards | -0.009 |
br | -0.009 |
Token | I |
Token ID | 314 |
Feature activation | +3.26e+00 |
Pos logit contributions | |
argue | +0.035 |
elbows | +0.035 |
cle | +0.033 |
ge | +0.033 |
afar | +0.032 |
Neg logit contributions | |
can | -0.018 |
has | -0.016 |
is | -0.016 |
lic | -0.014 |
helps | -0.014 |
Token | will |
Token ID | 481 |
Feature activation | +2.33e+00 |
Pos logit contributions | |
argue | +0.089 |
elbows | +0.089 |
cle | +0.085 |
ge | +0.083 |
gy | +0.082 |
Neg logit contributions | |
can | -0.043 |
has | -0.038 |
is | -0.036 |
lic | -0.035 |
helps | -0.033 |
Token | provide |
Token ID | 2148 |
Feature activation | -2.13e+00 |
Pos logit contributions | |
elbows | +0.055 |
cle | +0.052 |
argue | +0.052 |
ge | +0.050 |
afar | +0.049 |
Neg logit contributions | |
can | -0.041 |
is | -0.036 |
that | -0.035 |
has | -0.035 |
helps | -0.033 |
Token | They |
Token ID | 1119 |
Feature activation | -1.29e+00 |
Pos logit contributions | |
can | +0.008 |
has | +0.007 |
lic | +0.007 |
is | +0.007 |
br | +0.006 |
Neg logit contributions | |
argue | -0.018 |
elbows | -0.017 |
cle | -0.016 |
gy | -0.016 |
ge | -0.016 |
Token | did |
Token ID | 750 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
can | +0.017 |
lic | +0.016 |
has | +0.016 |
is | +0.015 |
br | +0.015 |
Neg logit contributions | |
argue | -0.034 |
elbows | -0.033 |
cle | -0.031 |
gy | -0.031 |
ge | -0.031 |
Token | not |
Token ID | 407 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
can | +0.044 |
lic | +0.042 |
has | +0.041 |
boards | +0.040 |
br | +0.039 |
Neg logit contributions | |
argue | -0.043 |
elbows | -0.040 |
ge | -0.037 |
afar | -0.037 |
gy | -0.037 |
Token | remain |
Token ID | 3520 |
Feature activation | +2.15e+00 |
Pos logit contributions | |
elbows | +0.061 |
cle | +0.060 |
argue | +0.055 |
gy | +0.053 |
ge | +0.053 |
Neg logit contributions | |
can | -0.079 |
has | -0.071 |
makes | -0.067 |
is | -0.067 |
that | -0.067 |
Token | sad |
Token ID | 6507 |
Feature activation | +2.17e+00 |
Pos logit contributions | |
argue | +0.056 |
cle | +0.055 |
elbows | +0.054 |
ree | +0.053 |
weep | +0.052 |
Neg logit contributions | |
can | -0.030 |
has | -0.027 |
is | -0.026 |
living | -0.025 |
makes | -0.025 |
Token | or |
Token ID | 393 |
Feature activation | +4.85e+00 |
Pos logit contributions | |
argue | +0.037 |
elbows | +0.035 |
ge | +0.034 |
worry | +0.033 |
reason | +0.032 |
Neg logit contributions | |
lic | -0.049 |
has | -0.044 |
can | -0.044 |
br | -0.044 |
contains | -0.042 |
Token | angry |
Token ID | 7954 |
Feature activation | +2.40e+00 |
Pos logit contributions | |
argue | +0.088 |
elbows | +0.080 |
weep | +0.074 |
ge | +0.074 |
worry | +0.073 |
Neg logit contributions | |
can | -0.108 |
lic | -0.107 |
boards | -0.105 |
br | -0.104 |
is | -0.102 |
Token | about |
Token ID | 546 |
Feature activation | +8.08e-01 |
Pos logit contributions | |
argue | +0.050 |
elbows | +0.048 |
ge | +0.044 |
afar | +0.044 |
worry | +0.044 |
Neg logit contributions | |
lic | -0.045 |
can | -0.044 |
has | -0.042 |
br | -0.041 |
helps | -0.040 |
Token | the |
Token ID | 262 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
argue | +0.019 |
elbows | +0.018 |
cle | +0.017 |
ge | +0.017 |
gy | +0.017 |
Neg logit contributions | |
can | -0.014 |
has | -0.013 |
lic | -0.013 |
is | -0.012 |
br | -0.012 |
Token | mud |
Token ID | 17492 |
Feature activation | +5.18e-01 |
Pos logit contributions | |
can | +0.021 |
has | +0.020 |
lic | +0.019 |
is | +0.019 |
br | +0.018 |
Neg logit contributions | |
argue | -0.027 |
elbows | -0.026 |
cle | -0.024 |
gy | -0.024 |
ge | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -3.58e-01 |
Pos logit contributions | |
argue | +0.011 |
elbows | +0.011 |
gy | +0.010 |
ge | +0.010 |
weep | +0.009 |
Neg logit contributions | |
lic | -0.010 |
can | -0.009 |
has | -0.009 |
br | -0.009 |
helps | -0.008 |
Token | 't |
Token ID | 470 |
Feature activation | +3.31e+00 |
Pos logit contributions | |
argue | +0.019 |
elbows | +0.019 |
cle | +0.018 |
afar | +0.017 |
gy | +0.017 |
Neg logit contributions | |
can | -0.013 |
has | -0.012 |
is | -0.012 |
lic | -0.011 |
br | -0.011 |
Token | want |
Token ID | 765 |
Feature activation | -9.87e-01 |
Pos logit contributions | |
elbows | +0.060 |
argue | +0.059 |
cle | +0.056 |
afar | +0.053 |
gy | +0.052 |
Neg logit contributions | |
can | -0.075 |
has | -0.070 |
is | -0.068 |
lic | -0.067 |
helps | -0.065 |
Token | his |
Token ID | 465 |
Feature activation | +2.48e+00 |
Pos logit contributions | |
can | +0.014 |
is | +0.012 |
has | +0.012 |
that | +0.012 |
makes | +0.012 |
Neg logit contributions | |
argue | -0.026 |
elbows | -0.026 |
cle | -0.025 |
ge | -0.025 |
gy | -0.024 |
Token | ball |
Token ID | 2613 |
Feature activation | +1.32e+00 |
Pos logit contributions | |
cle | +0.076 |
elbows | +0.073 |
ge | +0.072 |
iver | +0.070 |
ree | +0.070 |
Neg logit contributions | |
can | -0.034 |
is | -0.028 |
box | -0.026 |
big | -0.026 |
has | -0.026 |
Token | to |
Token ID | 284 |
Feature activation | +6.39e+00 |
Pos logit contributions | |
elbows | +0.035 |
argue | +0.035 |
cle | +0.035 |
afar | +0.033 |
ree | +0.032 |
Neg logit contributions | |
can | -0.019 |
has | -0.016 |
is | -0.016 |
of | -0.015 |
that | -0.015 |
Token | be |
Token ID | 307 |
Feature activation | +2.50e+00 |
Pos logit contributions | |
cle | +0.168 |
bie | +0.166 |
elbows | +0.166 |
bi | +0.160 |
packs | +0.159 |
Neg logit contributions | |
can | -0.104 |
that | -0.097 |
of | -0.088 |
is | -0.086 |
all | -0.083 |
Token | ruined |
Token ID | 20484 |
Feature activation | -6.81e-01 |
Pos logit contributions | |
cle | +0.064 |
argue | +0.061 |
elbows | +0.059 |
ree | +0.057 |
keeping | +0.057 |
Neg logit contributions | |
can | -0.039 |
has | -0.036 |
that | -0.035 |
of | -0.034 |
is | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | +8.32e-01 |
Pos logit contributions | |
can | +0.010 |
has | +0.009 |
is | +0.009 |
lic | +0.009 |
helps | +0.008 |
Neg logit contributions | |
argue | -0.017 |
elbows | -0.017 |
cle | -0.016 |
afar | -0.016 |
gy | -0.016 |
Token |
|
Token ID | 198 |
Feature activation | +4.12e-01 |
Pos logit contributions | |
argue | +0.024 |
elbows | +0.024 |
ge | +0.023 |
cle | +0.022 |
iver | +0.022 |
Neg logit contributions | |
can | -0.011 |
is | -0.010 |
has | -0.010 |
that | -0.009 |
lic | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | +6.07e-01 |
Pos logit contributions | |
elbows | +0.012 |
argue | +0.012 |
afar | +0.011 |
ieties | +0.011 |
cle | +0.011 |
Neg logit contributions | |
can | -0.005 |
is | -0.004 |
lic | -0.004 |
has | -0.004 |
of | -0.004 |
Token | But |
Token ID | 1537 |
Feature activation | +7.72e-01 |
Pos logit contributions | |
argue | +0.013 |
elbows | +0.013 |
afar | +0.012 |
ge | +0.011 |
weep | +0.011 |
Neg logit contributions | |
can | -0.012 |
lic | -0.011 |
has | -0.011 |
is | -0.011 |
that | -0.011 |
Token | friend |
Token ID | 1545 |
Feature activation | -2.59e-01 |
Pos logit contributions | |
argue | +0.045 |
elbows | +0.044 |
cle | +0.041 |
ge | +0.040 |
afar | +0.040 |
Neg logit contributions | |
can | -0.056 |
has | -0.051 |
is | -0.051 |
lic | -0.050 |
helps | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +2.80e+00 |
Pos logit contributions | |
can | +0.004 |
has | +0.004 |
is | +0.004 |
lic | +0.004 |
living | +0.003 |
Neg logit contributions | |
argue | -0.006 |
elbows | -0.006 |
cle | -0.006 |
ge | -0.006 |
afar | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -5.24e-01 |
Pos logit contributions | |
argue | +0.072 |
elbows | +0.071 |
cle | +0.066 |
ge | +0.065 |
ree | +0.065 |
Neg logit contributions | |
can | -0.044 |
has | -0.041 |
is | -0.039 |
living | -0.039 |
that | -0.037 |
Token | cow |
Token ID | 9875 |
Feature activation | +1.18e+00 |
Pos logit contributions | |
can | +0.008 |
has | +0.008 |
lic | +0.008 |
is | +0.008 |
boards | +0.007 |
Neg logit contributions | |
argue | -0.012 |
elbows | -0.012 |
cle | -0.012 |
gy | -0.011 |
weep | -0.011 |
Token | named |
Token ID | 3706 |
Feature activation | +2.66e+00 |
Pos logit contributions | |
argue | +0.020 |
elbows | +0.020 |
cle | +0.018 |
ge | +0.018 |
afar | +0.017 |
Neg logit contributions | |
can | -0.028 |
has | -0.026 |
is | -0.026 |
lic | -0.025 |
living | -0.025 |
Token | Daisy |
Token ID | 40355 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
argue | +0.050 |
elbows | +0.049 |
cle | +0.046 |
ge | +0.044 |
gy | +0.044 |
Neg logit contributions | |
can | -0.057 |
has | -0.053 |
lic | -0.052 |
is | -0.052 |
helps | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -2.00e-01 |
Pos logit contributions | |
argue | +0.090 |
elbows | +0.088 |
cle | +0.084 |
gy | +0.082 |
ge | +0.082 |
Neg logit contributions | |
can | -0.059 |
has | -0.054 |
lic | -0.052 |
is | -0.052 |
helps | -0.049 |
Token | They |
Token ID | 1119 |
Feature activation | -1.19e+00 |
Pos logit contributions | |
can | +0.003 |
has | +0.003 |
lic | +0.003 |
is | +0.003 |
br | +0.003 |
Neg logit contributions | |
argue | -0.005 |
elbows | -0.005 |
cle | -0.005 |
gy | -0.004 |
ge | -0.004 |
Token | loved |
Token ID | 6151 |
Feature activation | -8.13e-01 |
Pos logit contributions | |
can | +0.016 |
has | +0.015 |
is | +0.014 |
lic | +0.014 |
helps | +0.013 |
Neg logit contributions | |
argue | -0.032 |
elbows | -0.031 |
cle | -0.030 |
ge | -0.029 |
ree | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +4.75e+00 |
Pos logit contributions | |
can | +0.012 |
has | +0.011 |
is | +0.011 |
living | +0.010 |
lic | +0.010 |
Neg logit contributions | |
argue | -0.021 |
elbows | -0.021 |
ge | -0.020 |
cle | -0.020 |
iver | -0.019 |
Token | play |
Token ID | 711 |
Feature activation | +2.62e-01 |
Pos logit contributions | |
elbows | +0.081 |
argue | +0.079 |
cle | +0.075 |
ge | +0.074 |
ree | +0.071 |
Neg logit contributions | |
can | -0.112 |
has | -0.104 |
is | -0.103 |
helps | -0.100 |
makes | -0.098 |
Token | happy |
Token ID | 3772 |
Feature activation | +5.40e-01 |
Pos logit contributions | |
can | +0.016 |
boards | +0.016 |
lic | +0.015 |
has | +0.015 |
br | +0.014 |
Neg logit contributions | |
argue | -0.019 |
gy | -0.018 |
elbows | -0.018 |
worry | -0.018 |
weep | -0.018 |
Token | and |
Token ID | 290 |
Feature activation | +1.09e+00 |
Pos logit contributions | |
argue | +0.011 |
elbows | +0.011 |
worry | +0.010 |
afar | +0.010 |
gy | +0.010 |
Neg logit contributions | |
lic | -0.010 |
can | -0.010 |
has | -0.009 |
br | -0.009 |
boards | -0.009 |
Token | have |
Token ID | 423 |
Feature activation | -2.90e+00 |
Pos logit contributions | |
argue | +0.017 |
elbows | +0.017 |
cle | +0.017 |
worry | +0.017 |
gy | +0.017 |
Neg logit contributions | |
boards | -0.025 |
lic | -0.024 |
can | -0.024 |
br | -0.023 |
der | -0.022 |
Token | been |
Token ID | 587 |
Feature activation | -1.96e+00 |
Pos logit contributions | |
can | +0.056 |
lic | +0.052 |
has | +0.052 |
boards | +0.050 |
helps | +0.050 |
Neg logit contributions | |
argue | -0.054 |
elbows | -0.054 |
cle | -0.052 |
gy | -0.051 |
afar | -0.050 |
Token | living |
Token ID | 2877 |
Feature activation | -1.98e+00 |
Pos logit contributions | |
can | +0.039 |
has | +0.036 |
lic | +0.036 |
is | +0.035 |
boards | +0.035 |
Neg logit contributions | |
argue | -0.039 |
elbows | -0.038 |
cle | -0.037 |
gy | -0.036 |
ge | -0.035 |
Token | in |
Token ID | 287 |
Feature activation | +2.56e+00 |
Pos logit contributions | |
lic | +0.040 |
boards | +0.038 |
br | +0.036 |
can | +0.033 |
has | +0.033 |
Neg logit contributions | |
argue | -0.039 |
elbows | -0.038 |
worry | -0.037 |
afar | -0.037 |
keeping | -0.036 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e+00 |
Pos logit contributions | |
argue | +0.054 |
elbows | +0.053 |
cle | +0.050 |
afar | +0.049 |
gy | +0.048 |
Neg logit contributions | |
can | -0.048 |
lic | -0.045 |
has | -0.045 |
is | -0.043 |
boards | -0.043 |
Token | garden |
Token ID | 11376 |
Feature activation | -1.80e+00 |
Pos logit contributions | |
lic | +0.021 |
can | +0.020 |
boards | +0.019 |
br | +0.018 |
has | +0.018 |
Neg logit contributions | |
argue | -0.022 |
elbows | -0.022 |
afar | -0.022 |
cle | -0.021 |
worry | -0.021 |
Token | ever |
Token ID | 1683 |
Feature activation | +3.93e+00 |
Pos logit contributions | |
lic | +0.034 |
can | +0.033 |
has | +0.031 |
br | +0.031 |
boards | +0.031 |
Neg logit contributions | |
gy | -0.034 |
argue | -0.034 |
elbows | -0.032 |
cle | -0.032 |
worry | -0.032 |
Token | since |
Token ID | 1201 |
Feature activation | -8.02e-01 |
Pos logit contributions | |
elbows | +0.069 |
argue | +0.069 |
cle | +0.063 |
ree | +0.061 |
gy | +0.060 |
Neg logit contributions | |
can | -0.091 |
has | -0.086 |
is | -0.083 |
lic | -0.082 |
living | -0.080 |
Token | . |
Token ID | 13 |
Feature activation | -1.68e+00 |
Pos logit contributions | |
lic | +0.013 |
can | +0.013 |
boards | +0.012 |
br | +0.012 |
has | +0.012 |
Neg logit contributions | |
argue | -0.018 |
elbows | -0.018 |
cle | -0.017 |
afar | -0.017 |
gy | -0.017 |
Token | with |
Token ID | 351 |
Feature activation | -1.85e+00 |
Pos logit contributions | |
can | +0.021 |
lic | +0.020 |
has | +0.020 |
helps | +0.019 |
boards | +0.019 |
Neg logit contributions | |
argue | -0.021 |
gy | -0.020 |
elbows | -0.020 |
ge | -0.020 |
afar | -0.019 |
Token | stars |
Token ID | 5788 |
Feature activation | +4.47e-01 |
Pos logit contributions | |
can | +0.039 |
has | +0.037 |
lic | +0.036 |
is | +0.035 |
br | +0.035 |
Neg logit contributions | |
argue | -0.035 |
elbows | -0.035 |
cle | -0.032 |
afar | -0.031 |
gy | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
ge | +0.008 |
argue | +0.008 |
gy | +0.008 |
worry | +0.007 |
elbows | +0.007 |
Neg logit contributions | |
can | -0.009 |
lic | -0.009 |
teaches | -0.009 |
has | -0.009 |
helps | -0.008 |
Token | |
Token ID | 220 |
Feature activation | -7.24e-01 |
Pos logit contributions | |
can | +0.032 |
br | +0.032 |
lic | +0.032 |
boards | +0.031 |
has | +0.031 |
Neg logit contributions | |
elbows | -0.027 |
argue | -0.027 |
ree | -0.026 |
weep | -0.025 |
gy | -0.025 |
Token |
|
Token ID | 198 |
Feature activation | -1.36e+00 |
Pos logit contributions | |
can | +0.012 |
has | +0.011 |
lic | +0.011 |
is | +0.011 |
br | +0.011 |
Neg logit contributions | |
argue | -0.016 |
elbows | -0.016 |
cle | -0.015 |
gy | -0.015 |
ree | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -1.40e+00 |
Pos logit contributions | |
can | +0.026 |
has | +0.024 |
boards | +0.023 |
is | +0.023 |
helps | +0.023 |
Neg logit contributions | |
argue | -0.026 |
elbows | -0.026 |
cle | -0.025 |
ree | -0.025 |
iver | -0.024 |
Token | As |
Token ID | 1722 |
Feature activation | -1.27e+00 |
Pos logit contributions | |
can | +0.031 |
has | +0.030 |
is | +0.029 |
boards | +0.028 |
helps | +0.028 |
Neg logit contributions | |
argue | -0.023 |
elbows | -0.022 |
cle | -0.022 |
ree | -0.021 |
iver | -0.020 |
Token | the |
Token ID | 262 |
Feature activation | -4.22e+00 |
Pos logit contributions | |
lic | +0.027 |
boards | +0.027 |
can | +0.027 |
has | +0.025 |
is | +0.025 |
Neg logit contributions | |
argue | -0.020 |
elbows | -0.020 |
cle | -0.019 |
worry | -0.019 |
aster | -0.019 |
Token | stars |
Token ID | 5788 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
can | +0.088 |
has | +0.082 |
lic | +0.082 |
is | +0.080 |
br | +0.077 |
Neg logit contributions | |
argue | -0.082 |
elbows | -0.079 |
cle | -0.075 |
gy | -0.072 |
weep | -0.071 |
Token | sh |
Token ID | 427 |
Feature activation | +1.53e+00 |
Pos logit contributions | |
can | +0.043 |
lic | +0.042 |
has | +0.041 |
boards | +0.040 |
is | +0.039 |
Neg logit contributions | |
argue | -0.043 |
elbows | -0.040 |
ge | -0.039 |
weep | -0.039 |
worry | -0.038 |
Token | ined |
Token ID | 1389 |
Feature activation | -2.72e+00 |
Pos logit contributions | |
argue | +0.038 |
elbows | +0.036 |
cle | +0.034 |
ge | +0.033 |
worry | +0.033 |
Neg logit contributions | |
can | -0.024 |
lic | -0.024 |
has | -0.022 |
is | -0.022 |
br | -0.021 |
Token | , |
Token ID | 11 |
Feature activation | +2.70e+00 |
Pos logit contributions | |
elbows | +0.051 |
argue | +0.049 |
cle | +0.048 |
afar | +0.048 |
cker | +0.047 |
Neg logit contributions | |
can | -0.023 |
is | -0.021 |
has | -0.020 |
of | -0.018 |
that | -0.018 |
Token | there |
Token ID | 612 |
Feature activation | -2.52e+00 |
Pos logit contributions | |
argue | +0.071 |
elbows | +0.070 |
cle | +0.067 |
ge | +0.065 |
gy | +0.065 |
Neg logit contributions | |
can | -0.039 |
has | -0.035 |
is | -0.034 |
lic | -0.032 |
helps | -0.031 |
Token | was |
Token ID | 373 |
Feature activation | +5.22e-01 |
Pos logit contributions | |
can | +0.027 |
has | +0.023 |
lic | +0.023 |
is | +0.021 |
br | +0.021 |
Neg logit contributions | |
argue | -0.074 |
elbows | -0.072 |
cle | -0.070 |
gy | -0.069 |
ge | -0.068 |
Token | a |
Token ID | 257 |
Feature activation | +9.85e-01 |
Pos logit contributions | |
argue | +0.018 |
ge | +0.018 |
elbows | +0.018 |
cle | +0.017 |
ree | +0.016 |
Neg logit contributions | |
can | -0.005 |
is | -0.004 |
that | -0.004 |
of | -0.004 |
has | -0.004 |
Token | little |
Token ID | 1310 |
Feature activation | +3.23e+00 |
Pos logit contributions | |
argue | +0.027 |
elbows | +0.027 |
ge | +0.025 |
cle | +0.025 |
gy | +0.024 |
Neg logit contributions | |
can | -0.014 |
has | -0.012 |
is | -0.011 |
lic | -0.011 |
living | -0.011 |
Token | bear |
Token ID | 6842 |
Feature activation | +1.01e+00 |
Pos logit contributions | |
argue | +0.073 |
elbows | +0.071 |
cle | +0.068 |
gy | +0.066 |
weep | +0.066 |
Neg logit contributions | |
can | -0.055 |
lic | -0.051 |
has | -0.051 |
is | -0.050 |
boards | -0.048 |
Token | named |
Token ID | 3706 |
Feature activation | +2.43e+00 |
Pos logit contributions | |
elbows | +0.022 |
argue | +0.021 |
mischief | +0.019 |
afar | +0.019 |
cle | +0.018 |
Neg logit contributions | |
can | -0.020 |
that | -0.020 |
of | -0.019 |
living | -0.019 |
is | -0.019 |
Token | Benny |
Token ID | 44275 |
Feature activation | +3.36e+00 |
Pos logit contributions | |
argue | +0.041 |
elbows | +0.039 |
gy | +0.038 |
cle | +0.038 |
ge | +0.036 |
Neg logit contributions | |
can | -0.055 |
has | -0.052 |
lic | -0.051 |
is | -0.051 |
br | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | +3.50e-01 |
Pos logit contributions | |
elbows | +0.104 |
argue | +0.100 |
cle | +0.094 |
afar | +0.093 |
mischief | +0.093 |
Neg logit contributions | |
can | -0.040 |
has | -0.035 |
is | -0.035 |
living | -0.034 |
that | -0.033 |
Token | Benny |
Token ID | 44275 |
Feature activation | +1.19e+00 |
Pos logit contributions | |
argue | +0.005 |
gy | +0.005 |
elbows | +0.005 |
weep | +0.004 |
worry | +0.004 |
Neg logit contributions | |
lic | -0.009 |
br | -0.008 |
can | -0.008 |
has | -0.008 |
is | -0.008 |
Token | was |
Token ID | 373 |
Feature activation | -1.91e+00 |
Pos logit contributions | |
argue | +0.034 |
elbows | +0.034 |
cle | +0.032 |
ge | +0.032 |
ree | +0.031 |
Neg logit contributions | |
can | -0.015 |
has | -0.014 |
is | -0.013 |
lic | -0.011 |
living | -0.011 |
Token | monkey |
Token ID | 21657 |
Feature activation | +1.72e-01 |
Pos logit contributions | |
argue | +0.001 |
elbows | +0.001 |
cle | +0.001 |
ge | +0.001 |
iver | +0.001 |
Neg logit contributions | |
can | -0.001 |
is | -0.001 |
has | -0.001 |
living | -0.000 |
helps | -0.000 |
Token | ! |
Token ID | 0 |
Feature activation | -2.77e-01 |
Pos logit contributions | |
argue | +0.005 |
elbows | +0.005 |
gy | +0.005 |
weep | +0.005 |
worry | +0.005 |
Neg logit contributions | |
lic | -0.002 |
can | -0.002 |
boards | -0.002 |
br | -0.002 |
has | -0.001 |
Token | It |
Token ID | 632 |
Feature activation | -3.63e+00 |
Pos logit contributions | |
can | +0.004 |
has | +0.003 |
lic | +0.003 |
is | +0.003 |
br | +0.003 |
Neg logit contributions | |
argue | -0.007 |
elbows | -0.007 |
cle | -0.007 |
gy | -0.007 |
ree | -0.007 |
Token | broke |
Token ID | 6265 |
Feature activation | -4.70e-01 |
Pos logit contributions | |
lic | +0.062 |
boards | +0.057 |
br | +0.055 |
lessly | +0.054 |
can | +0.053 |
Neg logit contributions | |
gy | -0.079 |
argue | -0.078 |
weep | -0.077 |
worry | -0.074 |
panic | -0.071 |
Token | !" |
Token ID | 2474 |
Feature activation | +1.04e-01 |
Pos logit contributions | |
can | +0.008 |
has | +0.007 |
is | +0.007 |
lic | +0.007 |
helps | +0.007 |
Neg logit contributions | |
argue | -0.011 |
elbows | -0.011 |
cle | -0.010 |
ge | -0.010 |
gy | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | +6.12e-01 |
Pos logit contributions | |
argue | +0.002 |
elbows | +0.002 |
cle | +0.002 |
ge | +0.002 |
ree | +0.002 |
Neg logit contributions | |
can | -0.002 |
that | -0.002 |
of | -0.002 |
is | -0.002 |
lic | -0.002 |
Token |
|
Token ID | 198 |
Feature activation | +4.10e-01 |
Pos logit contributions | |
argue | +0.016 |
elbows | +0.016 |
afar | +0.015 |
sing | +0.015 |
ieties | +0.015 |
Neg logit contributions | |
can | -0.009 |
lic | -0.008 |
is | -0.008 |
of | -0.008 |
that | -0.008 |
Token | His |
Token ID | 6653 |
Feature activation | -5.17e-01 |
Pos logit contributions | |
elbows | +0.008 |
argue | +0.008 |
afar | +0.008 |
sing | +0.008 |
weep | +0.007 |
Neg logit contributions | |
can | -0.008 |
lic | -0.008 |
that | -0.008 |
of | -0.008 |
is | -0.008 |
Token | mom |
Token ID | 1995 |
Feature activation | +7.84e-01 |
Pos logit contributions | |
can | +0.010 |
has | +0.010 |
is | +0.009 |
lic | +0.009 |
helps | +0.009 |
Neg logit contributions | |
elbows | -0.011 |
argue | -0.011 |
cle | -0.010 |
ge | -0.010 |
gy | -0.010 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.77e+00 |
Pos logit contributions | |
argue | +0.017 |
elbows | +0.016 |
cle | +0.015 |
gy | +0.015 |
weep | +0.015 |
Neg logit contributions | |
can | -0.014 |
has | -0.013 |
br | -0.013 |
is | -0.013 |
lic | -0.012 |
Token | . |
Token ID | 13 |
Feature activation | -9.07e-01 |
Pos logit contributions | |
can | +0.030 |
has | +0.028 |
lic | +0.028 |
is | +0.027 |
br | +0.027 |
Neg logit contributions | |
argue | -0.041 |
elbows | -0.039 |
cle | -0.037 |
gy | -0.037 |
ge | -0.037 |
Token | sky |
Token ID | 6766 |
Feature activation | -4.77e-01 |
Pos logit contributions | |
can | +0.005 |
lic | +0.005 |
has | +0.004 |
br | +0.004 |
is | +0.004 |
Neg logit contributions | |
elbows | -0.004 |
argue | -0.004 |
cle | -0.004 |
gy | -0.004 |
afar | -0.004 |
Token | . |
Token ID | 13 |
Feature activation | -2.58e-01 |
Pos logit contributions | |
can | +0.008 |
has | +0.007 |
lic | +0.007 |
is | +0.007 |
br | +0.007 |
Neg logit contributions | |
argue | -0.011 |
elbows | -0.011 |
cle | -0.010 |
gy | -0.010 |
ge | -0.010 |
Token | It |
Token ID | 632 |
Feature activation | -3.81e+00 |
Pos logit contributions | |
can | +0.004 |
has | +0.004 |
is | +0.004 |
lic | +0.003 |
helps | +0.003 |
Neg logit contributions | |
argue | -0.007 |
elbows | -0.006 |
cle | -0.006 |
ge | -0.006 |
gy | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | -2.39e+00 |
Pos logit contributions | |
boards | +0.056 |
lic | +0.054 |
can | +0.053 |
der | +0.053 |
lessly | +0.052 |
Neg logit contributions | |
argue | -0.088 |
gy | -0.084 |
weep | -0.079 |
cker | -0.079 |
panic | -0.078 |
Token | so |
Token ID | 523 |
Feature activation | +2.58e-01 |
Pos logit contributions | |
can | +0.035 |
has | +0.032 |
lic | +0.031 |
is | +0.030 |
br | +0.029 |
Neg logit contributions | |
argue | -0.061 |
elbows | -0.060 |
cle | -0.057 |
gy | -0.056 |
ge | -0.056 |
Token | amazed |
Token ID | 24562 |
Feature activation | -1.97e+00 |
Pos logit contributions | |
argue | +0.006 |
worry | +0.006 |
panic | +0.006 |
cle | +0.005 |
afar | +0.005 |
Neg logit contributions | |
can | -0.004 |
boards | -0.004 |
der | -0.004 |
wand | -0.004 |
br | -0.003 |
Token | that |
Token ID | 326 |
Feature activation | -2.57e+00 |
Pos logit contributions | |
can | +0.034 |
has | +0.031 |
lic | +0.030 |
is | +0.030 |
br | +0.029 |
Neg logit contributions | |
argue | -0.045 |
elbows | -0.044 |
cle | -0.042 |
gy | -0.041 |
ge | -0.041 |
Token | it |
Token ID | 340 |
Feature activation | -3.89e+00 |
Pos logit contributions | |
lic | +0.054 |
boards | +0.048 |
br | +0.046 |
can | +0.045 |
has | +0.044 |
Neg logit contributions | |
argue | -0.050 |
worry | -0.047 |
elbows | -0.047 |
afar | -0.045 |
weep | -0.045 |
Token | started |
Token ID | 2067 |
Feature activation | -3.31e-01 |
Pos logit contributions | |
br | +0.060 |
lic | +0.059 |
boards | +0.059 |
arl | +0.057 |
der | +0.057 |
Neg logit contributions | |
argue | -0.082 |
gy | -0.078 |
weep | -0.077 |
panic | -0.076 |
worry | -0.073 |
Token | to |
Token ID | 284 |
Feature activation | +3.62e+00 |
Pos logit contributions | |
can | +0.004 |
has | +0.004 |
is | +0.004 |
living | +0.004 |
of | +0.004 |
Neg logit contributions | |
elbows | -0.009 |
argue | -0.009 |
cle | -0.009 |
iver | -0.008 |
ge | -0.008 |
Token | jump |
Token ID | 4391 |
Feature activation | +2.46e-01 |
Pos logit contributions | |
argue | +0.072 |
elbows | +0.071 |
cle | +0.067 |
ge | +0.064 |
gy | +0.064 |
Neg logit contributions | |
can | -0.073 |
has | -0.068 |
is | -0.066 |
lic | -0.066 |
helps | -0.064 |
Token | they |
Token ID | 484 |
Feature activation | -1.38e+00 |
Pos logit contributions | |
argue | +0.025 |
elbows | +0.023 |
weep | +0.022 |
worry | +0.022 |
gy | +0.021 |
Neg logit contributions | |
lic | -0.020 |
br | -0.020 |
can | -0.020 |
has | -0.019 |
boards | -0.018 |
Token | said |
Token ID | 531 |
Feature activation | -4.01e+00 |
Pos logit contributions | |
br | +0.020 |
can | +0.020 |
lic | +0.020 |
has | +0.019 |
is | +0.019 |
Neg logit contributions | |
argue | -0.036 |
elbows | -0.033 |
weep | -0.032 |
worry | -0.031 |
gy | -0.031 |
Token | it |
Token ID | 340 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
lic | +0.064 |
br | +0.059 |
can | +0.057 |
has | +0.057 |
helps | +0.056 |
Neg logit contributions | |
argue | -0.093 |
worry | -0.086 |
elbows | -0.084 |
weep | -0.082 |
afar | -0.079 |
Token | wasn |
Token ID | 2492 |
Feature activation | +1.82e+00 |
Pos logit contributions | |
lic | +0.063 |
can | +0.059 |
br | +0.058 |
living | +0.055 |
lessly | +0.054 |
Neg logit contributions | |
argue | -0.117 |
gy | -0.116 |
elbows | -0.109 |
weep | -0.105 |
worry | -0.104 |
Token | 't |
Token ID | 470 |
Feature activation | +1.80e+00 |
Pos logit contributions | |
argue | +0.041 |
elbows | +0.040 |
cle | +0.038 |
gy | +0.037 |
ge | +0.037 |
Neg logit contributions | |
can | -0.033 |
has | -0.030 |
lic | -0.029 |
is | -0.029 |
br | -0.028 |
Token | special |
Token ID | 2041 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
argue | +0.044 |
elbows | +0.043 |
cle | +0.042 |
gy | +0.040 |
ge | +0.040 |
Neg logit contributions | |
can | -0.029 |
has | -0.026 |
lic | -0.025 |
is | -0.025 |
br | -0.024 |
Token | at |
Token ID | 379 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
argue | +0.031 |
elbows | +0.029 |
ge | +0.028 |
cle | +0.028 |
gy | +0.027 |
Neg logit contributions | |
can | -0.022 |
lic | -0.022 |
has | -0.021 |
is | -0.020 |
br | -0.019 |
Token | all |
Token ID | 477 |
Feature activation | +3.58e+00 |
Pos logit contributions | |
elbows | +0.086 |
argue | +0.086 |
cle | +0.085 |
ree | +0.082 |
afar | +0.081 |
Neg logit contributions | |
can | -0.019 |
is | -0.014 |
has | -0.014 |
that | -0.011 |
makes | -0.011 |
Token | . |
Token ID | 13 |
Feature activation | -7.27e-01 |
Pos logit contributions | |
argue | +0.082 |
elbows | +0.078 |
ge | +0.075 |
cle | +0.075 |
gy | +0.074 |
Neg logit contributions | |
can | -0.061 |
lic | -0.058 |
has | -0.055 |
br | -0.054 |
is | -0.053 |
Token | Lily |
Token ID | 20037 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
can | +0.012 |
has | +0.011 |
lic | +0.011 |
br | +0.011 |
is | +0.011 |
Neg logit contributions | |
argue | -0.016 |
elbows | -0.016 |
gy | -0.015 |
ree | -0.015 |
weep | -0.015 |
Token | felt |
Token ID | 2936 |
Feature activation | -4.35e+00 |
Pos logit contributions | |
can | +0.006 |
has | +0.005 |
is | +0.005 |
lic | +0.005 |
helps | +0.005 |
Neg logit contributions | |
argue | -0.010 |
elbows | -0.010 |
cle | -0.010 |
ge | -0.009 |
afar | -0.009 |
Token | continue |
Token ID | 2555 |
Feature activation | +1.39e+00 |
Pos logit contributions | |
argue | +0.034 |
elbows | +0.032 |
cle | +0.030 |
gy | +0.030 |
ge | +0.029 |
Neg logit contributions | |
can | -0.032 |
lic | -0.031 |
has | -0.031 |
is | -0.029 |
br | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
argue | +0.031 |
elbows | +0.030 |
cle | +0.029 |
ge | +0.028 |
gy | +0.028 |
Neg logit contributions | |
can | -0.025 |
has | -0.023 |
is | -0.022 |
lic | -0.022 |
helps | -0.021 |
Token | dance |
Token ID | 9280 |
Feature activation | -4.93e-01 |
Pos logit contributions | |
argue | +0.097 |
elbows | +0.094 |
cle | +0.089 |
gy | +0.085 |
ge | +0.085 |
Neg logit contributions | |
can | -0.115 |
has | -0.108 |
lic | -0.106 |
is | -0.105 |
helps | -0.101 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e+00 |
Pos logit contributions | |
lic | +0.009 |
can | +0.009 |
has | +0.008 |
helps | +0.008 |
is | +0.008 |
Neg logit contributions | |
argue | -0.010 |
elbows | -0.010 |
afar | -0.009 |
ge | -0.009 |
ree | -0.009 |
Token | So |
Token ID | 1406 |
Feature activation | -9.03e-01 |
Pos logit contributions | |
can | +0.025 |
has | +0.023 |
lic | +0.022 |
is | +0.022 |
br | +0.021 |
Neg logit contributions | |
argue | -0.037 |
elbows | -0.036 |
cle | -0.034 |
gy | -0.033 |
ge | -0.033 |
Token | the |
Token ID | 262 |
Feature activation | -4.37e+00 |
Pos logit contributions | |
can | +0.015 |
lic | +0.015 |
boards | +0.014 |
has | +0.014 |
br | +0.014 |
Neg logit contributions | |
argue | -0.021 |
elbows | -0.019 |
cle | -0.019 |
gy | -0.019 |
worry | -0.019 |
Token | little |
Token ID | 1310 |
Feature activation | -1.55e+00 |
Pos logit contributions | |
can | +0.081 |
lic | +0.076 |
has | +0.075 |
br | +0.073 |
is | +0.072 |
Neg logit contributions | |
argue | -0.094 |
elbows | -0.091 |
cle | -0.087 |
afar | -0.084 |
weep | -0.084 |
Token | girl |
Token ID | 2576 |
Feature activation | -9.22e-01 |
Pos logit contributions | |
can | +0.025 |
has | +0.023 |
lic | +0.023 |
is | +0.022 |
br | +0.021 |
Neg logit contributions | |
argue | -0.037 |
elbows | -0.036 |
cle | -0.034 |
gy | -0.034 |
ge | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -1.56e+00 |
Pos logit contributions | |
can | +0.016 |
lic | +0.015 |
has | +0.014 |
br | +0.014 |
boards | +0.014 |
Neg logit contributions | |
argue | -0.021 |
elbows | -0.019 |
cle | -0.019 |
gy | -0.018 |
weep | -0.018 |
Token | her |
Token ID | 607 |
Feature activation | -7.26e-01 |
Pos logit contributions | |
can | +0.029 |
has | +0.028 |
is | +0.027 |
that | +0.026 |
helps | +0.026 |
Neg logit contributions | |
argue | -0.033 |
elbows | -0.032 |
ge | -0.031 |
cle | -0.031 |
iver | -0.031 |
Token | dog |
Token ID | 3290 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
can | +0.018 |
has | +0.017 |
lic | +0.016 |
is | +0.016 |
br | +0.016 |
Neg logit contributions | |
argue | -0.012 |
elbows | -0.011 |
cle | -0.011 |
gy | -0.010 |
ge | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +3.64e+00 |
Pos logit contributions | |
elbows | +0.041 |
argue | +0.040 |
cle | +0.039 |
afar | +0.038 |
mischief | +0.038 |
Neg logit contributions | |
can | -0.019 |
is | -0.017 |
that | -0.017 |
has | -0.017 |
of | -0.017 |
Token | play |
Token ID | 711 |
Feature activation | +8.55e-02 |
Pos logit contributions | |
argue | +0.073 |
elbows | +0.071 |
cle | +0.067 |
gy | +0.065 |
ge | +0.064 |
Neg logit contributions | |
can | -0.073 |
has | -0.068 |
lic | -0.068 |
is | -0.066 |
br | -0.065 |
Token | together |
Token ID | 1978 |
Feature activation | +1.87e+00 |
Pos logit contributions | |
argue | +0.002 |
elbows | +0.002 |
cle | +0.002 |
afar | +0.002 |
gy | +0.002 |
Neg logit contributions | |
can | -0.001 |
lic | -0.001 |
has | -0.001 |
is | -0.001 |
br | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
argue | +0.044 |
elbows | +0.042 |
cle | +0.040 |
ge | +0.039 |
gy | +0.039 |
Neg logit contributions | |
can | -0.031 |
lic | -0.029 |
has | -0.029 |
is | -0.027 |
br | -0.027 |
Token | They |
Token ID | 1119 |
Feature activation | -2.11e+00 |
Pos logit contributions | |
can | +0.006 |
has | +0.006 |
is | +0.005 |
lic | +0.005 |
helps | +0.005 |
Neg logit contributions | |
argue | -0.018 |
elbows | -0.017 |
cle | -0.017 |
ge | -0.017 |
gy | -0.016 |
Token | said |
Token ID | 531 |
Feature activation | -4.09e+00 |
Pos logit contributions | |
can | +0.034 |
lic | +0.033 |
has | +0.032 |
is | +0.031 |
br | +0.031 |
Neg logit contributions | |
argue | -0.050 |
elbows | -0.048 |
cle | -0.045 |
gy | -0.045 |
weep | -0.044 |
Token | sorry |
Token ID | 7926 |
Feature activation | -3.07e-01 |
Pos logit contributions | |
lic | +0.077 |
can | +0.075 |
has | +0.072 |
boards | +0.069 |
br | +0.068 |
Neg logit contributions | |
argue | -0.086 |
elbows | -0.081 |
worry | -0.075 |
weep | -0.074 |
cle | -0.074 |
Token | to |
Token ID | 284 |
Feature activation | +1.04e+00 |
Pos logit contributions | |
lic | +0.006 |
br | +0.006 |
boards | +0.006 |
has | +0.006 |
can | +0.006 |
Neg logit contributions | |
argue | -0.006 |
ree | -0.005 |
gy | -0.005 |
elbows | -0.005 |
weep | -0.005 |
Token | their |
Token ID | 511 |
Feature activation | +8.49e-01 |
Pos logit contributions | |
elbows | +0.028 |
argue | +0.027 |
ge | +0.027 |
iver | +0.026 |
cle | +0.026 |
Neg logit contributions | |
can | -0.015 |
has | -0.013 |
is | -0.013 |
that | -0.013 |
makes | -0.012 |
Token | mom |
Token ID | 1995 |
Feature activation | +3.14e+00 |
Pos logit contributions | |
elbows | +0.018 |
argue | +0.018 |
ge | +0.017 |
iver | +0.017 |
cle | +0.017 |
Neg logit contributions | |
can | -0.017 |
has | -0.015 |
is | -0.015 |
living | -0.015 |
helps | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
argue | +0.055 |
gy | +0.051 |
cle | +0.050 |
worry | +0.049 |
ge | +0.049 |
Neg logit contributions | |
lic | -0.068 |
br | -0.066 |
can | -0.062 |
boards | -0.060 |
has | -0.059 |
Token | bar |
Token ID | 2318 |
Feature activation | +1.14e+00 |
Pos logit contributions | |
argue | +0.012 |
gy | +0.011 |
cle | +0.011 |
elbows | +0.011 |
Johnson | +0.011 |
Neg logit contributions | |
lic | -0.010 |
can | -0.010 |
has | -0.009 |
helps | -0.009 |
br | -0.009 |
Token | waiting |
Token ID | 4953 |
Feature activation | +2.29e-01 |
Pos logit contributions | |
argue | +0.021 |
ge | +0.020 |
cle | +0.020 |
gy | +0.019 |
cker | +0.019 |
Neg logit contributions | |
lic | -0.023 |
can | -0.022 |
br | -0.021 |
helps | -0.021 |
has | -0.020 |
Token | for |
Token ID | 329 |
Feature activation | -1.12e+00 |
Pos logit contributions | |
argue | +0.006 |
cle | +0.006 |
elbows | +0.006 |
ge | +0.005 |
gy | +0.005 |
Neg logit contributions | |
lic | -0.003 |
can | -0.003 |
br | -0.003 |
has | -0.003 |
helps | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | +3.76e+00 |
Pos logit contributions | |
can | +0.021 |
has | +0.020 |
is | +0.020 |
that | +0.019 |
living | +0.019 |
Neg logit contributions | |
argue | -0.024 |
elbows | -0.023 |
gy | -0.022 |
ree | -0.022 |
cle | -0.022 |
Token | ! |
Token ID | 0 |
Feature activation | +1.42e-01 |
Pos logit contributions | |
elbows | +0.091 |
argue | +0.090 |
cle | +0.087 |
ree | +0.086 |
afar | +0.085 |
Neg logit contributions | |
can | -0.062 |
has | -0.056 |
is | -0.056 |
living | -0.052 |
that | -0.052 |
Token | The |
Token ID | 383 |
Feature activation | -4.07e+00 |
Pos logit contributions | |
argue | +0.004 |
elbows | +0.004 |
cle | +0.004 |
ge | +0.004 |
afar | +0.003 |
Neg logit contributions | |
can | -0.002 |
has | -0.002 |
is | -0.002 |
lic | -0.002 |
of | -0.002 |
Token | little |
Token ID | 1310 |
Feature activation | -5.05e-01 |
Pos logit contributions | |
can | +0.070 |
lic | +0.067 |
has | +0.064 |
br | +0.062 |
is | +0.062 |
Neg logit contributions | |
argue | -0.090 |
elbows | -0.088 |
cle | -0.085 |
weep | -0.081 |
worry | -0.081 |
Token | girl |
Token ID | 2576 |
Feature activation | -3.85e-01 |
Pos logit contributions | |
can | +0.008 |
has | +0.007 |
is | +0.007 |
lic | +0.007 |
helps | +0.007 |
Neg logit contributions | |
argue | -0.012 |
elbows | -0.012 |
cle | -0.012 |
ge | -0.011 |
gy | -0.011 |
Token | had |
Token ID | 550 |
Feature activation | -2.18e+00 |
Pos logit contributions | |
can | +0.006 |
lic | +0.005 |
br | +0.005 |
boards | +0.005 |
has | +0.005 |
Neg logit contributions | |
argue | -0.010 |
elbows | -0.009 |
gy | -0.009 |
weep | -0.009 |
cle | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | +6.17e-02 |
Pos logit contributions | |
can | +0.041 |
lic | +0.039 |
has | +0.038 |
br | +0.037 |
is | +0.036 |
Neg logit contributions | |
argue | -0.045 |
elbows | -0.044 |
cle | -0.041 |
afar | -0.040 |
gy | -0.040 |
Token | suspicion |
Token ID | 15123 |
Feature activation | -2.16e+00 |
Pos logit contributions | |
argue | +0.002 |
elbows | +0.002 |
cle | +0.002 |
gy | +0.002 |
ge | +0.002 |
Neg logit contributions | |
can | -0.001 |
has | -0.001 |
lic | -0.001 |
is | -0.001 |
helps | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -2.46e-01 |
Pos logit contributions | |
lic | +0.054 |
can | +0.051 |
has | +0.048 |
boards | +0.047 |
br | +0.047 |
Neg logit contributions | |
argue | -0.054 |
cle | -0.051 |
elbows | -0.051 |
gy | -0.048 |
aster | -0.048 |
Token | But |
Token ID | 887 |
Feature activation | -9.11e-02 |
Pos logit contributions | |
lic | +0.005 |
boards | +0.005 |
can | +0.004 |
br | +0.004 |
box | +0.004 |
Neg logit contributions | |
cle | -0.005 |
elbows | -0.004 |
afar | -0.004 |
argue | -0.004 |
ree | -0.004 |
Token | you |
Token ID | 345 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
lic | +0.002 |
boards | +0.002 |
br | +0.002 |
lessly | +0.002 |
les | +0.002 |
Neg logit contributions | |
worry | -0.002 |
argue | -0.002 |
moderation | -0.001 |
cle | -0.001 |
afar | -0.001 |
Token | have |
Token ID | 423 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
argue | +0.023 |
weep | +0.020 |
elbows | +0.020 |
worry | +0.020 |
gy | +0.020 |
Neg logit contributions | |
lic | -0.019 |
boards | -0.018 |
br | -0.018 |
can | -0.018 |
living | -0.017 |
Token | to |
Token ID | 284 |
Feature activation | +4.01e+00 |
Pos logit contributions | |
lic | +0.030 |
can | +0.029 |
br | +0.027 |
boards | +0.027 |
has | +0.027 |
Neg logit contributions | |
argue | -0.034 |
elbows | -0.033 |
cle | -0.030 |
afar | -0.030 |
worry | -0.030 |
Token | write |
Token ID | 3551 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
argue | +0.077 |
elbows | +0.074 |
cle | +0.070 |
gy | +0.068 |
ge | +0.068 |
Neg logit contributions | |
can | -0.085 |
has | -0.079 |
lic | -0.077 |
is | -0.077 |
helps | -0.074 |
Token | on |
Token ID | 319 |
Feature activation | +3.01e+00 |
Pos logit contributions | |
lic | +0.067 |
can | +0.063 |
boards | +0.060 |
has | +0.060 |
br | +0.058 |
Neg logit contributions | |
argue | -0.080 |
elbows | -0.078 |
cle | -0.076 |
afar | -0.075 |
ree | -0.072 |
Token | the |
Token ID | 262 |
Feature activation | -1.08e+00 |
Pos logit contributions | |
argue | +0.067 |
elbows | +0.065 |
cle | +0.062 |
afar | +0.060 |
gy | +0.060 |
Neg logit contributions | |
can | -0.053 |
lic | -0.050 |
has | -0.049 |
is | -0.047 |
br | -0.046 |
Token | right |
Token ID | 826 |
Feature activation | +1.05e+00 |
Pos logit contributions | |
lic | +0.020 |
can | +0.018 |
br | +0.017 |
has | +0.017 |
helps | +0.016 |
Neg logit contributions | |
argue | -0.024 |
elbows | -0.023 |
cle | -0.022 |
weep | -0.021 |
worry | -0.021 |
Token | things |
Token ID | 1243 |
Feature activation | +6.88e-01 |
Pos logit contributions | |
argue | +0.020 |
elbows | +0.018 |
cle | +0.017 |
gy | +0.017 |
reason | +0.017 |
Neg logit contributions | |
lic | -0.023 |
can | -0.022 |
br | -0.021 |
boards | -0.021 |
has | -0.020 |
Token | . |
Token ID | 13 |
Feature activation | -7.69e-01 |
Pos logit contributions | |
argue | +0.013 |
ge | +0.012 |
aster | +0.011 |
cle | +0.011 |
elbows | +0.011 |
Neg logit contributions | |
lic | -0.015 |
br | -0.012 |
boards | -0.012 |
lid | -0.011 |
can | -0.011 |
Token | angry |
Token ID | 7954 |
Feature activation | +6.03e-01 |
Pos logit contributions | |
can | +0.058 |
has | +0.053 |
lic | +0.052 |
is | +0.052 |
boards | +0.050 |
Neg logit contributions | |
argue | -0.060 |
elbows | -0.058 |
cle | -0.054 |
gy | -0.053 |
ge | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | +1.38e+00 |
Pos logit contributions | |
argue | +0.009 |
elbows | +0.008 |
worry | +0.008 |
ge | +0.008 |
ree | +0.008 |
Neg logit contributions | |
lic | -0.014 |
br | -0.013 |
can | -0.012 |
contains | -0.012 |
lid | -0.012 |
Token | the |
Token ID | 262 |
Feature activation | -3.79e+00 |
Pos logit contributions | |
argue | +0.027 |
elbows | +0.025 |
weep | +0.024 |
worry | +0.024 |
gy | +0.023 |
Neg logit contributions | |
can | -0.028 |
br | -0.027 |
lic | -0.026 |
boards | -0.026 |
has | -0.026 |
Token | other |
Token ID | 584 |
Feature activation | +4.53e-01 |
Pos logit contributions | |
can | +0.064 |
lic | +0.061 |
has | +0.059 |
is | +0.058 |
br | +0.058 |
Neg logit contributions | |
argue | -0.088 |
elbows | -0.084 |
cle | -0.079 |
worry | -0.079 |
weep | -0.079 |
Token | girl |
Token ID | 2576 |
Feature activation | -1.21e-01 |
Pos logit contributions | |
argue | +0.010 |
elbows | +0.010 |
gy | +0.009 |
ge | +0.009 |
cle | +0.009 |
Neg logit contributions | |
can | -0.008 |
lic | -0.008 |
has | -0.007 |
br | -0.007 |
is | -0.007 |
Token | told |
Token ID | 1297 |
Feature activation | -3.33e+00 |
Pos logit contributions | |
can | +0.002 |
has | +0.002 |
is | +0.001 |
lic | +0.001 |
helps | +0.001 |
Neg logit contributions | |
argue | -0.003 |
elbows | -0.003 |
cle | -0.003 |
ge | -0.003 |
gy | -0.003 |
Token | her |
Token ID | 607 |
Feature activation | +5.74e-01 |
Pos logit contributions | |
can | +0.071 |
is | +0.065 |
has | +0.065 |
that | +0.063 |
helps | +0.063 |
Neg logit contributions | |
argue | -0.063 |
elbows | -0.063 |
cle | -0.061 |
ge | -0.058 |
gy | -0.057 |
Token | that |
Token ID | 326 |
Feature activation | -2.65e+00 |
Pos logit contributions | |
argue | +0.015 |
worry | +0.014 |
weep | +0.013 |
elbows | +0.013 |
gy | +0.013 |
Neg logit contributions | |
lic | -0.007 |
can | -0.007 |
br | -0.007 |
has | -0.007 |
boards | -0.007 |
Token | she |
Token ID | 673 |
Feature activation | -6.13e-01 |
Pos logit contributions | |
can | +0.041 |
lic | +0.038 |
has | +0.038 |
is | +0.036 |
br | +0.035 |
Neg logit contributions | |
argue | -0.065 |
elbows | -0.063 |
cle | -0.060 |
ge | -0.059 |
gy | -0.059 |
Token | was |
Token ID | 373 |
Feature activation | -2.05e+00 |
Pos logit contributions | |
lic | +0.009 |
br | +0.009 |
can | +0.008 |
boards | +0.008 |
living | +0.008 |
Neg logit contributions | |
argue | -0.015 |
gy | -0.014 |
elbows | -0.014 |
weep | -0.014 |
worry | -0.013 |
Token | sorry |
Token ID | 7926 |
Feature activation | +1.03e+00 |
Pos logit contributions | |
can | +0.035 |
lic | +0.032 |
has | +0.032 |
is | +0.031 |
boards | +0.030 |
Neg logit contributions | |
argue | -0.047 |
elbows | -0.046 |
cle | -0.043 |
gy | -0.043 |
afar | -0.042 |