Token | his |
Token ID | 465 |
Feature activation | +2.12e-02 |
Pos logit contributions | |
bur | +0.118 |
ppa | +0.116 |
rying | +0.116 |
gie | +0.114 |
ior | +0.114 |
Neg logit contributions | |
vows | -0.070 |
prize | -0.067 |
great | -0.064 |
trophy | -0.061 |
are | -0.060 |
Token | head |
Token ID | 1182 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
rying | +0.044 |
bur | +0.044 |
ppa | +0.043 |
i | +0.041 |
ind | +0.041 |
Neg logit contributions | |
vows | -0.035 |
prize | -0.031 |
trophy | -0.031 |
contest | -0.030 |
apy | -0.028 |
Token | out |
Token ID | 503 |
Feature activation | +5.47e-03 |
Pos logit contributions | |
bur | +0.027 |
rying | +0.026 |
ppa | +0.026 |
ind | +0.025 |
i | +0.025 |
Neg logit contributions | |
vows | -0.025 |
prize | -0.022 |
contest | -0.022 |
trophy | -0.022 |
cakes | -0.021 |
Token | of |
Token ID | 286 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
bur | +0.011 |
rying | +0.011 |
ppa | +0.011 |
i | +0.011 |
ind | +0.011 |
Neg logit contributions | |
vows | -0.009 |
prize | -0.008 |
contest | -0.008 |
trophy | -0.008 |
cakes | -0.008 |
Token | his |
Token ID | 465 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
ppa | +0.061 |
rying | +0.061 |
bur | +0.060 |
ety | +0.058 |
i | +0.058 |
Neg logit contributions | |
vows | -0.037 |
prize | -0.035 |
contest | -0.033 |
trophy | -0.033 |
apy | -0.031 |
Token | bur |
Token ID | 4356 |
Feature activation | +1.24e-01 |
Pos logit contributions | |
rying | +0.066 |
bur | +0.066 |
ppa | +0.065 |
ety | +0.061 |
i | +0.060 |
Neg logit contributions | |
vows | -0.058 |
prize | -0.053 |
trophy | -0.052 |
contest | -0.051 |
apy | -0.048 |
Token | row |
Token ID | 808 |
Feature activation | +5.43e-02 |
Pos logit contributions | |
ior | +0.148 |
ppa | +0.129 |
ety | +0.129 |
ind | +0.124 |
Owl | +0.124 |
Neg logit contributions | |
ades | -0.243 |
uits | -0.238 |
vows | -0.221 |
ade | -0.217 |
are | -0.213 |
Token | and |
Token ID | 290 |
Feature activation | +2.81e-02 |
Pos logit contributions | |
bur | +0.116 |
ppa | +0.113 |
ind | +0.113 |
rying | +0.113 |
ior | +0.111 |
Neg logit contributions | |
vows | -0.079 |
case | -0.071 |
cakes | -0.071 |
prize | -0.069 |
contest | -0.069 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
bur | +0.056 |
rying | +0.055 |
ppa | +0.054 |
ind | +0.054 |
ety | +0.052 |
Neg logit contributions | |
vows | -0.049 |
prize | -0.043 |
apy | -0.042 |
trophy | -0.042 |
contest | -0.041 |
Token | something |
Token ID | 1223 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
bur | +0.049 |
rying | +0.049 |
ppa | +0.048 |
ind | +0.046 |
ety | +0.046 |
Neg logit contributions | |
vows | -0.030 |
prize | -0.026 |
trophy | -0.025 |
contest | -0.025 |
apy | -0.025 |
Token | new |
Token ID | 649 |
Feature activation | +1.60e-02 |
Pos logit contributions | |
vows | +0.046 |
Prize | +0.039 |
contest | +0.038 |
prize | +0.038 |
cakes | +0.038 |
Neg logit contributions | |
rying | -0.054 |
i | -0.053 |
bur | -0.053 |
ind | -0.052 |
ppa | -0.051 |
Token | who |
Token ID | 508 |
Feature activation | +6.54e-03 |
Pos logit contributions | |
bur | +0.091 |
rying | +0.087 |
ppa | +0.085 |
ior | +0.084 |
ind | +0.081 |
Neg logit contributions | |
contest | -0.081 |
vows | -0.080 |
prize | -0.078 |
trophy | -0.077 |
case | -0.076 |
Token | lived |
Token ID | 5615 |
Feature activation | +2.95e-02 |
Pos logit contributions | |
bur | +0.014 |
rying | +0.014 |
ppa | +0.014 |
i | +0.014 |
ind | +0.014 |
Neg logit contributions | |
vows | -0.010 |
prize | -0.009 |
contest | -0.008 |
trophy | -0.008 |
apy | -0.008 |
Token | in |
Token ID | 287 |
Feature activation | +4.26e-03 |
Pos logit contributions | |
bur | +0.059 |
ppa | +0.058 |
ior | +0.058 |
gie | +0.056 |
i | +0.056 |
Neg logit contributions | |
vows | -0.046 |
contest | -0.045 |
prize | -0.043 |
trophy | -0.042 |
apy | -0.041 |
Token | his |
Token ID | 465 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
bur | +0.010 |
rying | +0.010 |
ppa | +0.010 |
i | +0.009 |
ind | +0.009 |
Neg logit contributions | |
vows | -0.006 |
prize | -0.005 |
contest | -0.005 |
trophy | -0.005 |
cakes | -0.005 |
Token | cozy |
Token ID | 37438 |
Feature activation | +7.81e-02 |
Pos logit contributions | |
rying | +0.082 |
ppa | +0.078 |
bur | +0.077 |
gie | +0.072 |
ener | +0.072 |
Neg logit contributions | |
vows | -0.068 |
prize | -0.063 |
contest | -0.062 |
tea | -0.060 |
trophy | -0.060 |
Token | bur |
Token ID | 4356 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
rying | +0.140 |
bur | +0.131 |
ppa | +0.130 |
eking | +0.123 |
ior | +0.119 |
Neg logit contributions | |
vows | -0.147 |
tea | -0.137 |
prize | -0.135 |
team | -0.134 |
lot | -0.132 |
Token | row |
Token ID | 808 |
Feature activation | +7.41e-02 |
Pos logit contributions | |
ior | +0.159 |
fred | +0.130 |
Tooth | +0.130 |
ppa | +0.129 |
bur | +0.128 |
Neg logit contributions | |
ades | -0.233 |
vows | -0.214 |
uits | -0.214 |
ade | -0.206 |
case | -0.201 |
Token | . |
Token ID | 13 |
Feature activation | +1.72e-02 |
Pos logit contributions | |
bur | +0.171 |
ior | +0.169 |
ppa | +0.163 |
rying | +0.159 |
gie | +0.159 |
Neg logit contributions | |
vows | -0.089 |
case | -0.088 |
contest | -0.082 |
trophy | -0.082 |
prize | -0.080 |
Token | He |
Token ID | 679 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
rying | +0.039 |
bur | +0.038 |
ppa | +0.037 |
i | +0.036 |
ind | +0.036 |
Neg logit contributions | |
vows | -0.025 |
prize | -0.022 |
contest | -0.022 |
trophy | -0.022 |
cakes | -0.021 |
Token | loved |
Token ID | 6151 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
rying | +0.068 |
bur | +0.068 |
ppa | +0.065 |
ind | +0.062 |
ior | +0.062 |
Neg logit contributions | |
vows | -0.038 |
prize | -0.030 |
contest | -0.029 |
apy | -0.029 |
trophy | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | +2.62e-04 |
Pos logit contributions | |
ppa | +0.063 |
rying | +0.062 |
bur | +0.061 |
cker | +0.059 |
ener | +0.058 |
Neg logit contributions | |
vows | -0.044 |
prize | -0.041 |
trophy | -0.039 |
contest | -0.039 |
tea | -0.038 |
Token | to |
Token ID | 284 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
bur | +0.063 |
ppa | +0.062 |
ind | +0.061 |
rying | +0.061 |
ior | +0.059 |
Neg logit contributions | |
vows | -0.039 |
prize | -0.036 |
contest | -0.035 |
trophy | -0.035 |
joke | -0.033 |
Token | venture |
Token ID | 13189 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
vows | +0.022 |
cakes | +0.019 |
prize | +0.019 |
trophy | +0.019 |
contest | +0.019 |
Neg logit contributions | |
bur | -0.032 |
rying | -0.031 |
ppa | -0.030 |
i | -0.030 |
ind | -0.029 |
Token | out |
Token ID | 503 |
Feature activation | +4.81e-02 |
Pos logit contributions | |
ppa | +0.103 |
bur | +0.101 |
gie | +0.097 |
ior | +0.097 |
ind | +0.097 |
Neg logit contributions | |
contest | -0.062 |
prize | -0.060 |
tea | -0.058 |
vows | -0.057 |
are | -0.053 |
Token | from |
Token ID | 422 |
Feature activation | +5.70e-02 |
Pos logit contributions | |
ppa | +0.120 |
bur | +0.118 |
ior | +0.113 |
ind | +0.111 |
ety | +0.110 |
Neg logit contributions | |
contest | -0.055 |
prize | -0.052 |
are | -0.051 |
tea | -0.051 |
apy | -0.049 |
Token | his |
Token ID | 465 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
ppa | +0.153 |
bur | +0.137 |
i | +0.135 |
rying | +0.135 |
ety | +0.135 |
Neg logit contributions | |
contest | -0.065 |
prize | -0.064 |
tea | -0.058 |
festival | -0.056 |
trophy | -0.055 |
Token | bur |
Token ID | 4356 |
Feature activation | +1.22e-01 |
Pos logit contributions | |
rying | +0.072 |
ppa | +0.071 |
bur | +0.067 |
cker | +0.066 |
ior | +0.066 |
Neg logit contributions | |
prize | -0.080 |
vows | -0.079 |
tea | -0.075 |
contest | -0.074 |
third | -0.074 |
Token | row |
Token ID | 808 |
Feature activation | +6.77e-02 |
Pos logit contributions | |
ior | +0.166 |
ppa | +0.145 |
bruised | +0.141 |
pless | +0.138 |
eled | +0.137 |
Neg logit contributions | |
ades | -0.214 |
ade | -0.208 |
uits | -0.208 |
parties | -0.189 |
br | -0.187 |
Token | and |
Token ID | 290 |
Feature activation | +4.05e-02 |
Pos logit contributions | |
ior | +0.168 |
ind | +0.163 |
bur | +0.160 |
ppa | +0.159 |
gie | +0.154 |
Neg logit contributions | |
case | -0.073 |
contest | -0.072 |
uits | -0.065 |
cakes | -0.063 |
vows | -0.063 |
Token | explore |
Token ID | 7301 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
ind | +0.099 |
ppa | +0.098 |
bur | +0.098 |
rying | +0.095 |
ior | +0.093 |
Neg logit contributions | |
vows | -0.050 |
prize | -0.046 |
celebrate | -0.043 |
contest | -0.043 |
are | -0.043 |
Token | the |
Token ID | 262 |
Feature activation | +7.83e-02 |
Pos logit contributions | |
ppa | +0.060 |
bur | +0.059 |
rying | +0.056 |
ety | +0.056 |
cker | +0.055 |
Neg logit contributions | |
vows | -0.028 |
prize | -0.027 |
contest | -0.026 |
trophy | -0.025 |
are | -0.025 |
Token | forest |
Token ID | 8222 |
Feature activation | +1.95e-02 |
Pos logit contributions | |
ppa | +0.180 |
ior | +0.166 |
cker | +0.165 |
owing | +0.164 |
rying | +0.163 |
Neg logit contributions | |
great | -0.117 |
lot | -0.115 |
funny | -0.104 |
big | -0.102 |
tea | -0.097 |
Token | N |
Token ID | 45 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
vows | +0.000 |
prize | +0.000 |
contest | +0.000 |
trophy | +0.000 |
cakes | +0.000 |
Neg logit contributions | |
bur | -0.000 |
rying | -0.000 |
ppa | -0.000 |
ind | -0.000 |
i | -0.000 |
Token | ina |
Token ID | 1437 |
Feature activation | +1.27e-02 |
Pos logit contributions | |
bur | +0.036 |
rying | +0.034 |
ppa | +0.033 |
ind | +0.032 |
gie | +0.031 |
Neg logit contributions | |
vows | -0.039 |
prize | -0.033 |
trophy | -0.033 |
contest | -0.033 |
cakes | -0.033 |
Token | was |
Token ID | 373 |
Feature activation | +3.30e-03 |
Pos logit contributions | |
bur | +0.028 |
rying | +0.027 |
ppa | +0.027 |
ind | +0.026 |
i | +0.026 |
Neg logit contributions | |
vows | -0.020 |
prize | -0.017 |
contest | -0.017 |
trophy | -0.017 |
cakes | -0.016 |
Token | panic |
Token ID | 13619 |
Feature activation | -8.05e-04 |
Pos logit contributions | |
bur | +0.006 |
rying | +0.006 |
ppa | +0.006 |
i | +0.006 |
ind | +0.006 |
Neg logit contributions | |
vows | -0.006 |
prize | -0.005 |
contest | -0.005 |
trophy | -0.005 |
cakes | -0.005 |
Token | - |
Token ID | 12 |
Feature activation | +5.36e-02 |
Pos logit contributions | |
vows | +0.002 |
prize | +0.001 |
contest | +0.001 |
trophy | +0.001 |
cakes | +0.001 |
Neg logit contributions | |
rying | -0.001 |
bur | -0.001 |
ppa | -0.001 |
i | -0.001 |
ind | -0.001 |
Token | str |
Token ID | 2536 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
ior | +0.099 |
bur | +0.098 |
ppa | +0.094 |
ind | +0.093 |
gie | +0.092 |
Neg logit contributions | |
apy | -0.082 |
cakes | -0.081 |
contest | -0.078 |
case | -0.076 |
vows | -0.074 |
Token | icken |
Token ID | 5973 |
Feature activation | +2.46e-02 |
Pos logit contributions | |
ior | +0.155 |
axe | +0.147 |
oscope | +0.140 |
seen | +0.139 |
since | +0.135 |
Neg logit contributions | |
ades | -0.214 |
vows | -0.199 |
� | -0.197 |
apy | -0.188 |
ics | -0.182 |
Token | . |
Token ID | 13 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
bur | +0.050 |
rying | +0.049 |
ppa | +0.049 |
ind | +0.047 |
i | +0.046 |
Neg logit contributions | |
vows | -0.041 |
prize | -0.037 |
contest | -0.036 |
trophy | -0.036 |
cakes | -0.035 |
Token | She |
Token ID | 1375 |
Feature activation | +3.09e-02 |
Pos logit contributions | |
bur | +0.044 |
rying | +0.043 |
ppa | +0.043 |
ind | +0.041 |
i | +0.041 |
Neg logit contributions | |
vows | -0.024 |
contest | -0.020 |
prize | -0.020 |
trophy | -0.019 |
apy | -0.019 |
Token | screamed |
Token ID | 25421 |
Feature activation | -1.23e-02 |
Pos logit contributions | |
bur | +0.068 |
rying | +0.067 |
ppa | +0.065 |
ind | +0.063 |
ior | +0.061 |
Neg logit contributions | |
vows | -0.048 |
apy | -0.041 |
prize | -0.040 |
joke | -0.039 |
contest | -0.039 |
Token | for |
Token ID | 329 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
vows | +0.025 |
prize | +0.023 |
contest | +0.023 |
trophy | +0.023 |
cakes | +0.022 |
Neg logit contributions | |
rying | -0.020 |
bur | -0.020 |
ppa | -0.020 |
i | -0.019 |
ind | -0.019 |
Token | Benny |
Token ID | 44275 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
bur | +0.033 |
rying | +0.033 |
ppa | +0.033 |
i | +0.032 |
ind | +0.032 |
Neg logit contributions | |
vows | -0.026 |
prize | -0.024 |
trophy | -0.024 |
contest | -0.024 |
apy | -0.023 |
Token | lived |
Token ID | 5615 |
Feature activation | +3.11e-02 |
Pos logit contributions | |
rying | +0.085 |
bur | +0.084 |
ppa | +0.081 |
ener | +0.078 |
ind | +0.077 |
Neg logit contributions | |
vows | -0.039 |
are | -0.031 |
joke | -0.031 |
case | -0.031 |
trophy | -0.031 |
Token | in |
Token ID | 287 |
Feature activation | +1.26e-02 |
Pos logit contributions | |
bur | +0.065 |
ppa | +0.065 |
ior | +0.064 |
gie | +0.062 |
i | +0.062 |
Neg logit contributions | |
contest | -0.045 |
vows | -0.044 |
prize | -0.043 |
trophy | -0.041 |
apy | -0.040 |
Token | a |
Token ID | 257 |
Feature activation | +1.42e-02 |
Pos logit contributions | |
rying | +0.031 |
ppa | +0.031 |
bur | +0.030 |
i | +0.029 |
ind | +0.029 |
Neg logit contributions | |
vows | -0.015 |
prize | -0.014 |
contest | -0.014 |
trophy | -0.014 |
apy | -0.013 |
Token | cozy |
Token ID | 37438 |
Feature activation | +6.54e-02 |
Pos logit contributions | |
rying | +0.033 |
bur | +0.033 |
ppa | +0.033 |
i | +0.032 |
gie | +0.031 |
Neg logit contributions | |
vows | -0.019 |
contest | -0.017 |
prize | -0.017 |
trophy | -0.016 |
apy | -0.015 |
Token | bur |
Token ID | 4356 |
Feature activation | +1.18e-01 |
Pos logit contributions | |
rying | +0.128 |
bur | +0.120 |
ppa | +0.117 |
eking | +0.116 |
cker | +0.110 |
Neg logit contributions | |
vows | -0.109 |
team | -0.106 |
prize | -0.106 |
lot | -0.104 |
tea | -0.104 |
Token | row |
Token ID | 808 |
Feature activation | +7.96e-02 |
Pos logit contributions | |
ior | +0.156 |
shadow | +0.139 |
ppa | +0.130 |
gie | +0.129 |
Tooth | +0.127 |
Neg logit contributions | |
ade | -0.205 |
uits | -0.203 |
ades | -0.203 |
tea | -0.194 |
case | -0.192 |
Token | with |
Token ID | 351 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
ior | +0.183 |
bur | +0.181 |
ppa | +0.175 |
gie | +0.171 |
umper | +0.166 |
Neg logit contributions | |
case | -0.100 |
contest | -0.100 |
trophy | -0.091 |
prize | -0.088 |
vows | -0.087 |
Token | his |
Token ID | 465 |
Feature activation | +3.57e-02 |
Pos logit contributions | |
rying | +0.023 |
bur | +0.023 |
ppa | +0.023 |
i | +0.022 |
ind | +0.022 |
Neg logit contributions | |
vows | -0.015 |
prize | -0.013 |
contest | -0.013 |
trophy | -0.013 |
apy | -0.012 |
Token | family |
Token ID | 1641 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
rying | +0.083 |
ppa | +0.079 |
bur | +0.078 |
ior | +0.077 |
umper | +0.075 |
Neg logit contributions | |
vows | -0.050 |
prize | -0.048 |
trophy | -0.044 |
lot | -0.043 |
contest | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +1.10e-02 |
Pos logit contributions | |
rying | +0.073 |
bur | +0.073 |
ppa | +0.073 |
ior | +0.069 |
ind | +0.069 |
Neg logit contributions | |
vows | -0.045 |
trophy | -0.043 |
prize | -0.043 |
contest | -0.041 |
tea | -0.039 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.61e-02 |
Pos logit contributions | |
bur | +0.016 |
rying | +0.016 |
ppa | +0.016 |
i | +0.015 |
ind | +0.015 |
Neg logit contributions | |
vows | -0.011 |
prize | -0.010 |
contest | -0.009 |
trophy | -0.009 |
cakes | -0.009 |
Token | called |
Token ID | 1444 |
Feature activation | +2.67e-03 |
Pos logit contributions | |
rying | +0.098 |
ind | +0.097 |
bur | +0.095 |
ior | +0.093 |
cker | +0.092 |
Neg logit contributions | |
vows | -0.062 |
were | -0.059 |
contest | -0.058 |
cakes | -0.057 |
are | -0.057 |
Token | out |
Token ID | 503 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
i | +0.005 |
ind | +0.005 |
Neg logit contributions | |
vows | -0.004 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
cakes | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | +2.90e-02 |
Pos logit contributions | |
vows | +0.037 |
trophy | +0.034 |
prize | +0.033 |
contest | +0.033 |
cakes | +0.033 |
Neg logit contributions | |
rying | -0.029 |
i | -0.027 |
bur | -0.027 |
ind | -0.027 |
ppa | -0.027 |
Token | " |
Token ID | 366 |
Feature activation | +7.14e-02 |
Pos logit contributions | |
bur | +0.087 |
rying | +0.085 |
ppa | +0.085 |
ind | +0.084 |
cker | +0.082 |
Neg logit contributions | |
vows | -0.019 |
apy | -0.014 |
contest | -0.013 |
prize | -0.012 |
cakes | -0.012 |
Token | Mill |
Token ID | 22603 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
ppa | +0.133 |
rying | +0.132 |
cker | +0.132 |
asured | +0.131 |
ishing | +0.129 |
Neg logit contributions | |
Everyone | -0.100 |
Happy | -0.098 |
vows | -0.094 |
were | -0.094 |
Mine | -0.093 |
Token | ie |
Token ID | 494 |
Feature activation | +9.05e-03 |
Pos logit contributions | |
oscope | +0.207 |
territory | +0.192 |
ior | +0.186 |
crank | +0.181 |
cker | +0.181 |
Neg logit contributions | |
tea | -0.135 |
are | -0.133 |
parties | -0.124 |
were | -0.124 |
they | -0.123 |
Token | , |
Token ID | 11 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
bur | +0.021 |
rying | +0.021 |
ppa | +0.020 |
ind | +0.020 |
i | +0.020 |
Neg logit contributions | |
vows | -0.013 |
prize | -0.011 |
contest | -0.011 |
trophy | -0.011 |
cakes | -0.010 |
Token | come |
Token ID | 1282 |
Feature activation | +4.01e-02 |
Pos logit contributions | |
bur | +0.033 |
ppa | +0.033 |
rying | +0.032 |
ind | +0.031 |
i | +0.031 |
Neg logit contributions | |
vows | -0.023 |
prize | -0.021 |
contest | -0.020 |
trophy | -0.020 |
are | -0.019 |
Token | home |
Token ID | 1363 |
Feature activation | +3.13e-02 |
Pos logit contributions | |
ppa | +0.083 |
bur | +0.080 |
cker | +0.077 |
i | +0.076 |
ior | +0.075 |
Neg logit contributions | |
vows | -0.061 |
prize | -0.059 |
celebrate | -0.059 |
blast | -0.057 |
contest | -0.056 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.01e-02 |
Pos logit contributions | |
bur | +0.063 |
ppa | +0.062 |
rying | +0.059 |
cker | +0.059 |
gie | +0.058 |
Neg logit contributions | |
vows | -0.051 |
prize | -0.047 |
contest | -0.046 |
cakes | -0.044 |
trophy | -0.044 |
Token | was |
Token ID | 373 |
Feature activation | -1.93e-03 |
Pos logit contributions | |
vows | +0.027 |
prize | +0.023 |
trophy | +0.022 |
contest | +0.021 |
Prize | +0.021 |
Neg logit contributions | |
rying | -0.055 |
bur | -0.055 |
i | -0.054 |
ppa | -0.053 |
ety | -0.052 |
Token | struggling |
Token ID | 9648 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
vows | +0.004 |
prize | +0.003 |
trophy | +0.003 |
contest | +0.003 |
cakes | +0.003 |
Neg logit contributions | |
bur | -0.004 |
rying | -0.004 |
ppa | -0.004 |
i | -0.003 |
ind | -0.003 |
Token | . |
Token ID | 13 |
Feature activation | +3.48e-02 |
Pos logit contributions | |
bur | +0.075 |
ppa | +0.074 |
ior | +0.071 |
rying | +0.070 |
ind | +0.069 |
Neg logit contributions | |
vows | -0.045 |
contest | -0.045 |
prize | -0.044 |
trophy | -0.043 |
case | -0.042 |
Token |
|
Token ID | 198 |
Feature activation | +2.82e-02 |
Pos logit contributions | |
rying | +0.095 |
ppa | +0.094 |
bur | +0.093 |
ind | +0.092 |
i | +0.089 |
Neg logit contributions | |
vows | -0.032 |
Everyone | -0.031 |
apy | -0.030 |
cakes | -0.029 |
contest | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +3.34e-02 |
Pos logit contributions | |
rying | +0.077 |
bur | +0.074 |
ppa | +0.074 |
i | +0.073 |
ind | +0.071 |
Neg logit contributions | |
vows | -0.026 |
apy | -0.023 |
contest | -0.023 |
prize | -0.023 |
case | -0.022 |
Token | Mill |
Token ID | 22603 |
Feature activation | +1.16e-01 |
Pos logit contributions | |
bur | +0.058 |
rying | +0.057 |
ppa | +0.054 |
i | +0.053 |
ior | +0.052 |
Neg logit contributions | |
vows | -0.061 |
apy | -0.061 |
case | -0.058 |
contest | -0.058 |
Everyone | -0.058 |
Token | ie |
Token ID | 494 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
property | +0.215 |
territory | +0.211 |
spine | +0.208 |
rying | +0.206 |
shadow | +0.201 |
Neg logit contributions | |
were | -0.134 |
vows | -0.125 |
are | -0.115 |
ade | -0.110 |
tea | -0.108 |
Token | tried |
Token ID | 3088 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
bur | +0.139 |
rying | +0.133 |
ind | +0.124 |
ppa | +0.123 |
umper | +0.122 |
Neg logit contributions | |
vows | -0.081 |
case | -0.074 |
contest | -0.071 |
apy | -0.070 |
were | -0.067 |
Token | to |
Token ID | 284 |
Feature activation | +8.96e-03 |
Pos logit contributions | |
bur | +0.025 |
rying | +0.025 |
ppa | +0.025 |
ind | +0.024 |
i | +0.024 |
Neg logit contributions | |
vows | -0.022 |
prize | -0.020 |
contest | -0.020 |
trophy | -0.020 |
cakes | -0.019 |
Token | reach |
Token ID | 3151 |
Feature activation | +1.78e-02 |
Pos logit contributions | |
bur | +0.019 |
rying | +0.019 |
ppa | +0.019 |
ind | +0.018 |
i | +0.018 |
Neg logit contributions | |
vows | -0.014 |
prize | -0.012 |
contest | -0.012 |
trophy | -0.012 |
apy | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -1.50e-02 |
Pos logit contributions | |
ppa | +0.040 |
rying | +0.039 |
bur | +0.039 |
ind | +0.038 |
i | +0.037 |
Neg logit contributions | |
vows | -0.025 |
prize | -0.023 |
contest | -0.023 |
trophy | -0.022 |
apy | -0.021 |
Token | there |
Token ID | 612 |
Feature activation | +2.37e-02 |
Pos logit contributions | |
ppa | +0.074 |
bur | +0.073 |
rying | +0.071 |
ior | +0.070 |
ety | +0.068 |
Neg logit contributions | |
contest | -0.066 |
vows | -0.066 |
prize | -0.066 |
trophy | -0.064 |
festival | -0.059 |
Token | ?", |
Token ID | 35379 |
Feature activation | +3.58e-02 |
Pos logit contributions | |
ppa | +0.040 |
rying | +0.040 |
bur | +0.040 |
ind | +0.039 |
i | +0.038 |
Neg logit contributions | |
vows | -0.045 |
prize | -0.043 |
contest | -0.043 |
trophy | -0.042 |
cakes | -0.040 |
Token | asked |
Token ID | 1965 |
Feature activation | +2.84e-02 |
Pos logit contributions | |
rying | +0.078 |
bur | +0.078 |
ind | +0.075 |
ppa | +0.075 |
ety | +0.072 |
Neg logit contributions | |
vows | -0.052 |
apy | -0.050 |
prize | -0.049 |
contest | -0.049 |
trophy | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | +4.39e-02 |
Pos logit contributions | |
rying | +0.070 |
bur | +0.068 |
ind | +0.067 |
ppa | +0.067 |
ety | +0.064 |
Neg logit contributions | |
vows | -0.034 |
prize | -0.032 |
contest | -0.031 |
trophy | -0.031 |
apy | -0.030 |
Token | wood |
Token ID | 4898 |
Feature activation | +6.61e-02 |
Pos logit contributions | |
rying | +0.101 |
ppa | +0.097 |
bur | +0.097 |
ind | +0.093 |
ety | +0.092 |
Neg logit contributions | |
prize | -0.062 |
trophy | -0.062 |
contest | -0.062 |
vows | -0.059 |
third | -0.057 |
Token | pe |
Token ID | 431 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
bur | +0.104 |
ind | +0.102 |
ior | +0.101 |
ety | +0.099 |
umper | +0.097 |
Neg logit contributions | |
vows | -0.123 |
trophy | -0.123 |
contest | -0.120 |
prize | -0.120 |
case | -0.119 |
Token | cker |
Token ID | 15280 |
Feature activation | +7.31e-02 |
Pos logit contributions | |
ior | +0.131 |
bur | +0.130 |
athy | +0.119 |
umper | +0.119 |
ind | +0.118 |
Neg logit contributions | |
laugh | -0.234 |
vows | -0.232 |
ves | -0.224 |
trophy | -0.222 |
joke | -0.219 |
Token | . |
Token ID | 13 |
Feature activation | +1.09e-02 |
Pos logit contributions | |
bur | +0.183 |
ind | +0.177 |
ior | +0.170 |
ppa | +0.169 |
umper | +0.168 |
Neg logit contributions | |
laugh | -0.076 |
vows | -0.074 |
trophy | -0.069 |
prize | -0.068 |
g | -0.066 |
Token |
|
Token ID | 198 |
Feature activation | +1.52e-02 |
Pos logit contributions | |
bur | +0.026 |
rying | +0.026 |
ppa | +0.026 |
ind | +0.025 |
i | +0.025 |
Neg logit contributions | |
vows | -0.014 |
prize | -0.012 |
contest | -0.012 |
trophy | -0.012 |
apy | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +1.03e-02 |
Pos logit contributions | |
rying | +0.038 |
bur | +0.037 |
ppa | +0.037 |
i | +0.036 |
ind | +0.036 |
Neg logit contributions | |
vows | -0.018 |
prize | -0.016 |
contest | -0.016 |
trophy | -0.016 |
apy | -0.016 |
Token | The |
Token ID | 464 |
Feature activation | +5.01e-02 |
Pos logit contributions | |
bur | +0.023 |
rying | +0.022 |
ppa | +0.022 |
i | +0.022 |
ind | +0.021 |
Neg logit contributions | |
vows | -0.015 |
prize | -0.014 |
contest | -0.014 |
trophy | -0.013 |
apy | -0.013 |
Token | should |
Token ID | 815 |
Feature activation | +6.65e-03 |
Pos logit contributions | |
bur | +0.017 |
rying | +0.016 |
ppa | +0.016 |
ind | +0.016 |
i | +0.016 |
Neg logit contributions | |
vows | -0.011 |
prize | -0.010 |
contest | -0.009 |
trophy | -0.009 |
apy | -0.009 |
Token | never |
Token ID | 1239 |
Feature activation | +2.49e-02 |
Pos logit contributions | |
bur | +0.016 |
rying | +0.016 |
ppa | +0.015 |
ind | +0.015 |
i | +0.015 |
Neg logit contributions | |
vows | -0.009 |
prize | -0.008 |
contest | -0.008 |
trophy | -0.008 |
cakes | -0.007 |
Token | come |
Token ID | 1282 |
Feature activation | +4.75e-02 |
Pos logit contributions | |
bur | +0.063 |
ppa | +0.063 |
rying | +0.062 |
ind | +0.062 |
i | +0.060 |
Neg logit contributions | |
vows | -0.027 |
prize | -0.027 |
contest | -0.026 |
joke | -0.025 |
trophy | -0.025 |
Token | close |
Token ID | 1969 |
Feature activation | +6.90e-02 |
Pos logit contributions | |
ior | +0.102 |
ppa | +0.102 |
bur | +0.098 |
i | +0.096 |
ind | +0.094 |
Neg logit contributions | |
prize | -0.064 |
vows | -0.062 |
contest | -0.060 |
join | -0.058 |
celebrate | -0.057 |
Token | to |
Token ID | 284 |
Feature activation | +5.97e-02 |
Pos logit contributions | |
ppa | +0.166 |
ior | +0.163 |
cker | +0.157 |
bur | +0.156 |
gie | +0.154 |
Neg logit contributions | |
prize | -0.073 |
vows | -0.072 |
contest | -0.072 |
trophy | -0.066 |
are | -0.062 |
Token | an |
Token ID | 281 |
Feature activation | +1.15e-01 |
Pos logit contributions | |
rying | +0.156 |
ppa | +0.155 |
bur | +0.154 |
ior | +0.151 |
ishing | +0.151 |
Neg logit contributions | |
are | -0.056 |
prize | -0.056 |
celebrate | -0.053 |
tea | -0.052 |
contest | -0.051 |
Token | owl |
Token ID | 39610 |
Feature activation | +4.67e-02 |
Pos logit contributions | |
bur | +0.196 |
rying | +0.191 |
ishing | +0.180 |
ppa | +0.179 |
eking | +0.166 |
Neg logit contributions | |
prize | -0.203 |
idea | -0.195 |
great | -0.185 |
contest | -0.183 |
surprise | -0.180 |
Token | again |
Token ID | 757 |
Feature activation | +5.99e-02 |
Pos logit contributions | |
bur | +0.096 |
ppa | +0.092 |
ind | +0.092 |
rying | +0.091 |
ior | +0.089 |
Neg logit contributions | |
prize | -0.070 |
contest | -0.070 |
vows | -0.070 |
trophy | -0.067 |
case | -0.063 |
Token | !". |
Token ID | 48220 |
Feature activation | +1.86e-02 |
Pos logit contributions | |
bur | +0.137 |
ppa | +0.133 |
gie | +0.131 |
ior | +0.128 |
rying | +0.128 |
Neg logit contributions | |
vows | -0.075 |
prize | -0.074 |
contest | -0.073 |
win | -0.070 |
celebrate | -0.068 |
Token |
|
Token ID | 198 |
Feature activation | +7.97e-03 |
Pos logit contributions | |
bur | +0.047 |
rying | +0.047 |
ppa | +0.046 |
ind | +0.046 |
i | +0.045 |
Neg logit contributions | |
vows | -0.021 |
contest | -0.019 |
prize | -0.019 |
cakes | -0.018 |
trophy | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | -6.03e-03 |
Pos logit contributions | |
bur | +0.019 |
rying | +0.019 |
ppa | +0.018 |
i | +0.018 |
ind | +0.018 |
Neg logit contributions | |
vows | -0.010 |
prize | -0.009 |
contest | -0.009 |
trophy | -0.009 |
cakes | -0.009 |
Token | the |
Token ID | 262 |
Feature activation | +3.42e-02 |
Pos logit contributions | |
ppa | +0.037 |
rying | +0.037 |
bur | +0.037 |
i | +0.034 |
ind | +0.034 |
Neg logit contributions | |
vows | -0.020 |
prize | -0.018 |
contest | -0.018 |
trophy | -0.017 |
apy | -0.017 |
Token | sunshine |
Token ID | 34488 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
ppa | +0.080 |
rying | +0.078 |
bur | +0.077 |
ety | +0.072 |
i | +0.072 |
Neg logit contributions | |
vows | -0.050 |
prize | -0.044 |
trophy | -0.044 |
contest | -0.043 |
are | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +4.07e-02 |
Pos logit contributions | |
bur | +0.031 |
rying | +0.031 |
ppa | +0.031 |
ind | +0.029 |
i | +0.029 |
Neg logit contributions | |
vows | -0.024 |
prize | -0.022 |
contest | -0.022 |
trophy | -0.021 |
cakes | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +1.37e-02 |
Pos logit contributions | |
ppa | +0.117 |
rying | +0.116 |
bur | +0.115 |
ind | +0.112 |
i | +0.109 |
Neg logit contributions | |
Everyone | -0.034 |
vows | -0.032 |
apy | -0.031 |
cakes | -0.028 |
case | -0.028 |
Token |
|
Token ID | 198 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
rying | +0.034 |
bur | +0.033 |
ppa | +0.033 |
i | +0.032 |
ind | +0.032 |
Neg logit contributions | |
vows | -0.017 |
prize | -0.014 |
contest | -0.014 |
apy | -0.014 |
trophy | -0.014 |
Token | Mill |
Token ID | 22603 |
Feature activation | +1.14e-01 |
Pos logit contributions | |
bur | +0.062 |
rying | +0.061 |
ppa | +0.059 |
i | +0.058 |
ior | +0.057 |
Neg logit contributions | |
vows | -0.060 |
apy | -0.056 |
contest | -0.056 |
case | -0.055 |
Everyone | -0.054 |
Token | ie |
Token ID | 494 |
Feature activation | +5.20e-02 |
Pos logit contributions | |
property | +0.215 |
territory | +0.205 |
spine | +0.204 |
rying | +0.203 |
shadow | +0.201 |
Neg logit contributions | |
were | -0.132 |
vows | -0.122 |
are | -0.112 |
ade | -0.106 |
parties | -0.105 |
Token | was |
Token ID | 373 |
Feature activation | +2.03e-02 |
Pos logit contributions | |
bur | +0.118 |
rying | +0.112 |
ppa | +0.112 |
ior | +0.107 |
umper | +0.105 |
Neg logit contributions | |
vows | -0.075 |
contest | -0.064 |
were | -0.062 |
apy | -0.061 |
case | -0.061 |
Token | so |
Token ID | 523 |
Feature activation | -8.05e-03 |
Pos logit contributions | |
bur | +0.045 |
ppa | +0.045 |
rying | +0.044 |
ind | +0.043 |
i | +0.042 |
Neg logit contributions | |
vows | -0.029 |
contest | -0.026 |
prize | -0.025 |
trophy | -0.024 |
apy | -0.024 |
Token | excited |
Token ID | 6568 |
Feature activation | +3.32e-02 |
Pos logit contributions | |
vows | +0.013 |
prize | +0.011 |
trophy | +0.011 |
cakes | +0.011 |
contest | +0.011 |
Neg logit contributions | |
rying | -0.017 |
bur | -0.017 |
ppa | -0.017 |
i | -0.016 |
ind | -0.016 |
Token | that |
Token ID | 326 |
Feature activation | +1.45e-02 |
Pos logit contributions | |
bur | +0.076 |
ppa | +0.076 |
rying | +0.073 |
umper | +0.071 |
ind | +0.070 |
Neg logit contributions | |
vows | -0.044 |
prize | -0.042 |
contest | -0.042 |
cakes | -0.042 |
trophy | -0.039 |
Token | fluffy |
Token ID | 39145 |
Feature activation | +3.22e-02 |
Pos logit contributions | |
rying | +0.074 |
ppa | +0.071 |
bur | +0.070 |
ind | +0.068 |
ener | +0.067 |
Neg logit contributions | |
vows | -0.036 |
apy | -0.035 |
trophy | -0.032 |
prize | -0.032 |
joke | -0.031 |
Token | and |
Token ID | 290 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
rying | +0.078 |
bur | +0.078 |
ppa | +0.077 |
cker | +0.072 |
shadow | +0.070 |
Neg logit contributions | |
vows | -0.040 |
tea | -0.035 |
are | -0.034 |
prize | -0.034 |
lot | -0.034 |
Token | lived |
Token ID | 5615 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
rying | +0.034 |
bur | +0.034 |
ppa | +0.033 |
ind | +0.032 |
i | +0.032 |
Neg logit contributions | |
vows | -0.021 |
prize | -0.019 |
apy | -0.019 |
trophy | -0.019 |
contest | -0.018 |
Token | in |
Token ID | 287 |
Feature activation | +1.36e-02 |
Pos logit contributions | |
bur | +0.035 |
ppa | +0.034 |
rying | +0.034 |
i | +0.033 |
ior | +0.033 |
Neg logit contributions | |
vows | -0.031 |
contest | -0.029 |
prize | -0.029 |
trophy | -0.028 |
apy | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
rying | +0.034 |
ppa | +0.034 |
bur | +0.033 |
i | +0.032 |
ind | +0.032 |
Neg logit contributions | |
vows | -0.016 |
prize | -0.015 |
contest | -0.014 |
trophy | -0.014 |
apy | -0.013 |
Token | bur |
Token ID | 4356 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
bur | +0.026 |
rying | +0.026 |
ppa | +0.025 |
i | +0.025 |
ind | +0.024 |
Neg logit contributions | |
vows | -0.014 |
prize | -0.012 |
contest | -0.012 |
trophy | -0.012 |
apy | -0.011 |
Token | row |
Token ID | 808 |
Feature activation | +7.12e-02 |
Pos logit contributions | |
ior | +0.152 |
shadow | +0.133 |
Tooth | +0.128 |
ppa | +0.124 |
bur | +0.121 |
Neg logit contributions | |
ade | -0.196 |
ades | -0.194 |
uits | -0.188 |
lot | -0.184 |
br | -0.183 |
Token | in |
Token ID | 287 |
Feature activation | +2.64e-02 |
Pos logit contributions | |
ior | +0.174 |
bur | +0.173 |
ppa | +0.166 |
gie | +0.159 |
ety | +0.158 |
Neg logit contributions | |
contest | -0.080 |
case | -0.079 |
trophy | -0.070 |
vows | -0.070 |
prize | -0.068 |
Token | the |
Token ID | 262 |
Feature activation | +7.34e-02 |
Pos logit contributions | |
ppa | +0.069 |
rying | +0.069 |
bur | +0.066 |
i | +0.065 |
ener | +0.064 |
Neg logit contributions | |
vows | -0.026 |
prize | -0.026 |
contest | -0.025 |
trophy | -0.024 |
are | -0.023 |
Token | forest |
Token ID | 8222 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
rying | +0.172 |
ppa | +0.161 |
ener | +0.157 |
ishing | +0.155 |
owing | +0.154 |
Neg logit contributions | |
lot | -0.107 |
great | -0.104 |
tea | -0.104 |
third | -0.099 |
contest | -0.094 |
Token | . |
Token ID | 13 |
Feature activation | +1.29e-03 |
Pos logit contributions | |
bur | +0.095 |
ppa | +0.094 |
ior | +0.091 |
umper | +0.089 |
rying | +0.088 |
Neg logit contributions | |
vows | -0.046 |
contest | -0.045 |
are | -0.042 |
case | -0.042 |
prize | -0.041 |
Token | cry |
Token ID | 3960 |
Feature activation | +1.34e-02 |
Pos logit contributions | |
vows | +0.046 |
cakes | +0.039 |
contest | +0.037 |
prize | +0.037 |
trophy | +0.037 |
Neg logit contributions | |
owl | -0.057 |
ind | -0.057 |
rying | -0.057 |
Owl | -0.055 |
gie | -0.055 |
Token | coming |
Token ID | 2406 |
Feature activation | +3.43e-02 |
Pos logit contributions | |
bur | +0.026 |
ppa | +0.026 |
rying | +0.026 |
ind | +0.025 |
i | +0.024 |
Neg logit contributions | |
vows | -0.023 |
prize | -0.021 |
contest | -0.021 |
trophy | -0.020 |
apy | -0.020 |
Token | from |
Token ID | 422 |
Feature activation | +4.62e-02 |
Pos logit contributions | |
ppa | +0.078 |
bur | +0.076 |
ishing | +0.070 |
i | +0.069 |
rying | +0.069 |
Neg logit contributions | |
vows | -0.046 |
prize | -0.044 |
contest | -0.042 |
are | -0.041 |
trophy | -0.041 |
Token | outside |
Token ID | 2354 |
Feature activation | -4.22e-03 |
Pos logit contributions | |
ppa | +0.116 |
rying | +0.106 |
ety | +0.105 |
bur | +0.105 |
i | +0.103 |
Neg logit contributions | |
prize | -0.056 |
contest | -0.056 |
trophy | -0.052 |
festival | -0.052 |
tea | -0.050 |
Token | his |
Token ID | 465 |
Feature activation | +3.92e-02 |
Pos logit contributions | |
vows | +0.008 |
prize | +0.007 |
contest | +0.007 |
trophy | +0.007 |
cakes | +0.007 |
Neg logit contributions | |
rying | -0.008 |
bur | -0.008 |
ppa | -0.007 |
i | -0.007 |
ind | -0.007 |
Token | bur |
Token ID | 4356 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
rying | +0.087 |
ppa | +0.083 |
bur | +0.082 |
cker | +0.080 |
gie | +0.077 |
Neg logit contributions | |
prize | -0.059 |
vows | -0.058 |
trophy | -0.055 |
case | -0.053 |
tea | -0.052 |
Token | row |
Token ID | 808 |
Feature activation | +5.77e-02 |
Pos logit contributions | |
ior | +0.130 |
ppa | +0.127 |
shadow | +0.126 |
afar | +0.126 |
pless | +0.120 |
Neg logit contributions | |
ades | -0.187 |
ade | -0.181 |
uits | -0.179 |
br | -0.177 |
cakes | -0.166 |
Token | . |
Token ID | 13 |
Feature activation | +1.81e-02 |
Pos logit contributions | |
bur | +0.138 |
ior | +0.137 |
ppa | +0.136 |
ind | +0.136 |
rying | +0.132 |
Neg logit contributions | |
case | -0.066 |
vows | -0.061 |
contest | -0.059 |
cakes | -0.058 |
prize | -0.056 |
Token |
|
Token ID | 198 |
Feature activation | +8.94e-03 |
Pos logit contributions | |
rying | +0.042 |
bur | +0.042 |
ppa | +0.041 |
ind | +0.041 |
i | +0.040 |
Neg logit contributions | |
vows | -0.025 |
prize | -0.022 |
apy | -0.021 |
trophy | -0.021 |
contest | -0.021 |
Token |
|
Token ID | 198 |
Feature activation | +2.70e-03 |
Pos logit contributions | |
bur | +0.021 |
rying | +0.021 |
ppa | +0.021 |
i | +0.021 |
ind | +0.020 |
Neg logit contributions | |
vows | -0.011 |
prize | -0.010 |
contest | -0.010 |
trophy | -0.010 |
apy | -0.009 |
Token | He |
Token ID | 1544 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
i | +0.005 |
ind | +0.005 |
Neg logit contributions | |
vows | -0.005 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
cakes | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | +1.24e-02 |
Pos logit contributions | |
bur | +0.047 |
rying | +0.047 |
i | +0.046 |
ppa | +0.046 |
ind | +0.044 |
Neg logit contributions | |
vows | -0.029 |
apy | -0.027 |
case | -0.027 |
cakes | -0.027 |
prize | -0.027 |
Token | Who |
Token ID | 8241 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
rying | +0.023 |
bur | +0.022 |
ppa | +0.022 |
i | +0.021 |
ind | +0.021 |
Neg logit contributions | |
vows | -0.023 |
prize | -0.021 |
contest | -0.021 |
trophy | -0.020 |
cakes | -0.020 |
Token | 's |
Token ID | 338 |
Feature activation | +5.97e-03 |
Pos logit contributions | |
vows | +0.024 |
prize | +0.020 |
cakes | +0.020 |
trophy | +0.020 |
apy | +0.020 |
Neg logit contributions | |
bur | -0.043 |
ppa | -0.042 |
rying | -0.041 |
i | -0.041 |
ind | -0.040 |
Token | there |
Token ID | 612 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
bur | +0.011 |
rying | +0.010 |
ppa | +0.010 |
i | +0.010 |
ind | +0.010 |
Neg logit contributions | |
vows | -0.012 |
prize | -0.011 |
contest | -0.010 |
trophy | -0.010 |
cakes | -0.010 |
Token | ?" |
Token ID | 1701 |
Feature activation | +3.02e-02 |
Pos logit contributions | |
ppa | +0.044 |
rying | +0.044 |
bur | +0.043 |
ind | +0.042 |
i | +0.041 |
Neg logit contributions | |
vows | -0.045 |
prize | -0.043 |
contest | -0.043 |
trophy | -0.042 |
are | -0.040 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
rying | +0.073 |
bur | +0.072 |
ind | +0.071 |
ppa | +0.070 |
i | +0.066 |
Neg logit contributions | |
apy | -0.040 |
vows | -0.037 |
prize | -0.036 |
trophy | -0.036 |
contest | -0.036 |
Token | my |
Token ID | 1820 |
Feature activation | +8.58e-02 |
Pos logit contributions | |
ind | +0.143 |
predators | +0.142 |
rying | +0.141 |
cker | +0.137 |
property | +0.126 |
Neg logit contributions | |
laugh | -0.211 |
g | -0.207 |
joke | -0.203 |
third | -0.196 |
case | -0.195 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
bur | +0.182 |
rying | +0.178 |
ior | +0.171 |
ind | +0.170 |
property | +0.166 |
Neg logit contributions | |
g | -0.114 |
dance | -0.110 |
laugh | -0.109 |
joke | -0.109 |
third | -0.105 |
Token | . |
Token ID | 13 |
Feature activation | -2.71e-03 |
Pos logit contributions | |
bur | +0.038 |
rying | +0.037 |
ppa | +0.037 |
ind | +0.036 |
i | +0.035 |
Neg logit contributions | |
vows | -0.025 |
prize | -0.022 |
contest | -0.022 |
trophy | -0.022 |
apy | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | +1.90e-02 |
Pos logit contributions | |
vows | +0.004 |
prize | +0.004 |
contest | +0.003 |
trophy | +0.003 |
cakes | +0.003 |
Neg logit contributions | |
bur | -0.006 |
rying | -0.006 |
ppa | -0.006 |
i | -0.006 |
gie | -0.006 |
Token |
|
Token ID | 198 |
Feature activation | +1.08e-02 |
Pos logit contributions | |
rying | +0.049 |
bur | +0.048 |
ppa | +0.047 |
i | +0.047 |
ind | +0.046 |
Neg logit contributions | |
vows | -0.021 |
prize | -0.018 |
contest | -0.018 |
apy | -0.017 |
cakes | -0.017 |
Token |
|
Token ID | 198 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
rying | +0.040 |
bur | +0.040 |
ppa | +0.039 |
i | +0.038 |
ind | +0.038 |
Neg logit contributions | |
vows | -0.018 |
prize | -0.016 |
contest | -0.016 |
apy | -0.015 |
trophy | -0.015 |
Token | " |
Token ID | 1 |
Feature activation | +1.23e-02 |
Pos logit contributions | |
bur | +0.045 |
rying | +0.045 |
ppa | +0.044 |
i | +0.043 |
ind | +0.042 |
Neg logit contributions | |
vows | -0.027 |
apy | -0.025 |
cakes | -0.025 |
contest | -0.024 |
prize | -0.024 |
Token | What |
Token ID | 2061 |
Feature activation | -4.10e-02 |
Pos logit contributions | |
rying | +0.022 |
bur | +0.022 |
ppa | +0.021 |
i | +0.021 |
ind | +0.021 |
Neg logit contributions | |
vows | -0.023 |
prize | -0.021 |
contest | -0.021 |
trophy | -0.021 |
apy | -0.021 |
Token | happened |
Token ID | 3022 |
Feature activation | +2.74e-02 |
Pos logit contributions | |
vows | +0.076 |
cakes | +0.065 |
prize | +0.065 |
uits | +0.063 |
contest | +0.061 |
Neg logit contributions | |
my | -0.076 |
bur | -0.071 |
ety | -0.069 |
i | -0.069 |
rying | -0.066 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
bur | +0.058 |
ppa | +0.058 |
rying | +0.056 |
ind | +0.055 |
i | +0.054 |
Neg logit contributions | |
contest | -0.040 |
prize | -0.040 |
vows | -0.040 |
trophy | -0.040 |
joke | -0.037 |
Token | Tim |
Token ID | 5045 |
Feature activation | +1.12e-01 |
Pos logit contributions | |
rying | +0.054 |
bur | +0.054 |
ppa | +0.052 |
ind | +0.052 |
i | +0.049 |
Neg logit contributions | |
apy | -0.037 |
vows | -0.037 |
contest | -0.036 |
prize | -0.035 |
trophy | -0.035 |
Token | my |
Token ID | 1820 |
Feature activation | +9.24e-02 |
Pos logit contributions | |
ind | +0.149 |
rying | +0.145 |
predators | +0.145 |
orns | +0.139 |
cker | +0.139 |
Neg logit contributions | |
laugh | -0.210 |
g | -0.204 |
joke | -0.201 |
third | -0.191 |
smile | -0.188 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.99e-02 |
Pos logit contributions | |
bur | +0.209 |
rying | +0.207 |
property | +0.195 |
orns | +0.193 |
ind | +0.192 |
Neg logit contributions | |
g | -0.110 |
cl | -0.108 |
laugh | -0.107 |
dance | -0.107 |
joke | -0.106 |
Token | . |
Token ID | 13 |
Feature activation | -4.68e-04 |
Pos logit contributions | |
bur | +0.045 |
rying | +0.045 |
ind | +0.044 |
ppa | +0.044 |
i | +0.042 |
Neg logit contributions | |
vows | -0.027 |
contest | -0.025 |
prize | -0.025 |
trophy | -0.024 |
apy | -0.024 |
Token |
|
Token ID | 198 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
vows | +0.001 |
prize | +0.001 |
contest | +0.001 |
trophy | +0.001 |
cakes | +0.001 |
Neg logit contributions | |
bur | -0.001 |
rying | -0.001 |
ppa | -0.001 |
i | -0.001 |
ind | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +7.50e-03 |
Pos logit contributions | |
rying | +0.054 |
bur | +0.053 |
ppa | +0.052 |
i | +0.052 |
ind | +0.051 |
Neg logit contributions | |
vows | -0.022 |
contest | -0.019 |
prize | -0.019 |
apy | -0.019 |
cakes | -0.018 |
Token | mist |
Token ID | 4020 |
Feature activation | +5.69e-03 |
Pos logit contributions | |
rying | +0.054 |
ppa | +0.054 |
bur | +0.053 |
i | +0.051 |
ety | +0.049 |
Neg logit contributions | |
vows | -0.051 |
contest | -0.047 |
prize | -0.047 |
trophy | -0.046 |
festival | -0.045 |
Token | and |
Token ID | 290 |
Feature activation | +2.73e-02 |
Pos logit contributions | |
bur | +0.012 |
rying | +0.011 |
ppa | +0.011 |
i | +0.011 |
ind | +0.011 |
Neg logit contributions | |
vows | -0.009 |
prize | -0.008 |
contest | -0.008 |
trophy | -0.008 |
cakes | -0.008 |
Token | into |
Token ID | 656 |
Feature activation | +2.53e-03 |
Pos logit contributions | |
bur | +0.057 |
ppa | +0.056 |
rying | +0.055 |
ind | +0.054 |
i | +0.052 |
Neg logit contributions | |
vows | -0.045 |
contest | -0.040 |
prize | -0.040 |
apy | -0.038 |
trophy | -0.038 |
Token | their |
Token ID | 511 |
Feature activation | +1.87e-02 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
i | +0.005 |
ind | +0.005 |
Neg logit contributions | |
vows | -0.004 |
prize | -0.003 |
contest | -0.003 |
trophy | -0.003 |
cakes | -0.003 |
Token | cozy |
Token ID | 37438 |
Feature activation | +6.79e-02 |
Pos logit contributions | |
bur | +0.034 |
rying | +0.034 |
ppa | +0.034 |
i | +0.031 |
gie | +0.031 |
Neg logit contributions | |
vows | -0.036 |
prize | -0.032 |
contest | -0.031 |
trophy | -0.031 |
apy | -0.030 |
Token | bur |
Token ID | 4356 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
ppa | +0.134 |
bur | +0.134 |
rying | +0.130 |
umper | +0.127 |
ior | +0.123 |
Neg logit contributions | |
vows | -0.114 |
tea | -0.104 |
prize | -0.101 |
lot | -0.097 |
dance | -0.097 |
Token | rows |
Token ID | 8516 |
Feature activation | +2.30e-02 |
Pos logit contributions | |
ior | +0.152 |
ppa | +0.126 |
umper | +0.123 |
athy | +0.122 |
Tooth | +0.120 |
Neg logit contributions | |
uits | -0.217 |
ades | -0.215 |
vows | -0.204 |
apy | -0.197 |
ves | -0.197 |
Token | . |
Token ID | 13 |
Feature activation | +6.63e-03 |
Pos logit contributions | |
bur | +0.047 |
ppa | +0.046 |
rying | +0.045 |
ind | +0.044 |
ior | +0.043 |
Neg logit contributions | |
vows | -0.037 |
prize | -0.034 |
contest | -0.033 |
trophy | -0.033 |
cakes | -0.032 |
Token | The |
Token ID | 383 |
Feature activation | +3.06e-02 |
Pos logit contributions | |
bur | +0.015 |
rying | +0.015 |
ppa | +0.015 |
i | +0.015 |
ind | +0.015 |
Neg logit contributions | |
vows | -0.009 |
prize | -0.008 |
contest | -0.008 |
trophy | -0.008 |
cakes | -0.007 |
Token | end |
Token ID | 886 |
Feature activation | -7.77e-04 |
Pos logit contributions | |
bur | +0.062 |
rying | +0.061 |
ppa | +0.061 |
ior | +0.057 |
i | +0.056 |
Neg logit contributions | |
vows | -0.053 |
prize | -0.049 |
contest | -0.048 |
trophy | -0.046 |
festival | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +7.33e-03 |
Pos logit contributions | |
vows | +0.001 |
prize | +0.001 |
trophy | +0.001 |
contest | +0.001 |
cakes | +0.001 |
Neg logit contributions | |
bur | -0.001 |
rying | -0.001 |
ppa | -0.001 |
i | -0.001 |
ind | -0.001 |
Token | of |
Token ID | 286 |
Feature activation | +3.91e-02 |
Pos logit contributions | |
vows | +0.030 |
trophy | +0.026 |
prize | +0.026 |
apy | +0.025 |
cakes | +0.025 |
Neg logit contributions | |
rying | -0.034 |
i | -0.033 |
bur | -0.033 |
ppa | -0.033 |
ind | -0.031 |
Token | friendly |
Token ID | 8030 |
Feature activation | +1.12e-02 |
Pos logit contributions | |
bur | +0.078 |
rying | +0.076 |
ppa | +0.076 |
ety | +0.072 |
ior | +0.070 |
Neg logit contributions | |
vows | -0.065 |
contest | -0.062 |
prize | -0.062 |
joke | -0.058 |
great | -0.058 |
Token | ducks |
Token ID | 39694 |
Feature activation | +1.11e-02 |
Pos logit contributions | |
bur | +0.019 |
rying | +0.019 |
ppa | +0.018 |
ind | +0.017 |
i | +0.017 |
Neg logit contributions | |
vows | -0.023 |
prize | -0.021 |
contest | -0.020 |
trophy | -0.020 |
cakes | -0.019 |
Token | came |
Token ID | 1625 |
Feature activation | +2.00e-02 |
Pos logit contributions | |
bur | +0.022 |
ppa | +0.022 |
rying | +0.022 |
ind | +0.021 |
i | +0.021 |
Neg logit contributions | |
vows | -0.018 |
prize | -0.016 |
contest | -0.016 |
trophy | -0.016 |
apy | -0.015 |
Token | to |
Token ID | 284 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
ppa | +0.038 |
bur | +0.038 |
rying | +0.036 |
ior | +0.035 |
ind | +0.035 |
Neg logit contributions | |
vows | -0.035 |
prize | -0.032 |
contest | -0.031 |
trophy | -0.030 |
apy | -0.029 |
Token | Gig |
Token ID | 19525 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
rying | +0.031 |
bur | +0.031 |
ppa | +0.031 |
ind | +0.029 |
i | +0.029 |
Neg logit contributions | |
vows | -0.023 |
prize | -0.021 |
contest | -0.021 |
trophy | -0.020 |
cakes | -0.019 |
Token | i |
Token ID | 72 |
Feature activation | +3.24e-02 |
Pos logit contributions | |
asured | +0.113 |
oscope | +0.111 |
property | +0.103 |
axe | +0.102 |
keeping | +0.096 |
Neg logit contributions | |
vows | -0.233 |
tea | -0.209 |
they | -0.207 |
are | -0.205 |
were | -0.202 |
Token | 's |
Token ID | 338 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
bur | +0.064 |
ppa | +0.063 |
rying | +0.061 |
ind | +0.061 |
ior | +0.059 |
Neg logit contributions | |
vows | -0.052 |
prize | -0.048 |
contest | -0.047 |
trophy | -0.047 |
are | -0.045 |
Token | rescue |
Token ID | 9992 |
Feature activation | +2.02e-02 |
Pos logit contributions | |
ppa | +0.054 |
bur | +0.054 |
rying | +0.053 |
i | +0.050 |
umper | +0.050 |
Neg logit contributions | |
vows | -0.055 |
prize | -0.050 |
contest | -0.048 |
trophy | -0.047 |
joke | -0.046 |
Token | . |
Token ID | 13 |
Feature activation | +2.56e-02 |
Pos logit contributions | |
bur | +0.042 |
rying | +0.041 |
ppa | +0.041 |
ind | +0.040 |
ety | +0.039 |
Neg logit contributions | |
vows | -0.032 |
prize | -0.029 |
contest | -0.028 |
trophy | -0.027 |
cakes | -0.027 |
Token | They |
Token ID | 1119 |
Feature activation | -1.24e-02 |
Pos logit contributions | |
rying | +0.051 |
bur | +0.051 |
ppa | +0.050 |
ind | +0.049 |
i | +0.047 |
Neg logit contributions | |
vows | -0.044 |
prize | -0.039 |
cakes | -0.038 |
contest | -0.038 |
apy | -0.037 |
Token | , |
Token ID | 11 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
rying | +0.095 |
bur | +0.094 |
cker | +0.093 |
ppa | +0.091 |
ind | +0.091 |
Neg logit contributions | |
vows | -0.046 |
prize | -0.039 |
are | -0.039 |
contest | -0.038 |
tea | -0.036 |
Token | " |
Token ID | 366 |
Feature activation | +7.25e-02 |
Pos logit contributions | |
bur | +0.078 |
rying | +0.077 |
ind | +0.077 |
ppa | +0.077 |
i | +0.075 |
Neg logit contributions | |
vows | -0.018 |
prize | -0.015 |
contest | -0.015 |
trophy | -0.013 |
apy | -0.013 |
Token | What |
Token ID | 2061 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
rying | +0.149 |
ishing | +0.147 |
ior | +0.146 |
owing | +0.145 |
cker | +0.144 |
Neg logit contributions | |
Mine | -0.086 |
Me | -0.079 |
vows | -0.079 |
contest | -0.077 |
Everyone | -0.077 |
Token | happened |
Token ID | 3022 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
vows | +0.031 |
prize | +0.027 |
cakes | +0.027 |
trophy | +0.027 |
contest | +0.027 |
Neg logit contributions | |
bur | -0.032 |
i | -0.031 |
ppa | -0.031 |
rying | -0.031 |
ety | -0.030 |
Token | , |
Token ID | 11 |
Feature activation | +2.17e-02 |
Pos logit contributions | |
bur | +0.094 |
ppa | +0.094 |
rying | +0.090 |
ind | +0.089 |
ior | +0.088 |
Neg logit contributions | |
contest | -0.052 |
prize | -0.050 |
vows | -0.049 |
trophy | -0.048 |
joke | -0.045 |
Token | Gig |
Token ID | 19525 |
Feature activation | +1.11e-01 |
Pos logit contributions | |
rying | +0.036 |
bur | +0.035 |
ppa | +0.033 |
ind | +0.032 |
cker | +0.032 |
Neg logit contributions | |
vows | -0.045 |
prize | -0.042 |
trophy | -0.040 |
contest | -0.039 |
cakes | -0.039 |
Token | i |
Token ID | 72 |
Feature activation | +5.55e-02 |
Pos logit contributions | |
oscope | +0.117 |
keeping | +0.112 |
rying | +0.106 |
umbling | +0.102 |
property | +0.100 |
Neg logit contributions | |
vows | -0.230 |
are | -0.205 |
they | -0.196 |
tea | -0.195 |
were | -0.193 |
Token | ? |
Token ID | 30 |
Feature activation | +3.66e-02 |
Pos logit contributions | |
bur | +0.109 |
rying | +0.106 |
ppa | +0.103 |
ind | +0.103 |
ior | +0.102 |
Neg logit contributions | |
contest | -0.085 |
vows | -0.085 |
are | -0.084 |
prize | -0.079 |
trophy | -0.079 |
Token | Are |
Token ID | 4231 |
Feature activation | +3.54e-02 |
Pos logit contributions | |
bur | +0.080 |
rying | +0.078 |
ppa | +0.076 |
ind | +0.075 |
i | +0.074 |
Neg logit contributions | |
vows | -0.055 |
apy | -0.052 |
cakes | -0.049 |
case | -0.049 |
contest | -0.049 |
Token | you |
Token ID | 345 |
Feature activation | +5.06e-02 |
Pos logit contributions | |
rying | +0.073 |
bur | +0.071 |
ind | +0.070 |
ior | +0.070 |
cker | +0.069 |
Neg logit contributions | |
vows | -0.055 |
contest | -0.053 |
prize | -0.052 |
trophy | -0.051 |
are | -0.051 |
Token | okay |
Token ID | 8788 |
Feature activation | +3.97e-02 |
Pos logit contributions | |
ior | +0.099 |
bur | +0.098 |
rying | +0.096 |
ind | +0.094 |
ppa | +0.093 |
Neg logit contributions | |
vows | -0.075 |
are | -0.073 |
apy | -0.073 |
prize | -0.073 |
celebrate | -0.072 |
Token | able |
Token ID | 1498 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
bur | +0.031 |
rying | +0.030 |
ppa | +0.030 |
i | +0.029 |
ind | +0.029 |
Neg logit contributions | |
vows | -0.031 |
contest | -0.029 |
prize | -0.028 |
trophy | -0.028 |
apy | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -5.13e-03 |
Pos logit contributions | |
bur | +0.041 |
ppa | +0.040 |
rying | +0.040 |
ind | +0.039 |
i | +0.038 |
Neg logit contributions | |
vows | -0.034 |
prize | -0.031 |
contest | -0.030 |
trophy | -0.030 |
cakes | -0.029 |
Token | escape |
Token ID | 6654 |
Feature activation | +1.47e-02 |
Pos logit contributions | |
vows | +0.008 |
prize | +0.006 |
contest | +0.006 |
cakes | +0.006 |
trophy | +0.006 |
Neg logit contributions | |
bur | -0.011 |
rying | -0.011 |
ppa | -0.011 |
i | -0.011 |
ind | -0.011 |
Token | from |
Token ID | 422 |
Feature activation | +4.03e-02 |
Pos logit contributions | |
bur | +0.029 |
ppa | +0.028 |
rying | +0.028 |
ind | +0.027 |
i | +0.027 |
Neg logit contributions | |
vows | -0.025 |
prize | -0.023 |
trophy | -0.023 |
contest | -0.023 |
cakes | -0.022 |
Token | his |
Token ID | 465 |
Feature activation | +2.67e-03 |
Pos logit contributions | |
ppa | +0.096 |
bur | +0.093 |
rying | +0.092 |
ety | +0.091 |
ior | +0.090 |
Neg logit contributions | |
vows | -0.050 |
prize | -0.050 |
contest | -0.049 |
trophy | -0.047 |
apy | -0.043 |
Token | bur |
Token ID | 4356 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
i | +0.005 |
ind | +0.005 |
Neg logit contributions | |
vows | -0.005 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
cakes | -0.004 |
Token | row |
Token ID | 808 |
Feature activation | +4.20e-02 |
Pos logit contributions | |
ior | +0.130 |
ppa | +0.121 |
ety | +0.110 |
bur | +0.109 |
Tooth | +0.106 |
Neg logit contributions | |
ades | -0.222 |
uits | -0.216 |
vows | -0.205 |
prize | -0.204 |
ade | -0.203 |
Token | and |
Token ID | 290 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
bur | +0.085 |
ppa | +0.083 |
rying | +0.082 |
ind | +0.082 |
ior | +0.080 |
Neg logit contributions | |
vows | -0.066 |
prize | -0.060 |
contest | -0.060 |
trophy | -0.059 |
cakes | -0.059 |
Token | play |
Token ID | 711 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
bur | +0.042 |
rying | +0.041 |
ppa | +0.041 |
ind | +0.040 |
i | +0.039 |
Neg logit contributions | |
vows | -0.029 |
prize | -0.026 |
trophy | -0.025 |
contest | -0.025 |
apy | -0.024 |
Token | in |
Token ID | 287 |
Feature activation | -8.57e-03 |
Pos logit contributions | |
vows | +0.066 |
cakes | +0.056 |
apy | +0.055 |
Prize | +0.055 |
trophy | +0.055 |
Neg logit contributions | |
rying | -0.048 |
bur | -0.044 |
ind | -0.042 |
ppa | -0.042 |
i | -0.042 |
Token | the |
Token ID | 262 |
Feature activation | +3.20e-02 |
Pos logit contributions | |
vows | +0.015 |
cakes | +0.013 |
prize | +0.013 |
contest | +0.013 |
trophy | +0.013 |
Neg logit contributions | |
bur | -0.017 |
rying | -0.017 |
ppa | -0.016 |
ind | -0.016 |
i | -0.016 |
Token | . |
Token ID | 13 |
Feature activation | +3.35e-02 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.004 |
ppa | +0.004 |
i | +0.004 |
ind | +0.004 |
Neg logit contributions | |
vows | -0.004 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
cakes | -0.004 |
Token | One |
Token ID | 1881 |
Feature activation | +3.38e-02 |
Pos logit contributions | |
rying | +0.083 |
ppa | +0.081 |
ind | +0.078 |
bur | +0.077 |
i | +0.076 |
Neg logit contributions | |
vows | -0.040 |
prize | -0.037 |
contest | -0.035 |
Everyone | -0.035 |
are | -0.035 |
Token | day |
Token ID | 1110 |
Feature activation | +1.95e-03 |
Pos logit contributions | |
rying | +0.084 |
ppa | +0.082 |
bur | +0.078 |
ind | +0.076 |
ener | +0.076 |
Neg logit contributions | |
prize | -0.039 |
vows | -0.039 |
contest | -0.038 |
joke | -0.037 |
trophy | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +2.67e-02 |
Pos logit contributions | |
bur | +0.004 |
rying | +0.004 |
ppa | +0.004 |
i | +0.004 |
ind | +0.004 |
Neg logit contributions | |
vows | -0.003 |
prize | -0.002 |
contest | -0.002 |
trophy | -0.002 |
cakes | -0.002 |
Token | Stri |
Token ID | 26137 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
rying | +0.054 |
ppa | +0.052 |
ind | +0.052 |
bur | +0.051 |
cker | +0.048 |
Neg logit contributions | |
vows | -0.043 |
apy | -0.042 |
prize | -0.041 |
contest | -0.040 |
trophy | -0.039 |
Token | pe |
Token ID | 431 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
rying | +0.063 |
ind | +0.058 |
ety | +0.058 |
ppa | +0.058 |
bur | +0.057 |
Neg logit contributions | |
vows | -0.061 |
prize | -0.056 |
ves | -0.055 |
case | -0.055 |
contest | -0.055 |
Token | y |
Token ID | 88 |
Feature activation | +5.75e-02 |
Pos logit contributions | |
ior | +0.169 |
rying | +0.168 |
Owl | +0.167 |
ppa | +0.165 |
Tooth | +0.163 |
Neg logit contributions | |
were | -0.187 |
are | -0.182 |
vows | -0.181 |
ades | -0.169 |
joke | -0.167 |
Token | saw |
Token ID | 2497 |
Feature activation | +4.52e-02 |
Pos logit contributions | |
rying | +0.140 |
bur | +0.133 |
ind | +0.128 |
ppa | +0.126 |
ishing | +0.123 |
Neg logit contributions | |
vows | -0.070 |
case | -0.068 |
contest | -0.064 |
ves | -0.062 |
team | -0.061 |
Token | his |
Token ID | 465 |
Feature activation | +2.20e-02 |
Pos logit contributions | |
rying | +0.144 |
ppa | +0.133 |
ener | +0.132 |
ind | +0.131 |
ior | +0.131 |
Neg logit contributions | |
apy | -0.024 |
prize | -0.021 |
contest | -0.021 |
vows | -0.020 |
tea | -0.020 |
Token | friend |
Token ID | 1545 |
Feature activation | +1.98e-02 |
Pos logit contributions | |
rying | +0.046 |
ppa | +0.045 |
bur | +0.043 |
ior | +0.041 |
umper | +0.041 |
Neg logit contributions | |
vows | -0.037 |
prize | -0.035 |
trophy | -0.033 |
contest | -0.032 |
joke | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -9.03e-03 |
Pos logit contributions | |
rying | +0.044 |
bur | +0.043 |
ppa | +0.043 |
ind | +0.042 |
i | +0.040 |
Neg logit contributions | |
vows | -0.028 |
contest | -0.025 |
prize | -0.025 |
trophy | -0.024 |
cakes | -0.024 |
Token | peek |
Token ID | 27185 |
Feature activation | -1.84e-02 |
Pos logit contributions | |
vows | +0.023 |
prize | +0.021 |
contest | +0.020 |
trophy | +0.020 |
cakes | +0.020 |
Neg logit contributions | |
rying | -0.024 |
bur | -0.024 |
i | -0.024 |
ppa | -0.024 |
ind | -0.023 |
Token | ed |
Token ID | 276 |
Feature activation | +6.77e-03 |
Pos logit contributions | |
vows | +0.041 |
trophy | +0.039 |
prize | +0.039 |
contest | +0.039 |
Prize | +0.038 |
Neg logit contributions | |
rying | -0.027 |
i | -0.025 |
ppa | -0.024 |
bur | -0.024 |
ind | -0.024 |
Token | out |
Token ID | 503 |
Feature activation | +2.65e-03 |
Pos logit contributions | |
bur | +0.012 |
rying | +0.012 |
ppa | +0.012 |
i | +0.011 |
ind | +0.011 |
Neg logit contributions | |
vows | -0.013 |
prize | -0.012 |
contest | -0.012 |
trophy | -0.011 |
cakes | -0.011 |
Token | of |
Token ID | 286 |
Feature activation | +2.08e-02 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
i | +0.005 |
ind | +0.005 |
Neg logit contributions | |
vows | -0.004 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
cakes | -0.004 |
Token | his |
Token ID | 465 |
Feature activation | +2.28e-02 |
Pos logit contributions | |
rying | +0.050 |
ppa | +0.050 |
bur | +0.048 |
ind | +0.048 |
i | +0.047 |
Neg logit contributions | |
vows | -0.026 |
prize | -0.025 |
contest | -0.023 |
trophy | -0.023 |
apy | -0.021 |
Token | bur |
Token ID | 4356 |
Feature activation | +1.10e-01 |
Pos logit contributions | |
rying | +0.045 |
bur | +0.044 |
ppa | +0.044 |
i | +0.041 |
ind | +0.041 |
Neg logit contributions | |
vows | -0.040 |
prize | -0.038 |
trophy | -0.037 |
contest | -0.036 |
case | -0.034 |
Token | row |
Token ID | 808 |
Feature activation | +5.02e-02 |
Pos logit contributions | |
ior | +0.139 |
Owl | +0.129 |
ppa | +0.127 |
afar | +0.126 |
reckless | +0.122 |
Neg logit contributions | |
uits | -0.204 |
ades | -0.202 |
ade | -0.183 |
vows | -0.183 |
br | -0.177 |
Token | . |
Token ID | 13 |
Feature activation | +2.86e-03 |
Pos logit contributions | |
bur | +0.111 |
ind | +0.110 |
ppa | +0.109 |
ior | +0.109 |
rying | +0.108 |
Neg logit contributions | |
vows | -0.067 |
case | -0.063 |
cakes | -0.060 |
contest | -0.060 |
prize | -0.060 |
Token |
|
Token ID | 198 |
Feature activation | +1.41e-03 |
Pos logit contributions | |
bur | +0.006 |
rying | +0.006 |
ppa | +0.006 |
i | +0.006 |
ind | +0.006 |
Neg logit contributions | |
vows | -0.004 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
cakes | -0.004 |
Token |
|
Token ID | 198 |
Feature activation | -8.45e-03 |
Pos logit contributions | |
bur | +0.003 |
rying | +0.003 |
ppa | +0.003 |
i | +0.003 |
ind | +0.003 |
Neg logit contributions | |
vows | -0.002 |
prize | -0.002 |
contest | -0.002 |
trophy | -0.002 |
cakes | -0.002 |
Token | He |
Token ID | 1544 |
Feature activation | +7.85e-03 |
Pos logit contributions | |
vows | +0.015 |
prize | +0.014 |
trophy | +0.013 |
contest | +0.013 |
cakes | +0.013 |
Neg logit contributions | |
bur | -0.016 |
ppa | -0.016 |
rying | -0.016 |
ind | -0.015 |
i | -0.015 |
Token |
|
Token ID | 198 |
Feature activation | -7.36e-03 |
Pos logit contributions | |
vows | +0.012 |
prize | +0.010 |
contest | +0.010 |
trophy | +0.010 |
apy | +0.010 |
Neg logit contributions | |
bur | -0.011 |
rying | -0.011 |
ppa | -0.010 |
i | -0.010 |
ind | -0.010 |
Token |
|
Token ID | 198 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
vows | +0.012 |
prize | +0.010 |
trophy | +0.010 |
contest | +0.010 |
cakes | +0.010 |
Neg logit contributions | |
bur | -0.016 |
rying | -0.015 |
ppa | -0.015 |
ind | -0.015 |
i | -0.015 |
Token | The |
Token ID | 464 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
vows | +0.043 |
prize | +0.038 |
trophy | +0.037 |
contest | +0.037 |
tea | +0.036 |
Neg logit contributions | |
bur | -0.038 |
rying | -0.037 |
ind | -0.036 |
my | -0.035 |
ppa | -0.035 |
Token | kids |
Token ID | 3988 |
Feature activation | -4.02e-02 |
Pos logit contributions | |
apy | +0.076 |
vows | +0.070 |
case | +0.065 |
ades | +0.065 |
� | +0.065 |
Neg logit contributions | |
bur | -0.039 |
ppa | -0.038 |
ind | -0.037 |
owl | -0.037 |
rying | -0.037 |
Token | played |
Token ID | 2826 |
Feature activation | -8.43e-02 |
Pos logit contributions | |
vows | +0.071 |
prize | +0.065 |
apy | +0.064 |
trophy | +0.064 |
ades | +0.063 |
Neg logit contributions | |
i | -0.074 |
rying | -0.074 |
bur | -0.072 |
ppa | -0.071 |
my | -0.070 |
Token | a |
Token ID | 257 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
vows | +0.174 |
apy | +0.162 |
cakes | +0.154 |
Mine | +0.153 |
� | +0.150 |
Neg logit contributions | |
rying | -0.110 |
asking | -0.103 |
ishing | -0.100 |
forth | -0.097 |
ting | -0.095 |
Token | lot |
Token ID | 1256 |
Feature activation | -2.84e-02 |
Pos logit contributions | |
apy | +0.159 |
cakes | +0.149 |
vows | +0.148 |
� | +0.146 |
Both | +0.141 |
Neg logit contributions | |
ind | -0.210 |
rying | -0.167 |
nie | -0.167 |
ppa | -0.165 |
ich | -0.161 |
Token | of |
Token ID | 286 |
Feature activation | -4.86e-02 |
Pos logit contributions | |
vows | +0.063 |
apy | +0.057 |
Mine | +0.055 |
trophy | +0.053 |
prize | +0.053 |
Neg logit contributions | |
rying | -0.043 |
bur | -0.041 |
ppa | -0.040 |
i | -0.040 |
ind | -0.039 |
Token | fun |
Token ID | 1257 |
Feature activation | -5.17e-02 |
Pos logit contributions | |
vows | +0.067 |
apy | +0.058 |
cakes | +0.054 |
� | +0.053 |
case | +0.049 |
Neg logit contributions | |
rying | -0.103 |
ind | -0.102 |
ishing | -0.098 |
ior | -0.097 |
my | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | -1.36e-02 |
Pos logit contributions | |
vows | +0.091 |
Mine | +0.079 |
cakes | +0.073 |
trophy | +0.072 |
apy | +0.072 |
Neg logit contributions | |
rying | -0.095 |
ind | -0.089 |
i | -0.088 |
ishing | -0.087 |
ise | -0.087 |
Token | interesting |
Token ID | 3499 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
vows | +0.022 |
trophy | +0.019 |
prize | +0.019 |
contest | +0.019 |
ades | +0.019 |
Neg logit contributions | |
bur | -0.027 |
rying | -0.027 |
i | -0.026 |
ppa | -0.026 |
gie | -0.025 |
Token | were |
Token ID | 547 |
Feature activation | -3.66e-02 |
Pos logit contributions | |
vows | +0.058 |
prize | +0.050 |
Prize | +0.050 |
trophy | +0.048 |
contest | +0.047 |
Neg logit contributions | |
i | -0.112 |
bur | -0.109 |
my | -0.108 |
rying | -0.105 |
ppa | -0.105 |
Token | so |
Token ID | 523 |
Feature activation | -6.11e-02 |
Pos logit contributions | |
vows | +0.060 |
trophy | +0.055 |
apy | +0.055 |
prize | +0.055 |
Prize | +0.055 |
Neg logit contributions | |
bur | -0.069 |
i | -0.067 |
ppa | -0.066 |
rying | -0.066 |
ind | -0.065 |
Token | colorful |
Token ID | 20239 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
mat | +0.096 |
Prize | +0.096 |
trophy | +0.095 |
vows | +0.095 |
prize | +0.095 |
Neg logit contributions | |
ind | -0.105 |
i | -0.095 |
my | -0.093 |
ppa | -0.088 |
ety | -0.087 |
Token | and |
Token ID | 290 |
Feature activation | -2.12e-02 |
Pos logit contributions | |
vows | +0.066 |
apy | +0.059 |
Prize | +0.059 |
trophy | +0.058 |
contest | +0.058 |
Neg logit contributions | |
i | -0.044 |
rying | -0.044 |
bur | -0.043 |
ind | -0.041 |
ppa | -0.041 |
Token | the |
Token ID | 262 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
vows | +0.031 |
prize | +0.027 |
contest | +0.026 |
trophy | +0.026 |
ades | +0.025 |
Neg logit contributions | |
bur | -0.045 |
ppa | -0.044 |
rying | -0.044 |
i | -0.044 |
ind | -0.043 |
Token | stories |
Token ID | 3923 |
Feature activation | -1.09e-01 |
Pos logit contributions | |
bur | +0.020 |
rying | +0.020 |
ppa | +0.019 |
i | +0.018 |
ind | +0.018 |
Neg logit contributions | |
vows | -0.018 |
prize | -0.016 |
contest | -0.016 |
trophy | -0.016 |
cakes | -0.015 |
Token | were |
Token ID | 547 |
Feature activation | -3.30e-02 |
Pos logit contributions | |
Prize | +0.186 |
vows | +0.182 |
coach | +0.180 |
ades | +0.177 |
apy | +0.174 |
Neg logit contributions | |
my | -0.158 |
i | -0.150 |
since | -0.145 |
bur | -0.142 |
owl | -0.141 |
Token | so |
Token ID | 523 |
Feature activation | -5.94e-02 |
Pos logit contributions | |
vows | +0.055 |
contest | +0.050 |
apy | +0.050 |
Prize | +0.050 |
trophy | +0.049 |
Neg logit contributions | |
bur | -0.064 |
i | -0.062 |
rying | -0.061 |
ppa | -0.060 |
ind | -0.060 |
Token | fun |
Token ID | 1257 |
Feature activation | -2.83e-02 |
Pos logit contributions | |
Prize | +0.092 |
trophy | +0.091 |
vows | +0.091 |
prize | +0.090 |
contest | +0.090 |
Neg logit contributions | |
ind | -0.105 |
i | -0.096 |
my | -0.090 |
ppa | -0.089 |
rying | -0.088 |
Token | . |
Token ID | 13 |
Feature activation | -4.52e-03 |
Pos logit contributions | |
vows | +0.058 |
apy | +0.052 |
trophy | +0.052 |
Prize | +0.051 |
contest | +0.051 |
Neg logit contributions | |
rying | -0.045 |
bur | -0.043 |
i | -0.043 |
ind | -0.041 |
ppa | -0.041 |
Token | She |
Token ID | 1375 |
Feature activation | -2.25e-02 |
Pos logit contributions | |
vows | +0.007 |
prize | +0.006 |
trophy | +0.006 |
contest | +0.006 |
apy | +0.005 |
Neg logit contributions | |
bur | -0.010 |
rying | -0.010 |
ppa | -0.010 |
i | -0.010 |
ind | -0.009 |
Token |
|
Token ID | 198 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
vows | +0.032 |
prize | +0.028 |
trophy | +0.028 |
contest | +0.027 |
cakes | +0.026 |
Neg logit contributions | |
bur | -0.035 |
ppa | -0.035 |
rying | -0.034 |
ind | -0.033 |
i | -0.033 |
Token | Da |
Token ID | 26531 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
vows | +0.053 |
prize | +0.047 |
trophy | +0.047 |
contest | +0.044 |
cakes | +0.044 |
Neg logit contributions | |
ppa | -0.042 |
bur | -0.041 |
ind | -0.041 |
rying | -0.040 |
i | -0.038 |
Token | isy |
Token ID | 13560 |
Feature activation | -3.24e-02 |
Pos logit contributions | |
bur | +0.027 |
rying | +0.026 |
ppa | +0.025 |
ind | +0.024 |
i | +0.024 |
Neg logit contributions | |
vows | -0.027 |
prize | -0.025 |
contest | -0.024 |
trophy | -0.024 |
cakes | -0.023 |
Token | started |
Token ID | 2067 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
vows | +0.058 |
prize | +0.055 |
trophy | +0.054 |
cakes | +0.054 |
contest | +0.053 |
Neg logit contributions | |
i | -0.058 |
ppa | -0.056 |
rying | -0.055 |
bur | -0.055 |
ind | -0.054 |
Token | making |
Token ID | 1642 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
vows | +0.065 |
cakes | +0.061 |
trophy | +0.061 |
prize | +0.060 |
ades | +0.059 |
Neg logit contributions | |
rying | -0.042 |
i | -0.041 |
ind | -0.040 |
bur | -0.039 |
ppa | -0.038 |
Token | videos |
Token ID | 5861 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
vows | +0.091 |
trophy | +0.082 |
case | +0.082 |
cakes | +0.081 |
Prize | +0.081 |
Neg logit contributions | |
i | -0.093 |
ind | -0.089 |
rying | -0.088 |
bur | -0.086 |
ppa | -0.086 |
Token | and |
Token ID | 290 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
vows | +0.268 |
Mine | +0.242 |
apy | +0.240 |
Prize | +0.231 |
ades | +0.226 |
Neg logit contributions | |
my | -0.113 |
owl | -0.098 |
rying | -0.093 |
since | -0.093 |
ting | -0.092 |
Token | put |
Token ID | 1234 |
Feature activation | -2.96e-02 |
Pos logit contributions | |
vows | +0.022 |
prize | +0.020 |
trophy | +0.020 |
contest | +0.019 |
cakes | +0.019 |
Neg logit contributions | |
rying | -0.024 |
bur | -0.024 |
ppa | -0.023 |
i | -0.023 |
ind | -0.022 |
Token | them |
Token ID | 606 |
Feature activation | -5.90e-02 |
Pos logit contributions | |
vows | +0.049 |
apy | +0.044 |
trophy | +0.043 |
Prize | +0.043 |
prize | +0.043 |
Neg logit contributions | |
bur | -0.059 |
i | -0.056 |
ppa | -0.055 |
rying | -0.055 |
ind | -0.054 |
Token | up |
Token ID | 510 |
Feature activation | -9.33e-03 |
Pos logit contributions | |
vows | +0.124 |
Prize | +0.115 |
apy | +0.113 |
Mine | +0.113 |
cakes | +0.112 |
Neg logit contributions | |
rying | -0.087 |
bur | -0.086 |
i | -0.081 |
ppa | -0.079 |
ind | -0.078 |
Token | on |
Token ID | 319 |
Feature activation | -2.99e-02 |
Pos logit contributions | |
vows | +0.018 |
prize | +0.016 |
trophy | +0.016 |
cakes | +0.015 |
contest | +0.015 |
Neg logit contributions | |
bur | -0.017 |
rying | -0.017 |
ppa | -0.016 |
i | -0.016 |
ind | -0.016 |
Token | characters |
Token ID | 3435 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
vows | +0.032 |
apy | +0.031 |
cakes | +0.024 |
ades | +0.024 |
case | +0.024 |
Neg logit contributions | |
bur | -0.064 |
ind | -0.062 |
rying | -0.062 |
my | -0.061 |
gie | -0.060 |
Token | and |
Token ID | 290 |
Feature activation | -3.95e-03 |
Pos logit contributions | |
vows | +0.137 |
apy | +0.124 |
ades | +0.124 |
Prize | +0.121 |
cakes | +0.120 |
Neg logit contributions | |
rying | -0.092 |
i | -0.091 |
bur | -0.085 |
ppa | -0.081 |
my | -0.079 |
Token | watching |
Token ID | 4964 |
Feature activation | -5.65e-02 |
Pos logit contributions | |
vows | +0.007 |
prize | +0.006 |
contest | +0.006 |
trophy | +0.006 |
cakes | +0.006 |
Neg logit contributions | |
bur | -0.008 |
rying | -0.007 |
ppa | -0.007 |
i | -0.007 |
ind | -0.007 |
Token | the |
Token ID | 262 |
Feature activation | -4.28e-02 |
Pos logit contributions | |
vows | +0.095 |
apy | +0.088 |
case | +0.086 |
Prize | +0.086 |
prize | +0.085 |
Neg logit contributions | |
i | -0.103 |
ind | -0.101 |
rying | -0.097 |
bur | -0.095 |
my | -0.095 |
Token | funny |
Token ID | 8258 |
Feature activation | -5.63e-02 |
Pos logit contributions | |
apy | +0.052 |
vows | +0.052 |
uits | +0.044 |
ades | +0.041 |
case | +0.040 |
Neg logit contributions | |
ind | -0.099 |
my | -0.095 |
bur | -0.094 |
rying | -0.091 |
owl | -0.091 |
Token | video |
Token ID | 2008 |
Feature activation | -1.06e-01 |
Pos logit contributions | |
apy | +0.074 |
vows | +0.072 |
uits | +0.070 |
case | +0.067 |
Prize | +0.064 |
Neg logit contributions | |
ind | -0.116 |
i | -0.112 |
my | -0.111 |
ping | -0.111 |
gie | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
vows | +0.233 |
apy | +0.217 |
Mine | +0.211 |
Prize | +0.210 |
disco | +0.206 |
Neg logit contributions | |
my | -0.122 |
rying | -0.122 |
i | -0.120 |
forth | -0.111 |
ting | -0.109 |
Token | She |
Token ID | 1375 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
vows | +0.047 |
trophy | +0.045 |
prize | +0.044 |
ades | +0.042 |
contest | +0.041 |
Neg logit contributions | |
bur | -0.045 |
my | -0.044 |
ety | -0.044 |
i | -0.044 |
rying | -0.043 |
Token | went |
Token ID | 1816 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
vows | +0.034 |
prize | +0.031 |
contest | +0.031 |
cakes | +0.031 |
trophy | +0.031 |
Neg logit contributions | |
bur | -0.032 |
i | -0.031 |
ppa | -0.031 |
rying | -0.031 |
ind | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -2.57e-02 |
Pos logit contributions | |
vows | +0.032 |
apy | +0.029 |
trophy | +0.029 |
prize | +0.028 |
contest | +0.028 |
Neg logit contributions | |
rying | -0.022 |
bur | -0.021 |
ppa | -0.020 |
i | -0.020 |
ind | -0.019 |
Token | the |
Token ID | 262 |
Feature activation | -3.15e-02 |
Pos logit contributions | |
vows | +0.043 |
cakes | +0.040 |
ades | +0.040 |
apy | +0.038 |
case | +0.035 |
Neg logit contributions | |
bur | -0.050 |
rying | -0.049 |
i | -0.047 |
ind | -0.047 |
my | -0.046 |
Token | a |
Token ID | 257 |
Feature activation | -4.26e-02 |
Pos logit contributions | |
vows | +0.068 |
Prize | +0.063 |
contest | +0.061 |
prize | +0.060 |
trophy | +0.060 |
Neg logit contributions | |
bur | -0.074 |
i | -0.074 |
ppa | -0.073 |
ind | -0.070 |
rying | -0.069 |
Token | funny |
Token ID | 8258 |
Feature activation | -3.82e-02 |
Pos logit contributions | |
vows | +0.060 |
cakes | +0.054 |
Prize | +0.053 |
contest | +0.053 |
uits | +0.052 |
Neg logit contributions | |
ind | -0.088 |
ppa | -0.086 |
bur | -0.085 |
cker | -0.084 |
i | -0.083 |
Token | face |
Token ID | 1986 |
Feature activation | -2.09e-02 |
Pos logit contributions | |
vows | +0.061 |
contest | +0.056 |
Prize | +0.055 |
cakes | +0.054 |
case | +0.053 |
Neg logit contributions | |
i | -0.071 |
bur | -0.071 |
ind | -0.070 |
cker | -0.070 |
ppa | -0.069 |
Token | . |
Token ID | 13 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
vows | +0.041 |
prize | +0.037 |
contest | +0.037 |
trophy | +0.037 |
Prize | +0.036 |
Neg logit contributions | |
rying | -0.035 |
bur | -0.034 |
i | -0.034 |
ppa | -0.034 |
ind | -0.032 |
Token | The |
Token ID | 383 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
trophy | +0.083 |
prize | +0.081 |
contest | +0.080 |
vows | +0.077 |
ades | +0.077 |
Neg logit contributions | |
ior | -0.072 |
ety | -0.063 |
gie | -0.063 |
i | -0.062 |
ind | -0.061 |
Token | sandwiches |
Token ID | 29777 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
vows | +0.021 |
apy | +0.019 |
contest | +0.018 |
Prize | +0.018 |
prize | +0.018 |
Neg logit contributions | |
bur | -0.036 |
ppa | -0.034 |
i | -0.034 |
rying | -0.034 |
ind | -0.033 |
Token | are |
Token ID | 389 |
Feature activation | -2.17e-02 |
Pos logit contributions | |
Prize | +0.155 |
igsaw | +0.152 |
vows | +0.148 |
ival | +0.148 |
books | +0.133 |
Neg logit contributions | |
forth | -0.194 |
i | -0.192 |
my | -0.184 |
bur | -0.182 |
bruised | -0.172 |
Token | spicy |
Token ID | 26880 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
vows | +0.036 |
contest | +0.032 |
Prize | +0.032 |
prize | +0.031 |
trophy | +0.031 |
Neg logit contributions | |
bur | -0.045 |
ppa | -0.043 |
i | -0.043 |
rying | -0.042 |
ind | -0.041 |
Token | ! |
Token ID | 0 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
vows | +0.021 |
contest | +0.019 |
prize | +0.019 |
trophy | +0.019 |
apy | +0.018 |
Neg logit contributions | |
bur | -0.018 |
rying | -0.018 |
i | -0.018 |
ppa | -0.017 |
ind | -0.017 |
Token | They |
Token ID | 1119 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
vows | +0.083 |
trophy | +0.083 |
prize | +0.083 |
contest | +0.082 |
ades | +0.075 |
Neg logit contributions | |
ior | -0.084 |
ppa | -0.074 |
bur | -0.074 |
ety | -0.073 |
ind | -0.072 |
Token | have |
Token ID | 423 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
vows | +0.072 |
cakes | +0.072 |
ades | +0.070 |
contest | +0.068 |
prize | +0.065 |
Neg logit contributions | |
i | -0.111 |
bur | -0.108 |
cker | -0.104 |
ppa | -0.103 |
rying | -0.102 |
Token | She |
Token ID | 1375 |
Feature activation | -2.40e-02 |
Pos logit contributions | |
vows | +0.007 |
prize | +0.006 |
contest | +0.006 |
trophy | +0.006 |
apy | +0.005 |
Neg logit contributions | |
bur | -0.009 |
rying | -0.009 |
ppa | -0.009 |
i | -0.008 |
ety | -0.008 |
Token | played |
Token ID | 2826 |
Feature activation | -7.55e-02 |
Pos logit contributions | |
vows | +0.048 |
prize | +0.046 |
contest | +0.045 |
trophy | +0.045 |
cakes | +0.045 |
Neg logit contributions | |
ppa | -0.037 |
i | -0.037 |
bur | -0.036 |
rying | -0.035 |
ind | -0.034 |
Token | games |
Token ID | 1830 |
Feature activation | -7.28e-02 |
Pos logit contributions | |
vows | +0.180 |
apy | +0.156 |
Mine | +0.150 |
cakes | +0.149 |
Prize | +0.148 |
Neg logit contributions | |
owl | -0.089 |
asking | -0.089 |
rying | -0.086 |
forth | -0.083 |
ishing | -0.082 |
Token | and |
Token ID | 290 |
Feature activation | -9.77e-03 |
Pos logit contributions | |
vows | +0.183 |
apy | +0.175 |
Mine | +0.163 |
ades | +0.161 |
Sorry | +0.160 |
Neg logit contributions | |
my | -0.078 |
rying | -0.069 |
owl | -0.068 |
since | -0.067 |
asking | -0.066 |
Token | watched |
Token ID | 7342 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
vows | +0.016 |
prize | +0.014 |
trophy | +0.014 |
contest | +0.014 |
ades | +0.014 |
Neg logit contributions | |
bur | -0.019 |
rying | -0.019 |
ppa | -0.019 |
i | -0.019 |
ind | -0.018 |
Token | videos |
Token ID | 5861 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
vows | +0.095 |
Prize | +0.089 |
case | +0.085 |
ades | +0.083 |
� | +0.082 |
Neg logit contributions | |
ind | -0.073 |
rying | -0.072 |
asking | -0.072 |
i | -0.072 |
ting | -0.071 |
Token | on |
Token ID | 319 |
Feature activation | -3.32e-02 |
Pos logit contributions | |
vows | +0.258 |
apy | +0.243 |
Mine | +0.235 |
ades | +0.223 |
Prize | +0.223 |
Neg logit contributions | |
my | -0.103 |
ting | -0.102 |
since | -0.087 |
forth | -0.084 |
rying | -0.084 |
Token | the |
Token ID | 262 |
Feature activation | -1.73e-02 |
Pos logit contributions | |
vows | +0.066 |
apy | +0.060 |
cakes | +0.058 |
Prize | +0.058 |
ades | +0.058 |
Neg logit contributions | |
ind | -0.054 |
bur | -0.053 |
i | -0.052 |
ppa | -0.050 |
my | -0.048 |
Token | computer |
Token ID | 3644 |
Feature activation | -6.08e-02 |
Pos logit contributions | |
vows | +0.027 |
apy | +0.024 |
prize | +0.023 |
contest | +0.022 |
Prize | +0.022 |
Neg logit contributions | |
bur | -0.036 |
ind | -0.036 |
rying | -0.036 |
ppa | -0.035 |
ior | -0.034 |
Token | all |
Token ID | 477 |
Feature activation | +6.95e-03 |
Pos logit contributions | |
vows | +0.127 |
apy | +0.117 |
ades | +0.111 |
prize | +0.108 |
Prize | +0.108 |
Neg logit contributions | |
rying | -0.089 |
my | -0.088 |
i | -0.085 |
bur | -0.084 |
forth | -0.080 |
Token | day |
Token ID | 1110 |
Feature activation | -2.44e-02 |
Pos logit contributions | |
bur | +0.014 |
rying | +0.013 |
ppa | +0.013 |
i | +0.013 |
ind | +0.013 |
Neg logit contributions | |
vows | -0.012 |
prize | -0.011 |
contest | -0.011 |
trophy | -0.011 |
cakes | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -8.38e-03 |
Pos logit contributions | |
vows | +0.037 |
apy | +0.033 |
prize | +0.033 |
cakes | +0.033 |
contest | +0.032 |
Neg logit contributions | |
bur | -0.030 |
rying | -0.030 |
ppa | -0.029 |
i | -0.029 |
ind | -0.027 |
Token | arrows |
Token ID | 20507 |
Feature activation | -2.72e-02 |
Pos logit contributions | |
vows | +0.013 |
contest | +0.011 |
cakes | +0.011 |
prize | +0.011 |
trophy | +0.011 |
Neg logit contributions | |
bur | -0.018 |
ppa | -0.018 |
rying | -0.017 |
i | -0.017 |
ind | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
vows | +0.057 |
apy | +0.052 |
cakes | +0.052 |
Prize | +0.050 |
prize | +0.050 |
Neg logit contributions | |
bur | -0.042 |
rying | -0.041 |
i | -0.041 |
ppa | -0.040 |
cker | -0.038 |
Token | They |
Token ID | 1119 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
vows | +0.044 |
apy | +0.038 |
prize | +0.038 |
trophy | +0.038 |
contest | +0.035 |
Neg logit contributions | |
bur | -0.060 |
ety | -0.059 |
ior | -0.058 |
rying | -0.058 |
my | -0.058 |
Token | made |
Token ID | 925 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
vows | +0.038 |
cakes | +0.035 |
prize | +0.034 |
apy | +0.033 |
trophy | +0.033 |
Neg logit contributions | |
bur | -0.034 |
ppa | -0.034 |
i | -0.033 |
ety | -0.033 |
rying | -0.032 |
Token | them |
Token ID | 606 |
Feature activation | -1.04e-01 |
Pos logit contributions | |
vows | +0.062 |
cakes | +0.057 |
� | +0.057 |
contest | +0.055 |
apy | +0.054 |
Neg logit contributions | |
ind | -0.076 |
rying | -0.074 |
i | -0.073 |
bur | -0.073 |
ppa | -0.073 |
Token | from |
Token ID | 422 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
vows | +0.185 |
� | +0.183 |
cakes | +0.182 |
books | +0.169 |
apy | +0.166 |
Neg logit contributions | |
my | -0.177 |
rying | -0.166 |
forth | -0.165 |
ety | -0.164 |
i | -0.162 |
Token | sticks |
Token ID | 16461 |
Feature activation | -1.47e-02 |
Pos logit contributions | |
bur | +0.036 |
rying | +0.036 |
ppa | +0.036 |
i | +0.035 |
ind | +0.034 |
Neg logit contributions | |
vows | -0.022 |
prize | -0.020 |
contest | -0.019 |
trophy | -0.019 |
Prize | -0.017 |
Token | and |
Token ID | 290 |
Feature activation | +9.48e-03 |
Pos logit contributions | |
vows | +0.033 |
prize | +0.029 |
cakes | +0.029 |
contest | +0.029 |
apy | +0.029 |
Neg logit contributions | |
bur | -0.022 |
rying | -0.022 |
ppa | -0.021 |
i | -0.020 |
ind | -0.020 |
Token | strings |
Token ID | 13042 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
bur | +0.020 |
rying | +0.020 |
ppa | +0.020 |
ind | +0.019 |
i | +0.019 |
Neg logit contributions | |
vows | -0.015 |
prize | -0.014 |
contest | -0.013 |
trophy | -0.013 |
apy | -0.013 |
Token | and |
Token ID | 290 |
Feature activation | +4.43e-03 |
Pos logit contributions | |
vows | +0.076 |
cakes | +0.068 |
apy | +0.067 |
Prize | +0.067 |
prize | +0.067 |
Neg logit contributions | |
rying | -0.052 |
bur | -0.051 |
i | -0.049 |
ppa | -0.048 |
cker | -0.047 |
Token | They |
Token ID | 1119 |
Feature activation | -3.27e-02 |
Pos logit contributions | |
vows | +0.037 |
prize | +0.032 |
trophy | +0.032 |
contest | +0.030 |
apy | +0.029 |
Neg logit contributions | |
bur | -0.047 |
ety | -0.045 |
ior | -0.045 |
rying | -0.045 |
gie | -0.044 |
Token | shared |
Token ID | 4888 |
Feature activation | -4.47e-02 |
Pos logit contributions | |
vows | +0.063 |
prize | +0.061 |
apy | +0.061 |
ades | +0.059 |
trophy | +0.059 |
Neg logit contributions | |
i | -0.054 |
bur | -0.053 |
ppa | -0.053 |
rying | -0.053 |
my | -0.048 |
Token | food |
Token ID | 2057 |
Feature activation | -4.37e-02 |
Pos logit contributions | |
� | +0.074 |
vows | +0.073 |
Prize | +0.073 |
apy | +0.072 |
contest | +0.071 |
Neg logit contributions | |
bur | -0.078 |
my | -0.076 |
i | -0.074 |
ppa | -0.073 |
ind | -0.072 |
Token | and |
Token ID | 290 |
Feature activation | -4.63e-03 |
Pos logit contributions | |
vows | +0.102 |
Mine | +0.097 |
Prize | +0.097 |
apy | +0.096 |
contest | +0.093 |
Neg logit contributions | |
bur | -0.055 |
i | -0.054 |
ppa | -0.052 |
rying | -0.051 |
my | -0.047 |
Token | laughed |
Token ID | 13818 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
vows | +0.007 |
prize | +0.006 |
contest | +0.006 |
trophy | +0.006 |
apy | +0.006 |
Neg logit contributions | |
bur | -0.010 |
rying | -0.010 |
ppa | -0.010 |
i | -0.010 |
ind | -0.009 |
Token | a |
Token ID | 257 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
vows | +0.140 |
Prize | +0.136 |
Mine | +0.136 |
contest | +0.135 |
prize | +0.133 |
Neg logit contributions | |
rying | -0.066 |
i | -0.066 |
ping | -0.060 |
ind | -0.060 |
since | -0.059 |
Token | lot |
Token ID | 1256 |
Feature activation | -2.42e-02 |
Pos logit contributions | |
cakes | +0.135 |
vows | +0.131 |
case | +0.127 |
apy | +0.127 |
hips | +0.126 |
Neg logit contributions | |
ind | -0.163 |
my | -0.155 |
owl | -0.154 |
bur | -0.151 |
ppa | -0.150 |
Token | . |
Token ID | 13 |
Feature activation | -1.98e-02 |
Pos logit contributions | |
vows | +0.051 |
apy | +0.047 |
Mine | +0.047 |
contest | +0.045 |
Prize | +0.045 |
Neg logit contributions | |
rying | -0.038 |
ppa | -0.036 |
i | -0.036 |
bur | -0.035 |
ind | -0.035 |
Token |
|
Token ID | 198 |
Feature activation | -1.33e-02 |
Pos logit contributions | |
vows | +0.033 |
prize | +0.030 |
trophy | +0.030 |
contest | +0.029 |
ades | +0.028 |
Neg logit contributions | |
bur | -0.038 |
ior | -0.036 |
rying | -0.036 |
ety | -0.036 |
gie | -0.036 |
Token |
|
Token ID | 198 |
Feature activation | -2.90e-02 |
Pos logit contributions | |
vows | +0.022 |
prize | +0.019 |
trophy | +0.019 |
contest | +0.019 |
cakes | +0.018 |
Neg logit contributions | |
bur | -0.027 |
ppa | -0.026 |
rying | -0.026 |
ind | -0.026 |
i | -0.025 |
Token | The |
Token ID | 464 |
Feature activation | -1.82e-02 |
Pos logit contributions | |
vows | +0.066 |
prize | +0.060 |
trophy | +0.059 |
cakes | +0.058 |
contest | +0.056 |
Neg logit contributions | |
ind | -0.041 |
bur | -0.040 |
ppa | -0.040 |
rying | -0.039 |
cker | -0.036 |
Token | cheered |
Token ID | 34767 |
Feature activation | -4.00e-02 |
Pos logit contributions | |
vows | +0.058 |
ades | +0.055 |
prize | +0.053 |
case | +0.053 |
cakes | +0.053 |
Neg logit contributions | |
i | -0.060 |
bur | -0.057 |
ppa | -0.057 |
rying | -0.056 |
forth | -0.056 |
Token | very |
Token ID | 845 |
Feature activation | -6.26e-02 |
Pos logit contributions | |
vows | +0.096 |
case | +0.092 |
apy | +0.092 |
cakes | +0.091 |
Prize | +0.090 |
Neg logit contributions | |
rying | -0.049 |
i | -0.047 |
ind | -0.045 |
my | -0.041 |
forth | -0.040 |
Token | loudly |
Token ID | 23112 |
Feature activation | -3.59e-02 |
Pos logit contributions | |
cakes | +0.100 |
� | +0.096 |
vows | +0.094 |
Mine | +0.092 |
uits | +0.092 |
Neg logit contributions | |
ind | -0.120 |
i | -0.112 |
rying | -0.111 |
ppa | -0.104 |
aware | -0.097 |
Token | because |
Token ID | 780 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
vows | +0.075 |
apy | +0.072 |
trophy | +0.071 |
prize | +0.069 |
cakes | +0.069 |
Neg logit contributions | |
rying | -0.054 |
i | -0.050 |
ind | -0.048 |
bur | -0.048 |
gie | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | -5.30e-02 |
Pos logit contributions | |
vows | +0.038 |
ades | +0.029 |
prize | +0.028 |
Prize | +0.028 |
cakes | +0.027 |
Neg logit contributions | |
bur | -0.073 |
rying | -0.071 |
my | -0.071 |
ind | -0.070 |
owl | -0.070 |
Token | dance |
Token ID | 9280 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
vows | +0.080 |
apy | +0.079 |
ades | +0.073 |
cakes | +0.073 |
case | +0.067 |
Neg logit contributions | |
owl | -0.098 |
rying | -0.096 |
my | -0.093 |
forth | -0.093 |
ind | -0.092 |
Token | was |
Token ID | 373 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
vows | +0.184 |
apy | +0.180 |
Mine | +0.174 |
ades | +0.169 |
trophy | +0.162 |
Neg logit contributions | |
i | -0.144 |
rying | -0.143 |
ting | -0.134 |
row | -0.131 |
owl | -0.131 |
Token | so |
Token ID | 523 |
Feature activation | -6.09e-02 |
Pos logit contributions | |
vows | +0.075 |
cakes | +0.067 |
Mine | +0.066 |
apy | +0.065 |
prize | +0.065 |
Neg logit contributions | |
bur | -0.063 |
rying | -0.062 |
ppa | -0.057 |
i | -0.057 |
my | -0.056 |
Token | good |
Token ID | 922 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
vows | +0.110 |
� | +0.108 |
tray | +0.105 |
mat | +0.101 |
prize | +0.099 |
Neg logit contributions | |
ind | -0.095 |
rying | -0.088 |
ety | -0.087 |
aware | -0.083 |
my | -0.083 |
Token | . |
Token ID | 13 |
Feature activation | -3.33e-02 |
Pos logit contributions | |
vows | +0.050 |
apy | +0.045 |
Mine | +0.043 |
prize | +0.043 |
Prize | +0.043 |
Neg logit contributions | |
rying | -0.037 |
i | -0.035 |
bur | -0.035 |
ppa | -0.033 |
ind | -0.033 |
Token | Everyone |
Token ID | 11075 |
Feature activation | -4.42e-02 |
Pos logit contributions | |
vows | +0.053 |
trophy | +0.047 |
prize | +0.047 |
apy | +0.046 |
ades | +0.043 |
Neg logit contributions | |
ior | -0.064 |
bur | -0.064 |
my | -0.064 |
ety | -0.063 |
gie | -0.059 |
Token | taught |
Token ID | 7817 |
Feature activation | +1.28e-02 |
Pos logit contributions | |
vows | +0.022 |
prize | +0.021 |
contest | +0.020 |
cakes | +0.020 |
trophy | +0.020 |
Neg logit contributions | |
bur | -0.024 |
i | -0.023 |
rying | -0.023 |
ppa | -0.023 |
ind | -0.022 |
Token | her |
Token ID | 607 |
Feature activation | -3.87e-02 |
Pos logit contributions | |
rying | +0.029 |
bur | +0.029 |
ppa | +0.028 |
ind | +0.027 |
cker | +0.027 |
Neg logit contributions | |
vows | -0.018 |
prize | -0.016 |
contest | -0.016 |
trophy | -0.016 |
cakes | -0.015 |
Token | friends |
Token ID | 2460 |
Feature activation | -5.64e-02 |
Pos logit contributions | |
vows | +0.078 |
Prize | +0.072 |
contest | +0.071 |
Mine | +0.069 |
prize | +0.067 |
Neg logit contributions | |
i | -0.056 |
owl | -0.054 |
my | -0.054 |
ppa | -0.054 |
rying | -0.053 |
Token | and |
Token ID | 290 |
Feature activation | -9.29e-03 |
Pos logit contributions | |
vows | +0.123 |
Prize | +0.109 |
prize | +0.108 |
contest | +0.108 |
apy | +0.108 |
Neg logit contributions | |
my | -0.080 |
i | -0.080 |
rying | -0.079 |
bur | -0.074 |
ind | -0.072 |
Token | her |
Token ID | 607 |
Feature activation | -4.16e-02 |
Pos logit contributions | |
vows | +0.014 |
prize | +0.013 |
contest | +0.013 |
trophy | +0.012 |
cakes | +0.012 |
Neg logit contributions | |
bur | -0.020 |
rying | -0.019 |
ppa | -0.019 |
i | -0.019 |
ind | -0.018 |
Token | sisters |
Token ID | 15153 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
vows | +0.089 |
Prize | +0.081 |
Mine | +0.081 |
cakes | +0.079 |
apy | +0.079 |
Neg logit contributions | |
owl | -0.054 |
axe | -0.053 |
rying | -0.051 |
i | -0.051 |
my | -0.051 |
Token | how |
Token ID | 703 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
vows | +0.199 |
Prize | +0.182 |
apy | +0.174 |
Bang | +0.174 |
disco | +0.173 |
Neg logit contributions | |
my | -0.154 |
aware | -0.152 |
rying | -0.147 |
i | -0.136 |
asking | -0.135 |
Token | to |
Token ID | 284 |
Feature activation | -3.20e-03 |
Pos logit contributions | |
vows | +0.054 |
prize | +0.048 |
trophy | +0.046 |
Prize | +0.046 |
contest | +0.046 |
Neg logit contributions | |
rying | -0.039 |
i | -0.035 |
ppa | -0.035 |
ety | -0.034 |
bur | -0.034 |
Token | build |
Token ID | 1382 |
Feature activation | -4.92e-02 |
Pos logit contributions | |
vows | +0.005 |
prize | +0.004 |
contest | +0.004 |
cakes | +0.004 |
trophy | +0.004 |
Neg logit contributions | |
bur | -0.007 |
rying | -0.007 |
ppa | -0.007 |
i | -0.007 |
ind | -0.007 |
Token | them |
Token ID | 606 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
vows | +0.097 |
Prize | +0.081 |
cakes | +0.080 |
trophy | +0.078 |
apy | +0.077 |
Neg logit contributions | |
rying | -0.086 |
bur | -0.081 |
i | -0.080 |
my | -0.079 |
ishing | -0.077 |
Token | too |
Token ID | 1165 |
Feature activation | -2.38e-02 |
Pos logit contributions | |
vows | +0.119 |
Prize | +0.096 |
Mine | +0.096 |
apy | +0.094 |
cakes | +0.093 |
Neg logit contributions | |
rying | -0.100 |
my | -0.085 |
forth | -0.085 |
bur | -0.084 |
i | -0.083 |
Token | the |
Token ID | 262 |
Feature activation | -3.78e-03 |
Pos logit contributions | |
vows | +0.006 |
prize | +0.005 |
contest | +0.005 |
trophy | +0.005 |
cakes | +0.005 |
Neg logit contributions | |
bur | -0.008 |
rying | -0.008 |
ppa | -0.008 |
i | -0.008 |
ind | -0.007 |
Token | pictures |
Token ID | 5986 |
Feature activation | -5.50e-02 |
Pos logit contributions | |
vows | +0.005 |
apy | +0.004 |
prize | +0.004 |
contest | +0.004 |
trophy | +0.004 |
Neg logit contributions | |
bur | -0.009 |
rying | -0.008 |
ppa | -0.008 |
ind | -0.008 |
i | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | +6.94e-03 |
Pos logit contributions | |
vows | +0.130 |
Prize | +0.118 |
Mine | +0.117 |
apy | +0.115 |
ades | +0.114 |
Neg logit contributions | |
my | -0.064 |
i | -0.063 |
rying | -0.061 |
bur | -0.059 |
owl | -0.059 |
Token | said |
Token ID | 531 |
Feature activation | -6.51e-02 |
Pos logit contributions | |
bur | +0.013 |
rying | +0.013 |
ppa | +0.013 |
ind | +0.012 |
i | +0.012 |
Neg logit contributions | |
vows | -0.013 |
prize | -0.011 |
contest | -0.011 |
trophy | -0.011 |
cakes | -0.011 |
Token | the |
Token ID | 262 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
Mine | +0.132 |
� | +0.131 |
case | +0.127 |
vows | +0.126 |
blast | +0.125 |
Neg logit contributions | |
i | -0.082 |
owl | -0.081 |
Owl | -0.074 |
ppa | -0.073 |
asking | -0.071 |
Token | names |
Token ID | 3891 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
vows | +0.025 |
apy | +0.024 |
cakes | +0.022 |
ades | +0.022 |
trophy | +0.021 |
Neg logit contributions | |
bur | -0.035 |
ppa | -0.035 |
rying | -0.035 |
ind | -0.034 |
i | -0.034 |
Token | of |
Token ID | 286 |
Feature activation | -2.60e-02 |
Pos logit contributions | |
Prize | +0.207 |
� | +0.207 |
vows | +0.205 |
apy | +0.200 |
Mine | +0.199 |
Neg logit contributions | |
my | -0.131 |
i | -0.121 |
owl | -0.111 |
bur | -0.107 |
ting | -0.103 |
Token | the |
Token ID | 262 |
Feature activation | -1.25e-02 |
Pos logit contributions | |
vows | +0.046 |
cakes | +0.042 |
apy | +0.042 |
case | +0.041 |
ades | +0.040 |
Neg logit contributions | |
bur | -0.048 |
i | -0.047 |
ind | -0.046 |
ppa | -0.046 |
rying | -0.045 |
Token | things |
Token ID | 1243 |
Feature activation | -7.72e-02 |
Pos logit contributions | |
vows | +0.018 |
apy | +0.017 |
trophy | +0.016 |
cakes | +0.016 |
prize | +0.016 |
Neg logit contributions | |
bur | -0.026 |
rying | -0.026 |
ppa | -0.026 |
ind | -0.026 |
i | -0.025 |
Token | she |
Token ID | 673 |
Feature activation | +1.00e-02 |
Pos logit contributions | |
vows | +0.153 |
Prize | +0.144 |
apy | +0.139 |
blast | +0.137 |
Mine | +0.137 |
Neg logit contributions | |
i | -0.120 |
my | -0.110 |
rying | -0.109 |
bur | -0.107 |
owl | -0.104 |
Token | saw |
Token ID | 2497 |
Feature activation | +2.61e-03 |
Pos logit contributions | |
bur | +0.020 |
rying | +0.020 |
ppa | +0.019 |
ind | +0.018 |
i | +0.018 |
Neg logit contributions | |
vows | -0.017 |
prize | -0.016 |
contest | -0.015 |
trophy | -0.015 |
cakes | -0.015 |
Token | funny |
Token ID | 8258 |
Feature activation | -5.21e-02 |
Pos logit contributions | |
vows | +0.081 |
apy | +0.081 |
ades | +0.067 |
ves | +0.067 |
Prize | +0.064 |
Neg logit contributions | |
my | -0.102 |
bur | -0.098 |
owl | -0.094 |
ind | -0.090 |
ior | -0.089 |
Token | animals |
Token ID | 4695 |
Feature activation | -4.57e-02 |
Pos logit contributions | |
vows | +0.076 |
apy | +0.070 |
Prize | +0.068 |
prize | +0.067 |
contest | +0.067 |
Neg logit contributions | |
my | -0.105 |
ind | -0.100 |
ping | -0.099 |
ior | -0.098 |
owl | -0.097 |
Token | and |
Token ID | 290 |
Feature activation | -1.29e-02 |
Pos logit contributions | |
vows | +0.107 |
Mine | +0.099 |
apy | +0.097 |
prize | +0.095 |
Prize | +0.095 |
Neg logit contributions | |
i | -0.063 |
rying | -0.060 |
bur | -0.059 |
my | -0.056 |
ppa | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
vows | +0.021 |
prize | +0.019 |
contest | +0.019 |
trophy | +0.019 |
ades | +0.018 |
Neg logit contributions | |
bur | -0.026 |
ppa | -0.025 |
i | -0.025 |
rying | -0.025 |
ety | -0.024 |
Token | silly |
Token ID | 14397 |
Feature activation | -2.85e-02 |
Pos logit contributions | |
vows | +0.042 |
apy | +0.039 |
prize | +0.037 |
cakes | +0.037 |
trophy | +0.036 |
Neg logit contributions | |
bur | -0.043 |
rying | -0.040 |
ind | -0.040 |
i | -0.039 |
gie | -0.039 |
Token | jokes |
Token ID | 14532 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
vows | +0.052 |
apy | +0.048 |
prize | +0.048 |
trophy | +0.047 |
contest | +0.047 |
Neg logit contributions | |
i | -0.048 |
ind | -0.048 |
bur | -0.047 |
rying | -0.047 |
gie | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | -2.24e-02 |
Pos logit contributions | |
vows | +0.220 |
igsaw | +0.217 |
Prize | +0.215 |
Mine | +0.211 |
ades | +0.206 |
Neg logit contributions | |
i | -0.114 |
ting | -0.107 |
my | -0.101 |
bur | -0.097 |
gie | -0.097 |
Token | But |
Token ID | 887 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
vows | +0.039 |
prize | +0.035 |
trophy | +0.035 |
contest | +0.033 |
apy | +0.033 |
Neg logit contributions | |
bur | -0.044 |
ety | -0.043 |
my | -0.042 |
ior | -0.042 |
rying | -0.039 |
Token | sometimes |
Token ID | 3360 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
rying | +0.035 |
bur | +0.034 |
ppa | +0.034 |
ind | +0.033 |
i | +0.032 |
Neg logit contributions | |
vows | -0.029 |
prize | -0.026 |
contest | -0.026 |
trophy | -0.025 |
apy | -0.025 |
Token | they |
Token ID | 484 |
Feature activation | -2.97e-02 |
Pos logit contributions | |
vows | +0.035 |
cakes | +0.031 |
ades | +0.029 |
prize | +0.029 |
trophy | +0.028 |
Neg logit contributions | |
i | -0.063 |
bur | -0.061 |
ppa | -0.060 |
rying | -0.059 |
ety | -0.058 |
Token | wanted |
Token ID | 2227 |
Feature activation | -3.11e-02 |
Pos logit contributions | |
vows | +0.056 |
prize | +0.052 |
cakes | +0.050 |
ades | +0.049 |
trophy | +0.049 |
Neg logit contributions | |
bur | -0.054 |
i | -0.053 |
ppa | -0.051 |
ety | -0.050 |
rying | -0.050 |
Token | diamond |
Token ID | 15291 |
Feature activation | -3.83e-02 |
Pos logit contributions | |
vows | +0.084 |
cakes | +0.082 |
ades | +0.074 |
apy | +0.072 |
ves | +0.069 |
Neg logit contributions | |
owl | -0.103 |
bur | -0.099 |
cker | -0.098 |
axe | -0.097 |
my | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
vows | +0.076 |
apy | +0.070 |
cakes | +0.069 |
Mine | +0.069 |
ades | +0.068 |
Neg logit contributions | |
i | -0.060 |
rying | -0.059 |
bur | -0.059 |
cker | -0.057 |
gie | -0.055 |
Token | They |
Token ID | 1119 |
Feature activation | -5.02e-02 |
Pos logit contributions | |
vows | +0.022 |
trophy | +0.020 |
prize | +0.020 |
contest | +0.019 |
cakes | +0.018 |
Neg logit contributions | |
bur | -0.034 |
ety | -0.033 |
ppa | -0.033 |
rying | -0.033 |
i | -0.033 |
Token | said |
Token ID | 531 |
Feature activation | -7.40e-02 |
Pos logit contributions | |
vows | +0.084 |
cakes | +0.081 |
apy | +0.079 |
prize | +0.078 |
ades | +0.078 |
Neg logit contributions | |
i | -0.095 |
bur | -0.094 |
my | -0.092 |
ppa | -0.088 |
cker | -0.087 |
Token | the |
Token ID | 262 |
Feature activation | -2.41e-02 |
Pos logit contributions | |
� | +0.166 |
case | +0.156 |
cakes | +0.150 |
Mine | +0.149 |
books | +0.146 |
Neg logit contributions | |
i | -0.082 |
owl | -0.080 |
Owl | -0.072 |
asking | -0.071 |
ener | -0.068 |
Token | names |
Token ID | 3891 |
Feature activation | -1.02e-01 |
Pos logit contributions | |
vows | +0.037 |
apy | +0.034 |
cakes | +0.034 |
ades | +0.031 |
ves | +0.029 |
Neg logit contributions | |
bur | -0.049 |
rying | -0.047 |
owl | -0.047 |
cker | -0.047 |
my | -0.046 |
Token | of |
Token ID | 286 |
Feature activation | -3.02e-02 |
Pos logit contributions | |
vows | +0.205 |
� | +0.203 |
Prize | +0.195 |
Mine | +0.190 |
apy | +0.190 |
Neg logit contributions | |
my | -0.131 |
i | -0.122 |
owl | -0.111 |
ener | -0.107 |
ie | -0.106 |
Token | the |
Token ID | 262 |
Feature activation | -2.21e-02 |
Pos logit contributions | |
vows | +0.055 |
cakes | +0.051 |
case | +0.051 |
apy | +0.049 |
prize | +0.047 |
Neg logit contributions | |
bur | -0.054 |
i | -0.053 |
ind | -0.052 |
rying | -0.050 |
ppa | -0.050 |
Token | shapes |
Token ID | 15268 |
Feature activation | -1.03e-01 |
Pos logit contributions | |
vows | +0.034 |
apy | +0.031 |
cakes | +0.030 |
ades | +0.028 |
case | +0.027 |
Neg logit contributions | |
bur | -0.045 |
rying | -0.044 |
i | -0.043 |
ind | -0.043 |
my | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | -8.87e-03 |
Pos logit contributions | |
vows | +0.224 |
Mine | +0.219 |
Goal | +0.218 |
apy | +0.217 |
� | +0.217 |
Neg logit contributions | |
i | -0.126 |
my | -0.116 |
rying | -0.106 |
cker | -0.101 |
owl | -0.101 |
Token | looked |
Token ID | 3114 |
Feature activation | -4.17e-02 |
Pos logit contributions | |
vows | +0.013 |
prize | +0.012 |
contest | +0.011 |
cakes | +0.011 |
trophy | +0.011 |
Neg logit contributions | |
bur | -0.019 |
rying | -0.019 |
ppa | -0.018 |
i | -0.018 |
ind | -0.018 |
Token | a |
Token ID | 257 |
Feature activation | -7.83e-02 |
Pos logit contributions | |
vows | +0.113 |
cakes | +0.095 |
apy | +0.094 |
Mine | +0.094 |
Prize | +0.093 |
Neg logit contributions | |
rying | -0.060 |
owl | -0.054 |
ishing | -0.053 |
bur | -0.051 |
ppa | -0.051 |
Token | game |
Token ID | 983 |
Feature activation | -4.13e-02 |
Pos logit contributions | |
vows | +0.100 |
uits | +0.091 |
apy | +0.088 |
cakes | +0.086 |
Both | +0.086 |
Neg logit contributions | |
ind | -0.173 |
rying | -0.154 |
ppa | -0.153 |
owl | -0.153 |
ich | -0.147 |
Token | . |
Token ID | 13 |
Feature activation | -7.28e-03 |
Pos logit contributions | |
vows | +0.091 |
apy | +0.075 |
trophy | +0.074 |
prize | +0.073 |
Prize | +0.073 |
Neg logit contributions | |
rying | -0.065 |
bur | -0.060 |
my | -0.058 |
ppa | -0.057 |
i | -0.057 |
Token | She |
Token ID | 1375 |
Feature activation | +3.84e-03 |
Pos logit contributions | |
vows | +0.012 |
prize | +0.010 |
trophy | +0.010 |
contest | +0.010 |
ades | +0.010 |
Neg logit contributions | |
bur | -0.015 |
ppa | -0.015 |
rying | -0.015 |
ety | -0.014 |
i | -0.014 |
Token | won |
Token ID | 1839 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
bur | +0.007 |
rying | +0.007 |
ppa | +0.007 |
i | +0.007 |
ind | +0.007 |
Neg logit contributions | |
vows | -0.007 |
prize | -0.006 |
contest | -0.006 |
trophy | -0.006 |
cakes | -0.006 |
Token | a |
Token ID | 257 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
vows | +0.046 |
trophy | +0.040 |
prize | +0.038 |
apy | +0.038 |
ades | +0.038 |
Neg logit contributions | |
bur | -0.042 |
rying | -0.041 |
ppa | -0.040 |
i | -0.039 |
my | -0.038 |
Token | prize |
Token ID | 11596 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
uits | +0.128 |
vows | +0.119 |
apy | +0.117 |
are | +0.106 |
Everybody | +0.099 |
Neg logit contributions | |
ind | -0.207 |
ety | -0.195 |
owl | -0.193 |
rying | -0.192 |
ppa | -0.186 |
Token | ! |
Token ID | 0 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
vows | +0.059 |
apy | +0.053 |
Mine | +0.050 |
ades | +0.050 |
trophy | +0.049 |
Neg logit contributions | |
rying | -0.041 |
bur | -0.040 |
i | -0.039 |
ppa | -0.039 |
ety | -0.036 |
Token | It |
Token ID | 632 |
Feature activation | -3.60e-02 |
Pos logit contributions | |
vows | +0.018 |
prize | +0.015 |
trophy | +0.015 |
contest | +0.015 |
ades | +0.015 |
Neg logit contributions | |
bur | -0.022 |
ppa | -0.021 |
ety | -0.021 |
rying | -0.021 |
my | -0.020 |
Token | was |
Token ID | 373 |
Feature activation | -2.68e-02 |
Pos logit contributions | |
vows | +0.074 |
apy | +0.065 |
prize | +0.064 |
trophy | +0.064 |
ades | +0.063 |
Neg logit contributions | |
bur | -0.060 |
i | -0.058 |
my | -0.057 |
rying | -0.055 |
ety | -0.055 |
Token | a |
Token ID | 257 |
Feature activation | -6.62e-02 |
Pos logit contributions | |
vows | +0.055 |
trophy | +0.047 |
ades | +0.047 |
apy | +0.046 |
cakes | +0.046 |
Neg logit contributions | |
bur | -0.047 |
i | -0.042 |
ppa | -0.042 |
rying | -0.042 |
ety | -0.042 |
Token | talked |
Token ID | 6619 |
Feature activation | -5.57e-02 |
Pos logit contributions | |
vows | +0.069 |
prize | +0.069 |
trophy | +0.068 |
contest | +0.067 |
Prize | +0.065 |
Neg logit contributions | |
ppa | -0.054 |
i | -0.053 |
bur | -0.052 |
ety | -0.048 |
rying | -0.048 |
Token | to |
Token ID | 284 |
Feature activation | -1.16e-02 |
Pos logit contributions | |
vows | +0.134 |
� | +0.133 |
Prize | +0.131 |
apy | +0.131 |
trophy | +0.130 |
Neg logit contributions | |
my | -0.056 |
bur | -0.048 |
rying | -0.047 |
i | -0.047 |
ppa | -0.047 |
Token | them |
Token ID | 606 |
Feature activation | -7.02e-02 |
Pos logit contributions | |
vows | +0.017 |
prize | +0.015 |
trophy | +0.015 |
contest | +0.015 |
cakes | +0.015 |
Neg logit contributions | |
bur | -0.025 |
ppa | -0.025 |
i | -0.024 |
rying | -0.024 |
ind | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
apy | +0.171 |
vows | +0.171 |
Mine | +0.164 |
Prize | +0.162 |
� | +0.159 |
Neg logit contributions | |
i | -0.076 |
rying | -0.073 |
my | -0.072 |
bur | -0.063 |
owl | -0.062 |
Token | made |
Token ID | 925 |
Feature activation | -3.69e-02 |
Pos logit contributions | |
vows | +0.030 |
prize | +0.028 |
trophy | +0.027 |
contest | +0.027 |
ades | +0.027 |
Neg logit contributions | |
bur | -0.029 |
ppa | -0.029 |
rying | -0.028 |
i | -0.028 |
ety | -0.026 |
Token | them |
Token ID | 606 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
vows | +0.055 |
Prize | +0.052 |
trophy | +0.052 |
prize | +0.051 |
contest | +0.051 |
Neg logit contributions | |
i | -0.075 |
ind | -0.074 |
rying | -0.074 |
bur | -0.073 |
ppa | -0.073 |
Token | talk |
Token ID | 1561 |
Feature activation | -6.20e-02 |
Pos logit contributions | |
� | +0.163 |
Prize | +0.156 |
vows | +0.149 |
Mine | +0.146 |
ival | +0.142 |
Neg logit contributions | |
my | -0.189 |
rying | -0.186 |
i | -0.173 |
ety | -0.166 |
bur | -0.165 |
Token | back |
Token ID | 736 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
apy | +0.148 |
� | +0.147 |
Prize | +0.142 |
vows | +0.142 |
Mine | +0.141 |
Neg logit contributions | |
my | -0.065 |
rying | -0.065 |
ind | -0.061 |
i | -0.060 |
owl | -0.058 |
Token | . |
Token ID | 13 |
Feature activation | -1.41e-02 |
Pos logit contributions | |
vows | +0.033 |
contest | +0.030 |
prize | +0.030 |
apy | +0.030 |
trophy | +0.030 |
Neg logit contributions | |
rying | -0.028 |
bur | -0.028 |
ind | -0.027 |
i | -0.027 |
ppa | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +9.07e-03 |
Pos logit contributions | |
vows | +0.023 |
prize | +0.021 |
trophy | +0.021 |
contest | +0.020 |
cakes | +0.019 |
Neg logit contributions | |
bur | -0.029 |
ppa | -0.028 |
rying | -0.027 |
ety | -0.027 |
i | -0.027 |
Token |
|
Token ID | 198 |
Feature activation | +9.30e-03 |
Pos logit contributions | |
bur | +0.021 |
rying | +0.021 |
ppa | +0.021 |
i | +0.021 |
ind | +0.020 |
Neg logit contributions | |
vows | -0.012 |
prize | -0.010 |
contest | -0.010 |
trophy | -0.010 |
apy | -0.010 |
Token | dolls |
Token ID | 36062 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
apy | +0.034 |
vows | +0.034 |
cakes | +0.031 |
ades | +0.031 |
case | +0.031 |
Neg logit contributions | |
bur | -0.048 |
ppa | -0.048 |
rying | -0.046 |
i | -0.046 |
ind | -0.046 |
Token | ' |
Token ID | 6 |
Feature activation | -4.06e-03 |
Pos logit contributions | |
vows | +0.061 |
Prize | +0.055 |
apy | +0.055 |
Mine | +0.055 |
cakes | +0.054 |
Neg logit contributions | |
rying | -0.044 |
bur | -0.043 |
i | -0.042 |
ppa | -0.042 |
ind | -0.039 |
Token | hands |
Token ID | 2832 |
Feature activation | +9.05e-04 |
Pos logit contributions | |
vows | +0.006 |
prize | +0.006 |
trophy | +0.006 |
contest | +0.006 |
apy | +0.006 |
Neg logit contributions | |
bur | -0.008 |
rying | -0.008 |
ppa | -0.008 |
ind | -0.008 |
i | -0.008 |
Token | and |
Token ID | 290 |
Feature activation | -1.42e-02 |
Pos logit contributions | |
bur | +0.002 |
rying | +0.002 |
ppa | +0.002 |
i | +0.001 |
ind | +0.001 |
Neg logit contributions | |
vows | -0.002 |
prize | -0.002 |
contest | -0.002 |
trophy | -0.002 |
cakes | -0.002 |
Token | made |
Token ID | 925 |
Feature activation | -4.93e-02 |
Pos logit contributions | |
vows | +0.024 |
prize | +0.022 |
contest | +0.022 |
trophy | +0.022 |
cakes | +0.022 |
Neg logit contributions | |
bur | -0.027 |
ppa | -0.027 |
i | -0.026 |
rying | -0.026 |
cker | -0.025 |
Token | them |
Token ID | 606 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
� | +0.075 |
vows | +0.075 |
trophy | +0.072 |
Prize | +0.071 |
contest | +0.071 |
Neg logit contributions | |
i | -0.093 |
ind | -0.092 |
rying | -0.091 |
ppa | -0.090 |
bur | -0.089 |
Token | say |
Token ID | 910 |
Feature activation | -9.12e-02 |
Pos logit contributions | |
� | +0.154 |
Prize | +0.136 |
Mine | +0.134 |
vows | +0.130 |
cakes | +0.126 |
Neg logit contributions | |
rying | -0.194 |
my | -0.190 |
i | -0.189 |
aware | -0.174 |
bur | -0.174 |
Token | , |
Token ID | 11 |
Feature activation | -4.56e-02 |
Pos logit contributions | |
Mine | +0.184 |
case | +0.169 |
� | +0.165 |
trophy | +0.158 |
igsaw | +0.157 |
Neg logit contributions | |
i | -0.120 |
owl | -0.109 |
asking | -0.107 |
ppa | -0.106 |
rying | -0.102 |
Token | " |
Token ID | 366 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
vows | +0.070 |
prize | +0.065 |
trophy | +0.063 |
case | +0.063 |
contest | +0.062 |
Neg logit contributions | |
gie | -0.089 |
rying | -0.088 |
bur | -0.086 |
ppa | -0.085 |
i | -0.084 |
Token | I |
Token ID | 40 |
Feature activation | -4.88e-02 |
Pos logit contributions | |
vows | +0.030 |
trophy | +0.028 |
prize | +0.028 |
apy | +0.027 |
contest | +0.027 |
Neg logit contributions | |
bur | -0.038 |
ppa | -0.037 |
ind | -0.036 |
i | -0.035 |
ety | -0.035 |
Token | do |
Token ID | 466 |
Feature activation | -5.06e-02 |
Pos logit contributions | |
cakes | +0.091 |
apy | +0.088 |
trophy | +0.087 |
ades | +0.087 |
vows | +0.086 |
Neg logit contributions | |
i | -0.081 |
bur | -0.080 |
rying | -0.074 |
my | -0.074 |
seen | -0.074 |
Token | fan |
Token ID | 4336 |
Feature activation | -1.72e-02 |
Pos logit contributions | |
vows | +0.071 |
Prize | +0.057 |
cakes | +0.057 |
apy | +0.056 |
case | +0.054 |
Neg logit contributions | |
bur | -0.082 |
my | -0.076 |
axe | -0.075 |
ind | -0.074 |
owl | -0.074 |
Token | . |
Token ID | 13 |
Feature activation | -3.40e-02 |
Pos logit contributions | |
vows | +0.033 |
apy | +0.029 |
prize | +0.029 |
trophy | +0.029 |
cakes | +0.028 |
Neg logit contributions | |
rying | -0.031 |
bur | -0.030 |
i | -0.029 |
ppa | -0.028 |
ind | -0.028 |
Token | They |
Token ID | 1119 |
Feature activation | -6.04e-02 |
Pos logit contributions | |
vows | +0.056 |
trophy | +0.050 |
prize | +0.048 |
contest | +0.046 |
festival | +0.045 |
Neg logit contributions | |
gie | -0.067 |
bur | -0.064 |
ety | -0.063 |
rying | -0.063 |
my | -0.063 |
Token | pretend |
Token ID | 16614 |
Feature activation | -5.27e-02 |
Pos logit contributions | |
cakes | +0.109 |
vows | +0.106 |
ades | +0.101 |
apy | +0.093 |
ival | +0.088 |
Neg logit contributions | |
my | -0.115 |
bur | -0.114 |
i | -0.110 |
forth | -0.109 |
ety | -0.104 |
Token | the |
Token ID | 262 |
Feature activation | -4.34e-02 |
Pos logit contributions | |
vows | +0.107 |
Prize | +0.099 |
� | +0.098 |
Mine | +0.095 |
prize | +0.093 |
Neg logit contributions | |
bur | -0.070 |
rying | -0.069 |
owl | -0.069 |
i | -0.068 |
forth | -0.068 |
Token | shapes |
Token ID | 15268 |
Feature activation | -1.01e-01 |
Pos logit contributions | |
vows | +0.069 |
apy | +0.061 |
cakes | +0.059 |
Prize | +0.058 |
uits | +0.057 |
Neg logit contributions | |
bur | -0.086 |
owl | -0.078 |
my | -0.078 |
axe | -0.077 |
ind | -0.075 |
Token | are |
Token ID | 389 |
Feature activation | -1.07e-02 |
Pos logit contributions | |
vows | +0.196 |
� | +0.187 |
Prize | +0.186 |
ival | +0.184 |
cakes | +0.183 |
Neg logit contributions | |
i | -0.143 |
rying | -0.136 |
cker | -0.135 |
my | -0.134 |
bur | -0.130 |
Token | flying |
Token ID | 7348 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
vows | +0.021 |
prize | +0.019 |
cakes | +0.019 |
trophy | +0.019 |
contest | +0.019 |
Neg logit contributions | |
bur | -0.019 |
rying | -0.018 |
ppa | -0.018 |
i | -0.017 |
ind | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
vows | +0.064 |
cakes | +0.057 |
apy | +0.057 |
trophy | +0.055 |
prize | +0.054 |
Neg logit contributions | |
rying | -0.040 |
bur | -0.039 |
i | -0.038 |
ind | -0.037 |
ety | -0.036 |
Token | They |
Token ID | 1119 |
Feature activation | -6.73e-02 |
Pos logit contributions | |
vows | +0.052 |
trophy | +0.047 |
prize | +0.045 |
contest | +0.042 |
festival | +0.042 |
Neg logit contributions | |
gie | -0.066 |
bur | -0.064 |
ety | -0.064 |
my | -0.063 |
rying | -0.063 |
Token | have |
Token ID | 423 |
Feature activation | -4.50e-02 |
Pos logit contributions | |
cakes | +0.118 |
vows | +0.110 |
ades | +0.107 |
apy | +0.099 |
ival | +0.095 |
Neg logit contributions | |
bur | -0.129 |
my | -0.129 |
i | -0.127 |
forth | -0.123 |
cker | -0.119 |
Token | . |
Token ID | 13 |
Feature activation | -5.14e-02 |
Pos logit contributions | |
vows | +0.132 |
Prize | +0.123 |
cakes | +0.121 |
apy | +0.121 |
prize | +0.118 |
Neg logit contributions | |
rying | -0.072 |
i | -0.069 |
my | -0.065 |
bur | -0.063 |
cker | -0.061 |
Token | They |
Token ID | 1119 |
Feature activation | -4.54e-02 |
Pos logit contributions | |
vows | +0.089 |
prize | +0.084 |
trophy | +0.083 |
kin | +0.081 |
ades | +0.081 |
Neg logit contributions | |
ior | -0.090 |
ety | -0.079 |
gie | -0.077 |
my | -0.076 |
bur | -0.074 |
Token | both |
Token ID | 1111 |
Feature activation | -3.74e-02 |
Pos logit contributions | |
vows | +0.069 |
cakes | +0.068 |
apy | +0.063 |
ades | +0.062 |
ves | +0.062 |
Neg logit contributions | |
i | -0.094 |
my | -0.093 |
bur | -0.092 |
rying | -0.088 |
ppa | -0.088 |
Token | think |
Token ID | 892 |
Feature activation | -5.39e-02 |
Pos logit contributions | |
vows | +0.052 |
cakes | +0.051 |
ades | +0.047 |
apy | +0.045 |
prize | +0.044 |
Neg logit contributions | |
i | -0.082 |
rying | -0.081 |
my | -0.081 |
bur | -0.080 |
cker | -0.079 |
Token | their |
Token ID | 511 |
Feature activation | -4.59e-02 |
Pos logit contributions | |
vows | +0.102 |
Prize | +0.092 |
Mine | +0.089 |
� | +0.087 |
cakes | +0.084 |
Neg logit contributions | |
i | -0.081 |
rying | -0.076 |
my | -0.075 |
owl | -0.074 |
asking | -0.074 |
Token | shapes |
Token ID | 15268 |
Feature activation | -9.94e-02 |
Pos logit contributions | |
cakes | +0.081 |
ades | +0.071 |
apy | +0.071 |
ival | +0.071 |
Prize | +0.071 |
Neg logit contributions | |
ind | -0.081 |
i | -0.074 |
owl | -0.072 |
bur | -0.071 |
ener | -0.070 |
Token | are |
Token ID | 389 |
Feature activation | -3.48e-02 |
Pos logit contributions | |
vows | +0.133 |
Prize | +0.128 |
cakes | +0.120 |
apy | +0.120 |
ival | +0.119 |
Neg logit contributions | |
my | -0.211 |
i | -0.203 |
cker | -0.197 |
rying | -0.194 |
bur | -0.191 |
Token | good |
Token ID | 922 |
Feature activation | -1.86e-02 |
Pos logit contributions | |
vows | +0.058 |
cakes | +0.053 |
apy | +0.051 |
Prize | +0.050 |
case | +0.050 |
Neg logit contributions | |
bur | -0.067 |
rying | -0.067 |
i | -0.066 |
ppa | -0.066 |
cker | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
vows | +0.039 |
apy | +0.035 |
cakes | +0.034 |
ades | +0.034 |
trophy | +0.034 |
Neg logit contributions | |
rying | -0.030 |
i | -0.029 |
bur | -0.028 |
ppa | -0.027 |
ety | -0.027 |
Token | But |
Token ID | 887 |
Feature activation | -4.00e-03 |
Pos logit contributions | |
vows | +0.039 |
trophy | +0.037 |
prize | +0.037 |
contest | +0.035 |
ades | +0.033 |
Neg logit contributions | |
ior | -0.055 |
bur | -0.053 |
ety | -0.053 |
my | -0.050 |
ind | -0.050 |
Token | they |
Token ID | 484 |
Feature activation | -3.17e-02 |
Pos logit contributions | |
vows | +0.006 |
prize | +0.006 |
trophy | +0.006 |
contest | +0.006 |
cakes | +0.006 |
Neg logit contributions | |
bur | -0.008 |
rying | -0.008 |
ppa | -0.008 |
i | -0.008 |
ind | -0.008 |
Token | pushed |
Token ID | 7121 |
Feature activation | +6.40e-03 |
Pos logit contributions | |
vows | +0.068 |
prize | +0.064 |
trophy | +0.061 |
contest | +0.060 |
Prize | +0.059 |
Neg logit contributions | |
ppa | -0.057 |
i | -0.057 |
my | -0.057 |
rying | -0.055 |
bur | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | -3.51e-02 |
Pos logit contributions | |
bur | +0.014 |
rying | +0.014 |
ppa | +0.014 |
ind | +0.013 |
i | +0.013 |
Neg logit contributions | |
vows | -0.010 |
prize | -0.009 |
contest | -0.008 |
trophy | -0.008 |
cakes | -0.008 |
Token | buttons |
Token ID | 12163 |
Feature activation | -3.81e-02 |
Pos logit contributions | |
vows | +0.046 |
apy | +0.044 |
prize | +0.039 |
ves | +0.039 |
Prize | +0.038 |
Neg logit contributions | |
my | -0.074 |
ind | -0.074 |
rying | -0.073 |
ener | -0.072 |
bur | -0.071 |
Token | and |
Token ID | 290 |
Feature activation | -8.03e-03 |
Pos logit contributions | |
vows | +0.088 |
Prize | +0.076 |
prize | +0.076 |
cakes | +0.075 |
contest | +0.074 |
Neg logit contributions | |
rying | -0.055 |
bur | -0.053 |
i | -0.051 |
my | -0.049 |
gie | -0.047 |
Token | the |
Token ID | 262 |
Feature activation | -3.85e-02 |
Pos logit contributions | |
vows | +0.015 |
prize | +0.013 |
trophy | +0.013 |
contest | +0.013 |
cakes | +0.012 |
Neg logit contributions | |
bur | -0.015 |
rying | -0.015 |
ppa | -0.014 |
i | -0.014 |
gie | -0.014 |
Token | images |
Token ID | 4263 |
Feature activation | -9.94e-02 |
Pos logit contributions | |
vows | +0.071 |
apy | +0.068 |
Prize | +0.065 |
ades | +0.065 |
ves | +0.064 |
Neg logit contributions | |
my | -0.058 |
ener | -0.058 |
owl | -0.057 |
ind | -0.056 |
rying | -0.056 |
Token | changed |
Token ID | 3421 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
vows | +0.180 |
Prize | +0.177 |
prize | +0.155 |
festival | +0.155 |
coach | +0.155 |
Neg logit contributions | |
rying | -0.156 |
forth | -0.153 |
i | -0.152 |
my | -0.148 |
ener | -0.144 |
Token | back |
Token ID | 736 |
Feature activation | +2.64e-03 |
Pos logit contributions | |
vows | +0.047 |
prize | +0.043 |
contest | +0.043 |
trophy | +0.043 |
cakes | +0.042 |
Neg logit contributions | |
rying | -0.043 |
bur | -0.041 |
i | -0.041 |
ind | -0.040 |
ppa | -0.039 |
Token | to |
Token ID | 284 |
Feature activation | -2.71e-02 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
i | +0.005 |
ind | +0.005 |
Neg logit contributions | |
vows | -0.005 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
cakes | -0.004 |
Token | the |
Token ID | 262 |
Feature activation | -2.33e-02 |
Pos logit contributions | |
vows | +0.045 |
cakes | +0.042 |
ades | +0.040 |
trophy | +0.040 |
prize | +0.039 |
Neg logit contributions | |
rying | -0.052 |
bur | -0.051 |
ind | -0.050 |
i | -0.049 |
my | -0.048 |
Token | way |
Token ID | 835 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
vows | +0.031 |
apy | +0.029 |
prize | +0.026 |
ves | +0.026 |
ades | +0.025 |
Neg logit contributions | |
ind | -0.052 |
rying | -0.051 |
bur | -0.051 |
my | -0.050 |
ppa | -0.049 |
Token | my |
Token ID | 1820 |
Feature activation | -1.05e-03 |
Pos logit contributions | |
rying | +0.032 |
bur | +0.031 |
ppa | +0.031 |
ind | +0.030 |
cker | +0.028 |
Neg logit contributions | |
vows | -0.046 |
prize | -0.042 |
contest | -0.042 |
trophy | -0.042 |
cakes | -0.041 |
Token | and |
Token ID | 290 |
Feature activation | -3.18e-03 |
Pos logit contributions | |
vows | +0.002 |
prize | +0.002 |
contest | +0.002 |
trophy | +0.002 |
apy | +0.002 |
Neg logit contributions | |
bur | -0.002 |
rying | -0.002 |
ppa | -0.002 |
i | -0.002 |
ind | -0.002 |
Token | daddy |
Token ID | 35822 |
Feature activation | -2.56e-02 |
Pos logit contributions | |
vows | +0.006 |
prize | +0.005 |
contest | +0.005 |
trophy | +0.005 |
cakes | +0.005 |
Neg logit contributions | |
bur | -0.006 |
ppa | -0.006 |
rying | -0.006 |
i | -0.006 |
ind | -0.006 |
Token | and |
Token ID | 290 |
Feature activation | -1.09e-02 |
Pos logit contributions | |
vows | +0.050 |
prize | +0.046 |
apy | +0.045 |
cakes | +0.045 |
contest | +0.045 |
Neg logit contributions | |
bur | -0.044 |
i | -0.044 |
rying | -0.043 |
ppa | -0.043 |
my | -0.041 |
Token | made |
Token ID | 925 |
Feature activation | -3.88e-02 |
Pos logit contributions | |
vows | +0.017 |
prize | +0.015 |
contest | +0.015 |
trophy | +0.015 |
ades | +0.015 |
Neg logit contributions | |
bur | -0.023 |
ppa | -0.022 |
i | -0.022 |
rying | -0.022 |
ety | -0.021 |
Token | them |
Token ID | 606 |
Feature activation | -9.93e-02 |
Pos logit contributions | |
vows | +0.067 |
Prize | +0.058 |
prize | +0.058 |
case | +0.058 |
trophy | +0.057 |
Neg logit contributions | |
i | -0.074 |
rying | -0.071 |
ind | -0.071 |
ppa | -0.071 |
bur | -0.070 |
Token | smile |
Token ID | 8212 |
Feature activation | -3.90e-02 |
Pos logit contributions | |
vows | +0.163 |
� | +0.148 |
Prize | +0.144 |
books | +0.143 |
case | +0.140 |
Neg logit contributions | |
my | -0.188 |
rying | -0.178 |
forth | -0.168 |
i | -0.161 |
bur | -0.157 |
Token | . |
Token ID | 13 |
Feature activation | -5.41e-03 |
Pos logit contributions | |
vows | +0.083 |
contest | +0.080 |
prize | +0.079 |
cakes | +0.079 |
ades | +0.078 |
Neg logit contributions | |
i | -0.055 |
rying | -0.054 |
bur | -0.052 |
ppa | -0.051 |
ind | -0.051 |
Token | One |
Token ID | 1881 |
Feature activation | -7.31e-03 |
Pos logit contributions | |
vows | +0.008 |
prize | +0.007 |
trophy | +0.007 |
contest | +0.007 |
cakes | +0.007 |
Neg logit contributions | |
bur | -0.012 |
rying | -0.012 |
ppa | -0.012 |
i | -0.011 |
ind | -0.011 |
Token | day |
Token ID | 1110 |
Feature activation | -4.31e-02 |
Pos logit contributions | |
vows | +0.015 |
prize | +0.013 |
cakes | +0.013 |
trophy | +0.013 |
contest | +0.013 |
Neg logit contributions | |
bur | -0.012 |
rying | -0.012 |
i | -0.012 |
ppa | -0.012 |
ind | -0.011 |
Token | , |
Token ID | 11 |
Feature activation | -2.35e-02 |
Pos logit contributions | |
vows | +0.089 |
ades | +0.085 |
case | +0.084 |
trophy | +0.084 |
cakes | +0.081 |
Neg logit contributions | |
i | -0.065 |
ppa | -0.057 |
bur | -0.057 |
my | -0.055 |
Owl | -0.054 |
Token | for |
Token ID | 329 |
Feature activation | +1.82e-02 |
Pos logit contributions | |
vows | +0.004 |
prize | +0.003 |
contest | +0.003 |
trophy | +0.003 |
apy | +0.003 |
Neg logit contributions | |
bur | -0.004 |
rying | -0.004 |
ppa | -0.004 |
i | -0.004 |
ind | -0.004 |
Token | him |
Token ID | 683 |
Feature activation | +7.40e-03 |
Pos logit contributions | |
rying | +0.037 |
bur | +0.037 |
ppa | +0.036 |
ind | +0.035 |
i | +0.035 |
Neg logit contributions | |
vows | -0.030 |
prize | -0.028 |
contest | -0.027 |
trophy | -0.027 |
apy | -0.026 |
Token | . |
Token ID | 13 |
Feature activation | +2.13e-02 |
Pos logit contributions | |
bur | +0.014 |
rying | +0.014 |
ppa | +0.014 |
ind | +0.014 |
i | +0.014 |
Neg logit contributions | |
vows | -0.013 |
prize | -0.012 |
contest | -0.011 |
trophy | -0.011 |
cakes | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
rying | +0.057 |
ppa | +0.056 |
bur | +0.055 |
ind | +0.055 |
i | +0.054 |
Neg logit contributions | |
vows | -0.021 |
cakes | -0.019 |
contest | -0.019 |
prize | -0.018 |
apy | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +2.86e-02 |
Pos logit contributions | |
rying | +0.065 |
bur | +0.064 |
ppa | +0.063 |
i | +0.062 |
ind | +0.061 |
Neg logit contributions | |
vows | -0.024 |
prize | -0.022 |
contest | -0.021 |
apy | -0.021 |
case | -0.021 |
Token | Tim |
Token ID | 14967 |
Feature activation | +8.65e-02 |
Pos logit contributions | |
rying | +0.064 |
bur | +0.063 |
i | +0.062 |
ppa | +0.061 |
ener | +0.060 |
Neg logit contributions | |
case | -0.039 |
apy | -0.039 |
vows | -0.038 |
ades | -0.037 |
cakes | -0.037 |
Token | my |
Token ID | 1820 |
Feature activation | +5.04e-02 |
Pos logit contributions | |
rying | +0.130 |
ind | +0.120 |
keeping | +0.119 |
predators | +0.118 |
shadow | +0.117 |
Neg logit contributions | |
were | -0.147 |
game | -0.144 |
laugh | -0.142 |
are | -0.142 |
joke | -0.141 |
Token | started |
Token ID | 2067 |
Feature activation | +1.97e-03 |
Pos logit contributions | |
rying | +0.122 |
bur | +0.120 |
ind | +0.111 |
ppa | +0.108 |
keeping | +0.107 |
Neg logit contributions | |
vows | -0.060 |
case | -0.054 |
contest | -0.054 |
were | -0.054 |
joke | -0.052 |
Token | to |
Token ID | 284 |
Feature activation | +4.04e-03 |
Pos logit contributions | |
bur | +0.004 |
rying | +0.003 |
ppa | +0.003 |
i | +0.003 |
ind | +0.003 |
Neg logit contributions | |
vows | -0.004 |
prize | -0.003 |
contest | -0.003 |
trophy | -0.003 |
cakes | -0.003 |
Token | complain |
Token ID | 13121 |
Feature activation | +8.59e-03 |
Pos logit contributions | |
bur | +0.008 |
rying | +0.008 |
ppa | +0.008 |
i | +0.008 |
ind | +0.008 |
Neg logit contributions | |
vows | -0.007 |
prize | -0.006 |
contest | -0.006 |
trophy | -0.006 |
cakes | -0.006 |
Token | to |
Token ID | 284 |
Feature activation | +2.04e-02 |
Pos logit contributions | |
bur | +0.017 |
rying | +0.017 |
ppa | +0.016 |
i | +0.016 |
ind | +0.016 |
Neg logit contributions | |
vows | -0.015 |
prize | -0.014 |
contest | -0.013 |
trophy | -0.013 |
cakes | -0.013 |
Token | eating |
Token ID | 6600 |
Feature activation | -1.79e-02 |
Pos logit contributions | |
bur | +0.021 |
rying | +0.021 |
ppa | +0.021 |
ind | +0.020 |
i | +0.020 |
Neg logit contributions | |
vows | -0.025 |
prize | -0.023 |
contest | -0.023 |
trophy | -0.023 |
cakes | -0.022 |
Token | their |
Token ID | 511 |
Feature activation | +2.41e-03 |
Pos logit contributions | |
vows | +0.032 |
contest | +0.027 |
prize | +0.027 |
case | +0.026 |
Prize | +0.026 |
Neg logit contributions | |
bur | -0.035 |
i | -0.033 |
rying | -0.033 |
ppa | -0.032 |
ind | -0.031 |
Token | ice |
Token ID | 4771 |
Feature activation | +8.60e-03 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.004 |
ppa | +0.004 |
i | +0.004 |
ind | +0.004 |
Neg logit contributions | |
vows | -0.004 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
cakes | -0.004 |
Token | cream |
Token ID | 8566 |
Feature activation | -1.88e-02 |
Pos logit contributions | |
bur | +0.017 |
rying | +0.017 |
ppa | +0.017 |
ind | +0.016 |
i | +0.016 |
Neg logit contributions | |
vows | -0.014 |
prize | -0.013 |
contest | -0.013 |
trophy | -0.013 |
cakes | -0.013 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
vows | +0.032 |
prize | +0.027 |
contest | +0.027 |
Prize | +0.027 |
apy | +0.027 |
Neg logit contributions | |
bur | -0.038 |
i | -0.036 |
rying | -0.036 |
ppa | -0.036 |
ety | -0.034 |
Token | Tim |
Token ID | 5045 |
Feature activation | +8.57e-02 |
Pos logit contributions | |
vows | +0.028 |
prize | +0.024 |
contest | +0.024 |
trophy | +0.023 |
cakes | +0.023 |
Neg logit contributions | |
bur | -0.028 |
rying | -0.026 |
ppa | -0.026 |
i | -0.026 |
gie | -0.026 |
Token | my |
Token ID | 1820 |
Feature activation | +5.13e-02 |
Pos logit contributions | |
rying | +0.115 |
ind | +0.109 |
predators | +0.099 |
cker | +0.096 |
property | +0.093 |
Neg logit contributions | |
were | -0.172 |
team | -0.162 |
case | -0.159 |
are | -0.159 |
third | -0.156 |
Token | 's |
Token ID | 338 |
Feature activation | +4.22e-03 |
Pos logit contributions | |
rying | +0.113 |
bur | +0.106 |
ind | +0.105 |
ior | +0.098 |
cker | +0.096 |
Neg logit contributions | |
vows | -0.075 |
contest | -0.065 |
trophy | -0.065 |
case | -0.065 |
apy | -0.065 |
Token | mom |
Token ID | 1995 |
Feature activation | +4.04e-02 |
Pos logit contributions | |
bur | +0.009 |
rying | +0.009 |
ppa | +0.009 |
i | +0.009 |
ind | +0.009 |
Neg logit contributions | |
vows | -0.006 |
prize | -0.005 |
contest | -0.005 |
trophy | -0.005 |
cakes | -0.005 |
Token | told |
Token ID | 1297 |
Feature activation | +2.05e-03 |
Pos logit contributions | |
rying | +0.080 |
ind | +0.079 |
bur | +0.077 |
ior | +0.073 |
cker | +0.073 |
Neg logit contributions | |
vows | -0.063 |
cakes | -0.059 |
contest | -0.056 |
were | -0.055 |
are | -0.054 |
Token | him |
Token ID | 683 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
bur | +0.003 |
rying | +0.003 |
ppa | +0.003 |
i | +0.003 |
ind | +0.003 |
Neg logit contributions | |
vows | -0.004 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
cakes | -0.004 |
Token | " |
Token ID | 1 |
Feature activation | +2.75e-02 |
Pos logit contributions | |
bur | +0.011 |
rying | +0.011 |
ppa | +0.011 |
i | +0.011 |
ind | +0.011 |
Neg logit contributions | |
vows | -0.010 |
prize | -0.009 |
contest | -0.009 |
trophy | -0.008 |
cakes | -0.008 |
Token | What |
Token ID | 2061 |
Feature activation | -3.00e-02 |
Pos logit contributions | |
rying | +0.056 |
ppa | +0.055 |
i | +0.054 |
bur | +0.053 |
ind | +0.052 |
Neg logit contributions | |
vows | -0.043 |
Mine | -0.040 |
contest | -0.039 |
cakes | -0.039 |
apy | -0.039 |
Token | is |
Token ID | 318 |
Feature activation | +1.04e-02 |
Pos logit contributions | |
vows | +0.056 |
prize | +0.048 |
cakes | +0.048 |
trophy | +0.047 |
contest | +0.047 |
Neg logit contributions | |
my | -0.052 |
i | -0.051 |
rying | -0.050 |
bur | -0.050 |
ppa | -0.049 |
Token | it |
Token ID | 340 |
Feature activation | +5.53e-03 |
Pos logit contributions | |
bur | +0.023 |
rying | +0.022 |
ppa | +0.022 |
i | +0.021 |
ind | +0.021 |
Neg logit contributions | |
vows | -0.016 |
prize | -0.015 |
contest | -0.015 |
trophy | -0.014 |
apy | -0.014 |
Token | , |
Token ID | 11 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
bur | +0.009 |
rying | +0.009 |
ppa | +0.009 |
i | +0.009 |
ind | +0.009 |
Neg logit contributions | |
vows | -0.011 |
prize | -0.010 |
contest | -0.010 |
trophy | -0.010 |
cakes | -0.010 |
Token | Mum |
Token ID | 38367 |
Feature activation | +8.63e-02 |
Pos logit contributions | |
vows | +0.024 |
contest | +0.022 |
prize | +0.022 |
trophy | +0.022 |
cakes | +0.021 |
Neg logit contributions | |
bur | -0.029 |
i | -0.029 |
rying | -0.029 |
ppa | -0.028 |
ind | -0.028 |
Token | ?" |
Token ID | 1701 |
Feature activation | +4.68e-03 |
Pos logit contributions | |
ind | +0.195 |
ppa | +0.183 |
eled | +0.183 |
gie | +0.181 |
rying | +0.179 |
Neg logit contributions | |
contest | -0.101 |
are | -0.094 |
celebrate | -0.093 |
parties | -0.091 |
trophy | -0.086 |
Token | she |
Token ID | 673 |
Feature activation | +6.98e-02 |
Pos logit contributions | |
bur | +0.010 |
rying | +0.010 |
ppa | +0.010 |
i | +0.009 |
ind | +0.009 |
Neg logit contributions | |
vows | -0.007 |
prize | -0.006 |
contest | -0.006 |
trophy | -0.006 |
cakes | -0.006 |
Token | asked |
Token ID | 1965 |
Feature activation | +1.85e-02 |
Pos logit contributions | |
bur | +0.138 |
rying | +0.138 |
ind | +0.129 |
ishing | +0.124 |
ior | +0.124 |
Neg logit contributions | |
vows | -0.107 |
third | -0.103 |
funny | -0.098 |
contest | -0.097 |
dance | -0.096 |
Token | . |
Token ID | 13 |
Feature activation | -8.53e-03 |
Pos logit contributions | |
bur | +0.041 |
ppa | +0.040 |
rying | +0.039 |
ind | +0.039 |
cker | +0.038 |
Neg logit contributions | |
vows | -0.027 |
prize | -0.024 |
contest | -0.024 |
apy | -0.023 |
trophy | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | -1.19e-02 |
Pos logit contributions | |
vows | +0.013 |
prize | +0.012 |
trophy | +0.012 |
contest | +0.012 |
cakes | +0.011 |
Neg logit contributions | |
bur | -0.018 |
rying | -0.018 |
ppa | -0.018 |
i | -0.017 |
ind | -0.017 |
Token | hoped |
Token ID | 10719 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
vows | +0.029 |
prize | +0.026 |
trophy | +0.026 |
cakes | +0.026 |
contest | +0.026 |
Neg logit contributions | |
bur | -0.025 |
ppa | -0.024 |
rying | -0.024 |
i | -0.024 |
ety | -0.023 |
Token | to |
Token ID | 284 |
Feature activation | +2.87e-02 |
Pos logit contributions | |
bur | +0.047 |
rying | +0.046 |
ppa | +0.046 |
ind | +0.045 |
ior | +0.044 |
Neg logit contributions | |
vows | -0.019 |
prize | -0.016 |
contest | -0.016 |
trophy | -0.015 |
cakes | -0.015 |
Token | find |
Token ID | 1064 |
Feature activation | +1.68e-02 |
Pos logit contributions | |
rying | +0.070 |
ppa | +0.069 |
bur | +0.068 |
i | +0.067 |
ior | +0.066 |
Neg logit contributions | |
vows | -0.035 |
prize | -0.033 |
contest | -0.032 |
celebrate | -0.031 |
trophy | -0.031 |
Token | another |
Token ID | 1194 |
Feature activation | +4.38e-02 |
Pos logit contributions | |
rying | +0.040 |
ppa | +0.040 |
bur | +0.039 |
ind | +0.038 |
i | +0.038 |
Neg logit contributions | |
vows | -0.022 |
prize | -0.020 |
contest | -0.019 |
trophy | -0.019 |
apy | -0.018 |
Token | rare |
Token ID | 4071 |
Feature activation | +4.15e-02 |
Pos logit contributions | |
ppa | +0.095 |
rying | +0.093 |
bur | +0.089 |
ind | +0.088 |
ior | +0.087 |
Neg logit contributions | |
prize | -0.070 |
vows | -0.065 |
trophy | -0.064 |
contest | -0.064 |
lot | -0.062 |
Token | rad |
Token ID | 2511 |
Feature activation | +8.50e-02 |
Pos logit contributions | |
ppa | +0.089 |
rying | +0.086 |
bur | +0.085 |
ior | +0.080 |
ind | +0.080 |
Neg logit contributions | |
vows | -0.068 |
prize | -0.066 |
trophy | -0.063 |
contest | -0.062 |
joke | -0.058 |
Token | ish |
Token ID | 680 |
Feature activation | -1.50e-03 |
Pos logit contributions | |
ppa | +0.134 |
eking | +0.130 |
oscope | +0.127 |
rying | +0.127 |
shadow | +0.126 |
Neg logit contributions | |
prize | -0.154 |
trophy | -0.146 |
are | -0.146 |
vows | -0.144 |
lot | -0.141 |
Token | . |
Token ID | 13 |
Feature activation | +4.23e-03 |
Pos logit contributions | |
vows | +0.003 |
prize | +0.002 |
contest | +0.002 |
trophy | +0.002 |
apy | +0.002 |
Neg logit contributions | |
bur | -0.003 |
rying | -0.003 |
ppa | -0.003 |
i | -0.003 |
ind | -0.003 |
Token | They |
Token ID | 1119 |
Feature activation | -8.81e-03 |
Pos logit contributions | |
bur | +0.011 |
rying | +0.011 |
ppa | +0.010 |
i | +0.010 |
ind | +0.010 |
Neg logit contributions | |
vows | -0.005 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
cakes | -0.004 |
Token | hoped |
Token ID | 10719 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
vows | +0.018 |
prize | +0.016 |
trophy | +0.016 |
contest | +0.016 |
cakes | +0.016 |
Neg logit contributions | |
bur | -0.015 |
ppa | -0.015 |
rying | -0.014 |
i | -0.014 |
ety | -0.013 |
Token | to |
Token ID | 284 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
rying | +0.064 |
bur | +0.064 |
ppa | +0.064 |
ind | +0.062 |
ior | +0.061 |
Neg logit contributions | |
vows | -0.026 |
prize | -0.023 |
contest | -0.022 |
trophy | -0.020 |
cakes | -0.020 |
Token | it |
Token ID | 340 |
Feature activation | +1.77e-02 |
Pos logit contributions | |
rying | +0.101 |
ppa | +0.100 |
cker | +0.098 |
ind | +0.097 |
ior | +0.097 |
Neg logit contributions | |
prize | -0.034 |
trophy | -0.032 |
vows | -0.031 |
contest | -0.029 |
great | -0.027 |
Token | forever |
Token ID | 8097 |
Feature activation | +4.80e-02 |
Pos logit contributions | |
bur | +0.036 |
rying | +0.036 |
ppa | +0.036 |
ind | +0.035 |
i | +0.034 |
Neg logit contributions | |
vows | -0.027 |
prize | -0.026 |
trophy | -0.025 |
contest | -0.025 |
cakes | -0.023 |
Token | . |
Token ID | 13 |
Feature activation | +2.41e-02 |
Pos logit contributions | |
bur | +0.133 |
ind | +0.131 |
ior | +0.130 |
umper | +0.128 |
rying | +0.127 |
Neg logit contributions | |
prize | -0.039 |
trophy | -0.034 |
are | -0.032 |
great | -0.031 |
vows | -0.031 |
Token |
|
Token ID | 198 |
Feature activation | +1.40e-02 |
Pos logit contributions | |
rying | +0.068 |
ppa | +0.066 |
ind | +0.066 |
bur | +0.065 |
i | +0.064 |
Neg logit contributions | |
vows | -0.021 |
prize | -0.019 |
cakes | -0.018 |
contest | -0.018 |
trophy | -0.018 |
Token |
|
Token ID | 198 |
Feature activation | +2.40e-02 |
Pos logit contributions | |
rying | +0.034 |
bur | +0.034 |
ppa | +0.034 |
i | +0.033 |
ind | +0.032 |
Neg logit contributions | |
vows | -0.017 |
prize | -0.015 |
contest | -0.015 |
trophy | -0.014 |
apy | -0.014 |
Token | Tim |
Token ID | 14967 |
Feature activation | +8.76e-02 |
Pos logit contributions | |
rying | +0.052 |
i | +0.051 |
bur | +0.051 |
ppa | +0.050 |
ener | +0.049 |
Neg logit contributions | |
vows | -0.033 |
case | -0.033 |
apy | -0.032 |
prize | -0.032 |
contest | -0.032 |
Token | my |
Token ID | 1820 |
Feature activation | +3.86e-02 |
Pos logit contributions | |
rying | +0.130 |
ind | +0.125 |
shadow | +0.123 |
predators | +0.123 |
ich | +0.121 |
Neg logit contributions | |
are | -0.148 |
were | -0.146 |
game | -0.145 |
laugh | -0.144 |
joke | -0.141 |
Token | played |
Token ID | 2826 |
Feature activation | -3.42e-02 |
Pos logit contributions | |
bur | +0.085 |
rying | +0.085 |
ind | +0.082 |
ppa | +0.079 |
ior | +0.077 |
Neg logit contributions | |
vows | -0.055 |
contest | -0.048 |
joke | -0.046 |
prize | -0.046 |
case | -0.045 |
Token | with |
Token ID | 351 |
Feature activation | +1.04e-04 |
Pos logit contributions | |
vows | +0.083 |
cakes | +0.068 |
apy | +0.067 |
Mine | +0.066 |
Prize | +0.066 |
Neg logit contributions | |
rying | -0.047 |
bur | -0.045 |
owl | -0.042 |
ishing | -0.041 |
forth | -0.041 |
Token | his |
Token ID | 465 |
Feature activation | -2.76e-02 |
Pos logit contributions | |
bur | +0.000 |
rying | +0.000 |
ppa | +0.000 |
i | +0.000 |
ind | +0.000 |
Neg logit contributions | |
vows | -0.000 |
prize | -0.000 |
contest | -0.000 |
trophy | -0.000 |
cakes | -0.000 |
Token | ball |
Token ID | 2613 |
Feature activation | +1.02e-02 |
Pos logit contributions | |
vows | +0.045 |
cakes | +0.038 |
ades | +0.035 |
apy | +0.034 |
Prize | +0.034 |
Neg logit contributions | |
bur | -0.057 |
ety | -0.055 |
rying | -0.054 |
ind | -0.054 |
axe | -0.054 |
Token | that |
Token ID | 326 |
Feature activation | -2.05e-02 |
Pos logit contributions | |
vows | +0.003 |
prize | +0.003 |
contest | +0.003 |
trophy | +0.003 |
cakes | +0.003 |
Neg logit contributions | |
bur | -0.003 |
rying | -0.003 |
ppa | -0.003 |
i | -0.003 |
ind | -0.003 |
Token | cared |
Token ID | 19951 |
Feature activation | -3.73e-02 |
Pos logit contributions | |
vows | +0.034 |
prize | +0.032 |
trophy | +0.032 |
contest | +0.030 |
cakes | +0.030 |
Neg logit contributions | |
bur | -0.041 |
i | -0.040 |
ppa | -0.039 |
rying | -0.039 |
cker | -0.038 |
Token | for |
Token ID | 329 |
Feature activation | +1.84e-02 |
Pos logit contributions | |
vows | +0.084 |
Mine | +0.082 |
trophy | +0.079 |
cakes | +0.078 |
contest | +0.078 |
Neg logit contributions | |
rying | -0.048 |
i | -0.043 |
bur | -0.043 |
ind | -0.042 |
ppa | -0.041 |
Token | them |
Token ID | 606 |
Feature activation | -2.02e-02 |
Pos logit contributions | |
rying | +0.044 |
bur | +0.043 |
ppa | +0.043 |
ind | +0.041 |
i | +0.041 |
Neg logit contributions | |
vows | -0.024 |
prize | -0.021 |
contest | -0.020 |
trophy | -0.019 |
apy | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | -7.37e-03 |
Pos logit contributions | |
vows | +0.040 |
apy | +0.037 |
trophy | +0.036 |
prize | +0.036 |
contest | +0.036 |
Neg logit contributions | |
rying | -0.034 |
bur | -0.034 |
ppa | -0.033 |
i | -0.033 |
ind | -0.032 |
Token | The |
Token ID | 383 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
vows | +0.011 |
prize | +0.010 |
trophy | +0.010 |
contest | +0.009 |
cakes | +0.009 |
Neg logit contributions | |
bur | -0.016 |
rying | -0.016 |
ppa | -0.015 |
i | -0.015 |
ind | -0.015 |
Token | family |
Token ID | 1641 |
Feature activation | -1.64e-02 |
Pos logit contributions | |
rying | +0.039 |
bur | +0.037 |
ppa | +0.037 |
i | +0.036 |
ety | +0.035 |
Neg logit contributions | |
vows | -0.039 |
prize | -0.034 |
contest | -0.033 |
cakes | -0.032 |
trophy | -0.032 |
Token | was |
Token ID | 373 |
Feature activation | -6.08e-03 |
Pos logit contributions | |
vows | +0.029 |
prize | +0.027 |
trophy | +0.026 |
contest | +0.026 |
cakes | +0.026 |
Neg logit contributions | |
bur | -0.031 |
rying | -0.030 |
i | -0.030 |
ppa | -0.030 |
ind | -0.029 |
Token | very |
Token ID | 845 |
Feature activation | -1.38e-02 |
Pos logit contributions | |
vows | +0.010 |
prize | +0.009 |
trophy | +0.009 |
cakes | +0.009 |
apy | +0.008 |
Neg logit contributions | |
bur | -0.013 |
rying | -0.012 |
ppa | -0.012 |
ind | -0.012 |
i | -0.012 |
Token | happy |
Token ID | 3772 |
Feature activation | +8.26e-03 |
Pos logit contributions | |
vows | +0.022 |
prize | +0.020 |
trophy | +0.019 |
cakes | +0.019 |
contest | +0.019 |
Neg logit contributions | |
rying | -0.029 |
ppa | -0.028 |
ind | -0.028 |
bur | -0.028 |
i | -0.027 |
Token | , |
Token ID | 11 |
Feature activation | -5.00e-03 |
Pos logit contributions | |
bur | +0.015 |
ppa | +0.014 |
rying | +0.014 |
ind | +0.014 |
i | +0.014 |
Neg logit contributions | |
vows | -0.016 |
prize | -0.014 |
contest | -0.014 |
trophy | -0.014 |
cakes | -0.014 |
Token | scared |
Token ID | 12008 |
Feature activation | +2.52e-02 |
Pos logit contributions | |
bur | +0.026 |
rying | +0.026 |
ppa | +0.025 |
ind | +0.024 |
i | +0.024 |
Neg logit contributions | |
vows | -0.020 |
prize | -0.017 |
contest | -0.017 |
trophy | -0.017 |
apy | -0.017 |
Token | of |
Token ID | 286 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
bur | +0.059 |
ppa | +0.059 |
rying | +0.056 |
ind | +0.054 |
cker | +0.053 |
Neg logit contributions | |
vows | -0.033 |
prize | -0.030 |
contest | -0.030 |
apy | -0.030 |
trophy | -0.029 |
Token | the |
Token ID | 262 |
Feature activation | +2.96e-02 |
Pos logit contributions | |
bur | +0.041 |
ppa | +0.041 |
rying | +0.041 |
ind | +0.039 |
ety | +0.039 |
Neg logit contributions | |
vows | -0.028 |
prize | -0.026 |
contest | -0.025 |
trophy | -0.024 |
apy | -0.023 |
Token | farmer |
Token ID | 18739 |
Feature activation | +3.98e-02 |
Pos logit contributions | |
bur | +0.053 |
rying | +0.053 |
ppa | +0.052 |
ety | +0.049 |
umper | +0.048 |
Neg logit contributions | |
vows | -0.056 |
prize | -0.051 |
contest | -0.051 |
joke | -0.049 |
tea | -0.048 |
Token | . |
Token ID | 13 |
Feature activation | +8.14e-03 |
Pos logit contributions | |
bur | +0.083 |
ppa | +0.081 |
ind | +0.080 |
rying | +0.080 |
ior | +0.075 |
Neg logit contributions | |
vows | -0.062 |
prize | -0.057 |
contest | -0.057 |
trophy | -0.055 |
are | -0.053 |
Token | But |
Token ID | 887 |
Feature activation | +3.89e-02 |
Pos logit contributions | |
bur | +0.017 |
rying | +0.017 |
ppa | +0.017 |
ind | +0.017 |
i | +0.016 |
Neg logit contributions | |
vows | -0.013 |
prize | -0.011 |
contest | -0.011 |
trophy | -0.011 |
cakes | -0.011 |
Token | eventually |
Token ID | 4191 |
Feature activation | -8.37e-03 |
Pos logit contributions | |
rying | +0.076 |
bur | +0.075 |
ppa | +0.074 |
ind | +0.074 |
umper | +0.070 |
Neg logit contributions | |
vows | -0.065 |
contest | -0.060 |
prize | -0.059 |
apy | -0.058 |
trophy | -0.058 |
Token | , |
Token ID | 11 |
Feature activation | +1.70e-02 |
Pos logit contributions | |
vows | +0.014 |
cakes | +0.012 |
trophy | +0.012 |
prize | +0.012 |
contest | +0.012 |
Neg logit contributions | |
bur | -0.017 |
i | -0.017 |
ppa | -0.017 |
rying | -0.017 |
cker | -0.016 |
Token | they |
Token ID | 484 |
Feature activation | -1.03e-02 |
Pos logit contributions | |
rying | +0.039 |
bur | +0.039 |
ppa | +0.039 |
ind | +0.038 |
ety | +0.037 |
Neg logit contributions | |
vows | -0.023 |
prize | -0.021 |
contest | -0.021 |
trophy | -0.020 |
apy | -0.020 |
Token | learned |
Token ID | 4499 |
Feature activation | +2.35e-04 |
Pos logit contributions | |
vows | +0.018 |
prize | +0.016 |
trophy | +0.016 |
contest | +0.016 |
cakes | +0.016 |
Neg logit contributions | |
bur | -0.020 |
ppa | -0.020 |
rying | -0.020 |
i | -0.019 |
cker | -0.018 |
Token | to |
Token ID | 284 |
Feature activation | +2.24e-02 |
Pos logit contributions | |
bur | +0.000 |
rying | +0.000 |
ppa | +0.000 |
i | +0.000 |
ind | +0.000 |
Neg logit contributions | |
vows | -0.000 |
prize | -0.000 |
contest | -0.000 |
trophy | -0.000 |
cakes | -0.000 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.66e-03 |
Pos logit contributions | |
bur | +0.081 |
ind | +0.081 |
ppa | +0.081 |
rying | +0.080 |
umper | +0.075 |
Neg logit contributions | |
vows | -0.055 |
contest | -0.050 |
trophy | -0.050 |
apy | -0.049 |
they | -0.049 |
Token | Lily |
Token ID | 20037 |
Feature activation | +4.52e-03 |
Pos logit contributions | |
bur | +0.012 |
rying | +0.012 |
ppa | +0.012 |
i | +0.012 |
ind | +0.012 |
Neg logit contributions | |
vows | -0.009 |
prize | -0.008 |
contest | -0.007 |
trophy | -0.007 |
cakes | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.31e-02 |
Pos logit contributions | |
bur | +0.008 |
rying | +0.008 |
ppa | +0.008 |
i | +0.008 |
ind | +0.008 |
Neg logit contributions | |
vows | -0.009 |
prize | -0.008 |
contest | -0.008 |
trophy | -0.008 |
cakes | -0.007 |
Token | He |
Token ID | 679 |
Feature activation | +1.76e-02 |
Pos logit contributions | |
vows | +0.025 |
prize | +0.022 |
contest | +0.021 |
trophy | +0.021 |
apy | +0.021 |
Neg logit contributions | |
bur | -0.023 |
rying | -0.023 |
ppa | -0.023 |
gie | -0.022 |
ety | -0.022 |
Token | was |
Token ID | 373 |
Feature activation | +1.71e-02 |
Pos logit contributions | |
rying | +0.037 |
bur | +0.037 |
ppa | +0.035 |
ind | +0.035 |
i | +0.034 |
Neg logit contributions | |
vows | -0.028 |
prize | -0.025 |
trophy | -0.024 |
contest | -0.024 |
apy | -0.024 |
Token | surprised |
Token ID | 6655 |
Feature activation | +4.09e-02 |
Pos logit contributions | |
rying | +0.034 |
bur | +0.034 |
ppa | +0.033 |
i | +0.032 |
ior | +0.032 |
Neg logit contributions | |
vows | -0.029 |
prize | -0.026 |
contest | -0.025 |
trophy | -0.025 |
apy | -0.024 |
Token | and |
Token ID | 290 |
Feature activation | +1.54e-02 |
Pos logit contributions | |
bur | +0.100 |
ppa | +0.100 |
cker | +0.094 |
oscope | +0.093 |
rying | +0.092 |
Neg logit contributions | |
prize | -0.043 |
vows | -0.043 |
they | -0.043 |
trophy | -0.043 |
contest | -0.041 |
Token | said |
Token ID | 531 |
Feature activation | -3.93e-02 |
Pos logit contributions | |
bur | +0.031 |
rying | +0.030 |
ppa | +0.030 |
ind | +0.029 |
i | +0.028 |
Neg logit contributions | |
vows | -0.026 |
prize | -0.023 |
contest | -0.023 |
trophy | -0.023 |
apy | -0.022 |
Token | , |
Token ID | 11 |
Feature activation | -7.60e-03 |
Pos logit contributions | |
vows | +0.077 |
cakes | +0.069 |
Mine | +0.069 |
prize | +0.068 |
case | +0.068 |
Neg logit contributions | |
i | -0.062 |
rying | -0.060 |
Owl | -0.059 |
owl | -0.058 |
ppa | -0.058 |
Token | " |
Token ID | 366 |
Feature activation | +1.89e-02 |
Pos logit contributions | |
vows | +0.009 |
prize | +0.008 |
contest | +0.008 |
trophy | +0.008 |
cakes | +0.007 |
Neg logit contributions | |
bur | -0.019 |
rying | -0.018 |
ppa | -0.018 |
i | -0.018 |
gie | -0.018 |
Token | Who |
Token ID | 8241 |
Feature activation | -1.11e-02 |
Pos logit contributions | |
rying | +0.038 |
bur | +0.037 |
ppa | +0.037 |
i | +0.036 |
ind | +0.035 |
Neg logit contributions | |
vows | -0.031 |
trophy | -0.028 |
contest | -0.028 |
prize | -0.028 |
cakes | -0.028 |
Token | a |
Token ID | 257 |
Feature activation | -1.44e-02 |
Pos logit contributions | |
rying | +0.026 |
bur | +0.025 |
ppa | +0.025 |
i | +0.024 |
ind | +0.024 |
Neg logit contributions | |
vows | -0.013 |
prize | -0.011 |
contest | -0.011 |
trophy | -0.011 |
apy | -0.011 |
Token | talking |
Token ID | 3375 |
Feature activation | -2.46e-02 |
Pos logit contributions | |
vows | +0.024 |
cakes | +0.021 |
prize | +0.020 |
contest | +0.020 |
apy | +0.020 |
Neg logit contributions | |
bur | -0.029 |
rying | -0.028 |
ppa | -0.028 |
ind | -0.027 |
i | -0.027 |
Token | bird |
Token ID | 6512 |
Feature activation | +3.72e-02 |
Pos logit contributions | |
vows | +0.045 |
apy | +0.041 |
cakes | +0.039 |
Mine | +0.039 |
ades | +0.039 |
Neg logit contributions | |
bur | -0.042 |
rying | -0.041 |
owl | -0.041 |
ind | -0.040 |
ppa | -0.040 |
Token | . |
Token ID | 13 |
Feature activation | -1.27e-02 |
Pos logit contributions | |
ppa | +0.084 |
bur | +0.084 |
ior | +0.084 |
rying | +0.080 |
ind | +0.078 |
Neg logit contributions | |
contest | -0.047 |
prize | -0.046 |
vows | -0.046 |
joke | -0.044 |
trophy | -0.043 |
Token | The |
Token ID | 383 |
Feature activation | +1.53e-02 |
Pos logit contributions | |
vows | +0.023 |
prize | +0.020 |
trophy | +0.020 |
contest | +0.020 |
ades | +0.019 |
Neg logit contributions | |
bur | -0.023 |
rying | -0.023 |
gie | -0.023 |
ior | -0.022 |
ppa | -0.022 |
Token | bird |
Token ID | 6512 |
Feature activation | +3.33e-02 |
Pos logit contributions | |
rying | +0.030 |
bur | +0.029 |
ppa | +0.029 |
i | +0.028 |
ind | +0.028 |
Neg logit contributions | |
vows | -0.028 |
prize | -0.026 |
contest | -0.026 |
trophy | -0.025 |
cakes | -0.024 |
Token | said |
Token ID | 531 |
Feature activation | -3.23e-02 |
Pos logit contributions | |
rying | +0.086 |
bur | +0.085 |
ppa | +0.084 |
ior | +0.080 |
ind | +0.080 |
Neg logit contributions | |
vows | -0.036 |
apy | -0.032 |
contest | -0.031 |
prize | -0.031 |
are | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | +5.45e-03 |
Pos logit contributions | |
vows | +0.063 |
Mine | +0.059 |
cakes | +0.057 |
case | +0.056 |
prize | +0.056 |
Neg logit contributions | |
i | -0.050 |
Owl | -0.050 |
owl | -0.049 |
bur | -0.047 |
ppa | -0.047 |
Token | " |
Token ID | 366 |
Feature activation | +3.40e-02 |
Pos logit contributions | |
bur | +0.014 |
rying | +0.014 |
ppa | +0.014 |
i | +0.014 |
ind | +0.014 |
Neg logit contributions | |
vows | -0.006 |
prize | -0.005 |
contest | -0.005 |
trophy | -0.004 |
cakes | -0.004 |
Token | Hi |
Token ID | 17250 |
Feature activation | +9.75e-03 |
Pos logit contributions | |
rying | +0.073 |
ppa | +0.068 |
ishing | +0.064 |
i | +0.064 |
ind | +0.064 |
Neg logit contributions | |
vows | -0.052 |
Mine | -0.050 |
cakes | -0.048 |
contest | -0.048 |
prize | -0.047 |
Token | , |
Token ID | 11 |
Feature activation | +4.93e-03 |
Pos logit contributions | |
bur | +0.022 |
rying | +0.022 |
ppa | +0.022 |
ind | +0.021 |
i | +0.021 |
Neg logit contributions | |
vows | -0.014 |
prize | -0.012 |
contest | -0.012 |
trophy | -0.012 |
cakes | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.15e-02 |
Pos logit contributions | |
vows | +0.018 |
prize | +0.016 |
trophy | +0.016 |
contest | +0.015 |
ades | +0.014 |
Neg logit contributions | |
bur | -0.023 |
ppa | -0.023 |
rying | -0.023 |
i | -0.022 |
ety | -0.022 |
Token |
|
Token ID | 198 |
Feature activation | -2.31e-02 |
Pos logit contributions | |
vows | +0.020 |
prize | +0.017 |
trophy | +0.017 |
contest | +0.017 |
cakes | +0.016 |
Neg logit contributions | |
bur | -0.023 |
ppa | -0.023 |
rying | -0.022 |
ind | -0.022 |
ety | -0.022 |
Token | L |
Token ID | 43 |
Feature activation | -5.81e-03 |
Pos logit contributions | |
vows | +0.050 |
prize | +0.046 |
trophy | +0.044 |
contest | +0.044 |
cakes | +0.043 |
Neg logit contributions | |
ppa | -0.037 |
ind | -0.036 |
bur | -0.035 |
rying | -0.034 |
ety | -0.033 |
Token | ily |
Token ID | 813 |
Feature activation | -5.97e-03 |
Pos logit contributions | |
vows | +0.010 |
prize | +0.009 |
trophy | +0.009 |
apy | +0.009 |
contest | +0.009 |
Neg logit contributions | |
rying | -0.012 |
ppa | -0.012 |
bur | -0.012 |
i | -0.011 |
ind | -0.011 |
Token | shrugged |
Token ID | 28271 |
Feature activation | +6.35e-03 |
Pos logit contributions | |
vows | +0.011 |
prize | +0.010 |
contest | +0.010 |
trophy | +0.009 |
cakes | +0.009 |
Neg logit contributions | |
bur | -0.011 |
rying | -0.011 |
ppa | -0.011 |
i | -0.011 |
ind | -0.010 |
Token | again |
Token ID | 757 |
Feature activation | +4.31e-02 |
Pos logit contributions | |
bur | +0.012 |
rying | +0.012 |
ppa | +0.011 |
ind | +0.011 |
i | +0.011 |
Neg logit contributions | |
vows | -0.012 |
prize | -0.011 |
contest | -0.010 |
trophy | -0.010 |
cakes | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | +2.44e-02 |
Pos logit contributions | |
bur | +0.105 |
ppa | +0.100 |
rying | +0.098 |
umper | +0.097 |
ind | +0.097 |
Neg logit contributions | |
vows | -0.052 |
prize | -0.051 |
contest | -0.047 |
trophy | -0.046 |
joke | -0.045 |
Token | said |
Token ID | 531 |
Feature activation | -3.72e-02 |
Pos logit contributions | |
bur | +0.048 |
ind | +0.048 |
rying | +0.047 |
ppa | +0.046 |
cker | +0.044 |
Neg logit contributions | |
vows | -0.041 |
contest | -0.037 |
prize | -0.037 |
trophy | -0.035 |
cakes | -0.035 |
Token | , |
Token ID | 11 |
Feature activation | -3.78e-03 |
Pos logit contributions | |
vows | +0.071 |
cakes | +0.066 |
Mine | +0.065 |
trophy | +0.065 |
prize | +0.064 |
Neg logit contributions | |
i | -0.059 |
rying | -0.058 |
ppa | -0.056 |
bur | -0.052 |
ener | -0.052 |
Token | " |
Token ID | 366 |
Feature activation | +2.11e-02 |
Pos logit contributions | |
vows | +0.004 |
prize | +0.004 |
contest | +0.004 |
trophy | +0.004 |
cakes | +0.003 |
Neg logit contributions | |
bur | -0.009 |
rying | -0.009 |
ppa | -0.009 |
i | -0.009 |
ind | -0.009 |
Token | No |
Token ID | 2949 |
Feature activation | -1.42e-03 |
Pos logit contributions | |
rying | +0.046 |
ppa | +0.045 |
bur | +0.045 |
i | +0.043 |
ind | +0.043 |
Neg logit contributions | |
vows | -0.031 |
prize | -0.027 |
Mine | -0.027 |
contest | -0.027 |
apy | -0.027 |
Token | felt |
Token ID | 2936 |
Feature activation | +9.33e-04 |
Pos logit contributions | |
rying | +0.053 |
bur | +0.052 |
ppa | +0.052 |
ind | +0.050 |
ior | +0.050 |
Neg logit contributions | |
vows | -0.040 |
prize | -0.036 |
apy | -0.035 |
contest | -0.034 |
trophy | -0.034 |
Token | like |
Token ID | 588 |
Feature activation | +1.49e-02 |
Pos logit contributions | |
bur | +0.002 |
rying | +0.002 |
ppa | +0.002 |
i | +0.002 |
ind | +0.002 |
Neg logit contributions | |
vows | -0.002 |
prize | -0.001 |
contest | -0.001 |
trophy | -0.001 |
cakes | -0.001 |
Token | he |
Token ID | 339 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
bur | +0.032 |
rying | +0.032 |
ppa | +0.032 |
ind | +0.030 |
i | +0.030 |
Neg logit contributions | |
vows | -0.023 |
prize | -0.021 |
contest | -0.020 |
trophy | -0.020 |
apy | -0.019 |
Token | was |
Token ID | 373 |
Feature activation | +1.61e-02 |
Pos logit contributions | |
bur | +0.051 |
ppa | +0.051 |
rying | +0.051 |
ind | +0.049 |
ior | +0.048 |
Neg logit contributions | |
vows | -0.029 |
prize | -0.025 |
contest | -0.024 |
trophy | -0.024 |
are | -0.023 |
Token | going |
Token ID | 1016 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
bur | +0.028 |
ppa | +0.028 |
rying | +0.028 |
ind | +0.027 |
i | +0.027 |
Neg logit contributions | |
vows | -0.030 |
prize | -0.028 |
contest | -0.028 |
trophy | -0.027 |
apy | -0.027 |
Token | to |
Token ID | 284 |
Feature activation | -9.30e-03 |
Pos logit contributions | |
ppa | +0.052 |
bur | +0.051 |
rying | +0.050 |
ior | +0.049 |
ind | +0.049 |
Neg logit contributions | |
vows | -0.039 |
prize | -0.038 |
contest | -0.038 |
trophy | -0.036 |
cakes | -0.033 |
Token | be |
Token ID | 307 |
Feature activation | +1.92e-02 |
Pos logit contributions | |
vows | +0.015 |
cakes | +0.013 |
contest | +0.013 |
trophy | +0.013 |
prize | +0.013 |
Neg logit contributions | |
bur | -0.019 |
rying | -0.019 |
ppa | -0.018 |
i | -0.018 |
ind | -0.018 |
Token | discovered |
Token ID | 5071 |
Feature activation | +2.51e-02 |
Pos logit contributions | |
bur | +0.037 |
rying | +0.036 |
ppa | +0.036 |
i | +0.035 |
ind | +0.035 |
Neg logit contributions | |
vows | -0.033 |
prize | -0.030 |
contest | -0.030 |
trophy | -0.029 |
apy | -0.029 |
Token | . |
Token ID | 13 |
Feature activation | +2.60e-02 |
Pos logit contributions | |
ppa | +0.053 |
bur | +0.052 |
rying | +0.051 |
ind | +0.050 |
i | +0.049 |
Neg logit contributions | |
vows | -0.039 |
prize | -0.037 |
contest | -0.035 |
trophy | -0.035 |
cakes | -0.034 |
Token |
|
Token ID | 198 |
Feature activation | +1.41e-02 |
Pos logit contributions | |
rying | +0.068 |
ppa | +0.067 |
bur | +0.067 |
ind | +0.067 |
i | +0.066 |
Neg logit contributions | |
vows | -0.026 |
Everyone | -0.024 |
prize | -0.024 |
apy | -0.024 |
case | -0.023 |
Token |
|
Token ID | 198 |
Feature activation | +2.83e-03 |
Pos logit contributions | |
rying | +0.035 |
bur | +0.035 |
ppa | +0.034 |
i | +0.034 |
ind | +0.033 |
Neg logit contributions | |
vows | -0.017 |
prize | -0.015 |
contest | -0.014 |
apy | -0.014 |
trophy | -0.014 |
Token | ." |
Token ID | 526 |
Feature activation | -5.62e-03 |
Pos logit contributions | |
bur | +0.014 |
rying | +0.014 |
ppa | +0.013 |
i | +0.013 |
ind | +0.013 |
Neg logit contributions | |
vows | -0.014 |
prize | -0.012 |
contest | -0.012 |
trophy | -0.012 |
cakes | -0.012 |
Token | Lily |
Token ID | 20037 |
Feature activation | -2.80e-02 |
Pos logit contributions | |
vows | +0.009 |
prize | +0.008 |
trophy | +0.008 |
contest | +0.008 |
Prize | +0.007 |
Neg logit contributions | |
bur | -0.012 |
ppa | -0.012 |
rying | -0.012 |
i | -0.011 |
ety | -0.011 |
Token | smiled |
Token ID | 13541 |
Feature activation | -1.78e-03 |
Pos logit contributions | |
vows | +0.053 |
contest | +0.053 |
prize | +0.052 |
Prize | +0.050 |
trophy | +0.050 |
Neg logit contributions | |
ppa | -0.048 |
i | -0.047 |
bur | -0.047 |
my | -0.045 |
ety | -0.043 |
Token | and |
Token ID | 290 |
Feature activation | -2.13e-02 |
Pos logit contributions | |
vows | +0.004 |
prize | +0.003 |
contest | +0.003 |
trophy | +0.003 |
cakes | +0.003 |
Neg logit contributions | |
bur | -0.003 |
rying | -0.003 |
ppa | -0.003 |
i | -0.003 |
ind | -0.003 |
Token | said |
Token ID | 531 |
Feature activation | -4.61e-02 |
Pos logit contributions | |
vows | +0.043 |
contest | +0.041 |
prize | +0.040 |
trophy | +0.040 |
ades | +0.040 |
Neg logit contributions | |
ppa | -0.035 |
bur | -0.034 |
i | -0.034 |
rying | -0.032 |
ety | -0.031 |
Token | , |
Token ID | 11 |
Feature activation | -1.54e-02 |
Pos logit contributions | |
vows | +0.092 |
Mine | +0.092 |
case | +0.089 |
blast | +0.088 |
festival | +0.087 |
Neg logit contributions | |
i | -0.066 |
ppa | -0.064 |
rying | -0.057 |
my | -0.057 |
ener | -0.056 |
Token | " |
Token ID | 366 |
Feature activation | +4.10e-03 |
Pos logit contributions | |
vows | +0.020 |
prize | +0.018 |
contest | +0.017 |
trophy | +0.017 |
ades | +0.016 |
Neg logit contributions | |
ppa | -0.036 |
bur | -0.036 |
rying | -0.035 |
i | -0.034 |
gie | -0.034 |
Token | I |
Token ID | 40 |
Feature activation | -3.14e-02 |
Pos logit contributions | |
bur | +0.008 |
rying | +0.008 |
ppa | +0.008 |
i | +0.007 |
ind | +0.007 |
Neg logit contributions | |
vows | -0.007 |
prize | -0.007 |
contest | -0.007 |
trophy | -0.006 |
cakes | -0.006 |
Token | love |
Token ID | 1842 |
Feature activation | +3.03e-03 |
Pos logit contributions | |
vows | +0.054 |
trophy | +0.052 |
cakes | +0.052 |
apy | +0.052 |
ades | +0.052 |
Neg logit contributions | |
bur | -0.058 |
ppa | -0.056 |
my | -0.056 |
i | -0.056 |
rying | -0.053 |
Token | you |
Token ID | 345 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.005 |
ppa | +0.005 |
i | +0.005 |
ind | +0.005 |
Neg logit contributions | |
vows | -0.006 |
prize | -0.006 |
contest | -0.006 |
trophy | -0.006 |
cakes | -0.005 |
Token | too |
Token ID | 1165 |
Feature activation | +4.40e-03 |
Pos logit contributions | |
vows | +0.037 |
apy | +0.034 |
prize | +0.034 |
contest | +0.034 |
cakes | +0.034 |
Neg logit contributions | |
bur | -0.030 |
ppa | -0.030 |
i | -0.029 |
my | -0.028 |
rying | -0.028 |
Token | sat |
Token ID | 3332 |
Feature activation | +2.55e-02 |
Pos logit contributions | |
bur | +0.015 |
rying | +0.015 |
ppa | +0.015 |
ind | +0.014 |
i | +0.014 |
Neg logit contributions | |
vows | -0.013 |
prize | -0.012 |
contest | -0.012 |
trophy | -0.012 |
cakes | -0.011 |
Token | down |
Token ID | 866 |
Feature activation | -2.14e-02 |
Pos logit contributions | |
bur | +0.050 |
ppa | +0.050 |
gie | +0.048 |
cker | +0.048 |
rying | +0.047 |
Neg logit contributions | |
vows | -0.042 |
contest | -0.038 |
prize | -0.038 |
trophy | -0.038 |
apy | -0.037 |
Token | at |
Token ID | 379 |
Feature activation | +1.26e-03 |
Pos logit contributions | |
vows | +0.048 |
prize | +0.043 |
Prize | +0.043 |
trophy | +0.043 |
apy | +0.043 |
Neg logit contributions | |
rying | -0.031 |
bur | -0.030 |
i | -0.028 |
ind | -0.027 |
ppa | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | -5.05e-02 |
Pos logit contributions | |
bur | +0.003 |
rying | +0.003 |
ppa | +0.003 |
i | +0.003 |
ind | +0.003 |
Neg logit contributions | |
vows | -0.002 |
prize | -0.002 |
contest | -0.002 |
trophy | -0.002 |
cakes | -0.002 |
Token | big |
Token ID | 1263 |
Feature activation | -2.55e-02 |
Pos logit contributions | |
vows | +0.083 |
apy | +0.074 |
cakes | +0.071 |
Everyone | +0.069 |
Everybody | +0.067 |
Neg logit contributions | |
ind | -0.097 |
bur | -0.092 |
ppa | -0.090 |
rying | -0.089 |
owl | -0.089 |
Token | table |
Token ID | 3084 |
Feature activation | +3.85e-03 |
Pos logit contributions | |
vows | +0.040 |
apy | +0.035 |
cakes | +0.034 |
ades | +0.032 |
Prize | +0.031 |
Neg logit contributions | |
bur | -0.054 |
ind | -0.052 |
i | -0.051 |
rying | -0.051 |
ppa | -0.050 |
Token | . |
Token ID | 13 |
Feature activation | -3.46e-02 |
Pos logit contributions | |
bur | +0.007 |
rying | +0.007 |
ppa | +0.007 |
i | +0.007 |
ind | +0.006 |
Neg logit contributions | |
vows | -0.007 |
prize | -0.007 |
contest | -0.006 |
trophy | -0.006 |
cakes | -0.006 |
Token | They |
Token ID | 1119 |
Feature activation | -2.04e-02 |
Pos logit contributions | |
vows | +0.055 |
trophy | +0.050 |
prize | +0.049 |
contest | +0.047 |
ades | +0.045 |
Neg logit contributions | |
ety | -0.068 |
ior | -0.066 |
gie | -0.066 |
bur | -0.066 |
rying | -0.065 |
Token | had |
Token ID | 550 |
Feature activation | -1.45e-02 |
Pos logit contributions | |
vows | +0.038 |
prize | +0.036 |
contest | +0.035 |
trophy | +0.035 |
cakes | +0.034 |
Neg logit contributions | |
bur | -0.037 |
ppa | -0.037 |
i | -0.036 |
rying | -0.035 |
ety | -0.033 |
Token | delicious |
Token ID | 12625 |
Feature activation | -1.75e-02 |
Pos logit contributions | |
vows | +0.023 |
trophy | +0.021 |
prize | +0.021 |
contest | +0.021 |
apy | +0.021 |
Neg logit contributions | |
bur | -0.030 |
ppa | -0.029 |
rying | -0.029 |
i | -0.028 |
ind | -0.028 |
Token | food |
Token ID | 2057 |
Feature activation | -2.28e-02 |
Pos logit contributions | |
vows | +0.023 |
trophy | +0.020 |
Prize | +0.020 |
contest | +0.020 |
prize | +0.020 |
Neg logit contributions | |
bur | -0.040 |
i | -0.039 |
rying | -0.038 |
ppa | -0.038 |
ind | -0.037 |
Token | again |
Token ID | 757 |
Feature activation | +4.18e-02 |
Pos logit contributions | |
vows | +0.032 |
apy | +0.028 |
prize | +0.028 |
Prize | +0.027 |
trophy | +0.027 |
Neg logit contributions | |
rying | -0.024 |
bur | -0.024 |
ppa | -0.024 |
i | -0.023 |
ety | -0.022 |
Token | . |
Token ID | 13 |
Feature activation | +1.44e-02 |
Pos logit contributions | |
bur | +0.105 |
rying | +0.101 |
ppa | +0.100 |
umper | +0.096 |
gie | +0.096 |
Neg logit contributions | |
vows | -0.047 |
prize | -0.043 |
contest | -0.042 |
are | -0.040 |
trophy | -0.038 |
Token | She |
Token ID | 1375 |
Feature activation | +4.06e-03 |
Pos logit contributions | |
rying | +0.036 |
bur | +0.036 |
ppa | +0.035 |
i | +0.034 |
ind | +0.034 |
Neg logit contributions | |
vows | -0.017 |
apy | -0.014 |
prize | -0.014 |
contest | -0.014 |
trophy | -0.014 |
Token | hoped |
Token ID | 10719 |
Feature activation | +2.18e-02 |
Pos logit contributions | |
bur | +0.007 |
rying | +0.007 |
ppa | +0.007 |
i | +0.007 |
ind | +0.007 |
Neg logit contributions | |
vows | -0.008 |
prize | -0.007 |
contest | -0.007 |
trophy | -0.007 |
cakes | -0.006 |
Token | her |
Token ID | 607 |
Feature activation | -3.62e-03 |
Pos logit contributions | |
rying | +0.054 |
bur | +0.054 |
ppa | +0.053 |
ind | +0.052 |
cker | +0.051 |
Neg logit contributions | |
vows | -0.027 |
prize | -0.024 |
contest | -0.023 |
cakes | -0.023 |
trophy | -0.023 |
Token | eyes |
Token ID | 2951 |
Feature activation | -1.95e-02 |
Pos logit contributions | |
vows | +0.006 |
contest | +0.005 |
prize | +0.005 |
trophy | +0.005 |
apy | +0.005 |
Neg logit contributions | |
bur | -0.008 |
ppa | -0.008 |
rying | -0.008 |
i | -0.007 |
ind | -0.007 |
Token | would |
Token ID | 561 |
Feature activation | -9.24e-03 |
Pos logit contributions | |
vows | +0.030 |
prize | +0.027 |
contest | +0.026 |
trophy | +0.026 |
Prize | +0.026 |
Neg logit contributions | |
bur | -0.042 |
rying | -0.041 |
ppa | -0.040 |
i | -0.040 |
ety | -0.039 |
Token | get |
Token ID | 651 |
Feature activation | +2.97e-02 |
Pos logit contributions | |
vows | +0.015 |
cakes | +0.013 |
prize | +0.013 |
contest | +0.013 |
trophy | +0.013 |
Neg logit contributions | |
bur | -0.019 |
rying | -0.019 |
ppa | -0.018 |
i | -0.018 |
ety | -0.017 |
Token | better |
Token ID | 1365 |
Feature activation | +4.46e-02 |
Pos logit contributions | |
rying | +0.065 |
bur | +0.064 |
ppa | +0.063 |
ind | +0.062 |
ior | +0.061 |
Neg logit contributions | |
vows | -0.043 |
prize | -0.038 |
apy | -0.037 |
contest | -0.037 |
tea | -0.037 |
Token | soon |
Token ID | 2582 |
Feature activation | +2.05e-02 |
Pos logit contributions | |
bur | +0.110 |
ind | +0.104 |
rying | +0.104 |
gie | +0.104 |
umper | +0.103 |
Neg logit contributions | |
vows | -0.051 |
prize | -0.048 |
contest | -0.045 |
are | -0.044 |
trophy | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | +1.58e-02 |
Pos logit contributions | |
bur | +0.044 |
rying | +0.043 |
ppa | +0.042 |
ind | +0.042 |
i | +0.041 |
Neg logit contributions | |
vows | -0.032 |
prize | -0.029 |
contest | -0.028 |
trophy | -0.027 |
cakes | -0.026 |
Token | and |
Token ID | 290 |
Feature activation | +4.52e-03 |
Pos logit contributions | |
vows | +0.024 |
prize | +0.022 |
contest | +0.022 |
trophy | +0.022 |
Prize | +0.021 |
Neg logit contributions | |
bur | -0.023 |
rying | -0.023 |
ppa | -0.022 |
i | -0.022 |
ind | -0.021 |
Token | a |
Token ID | 257 |
Feature activation | -2.63e-02 |
Pos logit contributions | |
bur | +0.009 |
rying | +0.009 |
ppa | +0.009 |
i | +0.009 |
ind | +0.009 |
Neg logit contributions | |
vows | -0.008 |
prize | -0.007 |
contest | -0.007 |
trophy | -0.007 |
cakes | -0.006 |
Token | big |
Token ID | 1263 |
Feature activation | -9.98e-03 |
Pos logit contributions | |
vows | +0.042 |
cakes | +0.036 |
prize | +0.035 |
contest | +0.034 |
trophy | +0.034 |
Neg logit contributions | |
bur | -0.053 |
ppa | -0.052 |
rying | -0.051 |
ind | -0.050 |
i | -0.050 |
Token | paper |
Token ID | 3348 |
Feature activation | -6.58e-03 |
Pos logit contributions | |
vows | +0.016 |
cakes | +0.014 |
prize | +0.014 |
contest | +0.013 |
trophy | +0.013 |
Neg logit contributions | |
bur | -0.021 |
rying | -0.020 |
ppa | -0.020 |
i | -0.019 |
ind | -0.019 |
Token | . |
Token ID | 13 |
Feature activation | +7.86e-03 |
Pos logit contributions | |
vows | +0.012 |
prize | +0.010 |
contest | +0.010 |
trophy | +0.010 |
cakes | +0.010 |
Neg logit contributions | |
bur | -0.012 |
rying | -0.012 |
ppa | -0.012 |
i | -0.012 |
ind | -0.011 |
Token | He |
Token ID | 679 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
bur | +0.018 |
rying | +0.018 |
ppa | +0.018 |
i | +0.017 |
ind | +0.017 |
Neg logit contributions | |
vows | -0.011 |
prize | -0.010 |
contest | -0.009 |
trophy | -0.009 |
cakes | -0.009 |
Token | dipped |
Token ID | 35300 |
Feature activation | +2.47e-02 |
Pos logit contributions | |
vows | +0.039 |
prize | +0.037 |
contest | +0.036 |
trophy | +0.036 |
cakes | +0.035 |
Neg logit contributions | |
bur | -0.038 |
i | -0.037 |
rying | -0.037 |
ppa | -0.037 |
ind | -0.036 |
Token | his |
Token ID | 465 |
Feature activation | +9.49e-03 |
Pos logit contributions | |
ppa | +0.056 |
rying | +0.056 |
bur | +0.055 |
ind | +0.053 |
ior | +0.052 |
Neg logit contributions | |
vows | -0.034 |
prize | -0.030 |
trophy | -0.030 |
apy | -0.030 |
contest | -0.029 |
Token | brush |
Token ID | 14093 |
Feature activation | +2.58e-03 |
Pos logit contributions | |
bur | +0.018 |
rying | +0.018 |
ppa | +0.017 |
ind | +0.017 |
i | +0.017 |
Neg logit contributions | |
vows | -0.017 |
prize | -0.016 |
contest | -0.015 |
trophy | -0.015 |
apy | -0.015 |
Token | in |
Token ID | 287 |
Feature activation | +1.25e-02 |
Pos logit contributions | |
bur | +0.005 |
rying | +0.004 |
ppa | +0.004 |
i | +0.004 |
ind | +0.004 |
Neg logit contributions | |
vows | -0.005 |
prize | -0.004 |
contest | -0.004 |
trophy | -0.004 |
cakes | -0.004 |
Token | red |
Token ID | 2266 |
Feature activation | +1.41e-03 |
Pos logit contributions | |
rying | +0.028 |
bur | +0.028 |
ppa | +0.027 |
ind | +0.026 |
i | +0.026 |
Neg logit contributions | |
vows | -0.018 |
prize | -0.017 |
trophy | -0.016 |
contest | -0.016 |
apy | -0.015 |
Token | the |
Token ID | 262 |
Feature activation | +1.50e-02 |
Pos logit contributions | |
bur | +0.014 |
rying | +0.014 |
ppa | +0.014 |
i | +0.014 |
ind | +0.013 |
Neg logit contributions | |
vows | -0.009 |
prize | -0.008 |
contest | -0.008 |
trophy | -0.008 |
apy | -0.008 |
Token | mess |
Token ID | 2085 |
Feature activation | -4.95e-02 |
Pos logit contributions | |
bur | +0.029 |
ppa | +0.029 |
rying | +0.029 |
i | +0.027 |
ety | +0.027 |
Neg logit contributions | |
vows | -0.026 |
prize | -0.024 |
contest | -0.024 |
trophy | -0.024 |
cakes | -0.023 |
Token | went |
Token ID | 1816 |
Feature activation | -1.12e-02 |
Pos logit contributions | |
vows | +0.089 |
prize | +0.078 |
Prize | +0.077 |
trophy | +0.076 |
contest | +0.075 |
Neg logit contributions | |
rying | -0.094 |
i | -0.089 |
bur | -0.088 |
ppa | -0.084 |
gie | -0.082 |
Token | away |
Token ID | 1497 |
Feature activation | -2.67e-02 |
Pos logit contributions | |
vows | +0.024 |
prize | +0.021 |
trophy | +0.021 |
apy | +0.021 |
cakes | +0.021 |
Neg logit contributions | |
rying | -0.018 |
bur | -0.018 |
ind | -0.016 |
ppa | -0.016 |
i | -0.016 |
Token | and |
Token ID | 290 |
Feature activation | +8.94e-03 |
Pos logit contributions | |
vows | +0.056 |
cakes | +0.050 |
contest | +0.050 |
trophy | +0.049 |
prize | +0.049 |
Neg logit contributions | |
rying | -0.044 |
bur | -0.041 |
i | -0.040 |
ppa | -0.039 |
ind | -0.038 |
Token | everything |
Token ID | 2279 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
bur | +0.019 |
rying | +0.019 |
ppa | +0.019 |
ind | +0.018 |
i | +0.018 |
Neg logit contributions | |
vows | -0.014 |
prize | -0.012 |
contest | -0.012 |
trophy | -0.012 |
cakes | -0.011 |
Token | was |
Token ID | 373 |
Feature activation | +3.82e-03 |
Pos logit contributions | |
vows | +0.112 |
Prize | +0.107 |
prize | +0.099 |
Mine | +0.097 |
uits | +0.096 |
Neg logit contributions | |
rying | -0.089 |
i | -0.082 |
bur | -0.081 |
forth | -0.079 |
my | -0.079 |
Token | clean |
Token ID | 3424 |
Feature activation | -7.75e-03 |
Pos logit contributions | |
bur | +0.007 |
rying | +0.007 |
ppa | +0.007 |
i | +0.006 |
ind | +0.006 |
Neg logit contributions | |
vows | -0.007 |
prize | -0.007 |
contest | -0.007 |
trophy | -0.006 |
cakes | -0.006 |
Token | again |
Token ID | 757 |
Feature activation | +2.91e-02 |
Pos logit contributions | |
vows | +0.015 |
prize | +0.013 |
contest | +0.013 |
trophy | +0.013 |
apy | +0.013 |
Neg logit contributions | |
bur | -0.014 |
rying | -0.014 |
ppa | -0.013 |
i | -0.013 |
ind | -0.013 |
Token | . |
Token ID | 13 |
Feature activation | -5.43e-03 |
Pos logit contributions | |
bur | +0.066 |
ppa | +0.065 |
rying | +0.064 |
ind | +0.062 |
umper | +0.062 |
Neg logit contributions | |
vows | -0.040 |
prize | -0.036 |
contest | -0.035 |
apy | -0.034 |
are | -0.033 |
Token | The |
Token ID | 383 |
Feature activation | -9.34e-03 |
Pos logit contributions | |
vows | +0.008 |
prize | +0.007 |
trophy | +0.007 |
contest | +0.007 |
cakes | +0.006 |
Neg logit contributions | |
bur | -0.012 |
rying | -0.012 |
ppa | -0.012 |
i | -0.011 |
ind | -0.011 |
Token | animals |
Token ID | 4695 |
Feature activation | -2.98e-02 |
Pos logit contributions | |
vows | +0.027 |
apy | +0.025 |
cakes | +0.023 |
trophy | +0.023 |
prize | +0.023 |
Neg logit contributions | |
rying | -0.031 |
bur | -0.031 |
ppa | -0.030 |
i | -0.030 |
ind | -0.030 |
Token | and |
Token ID | 290 |
Feature activation | -5.65e-03 |
Pos logit contributions | |
vows | +0.060 |
apy | +0.052 |
prize | +0.052 |
cakes | +0.051 |
trophy | +0.051 |
Neg logit contributions | |
rying | -0.052 |
bur | -0.049 |
i | -0.049 |
ppa | -0.048 |
ind | -0.045 |
Token | fill |
Token ID | 6070 |
Feature activation | -3.84e-02 |
Pos logit contributions | |
vows | +0.008 |
prize | +0.007 |
contest | +0.007 |
trophy | +0.007 |
cakes | +0.007 |
Neg logit contributions | |
bur | -0.012 |
rying | -0.012 |
ppa | -0.012 |
i | -0.012 |
ind | -0.012 |
Token | in |
Token ID | 287 |
Feature activation | -3.21e-02 |
Pos logit contributions | |
vows | +0.066 |
Prize | +0.058 |
trophy | +0.058 |
contest | +0.057 |
apy | +0.057 |
Neg logit contributions | |
bur | -0.073 |
i | -0.073 |
rying | -0.071 |
ind | -0.071 |
ppa | -0.068 |
Token | the |
Token ID | 262 |
Feature activation | -2.15e-02 |
Pos logit contributions | |
vows | +0.056 |
cakes | +0.050 |
apy | +0.048 |
contest | +0.048 |
Prize | +0.047 |
Neg logit contributions | |
bur | -0.059 |
rying | -0.058 |
ind | -0.058 |
i | -0.057 |
my | -0.057 |
Token | numbers |
Token ID | 3146 |
Feature activation | -5.18e-02 |
Pos logit contributions | |
vows | +0.039 |
apy | +0.036 |
cakes | +0.034 |
prize | +0.034 |
trophy | +0.033 |
Neg logit contributions | |
rying | -0.038 |
bur | -0.037 |
ind | -0.037 |
ppa | -0.036 |
my | -0.036 |
Token | . |
Token ID | 13 |
Feature activation | -3.07e-02 |
Pos logit contributions | |
vows | +0.116 |
Prize | +0.101 |
apy | +0.100 |
joke | +0.098 |
prize | +0.098 |
Neg logit contributions | |
rying | -0.075 |
i | -0.072 |
bur | -0.070 |
my | -0.067 |
ppa | -0.065 |
Token | Ana |
Token ID | 17639 |
Feature activation | -3.20e-02 |
Pos logit contributions | |
vows | +0.050 |
trophy | +0.050 |
prize | +0.047 |
contest | +0.045 |
ades | +0.045 |
Neg logit contributions | |
i | -0.058 |
rying | -0.057 |
bur | -0.056 |
ppa | -0.056 |
ior | -0.055 |
Token | was |
Token ID | 373 |
Feature activation | -3.26e-02 |
Pos logit contributions | |
vows | +0.057 |
prize | +0.054 |
trophy | +0.053 |
cakes | +0.052 |
contest | +0.052 |
Neg logit contributions | |
i | -0.058 |
ppa | -0.055 |
rying | -0.055 |
bur | -0.055 |
ind | -0.053 |
Token | so |
Token ID | 523 |
Feature activation | -5.13e-02 |
Pos logit contributions | |
vows | +0.066 |
ades | +0.061 |
cakes | +0.059 |
trophy | +0.058 |
prize | +0.058 |
Neg logit contributions | |
rying | -0.052 |
bur | -0.051 |
ppa | -0.049 |
i | -0.049 |
my | -0.048 |
Token | excited |
Token ID | 6568 |
Feature activation | -1.55e-03 |
Pos logit contributions | |
vows | +0.110 |
ades | +0.101 |
cakes | +0.096 |
prize | +0.095 |
ves | +0.094 |
Neg logit contributions | |
aware | -0.071 |
rying | -0.067 |
i | -0.065 |
my | -0.065 |
ind | -0.062 |
Token | swings |
Token ID | 26728 |
Feature activation | -1.70e-02 |
Pos logit contributions | |
vows | +0.001 |
prize | +0.001 |
contest | +0.001 |
trophy | +0.001 |
cakes | +0.001 |
Neg logit contributions | |
bur | -0.001 |
rying | -0.001 |
ppa | -0.001 |
ind | -0.001 |
i | -0.001 |
Token | and |
Token ID | 290 |
Feature activation | +4.99e-03 |
Pos logit contributions | |
vows | +0.037 |
prize | +0.032 |
trophy | +0.032 |
apy | +0.032 |
Prize | +0.032 |
Neg logit contributions | |
bur | -0.027 |
rying | -0.027 |
i | -0.026 |
ppa | -0.024 |
ety | -0.024 |
Token | slides |
Token ID | 19392 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
bur | +0.010 |
rying | +0.010 |
ppa | +0.010 |
i | +0.010 |
ind | +0.010 |
Neg logit contributions | |
vows | -0.008 |
prize | -0.007 |
contest | -0.007 |
trophy | -0.007 |
cakes | -0.007 |
Token | . |
Token ID | 13 |
Feature activation | -1.10e-02 |
Pos logit contributions | |
vows | +0.035 |
prize | +0.031 |
trophy | +0.031 |
contest | +0.030 |
apy | +0.030 |
Neg logit contributions | |
bur | -0.028 |
rying | -0.028 |
i | -0.026 |
ppa | -0.025 |
ety | -0.025 |
Token | She |
Token ID | 1375 |
Feature activation | -3.75e-04 |
Pos logit contributions | |
vows | +0.018 |
trophy | +0.016 |
prize | +0.016 |
contest | +0.016 |
ades | +0.015 |
Neg logit contributions | |
bur | -0.023 |
rying | -0.022 |
ppa | -0.022 |
i | -0.022 |
ind | -0.021 |
Token | couldn |
Token ID | 3521 |
Feature activation | -5.58e-02 |
Pos logit contributions | |
vows | +0.001 |
prize | +0.001 |
contest | +0.001 |
trophy | +0.001 |
cakes | +0.001 |
Neg logit contributions | |
bur | -0.001 |
rying | -0.001 |
ppa | -0.001 |
i | -0.001 |
ind | -0.001 |
Token | 't |
Token ID | 470 |
Feature activation | -1.83e-02 |
Pos logit contributions | |
vows | +0.110 |
props | +0.089 |
trophy | +0.088 |
prize | +0.084 |
ades | +0.083 |
Neg logit contributions | |
bur | -0.097 |
my | -0.091 |
Owl | -0.089 |
i | -0.088 |
rying | -0.088 |
Token | wait |
Token ID | 4043 |
Feature activation | -1.78e-02 |
Pos logit contributions | |
vows | +0.029 |
cakes | +0.026 |
apy | +0.026 |
ades | +0.025 |
trophy | +0.024 |
Neg logit contributions | |
rying | -0.038 |
bur | -0.038 |
ppa | -0.037 |
i | -0.037 |
cker | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | +2.26e-03 |
Pos logit contributions | |
vows | +0.039 |
cakes | +0.035 |
trophy | +0.035 |
prize | +0.035 |
apy | +0.035 |
Neg logit contributions | |
rying | -0.028 |
bur | -0.026 |
i | -0.025 |
ppa | -0.025 |
ind | -0.023 |
Token | play |
Token ID | 711 |
Feature activation | -4.27e-02 |
Pos logit contributions | |
bur | +0.006 |
rying | +0.005 |
ppa | +0.005 |
i | +0.005 |
ind | +0.005 |
Neg logit contributions | |
vows | -0.003 |
prize | -0.002 |
contest | -0.002 |
trophy | -0.002 |
cakes | -0.002 |
Token | , |
Token ID | 11 |
Feature activation | +7.93e-04 |
Pos logit contributions | |
vows | +0.100 |
apy | +0.086 |
Mine | +0.083 |
cakes | +0.083 |
Prize | +0.082 |
Neg logit contributions | |
rying | -0.062 |
bur | -0.057 |
i | -0.055 |
ppa | -0.051 |
forth | -0.051 |
Token | guitar |
Token ID | 10047 |
Feature activation | -3.39e-02 |
Pos logit contributions | |
vows | +0.039 |
apy | +0.036 |
cakes | +0.035 |
contest | +0.033 |
prize | +0.033 |
Neg logit contributions | |
ind | -0.052 |
bur | -0.051 |
ppa | -0.050 |
rying | -0.049 |
i | -0.049 |
Token | , |
Token ID | 11 |
Feature activation | +3.99e-03 |
Pos logit contributions | |
vows | +0.070 |
apy | +0.064 |
prize | +0.063 |
cakes | +0.062 |
trophy | +0.062 |
Neg logit contributions | |
rying | -0.053 |
i | -0.051 |
bur | -0.051 |
ppa | -0.050 |
ind | -0.048 |
Token | imagining |
Token ID | 34140 |
Feature activation | -3.79e-02 |
Pos logit contributions | |
bur | +0.007 |
rying | +0.007 |
ppa | +0.007 |
i | +0.007 |
ind | +0.007 |
Neg logit contributions | |
vows | -0.008 |
prize | -0.007 |
contest | -0.007 |
trophy | -0.007 |
cakes | -0.007 |
Token | all |
Token ID | 477 |
Feature activation | -1.85e-02 |
Pos logit contributions | |
vows | +0.068 |
Prize | +0.059 |
trophy | +0.058 |
contest | +0.058 |
cakes | +0.058 |
Neg logit contributions | |
rying | -0.069 |
i | -0.068 |
bur | -0.066 |
ppa | -0.065 |
ind | -0.064 |
Token | the |
Token ID | 262 |
Feature activation | -1.67e-02 |
Pos logit contributions | |
vows | +0.034 |
apy | +0.029 |
prize | +0.029 |
contest | +0.028 |
ades | +0.028 |
Neg logit contributions | |
bur | -0.035 |
rying | -0.034 |
i | -0.033 |
ind | -0.032 |
my | -0.032 |
Token | music |
Token ID | 2647 |
Feature activation | -7.18e-02 |
Pos logit contributions | |
vows | +0.022 |
apy | +0.021 |
cakes | +0.020 |
contest | +0.019 |
prize | +0.019 |
Neg logit contributions | |
bur | -0.038 |
ind | -0.037 |
rying | -0.037 |
ppa | -0.037 |
i | -0.037 |
Token | she |
Token ID | 673 |
Feature activation | +3.34e-03 |
Pos logit contributions | |
vows | +0.135 |
apy | +0.124 |
Mine | +0.120 |
Prize | +0.120 |
ades | +0.117 |
Neg logit contributions | |
i | -0.116 |
my | -0.113 |
rying | -0.112 |
bur | -0.111 |
owl | -0.107 |
Token | could |
Token ID | 714 |
Feature activation | -4.49e-02 |
Pos logit contributions | |
bur | +0.007 |
rying | +0.007 |
ppa | +0.007 |
i | +0.007 |
ind | +0.007 |
Neg logit contributions | |
vows | -0.005 |
prize | -0.005 |
contest | -0.005 |
trophy | -0.005 |
cakes | -0.005 |
Token | make |
Token ID | 787 |
Feature activation | -4.79e-02 |
Pos logit contributions | |
vows | +0.070 |
cakes | +0.064 |
apy | +0.061 |
Prize | +0.061 |
prize | +0.058 |
Neg logit contributions | |
bur | -0.091 |
rying | -0.090 |
i | -0.088 |
cker | -0.086 |
ind | -0.084 |
Token | . |
Token ID | 13 |
Feature activation | -1.34e-02 |
Pos logit contributions | |
vows | +0.091 |
Prize | +0.080 |
trophy | +0.080 |
apy | +0.079 |
prize | +0.078 |
Neg logit contributions | |
i | -0.081 |
rying | -0.080 |
bur | -0.077 |
ind | -0.076 |
ppa | -0.076 |
Token | She |
Token ID | 1375 |
Feature activation | -1.48e-02 |
Pos logit contributions | |
vows | +0.022 |
prize | +0.020 |
trophy | +0.019 |
contest | +0.019 |
ades | +0.018 |
Neg logit contributions | |
bur | -0.026 |
ppa | -0.026 |
rying | -0.026 |
ior | -0.025 |
ind | -0.025 |
Token | equipment |
Token ID | 5112 |
Feature activation | -1.58e-02 |
Pos logit contributions | |
vows | +0.025 |
cakes | +0.022 |
contest | +0.021 |
Prize | +0.021 |
prize | +0.021 |
Neg logit contributions | |
bur | -0.031 |
rying | -0.030 |
ppa | -0.029 |
i | -0.029 |
gie | -0.029 |
Token | to |
Token ID | 284 |
Feature activation | -1.90e-02 |
Pos logit contributions | |
vows | +0.033 |
apy | +0.029 |
prize | +0.029 |
trophy | +0.029 |
contest | +0.029 |
Neg logit contributions | |
bur | -0.025 |
rying | -0.025 |
ppa | -0.023 |
i | -0.023 |
ety | -0.022 |
Token | cook |
Token ID | 4255 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
vows | +0.031 |
cakes | +0.026 |
prize | +0.026 |
contest | +0.025 |
trophy | +0.025 |
Neg logit contributions | |
bur | -0.040 |
rying | -0.039 |
ppa | -0.037 |
i | -0.037 |
cker | -0.036 |
Token | up |
Token ID | 510 |
Feature activation | -1.94e-02 |
Pos logit contributions | |
vows | +0.051 |
Prize | +0.045 |
prize | +0.045 |
trophy | +0.045 |
contest | +0.043 |
Neg logit contributions | |
bur | -0.053 |
rying | -0.051 |
i | -0.051 |
ppa | -0.050 |
ind | -0.048 |
Token | some |
Token ID | 617 |
Feature activation | -8.60e-03 |
Pos logit contributions | |
vows | +0.035 |
prize | +0.030 |
trophy | +0.030 |
Prize | +0.030 |
contest | +0.030 |
Neg logit contributions | |
bur | -0.037 |
rying | -0.036 |
i | -0.035 |
ppa | -0.035 |
ind | -0.034 |
Token | pretend |
Token ID | 16614 |
Feature activation | -6.06e-02 |
Pos logit contributions | |
vows | +0.014 |
prize | +0.012 |
trophy | +0.012 |
contest | +0.012 |
Prize | +0.012 |
Neg logit contributions | |
rying | -0.017 |
bur | -0.017 |
ppa | -0.017 |
i | -0.017 |
ind | -0.017 |
Token | food |
Token ID | 2057 |
Feature activation | -5.41e-02 |
Pos logit contributions | |
vows | +0.105 |
Prize | +0.097 |
apy | +0.093 |
prize | +0.093 |
Mine | +0.093 |
Neg logit contributions | |
i | -0.103 |
bur | -0.102 |
rying | -0.101 |
ind | -0.098 |
cker | -0.097 |
Token | . |
Token ID | 13 |
Feature activation | -1.40e-02 |
Pos logit contributions | |
vows | +0.114 |
apy | +0.104 |
Prize | +0.102 |
Mine | +0.102 |
trophy | +0.101 |
Neg logit contributions | |
bur | -0.081 |
i | -0.080 |
rying | -0.079 |
ppa | -0.073 |
my | -0.073 |
Token | She |
Token ID | 1375 |
Feature activation | -1.18e-02 |
Pos logit contributions | |
vows | +0.024 |
prize | +0.021 |
trophy | +0.021 |
contest | +0.020 |
ades | +0.020 |
Neg logit contributions | |
bur | -0.027 |
rying | -0.027 |
ppa | -0.027 |
ety | -0.026 |
i | -0.026 |
Token | measured |
Token ID | 8630 |
Feature activation | +3.25e-02 |
Pos logit contributions | |
vows | +0.022 |
prize | +0.020 |
trophy | +0.020 |
contest | +0.020 |
cakes | +0.019 |
Neg logit contributions | |
bur | -0.021 |
ppa | -0.021 |
rying | -0.021 |
i | -0.021 |
ind | -0.020 |
Token | out |
Token ID | 503 |
Feature activation | -1.68e-02 |
Pos logit contributions | |
rying | +0.078 |
ppa | +0.077 |
bur | +0.076 |
ind | +0.073 |
cker | +0.072 |
Neg logit contributions | |
vows | -0.040 |
prize | -0.036 |
contest | -0.035 |
cakes | -0.034 |
apy | -0.034 |