Token | . |
Token ID | 13 |
Feature activation | +5.64e+00 |
Pos logit contributions | |
es | +0.108 |
le | +0.104 |
ices | +0.096 |
ymes | +0.096 |
les | +0.095 |
Neg logit contributions | |
disl | -0.176 |
Cr | -0.155 |
Twe | -0.147 |
Fro | -0.144 |
Joey | -0.141 |
Token | The |
Token ID | 383 |
Feature activation | +6.91e+00 |
Pos logit contributions | |
es | +0.079 |
on | +0.078 |
again | +0.077 |
y | +0.073 |
m | +0.073 |
Neg logit contributions | |
disl | -0.061 |
majesty | -0.035 |
Majesty | -0.035 |
Cr | -0.034 |
Fro | -0.032 |
Token | toy |
Token ID | 13373 |
Feature activation | +1.20e+01 |
Pos logit contributions | |
on | +0.041 |
es | +0.038 |
again | +0.038 |
y | +0.035 |
m | +0.032 |
Neg logit contributions | |
disl | -0.131 |
Cr | -0.102 |
majesty | -0.098 |
Fro | -0.098 |
Fre | -0.097 |
Token | was |
Token ID | 373 |
Feature activation | +6.75e+00 |
Pos logit contributions | |
es | +0.103 |
again | +0.097 |
le | +0.097 |
m | +0.091 |
ices | +0.089 |
Neg logit contributions | |
disl | -0.185 |
Cr | -0.145 |
Joey | -0.136 |
Twe | -0.135 |
Fro | -0.135 |
Token | a |
Token ID | 257 |
Feature activation | +8.62e+00 |
Pos logit contributions | |
on | +0.071 |
es | +0.069 |
again | +0.066 |
y | +0.062 |
m | +0.062 |
Neg logit contributions | |
disl | -0.100 |
Cr | -0.069 |
majesty | -0.067 |
Joey | -0.067 |
Majesty | -0.065 |
Token | laser |
Token ID | 12855 |
Feature activation | +1.61e+01 |
Pos logit contributions | |
es | +0.097 |
again | +0.091 |
on | +0.088 |
le | +0.086 |
m | +0.086 |
Neg logit contributions | |
disl | -0.117 |
Cr | -0.083 |
Joey | -0.078 |
Fro | -0.077 |
Twe | -0.075 |
Token | . |
Token ID | 13 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
packs | +0.141 |
ices | +0.136 |
pr | +0.132 |
ymes | +0.130 |
es | +0.130 |
Neg logit contributions | |
disl | -0.205 |
Twe | -0.180 |
This | -0.178 |
Cr | -0.171 |
Fro | -0.167 |
Token | Tim |
Token ID | 5045 |
Feature activation | +9.62e+00 |
Pos logit contributions | |
es | +0.091 |
again | +0.088 |
on | +0.088 |
m | +0.085 |
y | +0.083 |
Neg logit contributions | |
disl | -0.057 |
majesty | -0.031 |
Cr | -0.030 |
Majesty | -0.030 |
Fro | -0.029 |
Token | liked |
Token ID | 8288 |
Feature activation | +6.78e+00 |
Pos logit contributions | |
es | +0.095 |
again | +0.090 |
le | +0.085 |
ices | +0.083 |
ing | +0.083 |
Neg logit contributions | |
disl | -0.141 |
Cr | -0.103 |
Joey | -0.097 |
Twe | -0.097 |
Fro | -0.096 |
Token | the |
Token ID | 262 |
Feature activation | +7.98e+00 |
Pos logit contributions | |
es | +0.073 |
again | +0.070 |
on | +0.069 |
y | +0.064 |
m | +0.063 |
Neg logit contributions | |
disl | -0.095 |
Cr | -0.068 |
Joey | -0.064 |
majesty | -0.063 |
Fro | -0.063 |
Token | laser |
Token ID | 12855 |
Feature activation | +1.46e+01 |
Pos logit contributions | |
es | +0.090 |
again | +0.080 |
le | +0.078 |
m | +0.076 |
y | +0.075 |
Neg logit contributions | |
disl | -0.113 |
Cr | -0.081 |
Joey | -0.077 |
Twe | -0.075 |
Fro | -0.074 |
Token | had |
Token ID | 550 |
Feature activation | +5.73e+00 |
Pos logit contributions | |
ymes | +0.125 |
es | +0.118 |
ices | +0.117 |
ities | +0.115 |
packs | +0.113 |
Neg logit contributions | |
disl | -0.121 |
Joey | -0.102 |
Jon | -0.094 |
Twe | -0.090 |
Joe | -0.090 |
Token | given |
Token ID | 1813 |
Feature activation | +6.87e+00 |
Pos logit contributions | |
on | +0.058 |
es | +0.056 |
again | +0.055 |
m | +0.050 |
y | +0.048 |
Neg logit contributions | |
disl | -0.088 |
Cr | -0.064 |
Joey | -0.060 |
Fro | -0.060 |
Madd | -0.059 |
Token | her |
Token ID | 607 |
Feature activation | +8.25e+00 |
Pos logit contributions | |
again | +0.065 |
on | +0.064 |
es | +0.064 |
le | +0.057 |
ing | +0.056 |
Neg logit contributions | |
disl | -0.109 |
majesty | -0.078 |
Cr | -0.077 |
Fro | -0.075 |
Majesty | -0.074 |
Token | special |
Token ID | 2041 |
Feature activation | +8.29e+00 |
Pos logit contributions | |
es | +0.094 |
again | +0.089 |
on | +0.086 |
le | +0.084 |
m | +0.084 |
Neg logit contributions | |
disl | -0.111 |
Cr | -0.079 |
Joey | -0.073 |
Fro | -0.073 |
Twe | -0.071 |
Token | cool |
Token ID | 3608 |
Feature activation | +8.49e+00 |
Pos logit contributions | |
es | +0.080 |
again | +0.068 |
le | +0.067 |
m | +0.067 |
y | +0.065 |
Neg logit contributions | |
disl | -0.129 |
Cr | -0.094 |
pleasure | -0.092 |
Joey | -0.091 |
majesty | -0.089 |
Token | gears |
Token ID | 28713 |
Feature activation | +1.57e+01 |
Pos logit contributions | |
es | +0.075 |
again | +0.065 |
le | +0.063 |
m | +0.063 |
y | +0.061 |
Neg logit contributions | |
disl | -0.138 |
Cr | -0.103 |
Joey | -0.099 |
Twe | -0.098 |
pleasure | -0.097 |
Token | which |
Token ID | 543 |
Feature activation | +6.08e+00 |
Pos logit contributions | |
es | +0.128 |
le | +0.113 |
again | +0.111 |
ymes | +0.110 |
m | +0.108 |
Neg logit contributions | |
disl | -0.253 |
Cr | -0.193 |
Joey | -0.189 |
Twe | -0.184 |
pleasure | -0.179 |
Token | made |
Token ID | 925 |
Feature activation | +4.86e+00 |
Pos logit contributions | |
es | +0.056 |
again | +0.052 |
on | +0.050 |
le | +0.049 |
y | +0.048 |
Neg logit contributions | |
disl | -0.095 |
Cr | -0.071 |
Joey | -0.067 |
Fro | -0.067 |
majesty | -0.066 |
Token | it |
Token ID | 340 |
Feature activation | +8.17e+00 |
Pos logit contributions | |
es | +0.061 |
again | +0.057 |
m | +0.056 |
le | +0.056 |
y | +0.055 |
Neg logit contributions | |
disl | -0.058 |
Cr | -0.039 |
Joey | -0.038 |
Twe | -0.036 |
Fro | -0.036 |
Token | easier |
Token ID | 4577 |
Feature activation | +8.57e+00 |
Pos logit contributions | |
es | +0.088 |
again | +0.086 |
on | +0.083 |
le | +0.079 |
y | +0.078 |
Neg logit contributions | |
disl | -0.114 |
Cr | -0.083 |
Fro | -0.078 |
Joey | -0.077 |
majesty | -0.076 |
Token | for |
Token ID | 329 |
Feature activation | +4.45e+00 |
Pos logit contributions | |
es | +0.079 |
le | +0.070 |
m | +0.069 |
ymes | +0.069 |
ices | +0.069 |
Neg logit contributions | |
disl | -0.128 |
Cr | -0.092 |
Joey | -0.092 |
Twe | -0.089 |
Fro | -0.087 |
Token | strange |
Token ID | 6283 |
Feature activation | +9.79e+00 |
Pos logit contributions | |
es | +0.134 |
ices | +0.120 |
packs | +0.118 |
again | +0.117 |
m | +0.117 |
Neg logit contributions | |
disl | -0.115 |
Cr | -0.077 |
Joey | -0.077 |
Fro | -0.073 |
Twe | -0.071 |
Token | . |
Token ID | 13 |
Feature activation | +4.87e+00 |
Pos logit contributions | |
es | +0.077 |
ologist | +0.070 |
ymes | +0.070 |
ices | +0.070 |
m | +0.069 |
Neg logit contributions | |
disl | -0.147 |
Joey | -0.114 |
Joe | -0.110 |
Cr | -0.106 |
J | -0.105 |
Token | It |
Token ID | 632 |
Feature activation | +7.68e+00 |
Pos logit contributions | |
es | +0.064 |
again | +0.062 |
on | +0.062 |
boards | +0.059 |
ices | +0.057 |
Neg logit contributions | |
disl | -0.057 |
majesty | -0.034 |
Majesty | -0.032 |
Cr | -0.032 |
Fro | -0.031 |
Token | was |
Token ID | 373 |
Feature activation | +4.99e+00 |
Pos logit contributions | |
es | +0.063 |
again | +0.057 |
on | +0.054 |
le | +0.053 |
m | +0.053 |
Neg logit contributions | |
disl | -0.128 |
Cr | -0.098 |
Joey | -0.094 |
Fro | -0.092 |
Twe | -0.091 |
Token | a |
Token ID | 257 |
Feature activation | +7.54e+00 |
Pos logit contributions | |
on | +0.051 |
again | +0.049 |
es | +0.048 |
y | +0.043 |
m | +0.042 |
Neg logit contributions | |
disl | -0.077 |
majesty | -0.053 |
Cr | -0.053 |
Majesty | -0.051 |
APP | -0.049 |
Token | mask |
Token ID | 9335 |
Feature activation | +1.57e+01 |
Pos logit contributions | |
es | +0.082 |
again | +0.078 |
on | +0.076 |
m | +0.073 |
y | +0.073 |
Neg logit contributions | |
disl | -0.105 |
Cr | -0.075 |
Joey | -0.070 |
Fro | -0.069 |
Twe | -0.067 |
Token | ! |
Token ID | 0 |
Feature activation | +3.88e+00 |
Pos logit contributions | |
es | +0.148 |
ymes | +0.147 |
ices | +0.144 |
packs | +0.140 |
le | +0.135 |
Neg logit contributions | |
disl | -0.206 |
Cr | -0.157 |
Joey | -0.156 |
Twe | -0.155 |
Fro | -0.153 |
Token | It |
Token ID | 632 |
Feature activation | +7.58e+00 |
Pos logit contributions | |
es | +0.051 |
on | +0.049 |
again | +0.049 |
boards | +0.047 |
and | +0.045 |
Neg logit contributions | |
disl | -0.046 |
majesty | -0.029 |
Majesty | -0.028 |
pleasure | -0.025 |
icol | -0.025 |
Token | was |
Token ID | 373 |
Feature activation | +5.29e+00 |
Pos logit contributions | |
es | +0.056 |
again | +0.051 |
on | +0.050 |
le | +0.047 |
y | +0.047 |
Neg logit contributions | |
disl | -0.134 |
Cr | -0.103 |
majesty | -0.099 |
Joey | -0.098 |
pleasure | -0.098 |
Token | lying |
Token ID | 9105 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
on | +0.053 |
es | +0.048 |
again | +0.046 |
and | +0.042 |
y | +0.042 |
Neg logit contributions | |
disl | -0.087 |
majesty | -0.061 |
Cr | -0.060 |
Majesty | -0.059 |
APP | -0.057 |
Token | on |
Token ID | 319 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
es | +0.065 |
ices | +0.060 |
le | +0.052 |
ities | +0.051 |
ymes | +0.050 |
Neg logit contributions | |
disl | -0.158 |
Joey | -0.147 |
Cr | -0.139 |
Twe | -0.138 |
Fro | -0.137 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
on | +0.032 |
again | +0.028 |
es | +0.027 |
m | +0.027 |
and | +0.026 |
Neg logit contributions | |
disl | -0.060 |
Cr | -0.045 |
pleasure | -0.045 |
Majesty | -0.043 |
majesty | -0.043 |
Token | a |
Token ID | 257 |
Feature activation | +7.12e+00 |
Pos logit contributions | |
on | +0.058 |
again | +0.055 |
es | +0.055 |
ing | +0.050 |
m | +0.049 |
Neg logit contributions | |
disl | -0.101 |
majesty | -0.075 |
icol | -0.071 |
Majesty | -0.071 |
pleasure | -0.070 |
Token | man |
Token ID | 582 |
Feature activation | +1.26e+01 |
Pos logit contributions | |
es | +0.078 |
again | +0.073 |
on | +0.070 |
le | +0.069 |
m | +0.069 |
Neg logit contributions | |
disl | -0.099 |
Cr | -0.071 |
Joey | -0.067 |
Fro | -0.066 |
Twe | -0.065 |
Token | selling |
Token ID | 6301 |
Feature activation | +9.33e+00 |
Pos logit contributions | |
es | +0.120 |
boards | +0.111 |
ymes | +0.109 |
ices | +0.107 |
les | +0.106 |
Neg logit contributions | |
disl | -0.176 |
Cr | -0.136 |
Twe | -0.128 |
Fro | -0.128 |
Joey | -0.125 |
Token | colorful |
Token ID | 20239 |
Feature activation | +8.89e+00 |
Pos logit contributions | |
es | +0.089 |
again | +0.085 |
on | +0.083 |
m | +0.079 |
le | +0.077 |
Neg logit contributions | |
disl | -0.143 |
Cr | -0.104 |
Joey | -0.099 |
Fro | -0.098 |
majesty | -0.097 |
Token | fireworks |
Token ID | 26056 |
Feature activation | +1.56e+01 |
Pos logit contributions | |
es | +0.084 |
again | +0.077 |
m | +0.073 |
le | +0.073 |
y | +0.071 |
Neg logit contributions | |
disl | -0.136 |
Cr | -0.102 |
Twe | -0.097 |
Joey | -0.096 |
Fro | -0.093 |
Token | . |
Token ID | 13 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
es | +0.117 |
ymes | +0.111 |
ices | +0.111 |
le | +0.104 |
Will | +0.102 |
Neg logit contributions | |
disl | -0.235 |
Joey | -0.191 |
Cr | -0.191 |
Twe | -0.186 |
J | -0.181 |
Token | She |
Token ID | 1375 |
Feature activation | +6.42e+00 |
Pos logit contributions | |
again | +0.043 |
on | +0.040 |
and | +0.039 |
y | +0.037 |
m | +0.037 |
Neg logit contributions | |
disl | -0.069 |
Majesty | -0.052 |
majesty | -0.052 |
Fre | -0.050 |
pleasure | -0.049 |
Token | asked |
Token ID | 1965 |
Feature activation | +6.67e+00 |
Pos logit contributions | |
es | +0.048 |
again | +0.045 |
y | +0.044 |
on | +0.043 |
m | +0.042 |
Neg logit contributions | |
disl | -0.115 |
pleasure | -0.086 |
Cr | -0.086 |
majesty | -0.082 |
Fro | -0.081 |
Token | her |
Token ID | 607 |
Feature activation | +6.17e+00 |
Pos logit contributions | |
es | +0.086 |
again | +0.080 |
le | +0.078 |
on | +0.078 |
m | +0.078 |
Neg logit contributions | |
disl | -0.079 |
Cr | -0.055 |
Joey | -0.051 |
Fro | -0.050 |
Twe | -0.050 |
Token | mom |
Token ID | 1995 |
Feature activation | +8.69e+00 |
Pos logit contributions | |
es | +0.076 |
again | +0.070 |
le | +0.069 |
on | +0.068 |
m | +0.067 |
Neg logit contributions | |
disl | -0.078 |
Cr | -0.054 |
Joey | -0.051 |
Fro | -0.050 |
Twe | -0.049 |
Token | day |
Token ID | 1110 |
Feature activation | +6.47e+00 |
Pos logit contributions | |
es | +0.083 |
again | +0.072 |
ymes | +0.069 |
le | +0.067 |
ices | +0.067 |
Neg logit contributions | |
disl | -0.101 |
Cr | -0.073 |
Joey | -0.072 |
Fro | -0.071 |
Twe | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | +3.83e+00 |
Pos logit contributions | |
es | +0.053 |
again | +0.049 |
le | +0.047 |
ymes | +0.045 |
m | +0.045 |
Neg logit contributions | |
disl | -0.103 |
Cr | -0.080 |
Fro | -0.078 |
Joey | -0.077 |
Madd | -0.075 |
Token | she |
Token ID | 673 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
es | +0.050 |
again | +0.047 |
on | +0.046 |
le | +0.045 |
m | +0.045 |
Neg logit contributions | |
disl | -0.046 |
Cr | -0.031 |
Joey | -0.028 |
Fro | -0.028 |
Twe | -0.027 |
Token | found |
Token ID | 1043 |
Feature activation | +7.36e+00 |
Pos logit contributions | |
es | +0.055 |
again | +0.051 |
on | +0.048 |
le | +0.048 |
m | +0.047 |
Neg logit contributions | |
disl | -0.094 |
Cr | -0.071 |
Joey | -0.067 |
Fro | -0.066 |
Twe | -0.065 |
Token | a |
Token ID | 257 |
Feature activation | +8.20e+00 |
Pos logit contributions | |
es | +0.073 |
on | +0.072 |
again | +0.070 |
m | +0.064 |
ing | +0.063 |
Neg logit contributions | |
disl | -0.117 |
Cr | -0.081 |
majesty | -0.080 |
icol | -0.077 |
Joey | -0.077 |
Token | mask |
Token ID | 9335 |
Feature activation | +1.55e+01 |
Pos logit contributions | |
es | +0.095 |
again | +0.088 |
le | +0.085 |
on | +0.083 |
m | +0.083 |
Neg logit contributions | |
disl | -0.109 |
Cr | -0.077 |
Joey | -0.073 |
Fro | -0.072 |
Twe | -0.071 |
Token | on |
Token ID | 319 |
Feature activation | +4.27e+00 |
Pos logit contributions | |
ymes | +0.148 |
ices | +0.144 |
packs | +0.141 |
ins | +0.141 |
eness | +0.131 |
Neg logit contributions | |
disl | -0.170 |
This | -0.162 |
Twe | -0.151 |
this | -0.148 |
Fro | -0.144 |
Token | the |
Token ID | 262 |
Feature activation | +4.53e+00 |
Pos logit contributions | |
es | +0.054 |
again | +0.051 |
on | +0.051 |
le | +0.049 |
y | +0.048 |
Neg logit contributions | |
disl | -0.054 |
Cr | -0.036 |
majesty | -0.033 |
Joey | -0.033 |
pleasure | -0.032 |
Token | floor |
Token ID | 4314 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
es | +0.037 |
again | +0.037 |
on | +0.036 |
le | +0.033 |
y | +0.033 |
Neg logit contributions | |
disl | -0.075 |
Cr | -0.057 |
Joey | -0.054 |
pleasure | -0.052 |
Twe | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +4.82e+00 |
Pos logit contributions | |
ymes | +0.090 |
es | +0.082 |
le | +0.081 |
les | +0.076 |
eness | +0.074 |
Neg logit contributions | |
disl | -0.135 |
J | -0.110 |
Jill | -0.104 |
This | -0.104 |
Sandy | -0.102 |
Token | The |
Token ID | 383 |
Feature activation | +6.71e+00 |
Pos logit contributions | |
es | +0.060 |
again | +0.056 |
on | +0.055 |
m | +0.053 |
y | +0.053 |
Neg logit contributions | |
disl | -0.063 |
Cr | -0.042 |
majesty | -0.039 |
Joey | -0.038 |
Twe | -0.038 |
Token | my |
Token ID | 1820 |
Feature activation | +8.42e+00 |
Pos logit contributions | |
es | +0.049 |
boards | +0.041 |
ymes | +0.036 |
ing | +0.035 |
cases | +0.035 |
Neg logit contributions | |
disl | -0.137 |
Cr | -0.108 |
Joey | -0.108 |
Fro | -0.107 |
Twe | -0.106 |
Token | . |
Token ID | 13 |
Feature activation | +3.17e+00 |
Pos logit contributions | |
es | +0.048 |
boards | +0.039 |
again | +0.039 |
le | +0.038 |
ymes | +0.036 |
Neg logit contributions | |
disl | -0.159 |
Cr | -0.125 |
Twe | -0.122 |
Fro | -0.120 |
Joey | -0.120 |
Token | Tim |
Token ID | 5045 |
Feature activation | +7.98e+00 |
Pos logit contributions | |
es | +0.051 |
again | +0.048 |
le | +0.047 |
on | +0.047 |
m | +0.046 |
Neg logit contributions | |
disl | -0.029 |
Cr | -0.016 |
Joey | -0.015 |
Fro | -0.014 |
Twe | -0.014 |
Token | my |
Token ID | 1820 |
Feature activation | +8.25e+00 |
Pos logit contributions | |
es | +0.039 |
again | +0.030 |
ing | +0.028 |
le | +0.026 |
boards | +0.026 |
Neg logit contributions | |
disl | -0.157 |
Joey | -0.124 |
Cr | -0.123 |
Twe | -0.121 |
Fro | -0.121 |
Token | loved |
Token ID | 6151 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
es | +0.083 |
again | +0.078 |
on | +0.077 |
y | +0.075 |
m | +0.073 |
Neg logit contributions | |
disl | -0.123 |
Cr | -0.092 |
Joey | -0.085 |
Fro | -0.085 |
majesty | -0.083 |
Token | vehicles |
Token ID | 5672 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
es | +0.054 |
on | +0.053 |
again | +0.053 |
m | +0.047 |
y | +0.046 |
Neg logit contributions | |
disl | -0.101 |
Cr | -0.075 |
majesty | -0.072 |
pleasure | -0.072 |
Joey | -0.072 |
Token | , |
Token ID | 11 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
es | +0.147 |
ymes | +0.143 |
ices | +0.140 |
le | +0.140 |
les | +0.134 |
Neg logit contributions | |
disl | -0.208 |
Cr | -0.166 |
Twe | -0.163 |
Joey | -0.156 |
Fro | -0.152 |
Token | especially |
Token ID | 2592 |
Feature activation | +7.34e+00 |
Pos logit contributions | |
es | +0.056 |
again | +0.051 |
on | +0.049 |
le | +0.049 |
m | +0.048 |
Neg logit contributions | |
disl | -0.089 |
Cr | -0.066 |
Joey | -0.062 |
Fro | -0.062 |
Twe | -0.061 |
Token | cars |
Token ID | 5006 |
Feature activation | +1.44e+01 |
Pos logit contributions | |
es | +0.084 |
again | +0.082 |
le | +0.079 |
m | +0.077 |
ymes | +0.076 |
Neg logit contributions | |
disl | -0.096 |
Cr | -0.066 |
Twe | -0.066 |
Joey | -0.063 |
Fro | -0.062 |
Token | . |
Token ID | 13 |
Feature activation | +3.99e+00 |
Pos logit contributions | |
ymes | +0.134 |
pr | +0.129 |
ices | +0.127 |
le | +0.122 |
es | +0.113 |
Neg logit contributions | |
disl | -0.183 |
Twe | -0.152 |
This | -0.146 |
Cr | -0.144 |
The | -0.140 |
Token | One |
Token ID | 1881 |
Feature activation | +7.80e+00 |
Pos logit contributions | |
es | +0.043 |
again | +0.042 |
on | +0.040 |
m | +0.039 |
y | +0.039 |
Neg logit contributions | |
disl | -0.056 |
Cr | -0.038 |
majesty | -0.037 |
Fro | -0.036 |
Joey | -0.036 |
Token | , |
Token ID | 11 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
es | +0.055 |
le | +0.050 |
again | +0.049 |
ymes | +0.049 |
les | +0.046 |
Neg logit contributions | |
disl | -0.094 |
Cr | -0.072 |
Joey | -0.070 |
Twe | -0.068 |
Fro | -0.068 |
Token | they |
Token ID | 484 |
Feature activation | +6.83e+00 |
Pos logit contributions | |
es | +0.044 |
again | +0.041 |
on | +0.040 |
le | +0.039 |
m | +0.039 |
Neg logit contributions | |
disl | -0.056 |
Cr | -0.040 |
Joey | -0.038 |
Fro | -0.038 |
Twe | -0.037 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.27e+00 |
Pos logit contributions | |
es | +0.068 |
again | +0.061 |
le | +0.059 |
on | +0.058 |
ing | +0.057 |
Neg logit contributions | |
disl | -0.101 |
Cr | -0.077 |
Joey | -0.074 |
Fro | -0.072 |
Twe | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | +8.62e+00 |
Pos logit contributions | |
on | +0.059 |
es | +0.059 |
again | +0.057 |
ing | +0.053 |
y | +0.050 |
Neg logit contributions | |
disl | -0.101 |
majesty | -0.073 |
Cr | -0.071 |
Majesty | -0.069 |
LL | -0.069 |
Token | big |
Token ID | 1263 |
Feature activation | +7.68e+00 |
Pos logit contributions | |
es | +0.102 |
again | +0.096 |
on | +0.092 |
le | +0.091 |
m | +0.091 |
Neg logit contributions | |
disl | -0.112 |
Cr | -0.078 |
Joey | -0.073 |
Fro | -0.072 |
Twe | -0.071 |
Token | motorcycle |
Token ID | 18757 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
es | +0.068 |
again | +0.065 |
on | +0.063 |
y | +0.060 |
le | +0.060 |
Neg logit contributions | |
disl | -0.122 |
Cr | -0.091 |
Joey | -0.085 |
Fro | -0.085 |
majesty | -0.084 |
Token | parked |
Token ID | 19584 |
Feature activation | +8.79e+00 |
Pos logit contributions | |
ymes | +0.137 |
ices | +0.131 |
es | +0.130 |
eness | +0.124 |
packs | +0.123 |
Neg logit contributions | |
disl | -0.195 |
Cr | -0.173 |
Twe | -0.170 |
This | -0.168 |
LL | -0.158 |
Token | on |
Token ID | 319 |
Feature activation | +4.28e+00 |
Pos logit contributions | |
es | +0.076 |
le | +0.063 |
les | +0.062 |
ices | +0.059 |
eness | +0.058 |
Neg logit contributions | |
disl | -0.127 |
Cr | -0.112 |
Twe | -0.112 |
Joey | -0.108 |
J | -0.104 |
Token | the |
Token ID | 262 |
Feature activation | +4.52e+00 |
Pos logit contributions | |
es | +0.053 |
again | +0.052 |
on | +0.051 |
le | +0.049 |
y | +0.048 |
Neg logit contributions | |
disl | -0.054 |
Cr | -0.036 |
majesty | -0.035 |
Fro | -0.033 |
Joey | -0.033 |
Token | street |
Token ID | 4675 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
again | +0.037 |
on | +0.037 |
es | +0.036 |
y | +0.034 |
m | +0.033 |
Neg logit contributions | |
disl | -0.075 |
Cr | -0.057 |
Fro | -0.053 |
majesty | -0.052 |
Joey | -0.052 |
Token | . |
Token ID | 13 |
Feature activation | +4.46e+00 |
Pos logit contributions | |
es | +0.089 |
ymes | +0.081 |
le | +0.078 |
les | +0.072 |
pr | +0.068 |
Neg logit contributions | |
disl | -0.164 |
J | -0.131 |
Cr | -0.129 |
Twe | -0.126 |
This | -0.122 |
Token | 's |
Token ID | 338 |
Feature activation | +6.97e+00 |
Pos logit contributions | |
es | +0.060 |
again | +0.054 |
le | +0.050 |
m | +0.050 |
on | +0.049 |
Neg logit contributions | |
disl | -0.132 |
Cr | -0.100 |
Joey | -0.098 |
Twe | -0.096 |
Fro | -0.096 |
Token | mom |
Token ID | 1995 |
Feature activation | +9.58e+00 |
Pos logit contributions | |
es | +0.096 |
le | +0.089 |
again | +0.087 |
les | +0.085 |
y | +0.083 |
Neg logit contributions | |
disl | -0.077 |
Cr | -0.052 |
Fro | -0.050 |
pleasure | -0.049 |
Joey | -0.048 |
Token | bought |
Token ID | 5839 |
Feature activation | +7.19e+00 |
Pos logit contributions | |
es | +0.073 |
ymes | +0.065 |
le | +0.061 |
again | +0.060 |
ices | +0.059 |
Neg logit contributions | |
disl | -0.157 |
Joey | -0.126 |
Cr | -0.124 |
Twe | -0.122 |
J | -0.117 |
Token | her |
Token ID | 607 |
Feature activation | +7.51e+00 |
Pos logit contributions | |
es | +0.078 |
again | +0.074 |
on | +0.073 |
m | +0.069 |
y | +0.069 |
Neg logit contributions | |
disl | -0.106 |
Cr | -0.072 |
majesty | -0.071 |
Fro | -0.068 |
Joey | -0.068 |
Token | a |
Token ID | 257 |
Feature activation | +7.60e+00 |
Pos logit contributions | |
on | +0.075 |
es | +0.074 |
again | +0.072 |
m | +0.065 |
y | +0.065 |
Neg logit contributions | |
disl | -0.113 |
Cr | -0.081 |
majesty | -0.079 |
Fro | -0.077 |
Joey | -0.075 |
Token | candle |
Token ID | 26839 |
Feature activation | +1.54e+01 |
Pos logit contributions | |
es | +0.081 |
again | +0.078 |
on | +0.076 |
m | +0.073 |
y | +0.073 |
Neg logit contributions | |
disl | -0.107 |
Cr | -0.076 |
Joey | -0.071 |
Fro | -0.070 |
Twe | -0.069 |
Token | for |
Token ID | 329 |
Feature activation | +5.77e+00 |
Pos logit contributions | |
es | +0.117 |
ymes | +0.109 |
ices | +0.106 |
le | +0.098 |
again | +0.097 |
Neg logit contributions | |
disl | -0.239 |
Joey | -0.190 |
Cr | -0.189 |
Twe | -0.184 |
Fro | -0.181 |
Token | her |
Token ID | 607 |
Feature activation | +7.36e+00 |
Pos logit contributions | |
es | +0.061 |
again | +0.057 |
on | +0.056 |
m | +0.053 |
le | +0.052 |
Neg logit contributions | |
disl | -0.084 |
Cr | -0.059 |
Joey | -0.056 |
Fro | -0.056 |
majesty | -0.055 |
Token | birthday |
Token ID | 10955 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
es | +0.100 |
les | +0.089 |
ing | +0.089 |
le | +0.089 |
m | +0.087 |
Neg logit contributions | |
disl | -0.086 |
pleasure | -0.055 |
Cr | -0.052 |
Joey | -0.052 |
Twe | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
es | +0.111 |
ymes | +0.108 |
le | +0.096 |
ices | +0.096 |
les | +0.093 |
Neg logit contributions | |
disl | -0.144 |
This | -0.118 |
Twe | -0.118 |
Joey | -0.117 |
J | -0.116 |
Token | It |
Token ID | 632 |
Feature activation | +7.60e+00 |
Pos logit contributions | |
again | +0.055 |
on | +0.054 |
es | +0.053 |
m | +0.050 |
y | +0.049 |
Neg logit contributions | |
disl | -0.065 |
majesty | -0.044 |
Cr | -0.044 |
Majesty | -0.044 |
Fre | -0.042 |
Token | named |
Token ID | 3706 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
es | +0.130 |
again | +0.121 |
on | +0.118 |
y | +0.115 |
le | +0.115 |
Neg logit contributions | |
disl | -0.166 |
Cr | -0.119 |
Joey | -0.111 |
Fro | -0.110 |
majesty | -0.109 |
Token | Tim |
Token ID | 5045 |
Feature activation | +8.04e+00 |
Pos logit contributions | |
on | +0.048 |
es | +0.047 |
y | +0.044 |
my | +0.043 |
again | +0.042 |
Neg logit contributions | |
disl | -0.064 |
Majesty | -0.043 |
majesty | -0.042 |
icol | -0.040 |
talented | -0.040 |
Token | found |
Token ID | 1043 |
Feature activation | +7.57e+00 |
Pos logit contributions | |
es | +0.076 |
again | +0.071 |
le | +0.066 |
ing | +0.066 |
ymes | +0.065 |
Neg logit contributions | |
disl | -0.121 |
Cr | -0.089 |
Joey | -0.087 |
Twe | -0.086 |
Fro | -0.085 |
Token | a |
Token ID | 257 |
Feature activation | +7.95e+00 |
Pos logit contributions | |
on | +0.066 |
es | +0.060 |
again | +0.057 |
ing | +0.050 |
m | +0.048 |
Neg logit contributions | |
disl | -0.140 |
majesty | -0.110 |
Majesty | -0.106 |
icol | -0.104 |
pleasure | -0.100 |
Token | shiny |
Token ID | 22441 |
Feature activation | +8.65e+00 |
Pos logit contributions | |
again | +0.078 |
on | +0.078 |
es | +0.077 |
y | +0.075 |
m | +0.074 |
Neg logit contributions | |
disl | -0.116 |
Cr | -0.083 |
Joey | -0.076 |
majesty | -0.074 |
J | -0.074 |
Token | trophy |
Token ID | 16383 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
es | +0.088 |
again | +0.079 |
m | +0.076 |
le | +0.076 |
on | +0.075 |
Neg logit contributions | |
disl | -0.127 |
Cr | -0.094 |
Joey | -0.089 |
Fro | -0.088 |
Twe | -0.088 |
Token | in |
Token ID | 287 |
Feature activation | +4.73e+00 |
Pos logit contributions | |
es | +0.106 |
ices | +0.095 |
le | +0.093 |
ymes | +0.091 |
m | +0.088 |
Neg logit contributions | |
disl | -0.236 |
Cr | -0.201 |
Twe | -0.193 |
Fro | -0.189 |
Joey | -0.188 |
Token | the |
Token ID | 262 |
Feature activation | +4.10e+00 |
Pos logit contributions | |
es | +0.049 |
on | +0.048 |
again | +0.047 |
y | +0.044 |
le | +0.042 |
Neg logit contributions | |
disl | -0.069 |
majesty | -0.050 |
Majesty | -0.048 |
Cr | -0.047 |
pleasure | -0.047 |
Token | forest |
Token ID | 8222 |
Feature activation | +1.07e+01 |
Pos logit contributions | |
on | +0.026 |
again | +0.025 |
y | +0.023 |
st | +0.022 |
my | +0.022 |
Neg logit contributions | |
disl | -0.076 |
Cr | -0.057 |
majesty | -0.056 |
Joey | -0.055 |
Madd | -0.055 |
Token | . |
Token ID | 13 |
Feature activation | +4.95e+00 |
Pos logit contributions | |
es | +0.055 |
again | +0.047 |
le | +0.047 |
les | +0.043 |
m | +0.042 |
Neg logit contributions | |
disl | -0.206 |
Cr | -0.164 |
Joey | -0.158 |
Fro | -0.158 |
Twe | -0.157 |
Token | He |
Token ID | 679 |
Feature activation | +6.72e+00 |
Pos logit contributions | |
es | +0.061 |
on | +0.061 |
again | +0.060 |
m | +0.057 |
y | +0.056 |
Neg logit contributions | |
disl | -0.060 |
majesty | -0.038 |
Majesty | -0.038 |
Cr | -0.037 |
icol | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | +5.49e+00 |
Pos logit contributions | |
on | +0.051 |
es | +0.049 |
again | +0.049 |
m | +0.043 |
y | +0.043 |
Neg logit contributions | |
disl | -0.100 |
Cr | -0.074 |
majesty | -0.073 |
pleasure | -0.072 |
Joey | -0.071 |
Token | play |
Token ID | 711 |
Feature activation | +9.07e+00 |
Pos logit contributions | |
on | +0.044 |
es | +0.042 |
again | +0.041 |
le | +0.038 |
and | +0.038 |
Neg logit contributions | |
disl | -0.084 |
Cr | -0.066 |
Fro | -0.062 |
Fre | -0.062 |
pleasure | -0.062 |
Token | with |
Token ID | 351 |
Feature activation | +6.09e+00 |
Pos logit contributions | |
es | +0.073 |
m | +0.071 |
y | +0.070 |
packs | +0.066 |
le | +0.064 |
Neg logit contributions | |
disl | -0.142 |
Cr | -0.112 |
Fro | -0.107 |
Twe | -0.106 |
Joey | -0.102 |
Token | his |
Token ID | 465 |
Feature activation | +6.58e+00 |
Pos logit contributions | |
es | +0.068 |
on | +0.064 |
again | +0.063 |
y | +0.059 |
le | +0.059 |
Neg logit contributions | |
disl | -0.083 |
Cr | -0.059 |
pleasure | -0.057 |
Joey | -0.056 |
majesty | -0.055 |
Token | toy |
Token ID | 13373 |
Feature activation | +1.05e+01 |
Pos logit contributions | |
es | +0.051 |
again | +0.046 |
le | +0.045 |
m | +0.042 |
y | +0.041 |
Neg logit contributions | |
disl | -0.114 |
Cr | -0.088 |
Joey | -0.084 |
Fro | -0.084 |
Twe | -0.083 |
Token | cars |
Token ID | 5006 |
Feature activation | +1.53e+01 |
Pos logit contributions | |
le | +0.109 |
m | +0.104 |
pr | +0.104 |
es | +0.103 |
Today | +0.098 |
Neg logit contributions | |
disl | -0.122 |
Cr | -0.108 |
Twe | -0.105 |
Fro | -0.103 |
Nem | -0.099 |
Token | . |
Token ID | 13 |
Feature activation | +4.60e+00 |
Pos logit contributions | |
ymes | +0.159 |
ices | +0.156 |
Will | +0.152 |
le | +0.150 |
es | +0.150 |
Neg logit contributions | |
disl | -0.154 |
Twe | -0.138 |
Cr | -0.137 |
The | -0.124 |
Fro | -0.123 |
Token | One |
Token ID | 1881 |
Feature activation | +7.79e+00 |
Pos logit contributions | |
es | +0.056 |
again | +0.053 |
on | +0.051 |
le | +0.050 |
m | +0.050 |
Neg logit contributions | |
disl | -0.059 |
Cr | -0.040 |
Joey | -0.038 |
Fro | -0.037 |
majesty | -0.037 |
Token | day |
Token ID | 1110 |
Feature activation | +6.92e+00 |
Pos logit contributions | |
es | +0.087 |
again | +0.075 |
ymes | +0.072 |
le | +0.072 |
les | +0.070 |
Neg logit contributions | |
disl | -0.110 |
Cr | -0.080 |
Joey | -0.078 |
Fro | -0.077 |
Twe | -0.076 |
Token | , |
Token ID | 11 |
Feature activation | +4.54e+00 |
Pos logit contributions | |
es | +0.062 |
le | +0.057 |
again | +0.056 |
ymes | +0.055 |
les | +0.052 |
Neg logit contributions | |
disl | -0.107 |
Cr | -0.083 |
Joey | -0.081 |
Twe | -0.079 |
Fro | -0.079 |
Token | he |
Token ID | 339 |
Feature activation | +6.79e+00 |
Pos logit contributions | |
es | +0.066 |
again | +0.062 |
on | +0.060 |
le | +0.060 |
m | +0.060 |
Neg logit contributions | |
disl | -0.048 |
Cr | -0.030 |
Joey | -0.027 |
Fro | -0.027 |
Twe | -0.026 |
Token | named |
Token ID | 3706 |
Feature activation | +4.62e+00 |
Pos logit contributions | |
es | +0.128 |
again | +0.121 |
le | +0.115 |
ymes | +0.113 |
ing | +0.113 |
Neg logit contributions | |
disl | -0.122 |
Cr | -0.084 |
Twe | -0.078 |
Joey | -0.078 |
Fro | -0.077 |
Token | Tim |
Token ID | 5045 |
Feature activation | +8.17e+00 |
Pos logit contributions | |
es | +0.061 |
on | +0.061 |
again | +0.057 |
y | +0.057 |
m | +0.056 |
Neg logit contributions | |
disl | -0.055 |
Majesty | -0.034 |
majesty | -0.032 |
icol | -0.032 |
Cr | -0.032 |
Token | found |
Token ID | 1043 |
Feature activation | +7.75e+00 |
Pos logit contributions | |
es | +0.075 |
again | +0.068 |
le | +0.064 |
ing | +0.063 |
m | +0.062 |
Neg logit contributions | |
disl | -0.127 |
Cr | -0.094 |
Joey | -0.091 |
Twe | -0.090 |
Fro | -0.089 |
Token | a |
Token ID | 257 |
Feature activation | +7.91e+00 |
Pos logit contributions | |
on | +0.071 |
again | +0.063 |
es | +0.063 |
ing | +0.057 |
m | +0.055 |
Neg logit contributions | |
disl | -0.138 |
majesty | -0.104 |
Majesty | -0.101 |
icol | -0.099 |
pleasure | -0.097 |
Token | toy |
Token ID | 13373 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
es | +0.080 |
again | +0.080 |
on | +0.079 |
y | +0.076 |
m | +0.075 |
Neg logit contributions | |
disl | -0.113 |
Cr | -0.081 |
Joey | -0.075 |
Fro | -0.074 |
majesty | -0.072 |
Token | motorcycle |
Token ID | 18757 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
es | +0.106 |
le | +0.101 |
ymes | +0.095 |
ices | +0.094 |
les | +0.092 |
Neg logit contributions | |
disl | -0.162 |
Cr | -0.143 |
Twe | -0.137 |
Fro | -0.133 |
Joey | -0.132 |
Token | . |
Token ID | 13 |
Feature activation | +5.19e+00 |
Pos logit contributions | |
ymes | +0.125 |
ices | +0.119 |
le | +0.118 |
eness | +0.114 |
es | +0.114 |
Neg logit contributions | |
disl | -0.207 |
Twe | -0.187 |
This | -0.185 |
Cr | -0.185 |
Joey | -0.168 |
Token | It |
Token ID | 632 |
Feature activation | +7.42e+00 |
Pos logit contributions | |
es | +0.073 |
again | +0.072 |
on | +0.072 |
y | +0.067 |
m | +0.067 |
Neg logit contributions | |
disl | -0.055 |
majesty | -0.032 |
Cr | -0.031 |
Majesty | -0.031 |
Fro | -0.029 |
Token | was |
Token ID | 373 |
Feature activation | +6.04e+00 |
Pos logit contributions | |
es | +0.050 |
on | +0.047 |
again | +0.046 |
y | +0.042 |
m | +0.041 |
Neg logit contributions | |
disl | -0.138 |
Cr | -0.106 |
majesty | -0.103 |
Joey | -0.101 |
pleasure | -0.101 |
Token | red |
Token ID | 2266 |
Feature activation | +9.60e+00 |
Pos logit contributions | |
es | +0.063 |
on | +0.061 |
again | +0.060 |
m | +0.056 |
y | +0.056 |
Neg logit contributions | |
disl | -0.088 |
Cr | -0.062 |
Joey | -0.059 |
majesty | -0.058 |
Fro | -0.058 |
Token | and |
Token ID | 290 |
Feature activation | +4.00e+00 |
Pos logit contributions | |
es | +0.089 |
ymes | +0.087 |
pr | +0.086 |
le | +0.076 |
packs | +0.076 |
Neg logit contributions | |
disl | -0.112 |
Twe | -0.108 |
This | -0.108 |
Cr | -0.101 |
Joey | -0.100 |
Token | excited |
Token ID | 6568 |
Feature activation | +7.21e+00 |
Pos logit contributions | |
on | +0.026 |
m | +0.026 |
y | +0.022 |
ing | +0.020 |
next | +0.020 |
Neg logit contributions | |
disl | -0.048 |
icol | -0.041 |
tal | -0.040 |
Cr | -0.039 |
Joey | -0.035 |
Token | to |
Token ID | 284 |
Feature activation | +5.63e+00 |
Pos logit contributions | |
es | +0.066 |
again | +0.057 |
le | +0.055 |
m | +0.054 |
on | +0.054 |
Neg logit contributions | |
disl | -0.114 |
Cr | -0.086 |
Joey | -0.084 |
Twe | -0.081 |
Fro | -0.081 |
Token | get |
Token ID | 651 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
on | +0.040 |
and | +0.035 |
again | +0.034 |
es | +0.033 |
. | +0.031 |
Neg logit contributions | |
disl | -0.095 |
Cr | -0.076 |
Fro | -0.075 |
icol | -0.074 |
majesty | -0.071 |
Token | a |
Token ID | 257 |
Feature activation | +7.36e+00 |
Pos logit contributions | |
on | +0.062 |
again | +0.058 |
es | +0.057 |
m | +0.054 |
ing | +0.052 |
Neg logit contributions | |
disl | -0.108 |
majesty | -0.077 |
Cr | -0.076 |
icol | -0.075 |
Majesty | -0.074 |
Token | sc |
Token ID | 629 |
Feature activation | +7.03e+00 |
Pos logit contributions | |
es | +0.087 |
ices | +0.073 |
again | +0.072 |
le | +0.072 |
y | +0.070 |
Neg logit contributions | |
disl | -0.098 |
Cr | -0.070 |
Joey | -0.068 |
pleasure | -0.068 |
Fro | -0.068 |
Token | ooter |
Token ID | 25141 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
es | +0.060 |
m | +0.057 |
on | +0.057 |
again | +0.056 |
ing | +0.055 |
Neg logit contributions | |
disl | -0.115 |
Cr | -0.085 |
Joey | -0.081 |
Twe | -0.080 |
Madd | -0.078 |
Token | . |
Token ID | 13 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
es | +0.114 |
ymes | +0.101 |
ices | +0.096 |
le | +0.091 |
m | +0.085 |
Neg logit contributions | |
disl | -0.251 |
Twe | -0.203 |
Cr | -0.199 |
Joey | -0.192 |
J | -0.190 |
Token | She |
Token ID | 1375 |
Feature activation | +6.21e+00 |
Pos logit contributions | |
es | +0.049 |
again | +0.047 |
on | +0.046 |
m | +0.044 |
y | +0.043 |
Neg logit contributions | |
disl | -0.065 |
Cr | -0.045 |
majesty | -0.043 |
Fro | -0.042 |
Majesty | -0.041 |
Token | wanted |
Token ID | 2227 |
Feature activation | +6.66e+00 |
Pos logit contributions | |
es | +0.052 |
on | +0.048 |
again | +0.047 |
y | +0.045 |
le | +0.045 |
Neg logit contributions | |
disl | -0.105 |
Cr | -0.081 |
Fro | -0.076 |
Joey | -0.075 |
pleasure | -0.073 |
Token | to |
Token ID | 284 |
Feature activation | +5.17e+00 |
Pos logit contributions | |
es | +0.076 |
le | +0.068 |
again | +0.067 |
y | +0.066 |
m | +0.065 |
Neg logit contributions | |
disl | -0.090 |
Cr | -0.065 |
Joey | -0.062 |
Twe | -0.061 |
Fro | -0.060 |
Token | use |
Token ID | 779 |
Feature activation | +7.86e+00 |
Pos logit contributions | |
on | +0.043 |
again | +0.039 |
es | +0.036 |
and | +0.035 |
le | +0.035 |
Neg logit contributions | |
disl | -0.087 |
Cr | -0.067 |
Fro | -0.065 |
icol | -0.064 |
majesty | -0.064 |
Token | her |
Token ID | 607 |
Feature activation | +6.14e+00 |
Pos logit contributions | |
es | +0.041 |
again | +0.040 |
on | +0.039 |
m | +0.037 |
y | +0.037 |
Neg logit contributions | |
disl | -0.048 |
Cr | -0.033 |
Joey | -0.031 |
majesty | -0.031 |
Fro | -0.030 |
Token | parents |
Token ID | 3397 |
Feature activation | +9.79e+00 |
Pos logit contributions | |
es | +0.079 |
again | +0.072 |
le | +0.071 |
ices | +0.071 |
m | +0.070 |
Neg logit contributions | |
disl | -0.072 |
majesty | -0.047 |
pleasure | -0.046 |
Cr | -0.045 |
Fro | -0.044 |
Token | gave |
Token ID | 2921 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
es | +0.113 |
ymes | +0.106 |
ices | +0.100 |
again | +0.098 |
le | +0.096 |
Neg logit contributions | |
disl | -0.118 |
Joey | -0.093 |
Cr | -0.088 |
Twe | -0.087 |
J | -0.086 |
Token | her |
Token ID | 607 |
Feature activation | +7.62e+00 |
Pos logit contributions | |
es | +0.068 |
again | +0.062 |
le | +0.060 |
on | +0.060 |
m | +0.060 |
Neg logit contributions | |
disl | -0.070 |
Cr | -0.048 |
Joey | -0.045 |
Fro | -0.045 |
Twe | -0.044 |
Token | a |
Token ID | 257 |
Feature activation | +7.81e+00 |
Pos logit contributions | |
es | +0.090 |
again | +0.085 |
on | +0.082 |
le | +0.081 |
m | +0.080 |
Neg logit contributions | |
disl | -0.100 |
Cr | -0.069 |
Joey | -0.065 |
Fro | -0.064 |
Twe | -0.063 |
Token | microphone |
Token ID | 21822 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
es | +0.084 |
again | +0.080 |
on | +0.078 |
m | +0.075 |
le | +0.075 |
Neg logit contributions | |
disl | -0.109 |
Cr | -0.079 |
Joey | -0.074 |
Fro | -0.073 |
Twe | -0.071 |
Token | as |
Token ID | 355 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
es | +0.174 |
ymes | +0.167 |
ices | +0.163 |
m | +0.161 |
le | +0.160 |
Neg logit contributions | |
disl | -0.185 |
Cr | -0.133 |
Joey | -0.129 |
This | -0.124 |
Twe | -0.124 |
Token | a |
Token ID | 257 |
Feature activation | +7.43e+00 |
Pos logit contributions | |
es | +0.062 |
again | +0.058 |
on | +0.057 |
le | +0.055 |
y | +0.055 |
Neg logit contributions | |
disl | -0.070 |
Cr | -0.049 |
Joey | -0.045 |
Fro | -0.045 |
majesty | -0.044 |
Token | gift |
Token ID | 6979 |
Feature activation | +1.14e+01 |
Pos logit contributions | |
es | +0.087 |
le | +0.076 |
ices | +0.074 |
m | +0.073 |
again | +0.073 |
Neg logit contributions | |
disl | -0.101 |
Cr | -0.071 |
pleasure | -0.070 |
majesty | -0.068 |
Fro | -0.068 |
Token | , |
Token ID | 11 |
Feature activation | +5.53e+00 |
Pos logit contributions | |
ices | +0.085 |
ymes | +0.085 |
es | +0.084 |
ud | +0.078 |
m | +0.077 |
Neg logit contributions | |
disl | -0.161 |
Twe | -0.131 |
J | -0.128 |
Cr | -0.128 |
This | -0.126 |
Token | and |
Token ID | 290 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
es | +0.036 |
again | +0.030 |
le | +0.029 |
m | +0.028 |
y | +0.028 |
Neg logit contributions | |
disl | -0.102 |
Cr | -0.081 |
Joey | -0.078 |
Twe | -0.077 |
Fro | -0.077 |
Token | he |
Token ID | 339 |
Feature activation | +5.67e+00 |
Pos logit contributions | |
es | +0.073 |
again | +0.071 |
on | +0.069 |
m | +0.066 |
y | +0.065 |
Neg logit contributions | |
disl | -0.117 |
Cr | -0.081 |
majesty | -0.080 |
Majesty | -0.077 |
icol | -0.077 |
Token | found |
Token ID | 1043 |
Feature activation | +6.77e+00 |
Pos logit contributions | |
es | +0.058 |
again | +0.055 |
on | +0.052 |
m | +0.050 |
y | +0.050 |
Neg logit contributions | |
disl | -0.089 |
Cr | -0.063 |
Twe | -0.058 |
Joey | -0.058 |
majesty | -0.058 |
Token | lots |
Token ID | 6041 |
Feature activation | +7.99e+00 |
Pos logit contributions | |
es | +0.069 |
on | +0.063 |
again | +0.062 |
ing | +0.056 |
le | +0.054 |
Neg logit contributions | |
disl | -0.115 |
Cr | -0.076 |
LL | -0.075 |
icol | -0.075 |
majesty | -0.074 |
Token | of |
Token ID | 286 |
Feature activation | +5.96e+00 |
Pos logit contributions | |
es | +0.059 |
ymes | +0.050 |
ices | +0.050 |
m | +0.049 |
again | +0.048 |
Neg logit contributions | |
disl | -0.130 |
Joey | -0.104 |
Cr | -0.102 |
Fro | -0.098 |
Madd | -0.097 |
Token | colourful |
Token ID | 44799 |
Feature activation | +8.52e+00 |
Pos logit contributions | |
es | +0.068 |
again | +0.064 |
y | +0.060 |
m | +0.060 |
on | +0.060 |
Neg logit contributions | |
disl | -0.079 |
Cr | -0.056 |
Joey | -0.054 |
Fro | -0.052 |
Twe | -0.051 |
Token | gems |
Token ID | 23685 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
es | +0.082 |
again | +0.079 |
m | +0.079 |
le | +0.075 |
y | +0.075 |
Neg logit contributions | |
disl | -0.119 |
Cr | -0.087 |
Joey | -0.087 |
majesty | -0.083 |
Twe | -0.082 |
Token | ! |
Token ID | 0 |
Feature activation | +3.11e+00 |
Pos logit contributions | |
ymes | +0.110 |
es | +0.104 |
ices | +0.102 |
le | +0.102 |
Will | +0.098 |
Neg logit contributions | |
disl | -0.225 |
Joey | -0.193 |
Cr | -0.187 |
Twe | -0.177 |
Fro | -0.176 |
Token | He |
Token ID | 679 |
Feature activation | +6.34e+00 |
Pos logit contributions | |
es | +0.032 |
again | +0.030 |
on | +0.030 |
boards | +0.029 |
and | +0.027 |
Neg logit contributions | |
disl | -0.048 |
majesty | -0.032 |
Majesty | -0.031 |
talented | -0.030 |
LL | -0.028 |
Token | was |
Token ID | 373 |
Feature activation | +5.13e+00 |
Pos logit contributions | |
es | +0.052 |
again | +0.048 |
on | +0.045 |
y | +0.043 |
le | +0.043 |
Neg logit contributions | |
disl | -0.109 |
Cr | -0.082 |
Joey | -0.077 |
Fro | -0.077 |
Twe | -0.076 |
Token | very |
Token ID | 845 |
Feature activation | +2.44e+00 |
Pos logit contributions | |
on | +0.043 |
es | +0.038 |
and | +0.037 |
again | +0.036 |
m | +0.030 |
Neg logit contributions | |
disl | -0.097 |
icol | -0.068 |
majesty | -0.066 |
Cr | -0.065 |
APP | -0.065 |
Token | excited |
Token ID | 6568 |
Feature activation | +6.56e+00 |
Pos logit contributions | |
on | +0.019 |
and | +0.017 |
es | +0.017 |
again | +0.015 |
m | +0.015 |
Neg logit contributions | |
disl | -0.041 |
icol | -0.032 |
liv | -0.031 |
Cr | -0.030 |
€ | -0.030 |
Token | street |
Token ID | 4675 |
Feature activation | +1.01e+01 |
Pos logit contributions | |
on | +0.036 |
again | +0.036 |
y | +0.034 |
es | +0.034 |
ing | +0.032 |
Neg logit contributions | |
disl | -0.083 |
Cr | -0.063 |
Fro | -0.060 |
majesty | -0.060 |
pleasure | -0.059 |
Token | . |
Token ID | 13 |
Feature activation | +3.38e+00 |
Pos logit contributions | |
es | +0.076 |
ymes | +0.070 |
le | +0.068 |
les | +0.060 |
pr | +0.059 |
Neg logit contributions | |
disl | -0.162 |
J | -0.130 |
Joey | -0.129 |
Cr | -0.129 |
Twe | -0.126 |
Token | They |
Token ID | 1119 |
Feature activation | +6.88e+00 |
Pos logit contributions | |
es | +0.043 |
again | +0.043 |
on | +0.041 |
y | +0.040 |
m | +0.040 |
Neg logit contributions | |
disl | -0.040 |
Cr | -0.026 |
Fro | -0.026 |
majesty | -0.024 |
Madd | -0.023 |
Token | saw |
Token ID | 2497 |
Feature activation | +6.63e+00 |
Pos logit contributions | |
es | +0.068 |
again | +0.062 |
le | +0.060 |
ymes | +0.058 |
ing | +0.057 |
Neg logit contributions | |
disl | -0.101 |
Cr | -0.075 |
Joey | -0.074 |
Twe | -0.071 |
Fro | -0.070 |
Token | a |
Token ID | 257 |
Feature activation | +8.23e+00 |
Pos logit contributions | |
es | +0.077 |
again | +0.073 |
on | +0.070 |
le | +0.069 |
m | +0.069 |
Neg logit contributions | |
disl | -0.088 |
Cr | -0.062 |
Joey | -0.058 |
Fro | -0.057 |
Twe | -0.056 |
Token | motorcycle |
Token ID | 18757 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
es | +0.101 |
again | +0.093 |
le | +0.090 |
on | +0.088 |
m | +0.088 |
Neg logit contributions | |
disl | -0.104 |
Cr | -0.072 |
Joey | -0.068 |
Fro | -0.066 |
Twe | -0.066 |
Token | parked |
Token ID | 19584 |
Feature activation | +8.24e+00 |
Pos logit contributions | |
ymes | +0.156 |
ices | +0.149 |
es | +0.147 |
le | +0.142 |
ities | +0.137 |
Neg logit contributions | |
disl | -0.175 |
Twe | -0.150 |
This | -0.146 |
Cr | -0.146 |
J | -0.139 |
Token | on |
Token ID | 319 |
Feature activation | +4.25e+00 |
Pos logit contributions | |
es | +0.072 |
le | +0.061 |
les | +0.056 |
ices | +0.055 |
ymes | +0.054 |
Neg logit contributions | |
disl | -0.120 |
Twe | -0.105 |
Cr | -0.103 |
Joey | -0.102 |
J | -0.098 |
Token | the |
Token ID | 262 |
Feature activation | +4.80e+00 |
Pos logit contributions | |
es | +0.058 |
again | +0.055 |
on | +0.054 |
le | +0.053 |
y | +0.052 |
Neg logit contributions | |
disl | -0.048 |
Cr | -0.031 |
Joey | -0.028 |
Fro | -0.028 |
majesty | -0.027 |
Token | side |
Token ID | 1735 |
Feature activation | +9.13e+00 |
Pos logit contributions | |
es | +0.045 |
again | +0.043 |
on | +0.042 |
m | +0.040 |
le | +0.040 |
Neg logit contributions | |
disl | -0.074 |
Cr | -0.055 |
Fro | -0.051 |
Joey | -0.051 |
majesty | -0.050 |
Token | of |
Token ID | 286 |
Feature activation | +2.60e+00 |
Pos logit contributions | |
es | +0.073 |
ymes | +0.068 |
le | +0.061 |
pr | +0.058 |
les | +0.055 |
Neg logit contributions | |
disl | -0.137 |
J | -0.118 |
Joe | -0.117 |
Joey | -0.117 |
Cr | -0.111 |
Token | got |
Token ID | 1392 |
Feature activation | +6.11e+00 |
Pos logit contributions | |
es | +0.054 |
again | +0.050 |
le | +0.047 |
m | +0.047 |
on | +0.046 |
Neg logit contributions | |
disl | -0.092 |
Cr | -0.069 |
Joey | -0.067 |
Twe | -0.065 |
Fro | -0.065 |
Token | a |
Token ID | 257 |
Feature activation | +8.64e+00 |
Pos logit contributions | |
on | +0.059 |
again | +0.055 |
es | +0.054 |
m | +0.049 |
ing | +0.047 |
Neg logit contributions | |
disl | -0.100 |
majesty | -0.072 |
Cr | -0.070 |
icol | -0.069 |
Majesty | -0.068 |
Token | big |
Token ID | 1263 |
Feature activation | +7.96e+00 |
Pos logit contributions | |
es | +0.094 |
again | +0.086 |
le | +0.083 |
on | +0.083 |
m | +0.082 |
Neg logit contributions | |
disl | -0.122 |
Cr | -0.087 |
Joey | -0.083 |
Fro | -0.082 |
Twe | -0.080 |
Token | box |
Token ID | 3091 |
Feature activation | +1.42e+01 |
Pos logit contributions | |
es | +0.072 |
again | +0.064 |
le | +0.061 |
m | +0.061 |
on | +0.060 |
Neg logit contributions | |
disl | -0.127 |
Cr | -0.096 |
Joey | -0.092 |
Fro | -0.090 |
Twe | -0.089 |
Token | of |
Token ID | 286 |
Feature activation | +5.54e+00 |
Pos logit contributions | |
es | +0.114 |
ymes | +0.107 |
le | +0.096 |
again | +0.092 |
les | +0.092 |
Neg logit contributions | |
disl | -0.215 |
Joey | -0.175 |
Cr | -0.168 |
Twe | -0.166 |
Sus | -0.162 |
Token | blocks |
Token ID | 7021 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
es | +0.048 |
again | +0.044 |
on | +0.042 |
le | +0.041 |
m | +0.040 |
Neg logit contributions | |
disl | -0.090 |
Cr | -0.068 |
Joey | -0.065 |
Fro | -0.064 |
Twe | -0.063 |
Token | . |
Token ID | 13 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
es | +0.095 |
ymes | +0.087 |
le | +0.079 |
ices | +0.075 |
Will | +0.072 |
Neg logit contributions | |
disl | -0.262 |
Joey | -0.211 |
Cr | -0.210 |
Twe | -0.205 |
J | -0.198 |
Token | Mom |
Token ID | 11254 |
Feature activation | +8.45e+00 |
Pos logit contributions | |
again | +0.052 |
es | +0.051 |
on | +0.050 |
m | +0.049 |
y | +0.047 |
Neg logit contributions | |
disl | -0.047 |
Cr | -0.030 |
majesty | -0.029 |
Fro | -0.028 |
Majesty | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
es | +0.049 |
ymes | +0.047 |
again | +0.045 |
le | +0.043 |
ices | +0.041 |
Neg logit contributions | |
disl | -0.146 |
Joey | -0.121 |
Cr | -0.113 |
Joe | -0.111 |
Twe | -0.111 |
Token | Dad |
Token ID | 17415 |
Feature activation | +9.68e+00 |
Pos logit contributions | |
on | +0.044 |
and | +0.041 |
again | +0.041 |
m | +0.041 |
y | +0.039 |
Neg logit contributions | |
disl | -0.044 |
majesty | -0.030 |
Fro | -0.029 |
Majesty | -0.029 |
Cr | -0.028 |
Token | decided |
Token ID | 3066 |
Feature activation | +5.99e+00 |
Pos logit contributions | |
es | +0.109 |
again | +0.105 |
ymes | +0.105 |
le | +0.100 |
ices | +0.098 |
Neg logit contributions | |
disl | -0.116 |
Joey | -0.087 |
Cr | -0.079 |
Jon | -0.076 |
Sus | -0.075 |
Token | They |
Token ID | 1119 |
Feature activation | +5.68e+00 |
Pos logit contributions | |
es | +0.039 |
again | +0.036 |
on | +0.035 |
le | +0.035 |
m | +0.035 |
Neg logit contributions | |
disl | -0.038 |
Cr | -0.026 |
Joey | -0.024 |
Fro | -0.024 |
Twe | -0.023 |
Token | like |
Token ID | 588 |
Feature activation | +5.28e+00 |
Pos logit contributions | |
on | +0.045 |
es | +0.043 |
y | +0.042 |
again | +0.042 |
le | +0.042 |
Neg logit contributions | |
disl | -0.092 |
Cr | -0.071 |
icol | -0.070 |
Fro | -0.069 |
Joey | -0.068 |
Token | to |
Token ID | 284 |
Feature activation | +4.55e+00 |
Pos logit contributions | |
es | +0.052 |
again | +0.048 |
on | +0.047 |
le | +0.045 |
m | +0.045 |
Neg logit contributions | |
disl | -0.079 |
Cr | -0.058 |
Joey | -0.055 |
Fro | -0.055 |
Twe | -0.054 |
Token | play |
Token ID | 711 |
Feature activation | +7.83e+00 |
Pos logit contributions | |
es | +0.056 |
again | +0.052 |
m | +0.050 |
ing | +0.050 |
le | +0.050 |
Neg logit contributions | |
disl | -0.058 |
Cr | -0.040 |
Joey | -0.037 |
Fro | -0.037 |
Twe | -0.036 |
Token | with |
Token ID | 351 |
Feature activation | +5.72e+00 |
Pos logit contributions | |
m | +0.064 |
es | +0.059 |
iness | +0.059 |
bars | +0.058 |
ier | +0.058 |
Neg logit contributions | |
disl | -0.117 |
Cr | -0.096 |
Fro | -0.093 |
Twe | -0.087 |
Nem | -0.086 |
Token | magnets |
Token ID | 37446 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
es | +0.052 |
again | +0.049 |
m | +0.046 |
le | +0.046 |
ing | +0.044 |
Neg logit contributions | |
disl | -0.091 |
Cr | -0.068 |
Joey | -0.065 |
Fro | -0.064 |
Twe | -0.064 |
Token | . |
Token ID | 13 |
Feature activation | +3.70e+00 |
Pos logit contributions | |
Will | +0.131 |
ices | +0.131 |
le | +0.124 |
pr | +0.123 |
Today | +0.120 |
Neg logit contributions | |
disl | -0.174 |
Cr | -0.153 |
Fro | -0.144 |
Av | -0.139 |
Twe | -0.135 |
Token | Magn |
Token ID | 14872 |
Feature activation | +8.83e+00 |
Pos logit contributions | |
es | +0.047 |
again | +0.044 |
on | +0.043 |
le | +0.042 |
m | +0.042 |
Neg logit contributions | |
disl | -0.046 |
Cr | -0.031 |
Joey | -0.029 |
Fro | -0.028 |
Twe | -0.028 |
Token | ets |
Token ID | 1039 |
Feature activation | +7.41e+00 |
Pos logit contributions | |
es | +0.053 |
again | +0.047 |
on | +0.044 |
le | +0.043 |
y | +0.042 |
Neg logit contributions | |
disl | -0.166 |
Cr | -0.132 |
Joey | -0.126 |
Fro | -0.125 |
Twe | -0.124 |
Token | are |
Token ID | 389 |
Feature activation | +4.72e+00 |
Pos logit contributions | |
es | +0.078 |
again | +0.074 |
le | +0.073 |
m | +0.072 |
y | +0.071 |
Neg logit contributions | |
disl | -0.104 |
Cr | -0.072 |
Joey | -0.068 |
Twe | -0.066 |
majesty | -0.065 |
Token | things |
Token ID | 1243 |
Feature activation | +1.15e+01 |
Pos logit contributions | |
es | +0.050 |
again | +0.047 |
le | +0.046 |
m | +0.045 |
y | +0.045 |
Neg logit contributions | |
disl | -0.067 |
Cr | -0.048 |
Fro | -0.045 |
Joey | -0.045 |
majesty | -0.044 |
Token | to |
Token ID | 284 |
Feature activation | +5.42e+00 |
Pos logit contributions | |
es | +0.049 |
on | +0.049 |
again | +0.047 |
m | +0.043 |
y | +0.042 |
Neg logit contributions | |
disl | -0.094 |
Cr | -0.069 |
majesty | -0.067 |
Joey | -0.067 |
pleasure | -0.066 |
Token | play |
Token ID | 711 |
Feature activation | +8.77e+00 |
Pos logit contributions | |
es | +0.049 |
on | +0.048 |
again | +0.047 |
le | +0.043 |
y | +0.042 |
Neg logit contributions | |
disl | -0.080 |
Cr | -0.060 |
Joey | -0.057 |
Fro | -0.056 |
pleasure | -0.056 |
Token | with |
Token ID | 351 |
Feature activation | +5.81e+00 |
Pos logit contributions | |
es | +0.072 |
m | +0.071 |
y | +0.069 |
packs | +0.066 |
le | +0.064 |
Neg logit contributions | |
disl | -0.134 |
Cr | -0.106 |
Fro | -0.101 |
Twe | -0.099 |
This | -0.095 |
Token | his |
Token ID | 465 |
Feature activation | +6.39e+00 |
Pos logit contributions | |
es | +0.070 |
again | +0.065 |
on | +0.065 |
le | +0.062 |
y | +0.062 |
Neg logit contributions | |
disl | -0.075 |
Cr | -0.052 |
Joey | -0.049 |
Fro | -0.048 |
pleasure | -0.048 |
Token | toy |
Token ID | 13373 |
Feature activation | +1.04e+01 |
Pos logit contributions | |
es | +0.053 |
le | +0.049 |
again | +0.049 |
m | +0.044 |
y | +0.044 |
Neg logit contributions | |
disl | -0.107 |
Cr | -0.081 |
Fro | -0.079 |
Joey | -0.078 |
Twe | -0.076 |
Token | cars |
Token ID | 5006 |
Feature activation | +1.52e+01 |
Pos logit contributions | |
le | +0.111 |
pr | +0.105 |
m | +0.103 |
es | +0.102 |
Today | +0.097 |
Neg logit contributions | |
disl | -0.116 |
Cr | -0.105 |
Fro | -0.101 |
Twe | -0.100 |
Nem | -0.095 |
Token | and |
Token ID | 290 |
Feature activation | +3.78e+00 |
Pos logit contributions | |
ymes | +0.160 |
ices | +0.156 |
le | +0.154 |
eness | +0.150 |
Will | +0.150 |
Neg logit contributions | |
disl | -0.150 |
Cr | -0.133 |
Twe | -0.131 |
The | -0.124 |
Fro | -0.121 |
Token | trucks |
Token ID | 13960 |
Feature activation | +1.31e+01 |
Pos logit contributions | |
es | +0.025 |
on | +0.024 |
again | +0.023 |
y | +0.021 |
m | +0.020 |
Neg logit contributions | |
disl | -0.069 |
Cr | -0.054 |
Joey | -0.052 |
pleasure | -0.051 |
Fro | -0.051 |
Token | . |
Token ID | 13 |
Feature activation | +4.57e+00 |
Pos logit contributions | |
ymes | +0.119 |
le | +0.115 |
es | +0.115 |
ices | +0.110 |
pr | +0.108 |
Neg logit contributions | |
disl | -0.163 |
Cr | -0.134 |
Twe | -0.129 |
This | -0.125 |
Fro | -0.120 |
Token | One |
Token ID | 1881 |
Feature activation | +7.73e+00 |
Pos logit contributions | |
es | +0.057 |
again | +0.054 |
on | +0.052 |
le | +0.051 |
m | +0.051 |
Neg logit contributions | |
disl | -0.057 |
Cr | -0.039 |
Joey | -0.036 |
Fro | -0.036 |
Twe | -0.035 |
Token | day |
Token ID | 1110 |
Feature activation | +6.97e+00 |
Pos logit contributions | |
es | +0.085 |
again | +0.074 |
le | +0.070 |
ymes | +0.070 |
les | +0.069 |
Neg logit contributions | |
disl | -0.110 |
Cr | -0.079 |
Joey | -0.077 |
Fro | -0.076 |
Twe | -0.074 |
Token | sky |
Token ID | 6766 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
es | +0.057 |
le | +0.048 |
ices | +0.046 |
again | +0.046 |
y | +0.044 |
Neg logit contributions | |
disl | -0.082 |
Cr | -0.058 |
Twe | -0.057 |
Joey | -0.057 |
majesty | -0.056 |
Token | and |
Token ID | 290 |
Feature activation | +3.85e+00 |
Pos logit contributions | |
es | +0.106 |
ymes | +0.101 |
ests | +0.093 |
ices | +0.092 |
ins | +0.086 |
Neg logit contributions | |
disl | -0.182 |
J | -0.146 |
Twe | -0.144 |
Sus | -0.141 |
Joey | -0.139 |
Token | saw |
Token ID | 2497 |
Feature activation | +5.92e+00 |
Pos logit contributions | |
again | +0.035 |
on | +0.033 |
es | +0.033 |
le | +0.029 |
m | +0.029 |
Neg logit contributions | |
disl | -0.062 |
Cr | -0.047 |
Fro | -0.045 |
majesty | -0.045 |
Joey | -0.044 |
Token | a |
Token ID | 257 |
Feature activation | +7.76e+00 |
Pos logit contributions | |
es | +0.063 |
again | +0.062 |
on | +0.061 |
ing | +0.056 |
m | +0.055 |
Neg logit contributions | |
disl | -0.085 |
Cr | -0.060 |
majesty | -0.058 |
Fro | -0.057 |
Joey | -0.056 |
Token | shining |
Token ID | 22751 |
Feature activation | +9.42e+00 |
Pos logit contributions | |
es | +0.084 |
again | +0.080 |
on | +0.077 |
m | +0.075 |
y | +0.075 |
Neg logit contributions | |
disl | -0.108 |
Cr | -0.077 |
Joey | -0.072 |
Fro | -0.071 |
Twe | -0.070 |
Token | gem |
Token ID | 16840 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
es | +0.100 |
again | +0.086 |
m | +0.084 |
le | +0.083 |
on | +0.082 |
Neg logit contributions | |
disl | -0.135 |
Cr | -0.101 |
Joey | -0.096 |
Twe | -0.096 |
Fro | -0.094 |
Token | in |
Token ID | 287 |
Feature activation | +3.47e+00 |
Pos logit contributions | |
ices | +0.123 |
es | +0.115 |
packs | +0.112 |
ud | +0.111 |
eness | +0.110 |
Neg logit contributions | |
disl | -0.174 |
Twe | -0.166 |
Cr | -0.154 |
Fro | -0.148 |
Gret | -0.146 |
Token | the |
Token ID | 262 |
Feature activation | +3.84e+00 |
Pos logit contributions | |
es | +0.048 |
again | +0.046 |
on | +0.044 |
le | +0.044 |
m | +0.044 |
Neg logit contributions | |
disl | -0.038 |
Cr | -0.025 |
Joey | -0.023 |
Fro | -0.022 |
Twe | -0.022 |
Token | clouds |
Token ID | 15114 |
Feature activation | +1.19e+01 |
Pos logit contributions | |
es | +0.036 |
again | +0.030 |
le | +0.029 |
ices | +0.028 |
m | +0.028 |
Neg logit contributions | |
disl | -0.061 |
Cr | -0.046 |
Twe | -0.044 |
Joey | -0.044 |
pleasure | -0.043 |
Token | . |
Token ID | 13 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
es | +0.100 |
ymes | +0.092 |
ices | +0.084 |
ests | +0.078 |
ities | +0.077 |
Neg logit contributions | |
disl | -0.177 |
Joey | -0.141 |
J | -0.139 |
Twe | -0.138 |
Cr | -0.137 |
Token | She |
Token ID | 1375 |
Feature activation | +6.50e+00 |
Pos logit contributions | |
again | +0.039 |
on | +0.036 |
es | +0.035 |
and | +0.034 |
m | +0.032 |
Neg logit contributions | |
disl | -0.078 |
majesty | -0.058 |
Majesty | -0.056 |
Cr | -0.055 |
chie | -0.055 |
Token | They |
Token ID | 1119 |
Feature activation | +6.66e+00 |
Pos logit contributions | |
es | +0.058 |
again | +0.053 |
le | +0.052 |
ing | +0.051 |
y | +0.051 |
Neg logit contributions | |
disl | -0.058 |
Cr | -0.040 |
Joey | -0.038 |
Twe | -0.037 |
Fro | -0.037 |
Token | played |
Token ID | 2826 |
Feature activation | +8.18e+00 |
Pos logit contributions | |
es | +0.074 |
again | +0.069 |
ing | +0.068 |
le | +0.067 |
ices | +0.066 |
Neg logit contributions | |
disl | -0.087 |
Cr | -0.066 |
Fro | -0.062 |
Twe | -0.062 |
Joey | -0.062 |
Token | with |
Token ID | 351 |
Feature activation | +5.94e+00 |
Pos logit contributions | |
y | +0.057 |
m | +0.056 |
le | +0.055 |
es | +0.053 |
ing | +0.052 |
Neg logit contributions | |
disl | -0.133 |
Cr | -0.107 |
Fro | -0.105 |
Twe | -0.099 |
Joey | -0.097 |
Token | their |
Token ID | 511 |
Feature activation | +6.59e+00 |
Pos logit contributions | |
es | +0.069 |
again | +0.064 |
on | +0.062 |
le | +0.061 |
m | +0.061 |
Neg logit contributions | |
disl | -0.080 |
Cr | -0.056 |
Joey | -0.053 |
Fro | -0.052 |
majesty | -0.051 |
Token | toy |
Token ID | 13373 |
Feature activation | +1.08e+01 |
Pos logit contributions | |
es | +0.065 |
le | +0.061 |
again | +0.057 |
ices | +0.057 |
ier | +0.056 |
Neg logit contributions | |
disl | -0.099 |
Fro | -0.074 |
Cr | -0.074 |
Twe | -0.072 |
pleasure | -0.071 |
Token | cars |
Token ID | 5006 |
Feature activation | +1.51e+01 |
Pos logit contributions | |
le | +0.133 |
pr | +0.128 |
inning | +0.120 |
ge | +0.119 |
Today | +0.119 |
Neg logit contributions | |
Fro | -0.096 |
Cr | -0.090 |
Twe | -0.090 |
disl | -0.086 |
Bub | -0.086 |
Token | and |
Token ID | 290 |
Feature activation | +4.02e+00 |
Pos logit contributions | |
Will | +0.172 |
ices | +0.162 |
eness | +0.161 |
le | +0.156 |
ymes | +0.155 |
Neg logit contributions | |
disl | -0.124 |
The | -0.122 |
Twe | -0.118 |
Fro | -0.117 |
our | -0.116 |
Token | dolls |
Token ID | 36062 |
Feature activation | +1.23e+01 |
Pos logit contributions | |
es | +0.034 |
again | +0.031 |
le | +0.030 |
ing | +0.030 |
m | +0.030 |
Neg logit contributions | |
disl | -0.065 |
Cr | -0.050 |
Fro | -0.047 |
Joey | -0.047 |
Twe | -0.047 |
Token | . |
Token ID | 13 |
Feature activation | +4.83e+00 |
Pos logit contributions | |
ices | +0.121 |
eness | +0.118 |
ymes | +0.117 |
Today | +0.115 |
le | +0.113 |
Neg logit contributions | |
disl | -0.128 |
Fro | -0.102 |
The | -0.098 |
Twe | -0.095 |
Cr | -0.095 |
Token | They |
Token ID | 1119 |
Feature activation | +6.66e+00 |
Pos logit contributions | |
es | +0.065 |
le | +0.060 |
ymes | +0.059 |
ing | +0.058 |
again | +0.058 |
Neg logit contributions | |
disl | -0.055 |
Cr | -0.036 |
Twe | -0.036 |
Joey | -0.035 |
This | -0.034 |
Token | had |
Token ID | 550 |
Feature activation | +6.05e+00 |
Pos logit contributions | |
es | +0.065 |
again | +0.060 |
ing | +0.060 |
le | +0.059 |
ices | +0.058 |
Neg logit contributions | |
disl | -0.095 |
Cr | -0.074 |
Fro | -0.070 |
Twe | -0.069 |
Joey | -0.069 |
Token | When |
Token ID | 1649 |
Feature activation | -9.74e+00 |
Pos logit contributions | |
disl | +0.141 |
majesty | +0.093 |
Cr | +0.093 |
icol | +0.091 |
pleasure | +0.089 |
Neg logit contributions | |
es | -0.108 |
again | -0.103 |
on | -0.100 |
y | -0.093 |
m | -0.091 |
Token | Daisy |
Token ID | 40355 |
Feature activation | -6.65e+00 |
Pos logit contributions | |
disl | +0.148 |
Cr | +0.104 |
pleasure | +0.098 |
majesty | +0.097 |
Fro | +0.097 |
Neg logit contributions | |
on | -0.098 |
again | -0.097 |
es | -0.096 |
y | -0.081 |
m | -0.080 |
Token | put |
Token ID | 1234 |
Feature activation | -7.03e+00 |
Pos logit contributions | |
disl | +0.107 |
Cr | +0.081 |
Joey | +0.077 |
Fro | +0.077 |
Twe | +0.075 |
Neg logit contributions | |
es | -0.058 |
again | -0.053 |
on | -0.050 |
le | -0.049 |
m | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | -7.73e+00 |
Pos logit contributions | |
disl | +0.116 |
Cr | +0.089 |
Joey | +0.086 |
Fro | +0.085 |
Twe | +0.084 |
Neg logit contributions | |
es | -0.057 |
again | -0.052 |
le | -0.049 |
m | -0.049 |
y | -0.048 |
Token | magn |
Token ID | 7842 |
Feature activation | -5.38e+00 |
Pos logit contributions | |
disl | +0.117 |
Cr | +0.086 |
Joey | +0.082 |
Fro | +0.082 |
majesty | +0.081 |
Neg logit contributions | |
es | -0.076 |
again | -0.067 |
le | -0.064 |
y | -0.063 |
m | -0.063 |
Token | ifying |
Token ID | 4035 |
Feature activation | -2.31e+01 |
Pos logit contributions | |
disl | +0.046 |
Joey | +0.040 |
Cr | +0.038 |
This | +0.037 |
J | +0.036 |
Neg logit contributions | |
es | -0.061 |
ices | -0.060 |
m | -0.059 |
ymes | -0.059 |
again | -0.059 |
Token | glass |
Token ID | 5405 |
Feature activation | -5.00e+00 |
Pos logit contributions | |
disl | +0.424 |
Majesty | +0.310 |
majesty | +0.301 |
talented | +0.298 |
Cr | +0.293 |
Neg logit contributions | |
again | -0.185 |
on | -0.184 |
y | -0.158 |
es | -0.152 |
and | -0.151 |
Token | down |
Token ID | 866 |
Feature activation | -8.63e+00 |
Pos logit contributions | |
disl | +0.080 |
Joey | +0.061 |
Cr | +0.061 |
Madd | +0.059 |
Fro | +0.058 |
Neg logit contributions | |
es | -0.038 |
le | -0.033 |
again | -0.033 |
ymes | -0.033 |
ices | -0.033 |
Token | , |
Token ID | 11 |
Feature activation | -7.15e+00 |
Pos logit contributions | |
disl | +0.138 |
Cr | +0.104 |
Joey | +0.099 |
Fro | +0.098 |
Twe | +0.097 |
Neg logit contributions | |
es | -0.076 |
again | -0.070 |
on | -0.066 |
le | -0.066 |
m | -0.065 |
Token | the |
Token ID | 262 |
Feature activation | -8.61e+00 |
Pos logit contributions | |
disl | +0.122 |
Cr | +0.090 |
majesty | +0.088 |
icol | +0.087 |
LL | +0.085 |
Neg logit contributions | |
es | -0.062 |
on | -0.061 |
again | -0.060 |
le | -0.049 |
ing | -0.048 |
Token | cater |
Token ID | 20825 |
Feature activation | -7.84e+00 |
Pos logit contributions | |
disl | +0.127 |
Cr | +0.092 |
majesty | +0.090 |
Joey | +0.090 |
Fro | +0.088 |
Neg logit contributions | |
es | -0.086 |
again | -0.075 |
le | -0.073 |
ices | -0.072 |
y | -0.072 |
Token | 't |
Token ID | 470 |
Feature activation | -1.20e+01 |
Pos logit contributions | |
es | +0.052 |
again | +0.051 |
on | +0.049 |
m | +0.043 |
ing | +0.041 |
Neg logit contributions | |
disl | -0.118 |
Cr | -0.088 |
icol | -0.086 |
majesty | -0.086 |
Fro | -0.085 |
Token | know |
Token ID | 760 |
Feature activation | -8.78e+00 |
Pos logit contributions | |
disl | +0.163 |
Cr | +0.116 |
Fro | +0.109 |
Joey | +0.106 |
icol | +0.106 |
Neg logit contributions | |
es | -0.134 |
again | -0.132 |
on | -0.127 |
le | -0.122 |
y | -0.121 |
Token | the |
Token ID | 262 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
disl | +0.119 |
Cr | +0.083 |
Joey | +0.080 |
Twe | +0.078 |
Fro | +0.077 |
Neg logit contributions | |
es | -0.097 |
m | -0.090 |
le | -0.089 |
again | -0.089 |
y | -0.088 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
disl | +0.171 |
Cr | +0.126 |
Joey | +0.119 |
Fro | +0.118 |
Twe | +0.116 |
Neg logit contributions | |
es | -0.114 |
again | -0.106 |
on | -0.101 |
le | -0.100 |
m | -0.099 |
Token | in |
Token ID | 259 |
Feature activation | -9.05e+00 |
Pos logit contributions | |
disl | +0.193 |
Cr | +0.158 |
Twe | +0.148 |
Fro | +0.147 |
Joey | +0.145 |
Neg logit contributions | |
es | -0.067 |
again | -0.061 |
boards | -0.058 |
Today | -0.057 |
ices | -0.056 |
Token | oc |
Token ID | 420 |
Feature activation | -2.24e+01 |
Pos logit contributions | |
disl | +0.142 |
Cr | +0.106 |
Joey | +0.100 |
Fro | +0.099 |
Twe | +0.098 |
Neg logit contributions | |
es | -0.083 |
again | -0.077 |
on | -0.073 |
le | -0.072 |
m | -0.072 |
Token | eros |
Token ID | 27498 |
Feature activation | -6.12e+00 |
Pos logit contributions | |
disl | +0.267 |
Cr | +0.177 |
Joey | +0.165 |
Fro | +0.164 |
Twe | +0.158 |
Neg logit contributions | |
es | -0.290 |
again | -0.276 |
on | -0.264 |
le | -0.262 |
m | -0.260 |
Token | was |
Token ID | 373 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
disl | +0.099 |
Cr | +0.075 |
Joey | +0.072 |
Fro | +0.071 |
Twe | +0.070 |
Neg logit contributions | |
es | -0.051 |
again | -0.046 |
le | -0.045 |
m | -0.044 |
on | -0.044 |
Token | wild |
Token ID | 4295 |
Feature activation | -6.38e+00 |
Pos logit contributions | |
disl | +0.164 |
Cr | +0.121 |
majesty | +0.113 |
Fro | +0.113 |
Joey | +0.112 |
Neg logit contributions | |
again | -0.098 |
es | -0.097 |
on | -0.096 |
y | -0.086 |
m | -0.085 |
Token | . |
Token ID | 13 |
Feature activation | -9.12e+00 |
Pos logit contributions | |
disl | +0.113 |
Joey | +0.087 |
Cr | +0.086 |
Twe | +0.085 |
Fro | +0.083 |
Neg logit contributions | |
es | -0.042 |
m | -0.035 |
ymes | -0.034 |
ices | -0.034 |
le | -0.034 |
Token | Can |
Token ID | 1680 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
disl | +0.124 |
majesty | +0.082 |
icol | +0.079 |
Majesty | +0.077 |
talented | +0.077 |
Neg logit contributions | |
es | -0.100 |
again | -0.097 |
on | -0.090 |
m | -0.087 |
y | -0.086 |
Token | am |
Token ID | 716 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
disl | +0.147 |
Cr | +0.112 |
Joey | +0.105 |
Fro | +0.104 |
majesty | +0.103 |
Neg logit contributions | |
es | -0.083 |
again | -0.083 |
on | -0.079 |
le | -0.077 |
m | -0.076 |
Token | taking |
Token ID | 2263 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
disl | +0.152 |
icol | +0.115 |
Cr | +0.109 |
Fro | +0.099 |
Joey | +0.098 |
Neg logit contributions | |
on | -0.114 |
again | -0.106 |
es | -0.099 |
and | -0.090 |
. | -0.089 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
disl | +0.139 |
Cr | +0.097 |
Joey | +0.090 |
Fro | +0.090 |
majesty | +0.087 |
Neg logit contributions | |
es | -0.125 |
again | -0.119 |
on | -0.117 |
le | -0.112 |
y | -0.108 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
disl | +0.158 |
Cr | +0.115 |
Joey | +0.111 |
Fro | +0.109 |
Twe | +0.108 |
Neg logit contributions | |
es | -0.117 |
again | -0.103 |
le | -0.099 |
m | -0.098 |
y | -0.097 |
Token | in |
Token ID | 259 |
Feature activation | -8.88e+00 |
Pos logit contributions | |
disl | +0.186 |
Cr | +0.152 |
Twe | +0.144 |
Fro | +0.144 |
Joey | +0.142 |
Neg logit contributions | |
es | -0.061 |
again | -0.057 |
on | -0.051 |
boards | -0.050 |
Today | -0.049 |
Token | oc |
Token ID | 420 |
Feature activation | -2.19e+01 |
Pos logit contributions | |
disl | +0.130 |
Cr | +0.097 |
Joey | +0.091 |
Fro | +0.090 |
Twe | +0.090 |
Neg logit contributions | |
es | -0.089 |
again | -0.080 |
le | -0.077 |
m | -0.076 |
on | -0.076 |
Token | eros |
Token ID | 27498 |
Feature activation | -6.73e+00 |
Pos logit contributions | |
disl | +0.258 |
Cr | +0.170 |
Joey | +0.158 |
Fro | +0.156 |
Twe | +0.150 |
Neg logit contributions | |
es | -0.287 |
again | -0.273 |
on | -0.261 |
le | -0.259 |
y | -0.258 |
Token | to |
Token ID | 284 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
disl | +0.110 |
Cr | +0.083 |
Joey | +0.079 |
Fro | +0.078 |
Twe | +0.077 |
Neg logit contributions | |
es | -0.057 |
again | -0.052 |
on | -0.049 |
le | -0.049 |
m | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
disl | +0.150 |
icol | +0.108 |
Cr | +0.102 |
Madd | +0.099 |
APP | +0.099 |
Neg logit contributions | |
again | -0.111 |
on | -0.106 |
es | -0.100 |
and | -0.093 |
later | -0.090 |
Token | new |
Token ID | 649 |
Feature activation | -8.96e+00 |
Pos logit contributions | |
disl | +0.116 |
Cr | +0.083 |
Joey | +0.078 |
Fro | +0.077 |
majesty | +0.075 |
Neg logit contributions | |
es | -0.088 |
again | -0.086 |
on | -0.082 |
le | -0.079 |
y | -0.079 |
Token | home |
Token ID | 1363 |
Feature activation | -6.03e+00 |
Pos logit contributions | |
disl | +0.134 |
Cr | +0.099 |
Joey | +0.094 |
Fro | +0.092 |
Twe | +0.091 |
Neg logit contributions | |
es | -0.089 |
again | -0.082 |
on | -0.078 |
le | -0.078 |
m | -0.077 |
Token | he |
Token ID | 339 |
Feature activation | -8.32e+00 |
Pos logit contributions | |
disl | +0.184 |
Cr | +0.134 |
Fro | +0.125 |
majesty | +0.124 |
Joey | +0.123 |
Neg logit contributions | |
es | -0.119 |
again | -0.114 |
on | -0.110 |
y | -0.104 |
le | -0.104 |
Token | would |
Token ID | 561 |
Feature activation | -9.38e+00 |
Pos logit contributions | |
disl | +0.141 |
Cr | +0.108 |
Joey | +0.103 |
Fro | +0.102 |
Twe | +0.101 |
Neg logit contributions | |
es | -0.066 |
again | -0.060 |
on | -0.056 |
le | -0.055 |
m | -0.055 |
Token | take |
Token ID | 1011 |
Feature activation | -8.43e+00 |
Pos logit contributions | |
disl | +0.127 |
Cr | +0.091 |
Fro | +0.084 |
Joey | +0.084 |
Twe | +0.082 |
Neg logit contributions | |
es | -0.106 |
again | -0.100 |
on | -0.097 |
le | -0.095 |
y | -0.093 |
Token | the |
Token ID | 262 |
Feature activation | -9.85e+00 |
Pos logit contributions | |
disl | +0.111 |
Cr | +0.077 |
Joey | +0.072 |
Fro | +0.071 |
Twe | +0.069 |
Neg logit contributions | |
es | -0.100 |
again | -0.094 |
on | -0.091 |
le | -0.089 |
m | -0.088 |
Token | av |
Token ID | 1196 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
disl | +0.141 |
Cr | +0.103 |
Joey | +0.102 |
pleasure | +0.101 |
Fro | +0.098 |
Neg logit contributions | |
es | -0.107 |
again | -0.089 |
le | -0.087 |
m | -0.087 |
y | -0.086 |
Token | oc |
Token ID | 420 |
Feature activation | -2.14e+01 |
Pos logit contributions | |
disl | +0.169 |
Cr | +0.127 |
Joey | +0.119 |
Fro | +0.117 |
Twe | +0.117 |
Neg logit contributions | |
es | -0.117 |
again | -0.111 |
m | -0.104 |
on | -0.104 |
le | -0.102 |
Token | ados |
Token ID | 22484 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
disl | +0.325 |
Cr | +0.240 |
Joey | +0.227 |
Fro | +0.227 |
Twe | +0.221 |
Neg logit contributions | |
es | -0.208 |
again | -0.192 |
on | -0.182 |
le | -0.180 |
y | -0.179 |
Token | and |
Token ID | 290 |
Feature activation | -9.13e+00 |
Pos logit contributions | |
disl | +0.057 |
Cr | +0.044 |
Joey | +0.044 |
Fro | +0.041 |
Twe | +0.041 |
Neg logit contributions | |
es | -0.038 |
le | -0.034 |
ymes | -0.034 |
m | -0.033 |
ices | -0.033 |
Token | scatter |
Token ID | 41058 |
Feature activation | -6.61e+00 |
Pos logit contributions | |
disl | +0.136 |
Cr | +0.100 |
Fro | +0.096 |
Joey | +0.092 |
majesty | +0.092 |
Neg logit contributions | |
es | -0.091 |
again | -0.086 |
on | -0.084 |
y | -0.077 |
le | -0.077 |
Token | them |
Token ID | 606 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
disl | +0.093 |
Cr | +0.069 |
Joey | +0.066 |
Twe | +0.063 |
Fro | +0.063 |
Neg logit contributions | |
es | -0.070 |
again | -0.064 |
m | -0.062 |
le | -0.061 |
on | -0.060 |
Token | around |
Token ID | 1088 |
Feature activation | -8.31e+00 |
Pos logit contributions | |
disl | +0.093 |
Joey | +0.073 |
Cr | +0.072 |
Twe | +0.069 |
Fro | +0.068 |
Neg logit contributions | |
es | -0.040 |
m | -0.037 |
ices | -0.036 |
ymes | -0.036 |
le | -0.035 |
Token | give |
Token ID | 1577 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
disl | +0.170 |
icol | +0.137 |
Cr | +0.133 |
pleasure | +0.124 |
majesty | +0.123 |
Neg logit contributions | |
again | -0.116 |
on | -0.114 |
le | -0.104 |
es | -0.104 |
and | -0.099 |
Token | to |
Token ID | 284 |
Feature activation | -9.64e+00 |
Pos logit contributions | |
disl | +0.151 |
Cr | +0.108 |
majesty | +0.103 |
Fro | +0.101 |
icol | +0.100 |
Neg logit contributions | |
es | -0.117 |
again | -0.115 |
on | -0.112 |
le | -0.106 |
y | -0.103 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
disl | +0.130 |
icol | +0.103 |
LL | +0.101 |
Cr | +0.097 |
Fre | +0.093 |
Neg logit contributions | |
again | -0.099 |
es | -0.093 |
on | -0.091 |
and | -0.084 |
my | -0.081 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
disl | +0.171 |
Cr | +0.127 |
Joey | +0.121 |
Fro | +0.120 |
Twe | +0.119 |
Neg logit contributions | |
es | -0.105 |
again | -0.094 |
le | -0.091 |
on | -0.090 |
y | -0.089 |
Token | in |
Token ID | 259 |
Feature activation | -7.94e+00 |
Pos logit contributions | |
disl | +0.186 |
Cr | +0.151 |
Fro | +0.142 |
Twe | +0.140 |
majesty | +0.139 |
Neg logit contributions | |
es | -0.061 |
again | -0.056 |
on | -0.056 |
boards | -0.051 |
Today | -0.051 |
Token | oc |
Token ID | 420 |
Feature activation | -2.13e+01 |
Pos logit contributions | |
disl | +0.132 |
Cr | +0.099 |
Joey | +0.095 |
Fro | +0.093 |
majesty | +0.093 |
Neg logit contributions | |
es | -0.067 |
again | -0.063 |
on | -0.060 |
y | -0.057 |
le | -0.057 |
Token | eros |
Token ID | 27498 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
disl | +0.249 |
Cr | +0.164 |
Joey | +0.153 |
Fro | +0.151 |
Twe | +0.146 |
Neg logit contributions | |
es | -0.281 |
again | -0.267 |
on | -0.255 |
le | -0.253 |
y | -0.251 |
Token | . |
Token ID | 13 |
Feature activation | -9.04e+00 |
Pos logit contributions | |
disl | +0.115 |
Cr | +0.089 |
Joey | +0.084 |
Fro | +0.084 |
majesty | +0.083 |
Neg logit contributions | |
es | -0.049 |
again | -0.045 |
on | -0.042 |
le | -0.040 |
y | -0.040 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
disl | +0.120 |
majesty | +0.078 |
Cr | +0.075 |
talented | +0.074 |
pleasure | +0.074 |
Neg logit contributions | |
es | -0.101 |
again | -0.098 |
on | -0.091 |
y | -0.087 |
m | -0.087 |
Token | walked |
Token ID | 6807 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
disl | +0.087 |
Cr | +0.069 |
Joey | +0.065 |
pleasure | +0.064 |
Twe | +0.064 |
Neg logit contributions | |
es | -0.035 |
again | -0.032 |
on | -0.029 |
y | -0.028 |
le | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -7.65e+00 |
Pos logit contributions | |
disl | +0.062 |
Cr | +0.051 |
Joey | +0.050 |
Fro | +0.049 |
J | +0.047 |
Neg logit contributions | |
es | -0.042 |
ymes | -0.038 |
ities | -0.036 |
ices | -0.036 |
le | -0.036 |
Token | her |
Token ID | 607 |
Feature activation | -1.41e+01 |
Pos logit contributions | |
es | +0.033 |
again | +0.029 |
m | +0.029 |
ices | +0.028 |
le | +0.028 |
Neg logit contributions | |
disl | -0.064 |
Cr | -0.048 |
Fro | -0.046 |
Joey | -0.046 |
J | -0.044 |
Token | mom |
Token ID | 1995 |
Feature activation | -8.73e+00 |
Pos logit contributions | |
disl | +0.221 |
Cr | +0.169 |
Joey | +0.155 |
Fro | +0.152 |
Twe | +0.149 |
Neg logit contributions | |
es | -0.129 |
again | -0.127 |
on | -0.124 |
y | -0.114 |
m | -0.113 |
Token | my |
Token ID | 1820 |
Feature activation | -8.80e+00 |
Pos logit contributions | |
disl | +0.148 |
Cr | +0.113 |
Joey | +0.113 |
Twe | +0.110 |
Fro | +0.109 |
Neg logit contributions | |
es | -0.061 |
ymes | -0.053 |
le | -0.051 |
ices | -0.051 |
again | -0.050 |
Token | watched |
Token ID | 7342 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
disl | +0.148 |
Joey | +0.112 |
Cr | +0.112 |
Twe | +0.108 |
Fro | +0.107 |
Neg logit contributions | |
es | -0.064 |
again | -0.056 |
ymes | -0.056 |
le | -0.054 |
ices | -0.054 |
Token | in |
Token ID | 287 |
Feature activation | -9.00e+00 |
Pos logit contributions | |
disl | +0.177 |
Cr | +0.133 |
Fro | +0.125 |
Joey | +0.125 |
majesty | +0.123 |
Neg logit contributions | |
es | -0.102 |
again | -0.095 |
on | -0.091 |
le | -0.089 |
y | -0.087 |
Token | amaz |
Token ID | 40642 |
Feature activation | -2.07e+01 |
Pos logit contributions | |
disl | +0.121 |
Cr | +0.085 |
Joey | +0.081 |
Fro | +0.079 |
Twe | +0.078 |
Neg logit contributions | |
es | -0.103 |
again | -0.094 |
le | -0.092 |
on | -0.091 |
m | -0.091 |
Token | ement |
Token ID | 972 |
Feature activation | -7.82e+00 |
Pos logit contributions | |
disl | +0.386 |
Cr | +0.302 |
Joey | +0.292 |
Twe | +0.286 |
Fro | +0.285 |
Neg logit contributions | |
es | -0.127 |
again | -0.107 |
on | -0.103 |
m | -0.100 |
le | -0.099 |
Token | as |
Token ID | 355 |
Feature activation | -9.78e+00 |
Pos logit contributions | |
disl | +0.142 |
Cr | +0.110 |
Joey | +0.109 |
Twe | +0.106 |
Fro | +0.105 |
Neg logit contributions | |
es | -0.048 |
again | -0.040 |
m | -0.039 |
le | -0.038 |
ymes | -0.038 |
Token | the |
Token ID | 262 |
Feature activation | -9.38e+00 |
Pos logit contributions | |
disl | +0.130 |
Cr | +0.092 |
Fro | +0.085 |
Joey | +0.083 |
majesty | +0.082 |
Neg logit contributions | |
es | -0.114 |
again | -0.109 |
on | -0.105 |
le | -0.101 |
y | -0.100 |
Token | machine |
Token ID | 4572 |
Feature activation | -3.77e+00 |
Pos logit contributions | |
disl | +0.131 |
Cr | +0.092 |
Joey | +0.090 |
pleasure | +0.087 |
Twe | +0.087 |
Neg logit contributions | |
es | -0.107 |
again | -0.091 |
y | -0.090 |
le | -0.089 |
ices | -0.088 |
Token | flew |
Token ID | 13112 |
Feature activation | -6.83e+00 |
Pos logit contributions | |
disl | +0.057 |
Cr | +0.041 |
Joey | +0.041 |
J | +0.039 |
Twe | +0.039 |
Neg logit contributions | |
es | -0.033 |
ymes | -0.030 |
ices | -0.029 |
le | -0.029 |
m | -0.028 |
Token | it |
Token ID | 340 |
Feature activation | -6.33e+00 |
Pos logit contributions | |
disl | +0.176 |
Cr | +0.123 |
LL | +0.119 |
majesty | +0.117 |
icol | +0.116 |
Neg logit contributions | |
es | -0.136 |
again | -0.135 |
on | -0.131 |
le | -0.124 |
ing | -0.120 |
Token | to |
Token ID | 284 |
Feature activation | -9.94e+00 |
Pos logit contributions | |
disl | +0.100 |
Cr | +0.074 |
Fro | +0.070 |
Joey | +0.070 |
majesty | +0.069 |
Neg logit contributions | |
es | -0.058 |
again | -0.057 |
on | -0.054 |
le | -0.050 |
y | -0.050 |
Token | the |
Token ID | 262 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
disl | +0.137 |
icol | +0.096 |
LL | +0.093 |
Cr | +0.093 |
majesty | +0.089 |
Neg logit contributions | |
again | -0.106 |
on | -0.102 |
es | -0.101 |
le | -0.091 |
and | -0.090 |
Token | rh |
Token ID | 9529 |
Feature activation | -9.52e+00 |
Pos logit contributions | |
disl | +0.166 |
Cr | +0.122 |
Joey | +0.116 |
Fro | +0.114 |
Twe | +0.112 |
Neg logit contributions | |
es | -0.105 |
again | -0.100 |
on | -0.095 |
le | -0.092 |
m | -0.092 |
Token | in |
Token ID | 259 |
Feature activation | -7.53e+00 |
Pos logit contributions | |
disl | +0.163 |
Cr | +0.132 |
Fro | +0.125 |
Twe | +0.124 |
majesty | +0.122 |
Neg logit contributions | |
es | -0.054 |
again | -0.048 |
on | -0.048 |
boards | -0.045 |
Today | -0.044 |
Token | oc |
Token ID | 420 |
Feature activation | -2.00e+01 |
Pos logit contributions | |
disl | +0.113 |
Cr | +0.084 |
Joey | +0.079 |
Fro | +0.079 |
Twe | +0.077 |
Neg logit contributions | |
es | -0.073 |
again | -0.066 |
on | -0.064 |
le | -0.063 |
m | -0.063 |
Token | eros |
Token ID | 27498 |
Feature activation | -5.97e+00 |
Pos logit contributions | |
disl | +0.237 |
Cr | +0.155 |
Joey | +0.145 |
Fro | +0.144 |
Twe | +0.138 |
Neg logit contributions | |
es | -0.264 |
again | -0.252 |
on | -0.238 |
le | -0.237 |
y | -0.236 |
Token | . |
Token ID | 13 |
Feature activation | -8.94e+00 |
Pos logit contributions | |
disl | +0.117 |
Cr | +0.094 |
Joey | +0.090 |
Fro | +0.089 |
Twe | +0.088 |
Neg logit contributions | |
es | -0.031 |
again | -0.027 |
on | -0.024 |
le | -0.024 |
m | -0.023 |
Token | When |
Token ID | 1649 |
Feature activation | -8.21e+00 |
Pos logit contributions | |
disl | +0.115 |
majesty | +0.073 |
talented | +0.069 |
Majesty | +0.069 |
icol | +0.069 |
Neg logit contributions | |
es | -0.103 |
again | -0.101 |
on | -0.093 |
m | -0.088 |
y | -0.088 |
Token | he |
Token ID | 339 |
Feature activation | -7.05e+00 |
Pos logit contributions | |
disl | +0.120 |
Cr | +0.078 |
majesty | +0.078 |
pleasure | +0.076 |
icol | +0.075 |
Neg logit contributions | |
again | -0.089 |
on | -0.089 |
es | -0.087 |
ing | -0.073 |
m | -0.073 |
Token | tasted |
Token ID | 29187 |
Feature activation | -6.02e+00 |
Pos logit contributions | |
disl | +0.110 |
Cr | +0.084 |
Joey | +0.080 |
Fro | +0.079 |
Twe | +0.077 |
Neg logit contributions | |
es | -0.064 |
again | -0.058 |
on | -0.055 |
le | -0.055 |
m | -0.054 |
Token | quiet |
Token ID | 5897 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
es | +0.050 |
again | +0.049 |
on | +0.046 |
y | +0.044 |
le | +0.043 |
Neg logit contributions | |
disl | -0.106 |
Cr | -0.080 |
Joey | -0.075 |
Fro | -0.075 |
Twe | -0.074 |
Token | compared |
Token ID | 3688 |
Feature activation | -1.39e+01 |
Pos logit contributions | |
disl | +0.322 |
Cr | +0.257 |
Joey | +0.249 |
Fro | +0.247 |
Twe | +0.244 |
Neg logit contributions | |
es | -0.075 |
again | -0.062 |
on | -0.056 |
le | -0.055 |
m | -0.054 |
Token | to |
Token ID | 284 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
disl | +0.205 |
Cr | +0.150 |
Joey | +0.142 |
Fro | +0.141 |
Twe | +0.138 |
Neg logit contributions | |
es | -0.139 |
again | -0.130 |
on | -0.124 |
le | -0.122 |
m | -0.121 |
Token | the |
Token ID | 262 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
disl | +0.146 |
Cr | +0.108 |
Fro | +0.097 |
Joey | +0.096 |
Twe | +0.095 |
Neg logit contributions | |
es | -0.130 |
again | -0.126 |
on | -0.123 |
le | -0.117 |
y | -0.115 |
Token | noisy |
Token ID | 31210 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
disl | +0.186 |
Cr | +0.134 |
Joey | +0.130 |
Fro | +0.127 |
majesty | +0.126 |
Neg logit contributions | |
es | -0.125 |
again | -0.111 |
le | -0.107 |
m | -0.106 |
y | -0.105 |
Token | se |
Token ID | 384 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
disl | +0.180 |
Cr | +0.132 |
Joey | +0.128 |
Fro | +0.125 |
Twe | +0.124 |
Neg logit contributions | |
es | -0.104 |
again | -0.091 |
m | -0.088 |
le | -0.088 |
on | -0.087 |
Token | ag |
Token ID | 363 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
disl | +0.329 |
Cr | +0.260 |
Joey | +0.252 |
Fro | +0.248 |
Twe | +0.246 |
Neg logit contributions | |
es | -0.160 |
le | -0.148 |
again | -0.145 |
y | -0.139 |
les | -0.137 |
Token | ull |
Token ID | 724 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
disl | +0.190 |
Cr | +0.148 |
pleasure | +0.139 |
Twe | +0.138 |
icol | +0.138 |
Neg logit contributions | |
es | -0.106 |
y | -0.094 |
on | -0.093 |
again | -0.092 |
le | -0.089 |
Token | s |
Token ID | 82 |
Feature activation | -9.84e+00 |
Pos logit contributions | |
disl | +0.089 |
Cr | +0.069 |
Joey | +0.067 |
Fro | +0.067 |
Twe | +0.066 |
Neg logit contributions | |
es | -0.027 |
again | -0.023 |
on | -0.021 |
le | -0.021 |
m | -0.021 |
Token | outside |
Token ID | 2354 |
Feature activation | -8.91e+00 |
Pos logit contributions | |
disl | +0.175 |
Cr | +0.131 |
Joey | +0.130 |
pleasure | +0.129 |
majesty | +0.127 |
Neg logit contributions | |
es | -0.065 |
le | -0.057 |
m | -0.055 |
again | -0.053 |
ymes | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
disl | +0.168 |
Cr | +0.132 |
Joey | +0.129 |
Fro | +0.126 |
Twe | +0.126 |
Neg logit contributions | |
es | -0.052 |
again | -0.042 |
le | -0.041 |
m | -0.040 |
on | -0.038 |
Token | that |
Token ID | 326 |
Feature activation | -8.98e+00 |
Pos logit contributions | |
disl | +0.167 |
Cr | +0.130 |
Fro | +0.124 |
Joey | +0.123 |
majesty | +0.122 |
Neg logit contributions | |
es | -0.067 |
again | -0.063 |
on | -0.059 |
y | -0.056 |
le | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
disl | +0.127 |
Cr | +0.090 |
majesty | +0.086 |
Fro | +0.086 |
icol | +0.083 |
Neg logit contributions | |
es | -0.097 |
again | -0.096 |
on | -0.092 |
m | -0.084 |
y | -0.084 |
Token | bad |
Token ID | 2089 |
Feature activation | -9.81e+00 |
Pos logit contributions | |
disl | +0.156 |
Cr | +0.114 |
Joey | +0.108 |
Fro | +0.107 |
Twe | +0.105 |
Neg logit contributions | |
es | -0.109 |
again | -0.100 |
on | -0.096 |
le | -0.095 |
m | -0.094 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
disl | +0.153 |
Cr | +0.116 |
Fro | +0.110 |
Joey | +0.108 |
Twe | +0.107 |
Neg logit contributions | |
es | -0.087 |
again | -0.085 |
on | -0.080 |
le | -0.077 |
y | -0.077 |
Token | in |
Token ID | 259 |
Feature activation | -8.44e+00 |
Pos logit contributions | |
disl | +0.177 |
Cr | +0.144 |
Twe | +0.136 |
Joey | +0.135 |
Fro | +0.134 |
Neg logit contributions | |
es | -0.054 |
again | -0.050 |
packs | -0.046 |
boards | -0.046 |
on | -0.045 |
Token | oc |
Token ID | 420 |
Feature activation | -1.96e+01 |
Pos logit contributions | |
disl | +0.130 |
Cr | +0.097 |
Joey | +0.092 |
Fro | +0.091 |
Twe | +0.090 |
Neg logit contributions | |
es | -0.079 |
again | -0.072 |
on | -0.069 |
le | -0.068 |
m | -0.067 |
Token | eros |
Token ID | 27498 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
disl | +0.233 |
Cr | +0.155 |
Joey | +0.144 |
Fro | +0.142 |
Twe | +0.138 |
Neg logit contributions | |
es | -0.256 |
again | -0.242 |
on | -0.233 |
le | -0.231 |
m | -0.230 |
Token | was |
Token ID | 373 |
Feature activation | -9.62e+00 |
Pos logit contributions | |
disl | +0.085 |
Cr | +0.063 |
Joey | +0.061 |
Fro | +0.060 |
Twe | +0.059 |
Neg logit contributions | |
es | -0.048 |
again | -0.043 |
m | -0.041 |
le | -0.041 |
on | -0.041 |
Token | now |
Token ID | 783 |
Feature activation | -9.06e+00 |
Pos logit contributions | |
disl | +0.146 |
Cr | +0.107 |
icol | +0.103 |
majesty | +0.103 |
Fro | +0.102 |
Neg logit contributions | |
again | -0.100 |
on | -0.099 |
es | -0.090 |
m | -0.083 |
y | -0.080 |
Token | nice |
Token ID | 3621 |
Feature activation | -5.90e+00 |
Pos logit contributions | |
disl | +0.136 |
Cr | +0.102 |
Fro | +0.096 |
Joey | +0.094 |
majesty | +0.093 |
Neg logit contributions | |
es | -0.088 |
again | -0.085 |
on | -0.082 |
y | -0.077 |
m | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -8.76e+00 |
Pos logit contributions | |
disl | +0.106 |
Joey | +0.084 |
Cr | +0.083 |
Fro | +0.081 |
pleasure | +0.080 |
Neg logit contributions | |
es | -0.038 |
le | -0.032 |
ymes | -0.031 |
m | -0.030 |
ices | -0.029 |
Token | you |
Token ID | 345 |
Feature activation | -1.42e+01 |
Pos logit contributions | |
on | +0.039 |
again | +0.039 |
es | +0.037 |
m | +0.032 |
and | +0.031 |
Neg logit contributions | |
disl | -0.056 |
icol | -0.040 |
Majesty | -0.038 |
majesty | -0.038 |
Cr | -0.037 |
Token | go |
Token ID | 467 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
disl | +0.213 |
Cr | +0.159 |
icol | +0.148 |
Fro | +0.147 |
Twe | +0.147 |
Neg logit contributions | |
es | -0.139 |
again | -0.138 |
on | -0.135 |
le | -0.125 |
y | -0.124 |
Token | , |
Token ID | 11 |
Feature activation | -9.72e+00 |
Pos logit contributions | |
disl | +0.181 |
Cr | +0.134 |
Joey | +0.126 |
Fro | +0.125 |
majesty | +0.125 |
Neg logit contributions | |
again | -0.096 |
es | -0.095 |
on | -0.093 |
m | -0.084 |
le | -0.083 |
Token | my |
Token ID | 616 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
disl | +0.138 |
Cr | +0.098 |
icol | +0.089 |
Joey | +0.089 |
Fro | +0.087 |
Neg logit contributions | |
again | -0.105 |
on | -0.102 |
es | -0.102 |
le | -0.092 |
m | -0.090 |
Token | d |
Token ID | 288 |
Feature activation | -1.15e+01 |
Pos logit contributions | |
disl | +0.158 |
Cr | +0.116 |
Joey | +0.109 |
Fro | +0.106 |
Twe | +0.105 |
Neg logit contributions | |
es | -0.105 |
again | -0.102 |
on | -0.098 |
le | -0.094 |
y | -0.093 |
Token | arl |
Token ID | 7063 |
Feature activation | -1.95e+01 |
Pos logit contributions | |
disl | +0.177 |
Cr | +0.131 |
Joey | +0.125 |
Fro | +0.123 |
Twe | +0.121 |
Neg logit contributions | |
es | -0.110 |
again | -0.101 |
on | -0.097 |
le | -0.096 |
m | -0.095 |
Token | ings |
Token ID | 654 |
Feature activation | -7.81e+00 |
Pos logit contributions | |
disl | +0.343 |
Cr | +0.268 |
Joey | +0.255 |
Fro | +0.249 |
Twe | +0.247 |
Neg logit contributions | |
es | -0.151 |
again | -0.137 |
on | -0.134 |
y | -0.131 |
ing | -0.127 |
Token | . |
Token ID | 13 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
disl | +0.129 |
Cr | +0.098 |
Joey | +0.094 |
Fro | +0.093 |
Twe | +0.092 |
Neg logit contributions | |
es | -0.064 |
again | -0.058 |
le | -0.055 |
on | -0.054 |
m | -0.054 |
Token | Enjoy |
Token ID | 18179 |
Feature activation | -9.91e+00 |
Pos logit contributions | |
disl | +0.126 |
Joey | +0.075 |
str | +0.075 |
Cr | +0.075 |
Fro | +0.074 |
Neg logit contributions | |
es | -0.122 |
on | -0.111 |
again | -0.109 |
Will | -0.105 |
m | -0.104 |
Token | your |
Token ID | 534 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
disl | +0.118 |
Cr | +0.083 |
Joey | +0.074 |
pleasure | +0.072 |
Twe | +0.071 |
Neg logit contributions | |
es | -0.132 |
again | -0.130 |
on | -0.129 |
le | -0.125 |
les | -0.121 |
Token | lunch |
Token ID | 9965 |
Feature activation | -6.12e+00 |
Pos logit contributions | |
disl | +0.163 |
Cr | +0.122 |
Joey | +0.115 |
Fro | +0.114 |
Twe | +0.112 |
Neg logit contributions | |
es | -0.103 |
again | -0.099 |
on | -0.095 |
le | -0.091 |
m | -0.090 |
Token | grass |
Token ID | 8701 |
Feature activation | -6.80e+00 |
Pos logit contributions | |
disl | +0.095 |
Cr | +0.073 |
Joey | +0.073 |
Fro | +0.071 |
Twe | +0.071 |
Neg logit contributions | |
es | -0.032 |
again | -0.030 |
le | -0.028 |
ymes | -0.027 |
m | -0.027 |
Token | and |
Token ID | 290 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
disl | +0.123 |
Joey | +0.097 |
Cr | +0.097 |
Twe | +0.096 |
Fro | +0.095 |
Neg logit contributions | |
es | -0.037 |
le | -0.032 |
ymes | -0.032 |
ices | -0.030 |
again | -0.030 |
Token | rye |
Token ID | 47553 |
Feature activation | -1.18e+01 |
Pos logit contributions | |
disl | +0.156 |
Cr | +0.121 |
Fro | +0.110 |
Joey | +0.109 |
Twe | +0.108 |
Neg logit contributions | |
es | -0.093 |
on | -0.089 |
again | -0.088 |
y | -0.079 |
le | -0.079 |
Token | grass |
Token ID | 8701 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
disl | +0.207 |
Cr | +0.170 |
Fro | +0.153 |
Ag | +0.148 |
Joey | +0.148 |
Neg logit contributions | |
on | -0.083 |
es | -0.081 |
again | -0.079 |
and | -0.073 |
le | -0.069 |
Token | and |
Token ID | 290 |
Feature activation | -9.96e+00 |
Pos logit contributions | |
disl | +0.113 |
Cr | +0.088 |
Joey | +0.088 |
Fro | +0.086 |
Twe | +0.086 |
Neg logit contributions | |
es | -0.034 |
le | -0.029 |
again | -0.029 |
ymes | -0.028 |
ices | -0.028 |
Token | al |
Token ID | 435 |
Feature activation | -1.93e+01 |
Pos logit contributions | |
disl | +0.155 |
Cr | +0.120 |
Fro | +0.110 |
Joey | +0.109 |
Twe | +0.107 |
Neg logit contributions | |
es | -0.091 |
again | -0.086 |
on | -0.086 |
le | -0.077 |
y | -0.077 |
Token | f |
Token ID | 69 |
Feature activation | -9.43e+00 |
Pos logit contributions | |
disl | +0.339 |
Cr | +0.263 |
Joey | +0.252 |
Fro | +0.250 |
Twe | +0.246 |
Neg logit contributions | |
es | -0.141 |
again | -0.127 |
on | -0.119 |
le | -0.118 |
m | -0.117 |
Token | alf |
Token ID | 1604 |
Feature activation | -7.48e+00 |
Pos logit contributions | |
disl | +0.160 |
Cr | +0.123 |
Joey | +0.118 |
Fro | +0.117 |
Twe | +0.115 |
Neg logit contributions | |
es | -0.073 |
again | -0.066 |
on | -0.063 |
le | -0.061 |
m | -0.061 |
Token | a |
Token ID | 64 |
Feature activation | -5.85e+00 |
Pos logit contributions | |
disl | +0.130 |
Cr | +0.101 |
Fro | +0.096 |
Joey | +0.095 |
Twe | +0.094 |
Neg logit contributions | |
es | -0.057 |
again | -0.051 |
on | -0.049 |
le | -0.048 |
y | -0.048 |
Token | and |
Token ID | 290 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
disl | +0.104 |
Cr | +0.080 |
Joey | +0.078 |
Fro | +0.077 |
majesty | +0.077 |
Neg logit contributions | |
es | -0.039 |
again | -0.035 |
on | -0.032 |
le | -0.032 |
m | -0.032 |
Token | cl |
Token ID | 537 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
disl | +0.151 |
Cr | +0.114 |
Joey | +0.103 |
LL | +0.102 |
Fro | +0.102 |
Neg logit contributions | |
es | -0.103 |
on | -0.097 |
again | -0.095 |
y | -0.088 |
le | -0.085 |
Token | flashlight |
Token ID | 38371 |
Feature activation | -2.35e+00 |
Pos logit contributions | |
disl | +0.114 |
Cr | +0.085 |
Joey | +0.080 |
Fro | +0.079 |
Twe | +0.078 |
Neg logit contributions | |
es | -0.070 |
again | -0.065 |
on | -0.063 |
le | -0.061 |
m | -0.061 |
Token | , |
Token ID | 11 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
disl | +0.039 |
Joey | +0.029 |
Cr | +0.029 |
Twe | +0.028 |
majesty | +0.028 |
Neg logit contributions | |
es | -0.017 |
ymes | -0.016 |
ices | -0.015 |
m | -0.015 |
le | -0.015 |
Token | and |
Token ID | 290 |
Feature activation | -7.66e+00 |
Pos logit contributions | |
disl | +0.100 |
Cr | +0.076 |
Joey | +0.074 |
Twe | +0.074 |
Fro | +0.073 |
Neg logit contributions | |
es | -0.043 |
again | -0.039 |
m | -0.038 |
le | -0.038 |
y | -0.037 |
Token | a |
Token ID | 257 |
Feature activation | -7.34e+00 |
Pos logit contributions | |
disl | +0.111 |
Cr | +0.080 |
Joey | +0.075 |
Fro | +0.075 |
majesty | +0.073 |
Neg logit contributions | |
es | -0.081 |
again | -0.076 |
on | -0.074 |
le | -0.070 |
y | -0.070 |
Token | magn |
Token ID | 7842 |
Feature activation | -5.14e+00 |
Pos logit contributions | |
disl | +0.112 |
Cr | +0.082 |
Joey | +0.079 |
Fro | +0.078 |
majesty | +0.077 |
Neg logit contributions | |
es | -0.071 |
again | -0.064 |
le | -0.062 |
on | -0.061 |
m | -0.060 |
Token | ifying |
Token ID | 4035 |
Feature activation | -1.91e+01 |
Pos logit contributions | |
disl | +0.055 |
Joey | +0.044 |
Cr | +0.042 |
J | +0.042 |
Fre | +0.041 |
Neg logit contributions | |
es | -0.054 |
again | -0.051 |
ymes | -0.051 |
ices | -0.050 |
m | -0.050 |
Token | glass |
Token ID | 5405 |
Feature activation | -5.30e+00 |
Pos logit contributions | |
disl | +0.356 |
Majesty | +0.259 |
majesty | +0.257 |
talented | +0.252 |
Cr | +0.251 |
Neg logit contributions | |
again | -0.146 |
on | -0.142 |
y | -0.118 |
and | -0.116 |
pieces | -0.110 |
Token | . |
Token ID | 13 |
Feature activation | -7.43e+00 |
Pos logit contributions | |
disl | +0.092 |
Joey | +0.071 |
Cr | +0.071 |
Madd | +0.069 |
Twe | +0.069 |
Neg logit contributions | |
es | -0.032 |
m | -0.027 |
again | -0.026 |
ices | -0.026 |
ymes | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -8.48e+00 |
Pos logit contributions | |
disl | +0.103 |
Cr | +0.068 |
majesty | +0.065 |
Fro | +0.064 |
Joey | +0.063 |
Neg logit contributions | |
es | -0.084 |
again | -0.080 |
on | -0.077 |
m | -0.072 |
y | -0.072 |
Token |
|
Token ID | 198 |
Feature activation | -8.37e+00 |
Pos logit contributions | |
disl | +0.140 |
Cr | +0.105 |
majesty | +0.100 |
icol | +0.099 |
pleasure | +0.097 |
Neg logit contributions | |
es | -0.076 |
again | -0.070 |
on | -0.066 |
m | -0.065 |
y | -0.064 |
Token | As |
Token ID | 1722 |
Feature activation | -6.94e+00 |
Pos logit contributions | |
disl | +0.149 |
Cr | +0.117 |
Joey | +0.112 |
Fro | +0.111 |
pleasure | +0.110 |
Neg logit contributions | |
es | -0.059 |
again | -0.051 |
on | -0.049 |
y | -0.048 |
m | -0.048 |
Token | go |
Token ID | 467 |
Feature activation | -9.13e+00 |
Pos logit contributions | |
disl | +0.202 |
icol | +0.165 |
Cr | +0.159 |
LL | +0.152 |
APP | +0.147 |
Neg logit contributions | |
on | -0.130 |
again | -0.129 |
and | -0.112 |
es | -0.111 |
le | -0.110 |
Token | ! |
Token ID | 0 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
disl | +0.162 |
Cr | +0.124 |
majesty | +0.117 |
Fro | +0.116 |
Joey | +0.116 |
Neg logit contributions | |
es | -0.067 |
again | -0.066 |
on | -0.064 |
le | -0.058 |
m | -0.057 |
Token | Everyone |
Token ID | 11075 |
Feature activation | -5.95e+00 |
Pos logit contributions | |
disl | +0.142 |
Cr | +0.092 |
majesty | +0.092 |
icol | +0.088 |
Majesty | +0.087 |
Neg logit contributions | |
es | -0.123 |
again | -0.117 |
on | -0.112 |
y | -0.108 |
m | -0.107 |
Token | watched |
Token ID | 7342 |
Feature activation | -8.67e+00 |
Pos logit contributions | |
disl | +0.099 |
Cr | +0.076 |
Joey | +0.072 |
Fro | +0.072 |
Twe | +0.071 |
Neg logit contributions | |
es | -0.049 |
again | -0.045 |
on | -0.042 |
le | -0.041 |
y | -0.041 |
Token | in |
Token ID | 287 |
Feature activation | -7.75e+00 |
Pos logit contributions | |
disl | +0.133 |
Cr | +0.099 |
Joey | +0.095 |
Fro | +0.093 |
Twe | +0.092 |
Neg logit contributions | |
es | -0.082 |
again | -0.075 |
on | -0.071 |
le | -0.071 |
m | -0.071 |
Token | amaz |
Token ID | 40642 |
Feature activation | -1.91e+01 |
Pos logit contributions | |
disl | +0.107 |
Cr | +0.074 |
Joey | +0.074 |
pleasure | +0.073 |
Fro | +0.071 |
Neg logit contributions | |
es | -0.085 |
le | -0.075 |
m | -0.074 |
y | -0.074 |
ing | -0.074 |
Token | ement |
Token ID | 972 |
Feature activation | -7.11e+00 |
Pos logit contributions | |
disl | +0.345 |
Cr | +0.267 |
Joey | +0.261 |
Twe | +0.253 |
pleasure | +0.251 |
Neg logit contributions | |
es | -0.124 |
again | -0.103 |
on | -0.102 |
m | -0.101 |
y | -0.098 |
Token | as |
Token ID | 355 |
Feature activation | -9.67e+00 |
Pos logit contributions | |
disl | +0.127 |
Cr | +0.098 |
Joey | +0.096 |
Fro | +0.093 |
Twe | +0.093 |
Neg logit contributions | |
es | -0.047 |
again | -0.041 |
m | -0.040 |
le | -0.039 |
on | -0.038 |
Token | it |
Token ID | 340 |
Feature activation | -5.04e+00 |
Pos logit contributions | |
disl | +0.127 |
Cr | +0.090 |
Fro | +0.085 |
majesty | +0.082 |
icol | +0.080 |
Neg logit contributions | |
es | -0.113 |
again | -0.111 |
on | -0.108 |
le | -0.101 |
ing | -0.099 |
Token | took |
Token ID | 1718 |
Feature activation | -7.79e+00 |
Pos logit contributions | |
disl | +0.075 |
Cr | +0.054 |
Joey | +0.054 |
Fro | +0.052 |
Fre | +0.051 |
Neg logit contributions | |
es | -0.044 |
m | -0.041 |
ices | -0.040 |
again | -0.040 |
ymes | -0.039 |
Token | off |
Token ID | 572 |
Feature activation | -7.30e+00 |
Pos logit contributions | |
disl | +0.110 |
Cr | +0.079 |
Joey | +0.074 |
Fro | +0.073 |
Twe | +0.072 |
Neg logit contributions | |
es | -0.084 |
again | -0.078 |
on | -0.075 |
le | -0.074 |
m | -0.074 |
Token | twenty |
Token ID | 8208 |
Feature activation | -8.42e+00 |
Pos logit contributions | |
disl | +0.134 |
icol | +0.105 |
Cr | +0.100 |
majesty | +0.097 |
Twe | +0.094 |
Neg logit contributions | |
es | -0.086 |
again | -0.085 |
on | -0.084 |
m | -0.082 |
and | -0.076 |
Token | - |
Token ID | 12 |
Feature activation | -1.93e+01 |
Pos logit contributions | |
disl | +0.124 |
Cr | +0.085 |
majesty | +0.082 |
Fro | +0.082 |
Fre | +0.082 |
Neg logit contributions | |
es | -0.078 |
again | -0.075 |
on | -0.069 |
ing | -0.068 |
m | -0.068 |
Token | eight |
Token ID | 26022 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
disl | +0.311 |
Cr | +0.237 |
Joey | +0.227 |
Fro | +0.226 |
majesty | +0.222 |
Neg logit contributions | |
es | -0.169 |
again | -0.154 |
le | -0.148 |
on | -0.147 |
y | -0.145 |
Token | , |
Token ID | 11 |
Feature activation | -9.92e+00 |
Pos logit contributions | |
disl | +0.095 |
Cr | +0.070 |
Joey | +0.069 |
Fro | +0.068 |
J | +0.067 |
Neg logit contributions | |
es | -0.051 |
again | -0.048 |
le | -0.048 |
on | -0.046 |
m | -0.045 |
Token | twenty |
Token ID | 8208 |
Feature activation | -9.28e+00 |
Pos logit contributions | |
disl | +0.155 |
icol | +0.113 |
Cr | +0.113 |
majesty | +0.110 |
Fro | +0.107 |
Neg logit contributions | |
es | -0.090 |
again | -0.087 |
on | -0.085 |
m | -0.082 |
y | -0.077 |
Token | - |
Token ID | 12 |
Feature activation | -1.89e+01 |
Pos logit contributions | |
disl | +0.145 |
Cr | +0.101 |
majesty | +0.101 |
Fre | +0.101 |
Fro | +0.099 |
Neg logit contributions | |
es | -0.075 |
again | -0.074 |
on | -0.066 |
m | -0.066 |
ing | -0.065 |
Token | nine |
Token ID | 30888 |
Feature activation | -3.39e+00 |
Pos logit contributions | |
disl | +0.298 |
Cr | +0.224 |
Joey | +0.213 |
Fro | +0.212 |
majesty | +0.208 |
Neg logit contributions | |
es | -0.171 |
again | -0.157 |
on | -0.150 |
le | -0.149 |
m | -0.147 |
Token | , |
Token ID | 11 |
Feature activation | -9.42e+00 |
Pos logit contributions | |
disl | +0.055 |
Cr | +0.041 |
Joey | +0.040 |
Fro | +0.039 |
Twe | +0.039 |
Neg logit contributions | |
es | -0.027 |
again | -0.026 |
on | -0.024 |
ices | -0.024 |
ymes | -0.024 |
Token | thirty |
Token ID | 12277 |
Feature activation | -9.26e+00 |
Pos logit contributions | |
disl | +0.152 |
Cr | +0.110 |
majesty | +0.109 |
icol | +0.108 |
Fro | +0.108 |
Neg logit contributions | |
es | -0.081 |
again | -0.078 |
on | -0.078 |
m | -0.073 |
y | -0.069 |
Token | , |
Token ID | 11 |
Feature activation | -9.01e+00 |
Pos logit contributions | |
disl | +0.155 |
Cr | +0.113 |
majesty | +0.111 |
Joey | +0.110 |
Fro | +0.110 |
Neg logit contributions | |
es | -0.067 |
again | -0.066 |
on | -0.060 |
m | -0.058 |
ymes | -0.057 |
Token | thirty |
Token ID | 12277 |
Feature activation | -8.89e+00 |
Pos logit contributions | |
disl | +0.147 |
Cr | +0.106 |
Fro | +0.104 |
majesty | +0.104 |
icol | +0.104 |
Neg logit contributions | |
es | -0.078 |
on | -0.074 |
again | -0.074 |
m | -0.068 |
y | -0.065 |
Token | them |
Token ID | 606 |
Feature activation | -4.69e+00 |
Pos logit contributions | |
disl | +0.093 |
Cr | +0.065 |
Joey | +0.062 |
Fro | +0.061 |
Twe | +0.060 |
Neg logit contributions | |
es | -0.080 |
again | -0.075 |
on | -0.072 |
le | -0.072 |
y | -0.071 |
Token | and |
Token ID | 290 |
Feature activation | -9.25e+00 |
Pos logit contributions | |
disl | +0.076 |
Joey | +0.057 |
Cr | +0.057 |
pleasure | +0.056 |
Twe | +0.055 |
Neg logit contributions | |
es | -0.034 |
les | -0.032 |
ices | -0.031 |
le | -0.031 |
ymes | -0.030 |
Token | never |
Token ID | 1239 |
Feature activation | -7.84e+00 |
Pos logit contributions | |
disl | +0.123 |
Cr | +0.097 |
Fro | +0.091 |
icol | +0.090 |
Joey | +0.090 |
Neg logit contributions | |
again | -0.098 |
es | -0.097 |
on | -0.094 |
and | -0.083 |
m | -0.081 |
Token | threw |
Token ID | 9617 |
Feature activation | -7.13e+00 |
Pos logit contributions | |
disl | +0.106 |
Cr | +0.075 |
Joey | +0.070 |
Fro | +0.069 |
Twe | +0.068 |
Neg logit contributions | |
es | -0.090 |
again | -0.082 |
le | -0.080 |
on | -0.080 |
m | -0.079 |
Token | a |
Token ID | 257 |
Feature activation | -7.54e+00 |
Pos logit contributions | |
disl | +0.098 |
Cr | +0.071 |
Joey | +0.068 |
Twe | +0.067 |
Fro | +0.066 |
Neg logit contributions | |
es | -0.078 |
again | -0.070 |
m | -0.069 |
le | -0.068 |
y | -0.067 |
Token | tant |
Token ID | 24246 |
Feature activation | -1.87e+01 |
Pos logit contributions | |
disl | +0.107 |
Cr | +0.075 |
Fro | +0.074 |
Joey | +0.073 |
pleasure | +0.072 |
Neg logit contributions | |
es | -0.082 |
again | -0.069 |
ices | -0.068 |
le | -0.067 |
m | -0.066 |
Token | rum |
Token ID | 6582 |
Feature activation | -7.94e+00 |
Pos logit contributions | |
disl | +0.294 |
Cr | +0.218 |
Joey | +0.206 |
Fro | +0.204 |
Twe | +0.201 |
Neg logit contributions | |
es | -0.170 |
again | -0.159 |
on | -0.153 |
m | -0.148 |
le | -0.147 |
Token | again |
Token ID | 757 |
Feature activation | -6.16e+00 |
Pos logit contributions | |
disl | +0.147 |
Cr | +0.117 |
Joey | +0.116 |
Twe | +0.115 |
Fro | +0.111 |
Neg logit contributions | |
es | -0.038 |
le | -0.034 |
m | -0.032 |
ymes | -0.032 |
again | -0.031 |
Token | . |
Token ID | 13 |
Feature activation | -7.99e+00 |
Pos logit contributions | |
disl | +0.114 |
Joey | +0.087 |
Cr | +0.086 |
Twe | +0.085 |
Fro | +0.084 |
Neg logit contributions | |
es | -0.036 |
ymes | -0.032 |
le | -0.030 |
boards | -0.030 |
m | -0.030 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | -3.83e+00 |
Pos logit contributions | |
disl | +0.125 |
majesty | +0.092 |
talented | +0.089 |
chie | +0.089 |
Fre | +0.088 |
Neg logit contributions | |
again | -0.068 |
es | -0.064 |
Today | -0.058 |
m | -0.058 |
my | -0.056 |
Token | Once |
Token ID | 7454 |
Feature activation | -8.85e+00 |
Pos logit contributions | |
disl | +0.043 |
Cr | +0.030 |
Fro | +0.028 |
Joey | +0.028 |
Twe | +0.027 |
Neg logit contributions | |
es | -0.048 |
le | -0.046 |
again | -0.044 |
y | -0.044 |
ing | -0.043 |
Token | eddy |
Token ID | 21874 |
Feature activation | -8.90e+00 |
Pos logit contributions | |
disl | +0.239 |
Cr | +0.187 |
Joey | +0.178 |
Fro | +0.177 |
pleasure | +0.175 |
Neg logit contributions | |
es | -0.080 |
again | -0.070 |
y | -0.067 |
le | -0.065 |
on | -0.063 |
Token | bear |
Token ID | 6842 |
Feature activation | -4.63e+00 |
Pos logit contributions | |
disl | +0.154 |
Cr | +0.119 |
Joey | +0.114 |
Fro | +0.113 |
Twe | +0.112 |
Neg logit contributions | |
es | -0.066 |
again | -0.060 |
on | -0.056 |
m | -0.055 |
le | -0.055 |
Token | and |
Token ID | 290 |
Feature activation | -8.70e+00 |
Pos logit contributions | |
disl | +0.078 |
Cr | +0.059 |
Joey | +0.059 |
Twe | +0.058 |
Fro | +0.057 |
Neg logit contributions | |
es | -0.032 |
again | -0.030 |
ymes | -0.029 |
le | -0.029 |
m | -0.028 |
Token | watched |
Token ID | 7342 |
Feature activation | -8.86e+00 |
Pos logit contributions | |
disl | +0.134 |
Cr | +0.103 |
Fro | +0.096 |
Joey | +0.094 |
LL | +0.094 |
Neg logit contributions | |
es | -0.084 |
on | -0.078 |
again | -0.078 |
le | -0.068 |
y | -0.068 |
Token | in |
Token ID | 287 |
Feature activation | -7.07e+00 |
Pos logit contributions | |
disl | +0.131 |
Cr | +0.093 |
majesty | +0.088 |
Fro | +0.087 |
pleasure | +0.084 |
Neg logit contributions | |
es | -0.093 |
again | -0.092 |
on | -0.088 |
le | -0.085 |
ing | -0.080 |
Token | amaz |
Token ID | 40642 |
Feature activation | -1.87e+01 |
Pos logit contributions | |
disl | +0.089 |
Cr | +0.060 |
Joey | +0.057 |
Fro | +0.056 |
pleasure | +0.055 |
Neg logit contributions | |
es | -0.088 |
again | -0.079 |
le | -0.079 |
m | -0.078 |
y | -0.078 |
Token | ement |
Token ID | 972 |
Feature activation | -6.42e+00 |
Pos logit contributions | |
disl | +0.335 |
Cr | +0.258 |
Joey | +0.252 |
Twe | +0.247 |
pleasure | +0.243 |
Neg logit contributions | |
es | -0.123 |
on | -0.102 |
again | -0.102 |
m | -0.101 |
y | -0.098 |
Token | as |
Token ID | 355 |
Feature activation | -8.53e+00 |
Pos logit contributions | |
disl | +0.123 |
Cr | +0.097 |
Joey | +0.095 |
Fro | +0.093 |
Twe | +0.093 |
Neg logit contributions | |
es | -0.034 |
again | -0.028 |
m | -0.027 |
le | -0.026 |
on | -0.026 |
Token | it |
Token ID | 340 |
Feature activation | -4.87e+00 |
Pos logit contributions | |
disl | +0.115 |
Cr | +0.082 |
Fro | +0.075 |
Joey | +0.074 |
majesty | +0.073 |
Neg logit contributions | |
es | -0.099 |
again | -0.094 |
on | -0.091 |
le | -0.087 |
y | -0.086 |
Token | shrunk |
Token ID | 38900 |
Feature activation | -5.36e+00 |
Pos logit contributions | |
disl | +0.067 |
Cr | +0.048 |
Joey | +0.048 |
Madd | +0.048 |
Fro | +0.047 |
Neg logit contributions | |
es | -0.045 |
ices | -0.043 |
ymes | -0.043 |
m | -0.042 |
packs | -0.042 |
Token | an |
Token ID | 281 |
Feature activation | -9.07e+00 |
Pos logit contributions | |
disl | +0.093 |
Joey | +0.072 |
Cr | +0.071 |
Twe | +0.070 |
Fro | +0.069 |
Neg logit contributions | |
es | -0.037 |
m | -0.033 |
again | -0.031 |
on | -0.029 |
le | -0.029 |
Token | She |
Token ID | 1375 |
Feature activation | -5.07e+00 |
Pos logit contributions | |
disl | +0.080 |
Cr | +0.055 |
Fro | +0.051 |
Joey | +0.051 |
Twe | +0.050 |
Neg logit contributions | |
es | -0.095 |
le | -0.093 |
again | -0.089 |
m | -0.087 |
ymes | -0.087 |
Token | takes |
Token ID | 2753 |
Feature activation | -6.51e+00 |
Pos logit contributions | |
disl | +0.074 |
Cr | +0.054 |
Joey | +0.051 |
Fro | +0.050 |
majesty | +0.049 |
Neg logit contributions | |
es | -0.052 |
again | -0.048 |
on | -0.046 |
le | -0.046 |
m | -0.046 |
Token | out |
Token ID | 503 |
Feature activation | -4.95e+00 |
Pos logit contributions | |
disl | +0.094 |
Cr | +0.068 |
Joey | +0.065 |
Fro | +0.064 |
Twe | +0.063 |
Neg logit contributions | |
es | -0.068 |
again | -0.063 |
on | -0.061 |
le | -0.060 |
m | -0.060 |
Token | a |
Token ID | 257 |
Feature activation | -5.48e+00 |
Pos logit contributions | |
disl | +0.058 |
Cr | +0.039 |
Joey | +0.037 |
Fro | +0.036 |
Twe | +0.035 |
Neg logit contributions | |
es | -0.063 |
again | -0.060 |
le | -0.058 |
m | -0.058 |
y | -0.057 |
Token | magn |
Token ID | 7842 |
Feature activation | -3.41e+00 |
Pos logit contributions | |
disl | +0.076 |
Cr | +0.053 |
Joey | +0.052 |
pleasure | +0.051 |
Fro | +0.050 |
Neg logit contributions | |
es | -0.060 |
le | -0.053 |
again | -0.053 |
m | -0.052 |
y | -0.051 |
Token | ifying |
Token ID | 4035 |
Feature activation | -1.84e+01 |
Pos logit contributions | |
disl | +0.038 |
Cr | +0.029 |
Joey | +0.028 |
Fre | +0.028 |
J | +0.028 |
Neg logit contributions | |
es | -0.037 |
again | -0.036 |
m | -0.035 |
ices | -0.033 |
ymes | -0.033 |
Token | glass |
Token ID | 5405 |
Feature activation | -2.36e+00 |
Pos logit contributions | |
disl | +0.336 |
Majesty | +0.243 |
Jon | +0.239 |
majesty | +0.237 |
Joey | +0.237 |
Neg logit contributions | |
again | -0.145 |
on | -0.136 |
pieces | -0.115 |
y | -0.113 |
es | -0.112 |
Token | . |
Token ID | 13 |
Feature activation | -6.09e+00 |
Pos logit contributions | |
disl | +0.039 |
Cr | +0.030 |
Joey | +0.029 |
Fro | +0.029 |
Madd | +0.029 |
Neg logit contributions | |
es | -0.015 |
ices | -0.013 |
ymes | -0.013 |
m | -0.013 |
le | -0.013 |
Token | She |
Token ID | 1375 |
Feature activation | -4.65e+00 |
Pos logit contributions | |
disl | +0.074 |
Cr | +0.049 |
Joey | +0.046 |
Fro | +0.045 |
Twe | +0.044 |
Neg logit contributions | |
es | -0.078 |
again | -0.074 |
on | -0.071 |
le | -0.070 |
m | -0.070 |
Token | looks |
Token ID | 3073 |
Feature activation | -5.05e+00 |
Pos logit contributions | |
disl | +0.069 |
Cr | +0.051 |
Joey | +0.048 |
Fro | +0.048 |
Twe | +0.047 |
Neg logit contributions | |
es | -0.047 |
again | -0.043 |
on | -0.041 |
le | -0.041 |
m | -0.040 |
Token | at |
Token ID | 379 |
Feature activation | -6.26e+00 |
Pos logit contributions | |
disl | +0.092 |
Cr | +0.071 |
Fro | +0.068 |
Joey | +0.068 |
Twe | +0.067 |
Neg logit contributions | |
es | -0.035 |
again | -0.032 |
on | -0.031 |
le | -0.029 |
y | -0.028 |
Token | air |
Token ID | 1633 |
Feature activation | -1.78e+01 |
Pos logit contributions | |
es | +0.062 |
again | +0.058 |
on | +0.056 |
le | +0.054 |
m | +0.054 |
Neg logit contributions | |
disl | -0.071 |
Cr | -0.049 |
Fro | -0.046 |
majesty | -0.045 |
Joey | -0.045 |
Token | . |
Token ID | 13 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
disl | +0.346 |
Cr | +0.275 |
Joey | +0.269 |
Twe | +0.263 |
Fro | +0.263 |
Neg logit contributions | |
es | -0.092 |
again | -0.072 |
le | -0.067 |
m | -0.066 |
on | -0.063 |
Token | He |
Token ID | 679 |
Feature activation | -7.90e+00 |
Pos logit contributions | |
disl | +0.157 |
majesty | +0.104 |
Cr | +0.103 |
icol | +0.101 |
pleasure | +0.099 |
Neg logit contributions | |
es | -0.126 |
again | -0.122 |
on | -0.118 |
y | -0.110 |
m | -0.109 |
Token | watched |
Token ID | 7342 |
Feature activation | -9.61e+00 |
Pos logit contributions | |
disl | +0.128 |
Cr | +0.100 |
Joey | +0.094 |
pleasure | +0.092 |
Fro | +0.092 |
Neg logit contributions | |
es | -0.070 |
again | -0.066 |
on | -0.063 |
le | -0.061 |
y | -0.058 |
Token | with |
Token ID | 351 |
Feature activation | -9.28e+00 |
Pos logit contributions | |
disl | +0.134 |
Cr | +0.094 |
Fro | +0.087 |
Joey | +0.086 |
majesty | +0.086 |
Neg logit contributions | |
es | -0.107 |
again | -0.104 |
on | -0.099 |
le | -0.097 |
y | -0.094 |
Token | amaz |
Token ID | 40642 |
Feature activation | -1.81e+01 |
Pos logit contributions | |
disl | +0.129 |
Cr | +0.093 |
majesty | +0.085 |
Fro | +0.084 |
APP | +0.084 |
Neg logit contributions | |
again | -0.104 |
es | -0.101 |
on | -0.101 |
le | -0.092 |
y | -0.088 |
Token | ement |
Token ID | 972 |
Feature activation | -5.96e+00 |
Pos logit contributions | |
disl | +0.320 |
Cr | +0.247 |
Joey | +0.241 |
Twe | +0.234 |
pleasure | +0.231 |
Neg logit contributions | |
es | -0.122 |
m | -0.102 |
on | -0.102 |
again | -0.101 |
y | -0.099 |
Token | as |
Token ID | 355 |
Feature activation | -8.78e+00 |
Pos logit contributions | |
disl | +0.106 |
Cr | +0.082 |
Joey | +0.080 |
Fro | +0.078 |
Twe | +0.078 |
Neg logit contributions | |
es | -0.040 |
again | -0.035 |
m | -0.034 |
le | -0.033 |
ymes | -0.032 |
Token | the |
Token ID | 262 |
Feature activation | -8.61e+00 |
Pos logit contributions | |
disl | +0.116 |
Cr | +0.081 |
Fro | +0.075 |
Joey | +0.074 |
majesty | +0.073 |
Neg logit contributions | |
es | -0.103 |
again | -0.099 |
on | -0.096 |
le | -0.091 |
y | -0.090 |
Token | z |
Token ID | 1976 |
Feature activation | -8.79e+00 |
Pos logit contributions | |
disl | +0.124 |
Cr | +0.088 |
Joey | +0.086 |
pleasure | +0.084 |
majesty | +0.083 |
Neg logit contributions | |
es | -0.095 |
again | -0.081 |
y | -0.080 |
le | -0.079 |
ices | -0.077 |
Token | ig |
Token ID | 328 |
Feature activation | -5.54e+00 |
Pos logit contributions | |
disl | +0.163 |
Cr | +0.128 |
Joey | +0.123 |
Fro | +0.122 |
Twe | +0.121 |
Neg logit contributions | |
es | -0.057 |
again | -0.051 |
on | -0.047 |
le | -0.047 |
m | -0.045 |
Token | 't |
Token ID | 470 |
Feature activation | -7.49e+00 |
Pos logit contributions | |
disl | +0.140 |
majesty | +0.098 |
Cr | +0.097 |
Majesty | +0.096 |
pleasure | +0.095 |
Neg logit contributions | |
es | -0.101 |
on | -0.098 |
again | -0.096 |
m | -0.094 |
ing | -0.088 |
Token | touch |
Token ID | 3638 |
Feature activation | -6.75e+00 |
Pos logit contributions | |
disl | +0.098 |
Cr | +0.068 |
majesty | +0.064 |
Fro | +0.064 |
icol | +0.064 |
Neg logit contributions | |
again | -0.086 |
es | -0.085 |
on | -0.083 |
y | -0.081 |
le | -0.080 |
Token | the |
Token ID | 262 |
Feature activation | -8.53e+00 |
Pos logit contributions | |
disl | +0.082 |
Cr | +0.055 |
Joey | +0.051 |
Fro | +0.051 |
majesty | +0.050 |
Neg logit contributions | |
es | -0.087 |
again | -0.084 |
on | -0.081 |
le | -0.079 |
y | -0.079 |
Token | rh |
Token ID | 9529 |
Feature activation | -6.95e+00 |
Pos logit contributions | |
disl | +0.128 |
Cr | +0.093 |
Joey | +0.089 |
Fro | +0.089 |
Twe | +0.088 |
Neg logit contributions | |
es | -0.085 |
again | -0.076 |
le | -0.073 |
m | -0.072 |
on | -0.071 |
Token | in |
Token ID | 259 |
Feature activation | -5.56e+00 |
Pos logit contributions | |
disl | +0.110 |
Cr | +0.088 |
Twe | +0.085 |
Fro | +0.083 |
majesty | +0.081 |
Neg logit contributions | |
again | -0.041 |
es | -0.040 |
boards | -0.040 |
packs | -0.039 |
Today | -0.039 |
Token | oc |
Token ID | 420 |
Feature activation | -1.79e+01 |
Pos logit contributions | |
disl | +0.075 |
Cr | +0.055 |
Twe | +0.051 |
Joey | +0.051 |
Fro | +0.051 |
Neg logit contributions | |
es | -0.058 |
again | -0.053 |
ices | -0.052 |
ymes | -0.051 |
m | -0.051 |
Token | eros |
Token ID | 27498 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
disl | +0.211 |
Cr | +0.139 |
Joey | +0.130 |
Fro | +0.128 |
Twe | +0.123 |
Neg logit contributions | |
es | -0.236 |
again | -0.224 |
on | -0.214 |
le | -0.213 |
m | -0.212 |
Token | ! |
Token ID | 0 |
Feature activation | -9.14e+00 |
Pos logit contributions | |
disl | +0.039 |
Cr | +0.027 |
Joey | +0.026 |
Fro | +0.026 |
Twe | +0.026 |
Neg logit contributions | |
es | -0.032 |
ices | -0.030 |
m | -0.029 |
ymes | -0.029 |
again | -0.028 |
Token | It |
Token ID | 632 |
Feature activation | -6.21e+00 |
Pos logit contributions | |
disl | +0.107 |
majesty | +0.065 |
icol | +0.064 |
Cr | +0.063 |
Majesty | +0.062 |
Neg logit contributions | |
es | -0.119 |
again | -0.109 |
m | -0.106 |
on | -0.106 |
y | -0.103 |
Token | might |
Token ID | 1244 |
Feature activation | -8.86e+00 |
Pos logit contributions | |
disl | +0.109 |
Cr | +0.085 |
Joey | +0.082 |
pleasure | +0.081 |
Fro | +0.080 |
Neg logit contributions | |
es | -0.048 |
again | -0.044 |
on | -0.042 |
le | -0.041 |
y | -0.041 |
Token | bite |
Token ID | 13197 |
Feature activation | -6.30e+00 |
Pos logit contributions | |
disl | +0.144 |
icol | +0.116 |
Majesty | +0.114 |
majesty | +0.111 |
Cr | +0.110 |
Neg logit contributions | |
on | -0.077 |
again | -0.074 |
le | -0.065 |
and | -0.064 |
y | -0.064 |
Token | to |
Token ID | 284 |
Feature activation | -1.30e+01 |
Pos logit contributions | |
disl | +0.312 |
Cr | +0.236 |
icol | +0.225 |
majesty | +0.223 |
Fro | +0.221 |
Neg logit contributions | |
again | -0.160 |
on | -0.152 |
es | -0.149 |
y | -0.133 |
le | -0.132 |
Token | eat |
Token ID | 4483 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
disl | +0.188 |
Cr | +0.139 |
icol | +0.135 |
Fro | +0.130 |
majesty | +0.129 |
Neg logit contributions | |
again | -0.140 |
on | -0.130 |
es | -0.126 |
le | -0.122 |
and | -0.113 |
Token | the |
Token ID | 262 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
disl | +0.161 |
Cr | +0.115 |
Joey | +0.109 |
Fro | +0.107 |
Twe | +0.106 |
Neg logit contributions | |
es | -0.129 |
again | -0.119 |
on | -0.115 |
le | -0.114 |
m | -0.114 |
Token | y |
Token ID | 331 |
Feature activation | -1.57e+01 |
Pos logit contributions | |
disl | +0.168 |
Cr | +0.121 |
Joey | +0.115 |
Fro | +0.113 |
Twe | +0.112 |
Neg logit contributions | |
es | -0.128 |
again | -0.116 |
le | -0.111 |
on | -0.111 |
y | -0.110 |
Token | ummy |
Token ID | 13513 |
Feature activation | -1.16e+01 |
Pos logit contributions | |
disl | +0.184 |
Cr | +0.124 |
Joey | +0.123 |
Twe | +0.115 |
Fro | +0.113 |
Neg logit contributions | |
es | -0.207 |
on | -0.187 |
again | -0.187 |
m | -0.181 |
ymes | -0.179 |
Token | ins |
Token ID | 1035 |
Feature activation | -1.78e+01 |
Pos logit contributions | |
disl | +0.164 |
Joey | +0.117 |
Cr | +0.116 |
Twe | +0.110 |
Fro | +0.109 |
Neg logit contributions | |
es | -0.126 |
again | -0.109 |
m | -0.105 |
ices | -0.105 |
ymes | -0.105 |
Token | ides |
Token ID | 1460 |
Feature activation | -8.97e+00 |
Pos logit contributions | |
disl | +0.269 |
Cr | +0.200 |
Fro | +0.189 |
Joey | +0.186 |
Twe | +0.184 |
Neg logit contributions | |
es | -0.174 |
again | -0.161 |
le | -0.156 |
y | -0.153 |
m | -0.152 |
Token | . |
Token ID | 13 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
disl | +0.161 |
Joey | +0.127 |
Cr | +0.126 |
Twe | +0.121 |
Fro | +0.120 |
Neg logit contributions | |
es | -0.054 |
again | -0.045 |
le | -0.045 |
ymes | -0.044 |
m | -0.043 |
Token | From |
Token ID | 3574 |
Feature activation | -7.42e+00 |
Pos logit contributions | |
disl | +0.151 |
Cr | +0.098 |
majesty | +0.098 |
icol | +0.095 |
talented | +0.094 |
Neg logit contributions | |
es | -0.116 |
again | -0.113 |
on | -0.105 |
m | -0.102 |
y | -0.102 |
Token | that |
Token ID | 326 |
Feature activation | -7.50e+00 |
Pos logit contributions | |
disl | +0.123 |
Cr | +0.092 |
majesty | +0.089 |
Fro | +0.086 |
pleasure | +0.086 |
Neg logit contributions | |
again | -0.065 |
on | -0.063 |
es | -0.060 |
le | -0.056 |
y | -0.056 |
Token | day |
Token ID | 1110 |
Feature activation | -6.01e+00 |
Pos logit contributions | |
disl | +0.124 |
Cr | +0.094 |
Joey | +0.089 |
Fro | +0.089 |
Twe | +0.087 |
Neg logit contributions | |
es | -0.064 |
again | -0.058 |
on | -0.055 |
le | -0.054 |
m | -0.054 |
Token | !" |
Token ID | 2474 |
Feature activation | -2.45e+00 |
Pos logit contributions | |
disl | +0.013 |
Cr | +0.009 |
Joey | +0.009 |
Twe | +0.008 |
Fro | +0.008 |
Neg logit contributions | |
es | -0.010 |
again | -0.009 |
m | -0.009 |
le | -0.009 |
on | -0.008 |
Token | |
Token ID | 220 |
Feature activation | -4.74e+00 |
Pos logit contributions | |
disl | +0.032 |
Cr | +0.021 |
majesty | +0.021 |
Majesty | +0.020 |
Fro | +0.020 |
Neg logit contributions | |
es | -0.030 |
again | -0.029 |
on | -0.028 |
m | -0.027 |
ing | -0.026 |
Token |
|
Token ID | 198 |
Feature activation | -2.46e+00 |
Pos logit contributions | |
disl | +0.085 |
Cr | +0.063 |
icol | +0.062 |
majesty | +0.062 |
talented | +0.060 |
Neg logit contributions | |
es | -0.040 |
again | -0.037 |
on | -0.034 |
ing | -0.032 |
m | -0.030 |
Token |
|
Token ID | 198 |
Feature activation | -2.24e+00 |
Pos logit contributions | |
disl | +0.040 |
Cr | +0.029 |
majesty | +0.028 |
icol | +0.027 |
pleasure | +0.027 |
Neg logit contributions | |
es | -0.023 |
again | -0.022 |
on | -0.021 |
m | -0.020 |
ing | -0.019 |
Token | The |
Token ID | 464 |
Feature activation | -1.81e+00 |
Pos logit contributions | |
disl | +0.033 |
Cr | +0.024 |
Joey | +0.022 |
Fro | +0.022 |
majesty | +0.022 |
Neg logit contributions | |
es | -0.023 |
again | -0.022 |
on | -0.021 |
le | -0.020 |
m | -0.020 |
Token | person |
Token ID | 1048 |
Feature activation | +4.29e+00 |
Pos logit contributions | |
disl | +0.028 |
Cr | +0.020 |
Joey | +0.019 |
Fro | +0.019 |
Twe | +0.019 |
Neg logit contributions | |
es | -0.018 |
again | -0.017 |
on | -0.016 |
m | -0.016 |
le | -0.015 |
Token | sighed |
Token ID | 21893 |
Feature activation | +2.07e+00 |
Pos logit contributions | |
es | +0.046 |
ymes | +0.042 |
ices | +0.042 |
packs | +0.041 |
again | +0.041 |
Neg logit contributions | |
disl | -0.055 |
Cr | -0.041 |
Joey | -0.040 |
Fro | -0.039 |
Madd | -0.038 |
Token | , |
Token ID | 11 |
Feature activation | +6.48e-01 |
Pos logit contributions | |
es | +0.012 |
ymes | +0.010 |
ices | +0.009 |
m | +0.009 |
boards | +0.009 |
Neg logit contributions | |
disl | -0.038 |
Joey | -0.031 |
Cr | -0.031 |
Twe | -0.030 |
Fro | -0.029 |
Token | " |
Token ID | 366 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
es | +0.006 |
again | +0.006 |
on | +0.005 |
m | +0.005 |
y | +0.005 |
Neg logit contributions | |
disl | -0.010 |
Cr | -0.008 |
Fro | -0.007 |
majesty | -0.007 |
Joey | -0.007 |
Token | Well |
Token ID | 5779 |
Feature activation | -3.13e-01 |
Pos logit contributions | |
es | +0.004 |
again | +0.003 |
on | +0.003 |
le | +0.003 |
y | +0.003 |
Neg logit contributions | |
disl | -0.005 |
Cr | -0.004 |
Joey | -0.004 |
Fro | -0.004 |
Twe | -0.004 |
Token | , |
Token ID | 11 |
Feature activation | -9.25e-01 |
Pos logit contributions | |
disl | +0.006 |
Cr | +0.005 |
icol | +0.004 |
Fro | +0.004 |
Twe | +0.004 |
Neg logit contributions | |
es | -0.002 |
again | -0.002 |
on | -0.002 |
le | -0.002 |
m | -0.002 |
Token | . |
Token ID | 13 |
Feature activation | +3.46e+00 |
Pos logit contributions | |
ymes | +0.089 |
es | +0.085 |
le | +0.079 |
ices | +0.074 |
pr | +0.071 |
Neg logit contributions | |
disl | -0.170 |
Joey | -0.143 |
Cr | -0.142 |
Fro | -0.141 |
Twe | -0.140 |
Token | The |
Token ID | 383 |
Feature activation | +4.67e+00 |
Pos logit contributions | |
es | +0.051 |
again | +0.050 |
on | +0.050 |
m | +0.047 |
y | +0.047 |
Neg logit contributions | |
disl | -0.034 |
majesty | -0.019 |
Majesty | -0.019 |
Cr | -0.018 |
pleasure | -0.017 |
Token | man |
Token ID | 582 |
Feature activation | +9.56e+00 |
Pos logit contributions | |
es | +0.051 |
again | +0.046 |
le | +0.044 |
y | +0.043 |
on | +0.043 |
Neg logit contributions | |
disl | -0.069 |
Cr | -0.049 |
Joey | -0.046 |
Fro | -0.046 |
majesty | -0.045 |
Token | was |
Token ID | 373 |
Feature activation | +5.15e+00 |
Pos logit contributions | |
ices | +0.116 |
ymes | +0.113 |
es | +0.113 |
ities | +0.110 |
eness | +0.109 |
Neg logit contributions | |
disl | -0.105 |
Cr | -0.077 |
Joey | -0.075 |
Twe | -0.072 |
Fro | -0.070 |
Token | spraying |
Token ID | 40170 |
Feature activation | +8.78e+00 |
Pos logit contributions | |
on | +0.051 |
es | +0.042 |
m | +0.041 |
again | +0.040 |
y | +0.038 |
Neg logit contributions | |
disl | -0.088 |
icol | -0.062 |
majesty | -0.062 |
Majesty | -0.061 |
Cr | -0.061 |
Token | water |
Token ID | 1660 |
Feature activation | +1.06e+01 |
Pos logit contributions | |
es | +0.098 |
again | +0.089 |
le | +0.086 |
m | +0.085 |
y | +0.085 |
Neg logit contributions | |
disl | -0.121 |
Cr | -0.087 |
Joey | -0.083 |
Fro | -0.081 |
Twe | -0.080 |
Token | on |
Token ID | 319 |
Feature activation | +1.88e+00 |
Pos logit contributions | |
es | +0.067 |
ymes | +0.065 |
ices | +0.063 |
le | +0.058 |
ologist | +0.057 |
Neg logit contributions | |
disl | -0.174 |
Cr | -0.146 |
Fro | -0.145 |
Joey | -0.144 |
Twe | -0.141 |
Token | the |
Token ID | 262 |
Feature activation | +3.05e+00 |
Pos logit contributions | |
es | +0.026 |
again | +0.025 |
on | +0.024 |
le | +0.024 |
m | +0.024 |
Neg logit contributions | |
disl | -0.021 |
Cr | -0.013 |
Joey | -0.012 |
Fro | -0.012 |
Twe | -0.012 |
Token | flowers |
Token ID | 12734 |
Feature activation | +1.02e+01 |
Pos logit contributions | |
es | +0.031 |
again | +0.029 |
on | +0.028 |
le | +0.028 |
m | +0.027 |
Neg logit contributions | |
disl | -0.045 |
Cr | -0.033 |
Joey | -0.031 |
Fro | -0.031 |
Twe | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | +2.96e+00 |
Pos logit contributions | |
ymes | +0.079 |
es | +0.073 |
le | +0.070 |
ices | +0.069 |
pr | +0.067 |
Neg logit contributions | |
disl | -0.154 |
Joey | -0.123 |
Cr | -0.121 |
Fro | -0.120 |
J | -0.117 |
Token | Tim |
Token ID | 5045 |
Feature activation | +7.04e+00 |
Pos logit contributions | |
again | +0.038 |
es | +0.038 |
on | +0.038 |
boards | +0.036 |
and | +0.035 |
Neg logit contributions | |
disl | -0.033 |
majesty | -0.022 |
Majesty | -0.021 |
pleasure | -0.020 |
icol | -0.019 |
Token | ?" |
Token ID | 1701 |
Feature activation | +2.82e+00 |
Pos logit contributions | |
es | +0.049 |
again | +0.047 |
on | +0.046 |
le | +0.043 |
y | +0.043 |
Neg logit contributions | |
disl | -0.080 |
Cr | -0.058 |
Joey | -0.055 |
Fro | -0.055 |
majesty | -0.055 |
Token |
|
Token ID | 198 |
Feature activation | +2.67e+00 |
Pos logit contributions | |
es | +0.044 |
again | +0.041 |
le | +0.041 |
y | +0.041 |
m | +0.041 |
Neg logit contributions | |
disl | -0.027 |
Cr | -0.015 |
Joey | -0.014 |
Fro | -0.013 |
Twe | -0.013 |
Token |
|
Token ID | 198 |
Feature activation | +2.49e+00 |
Pos logit contributions | |
es | +0.027 |
again | +0.026 |
on | +0.025 |
m | +0.024 |
le | +0.024 |
Neg logit contributions | |
disl | -0.040 |
Cr | -0.029 |
majesty | -0.027 |
Joey | -0.027 |
Fro | -0.027 |
Token | The |
Token ID | 464 |
Feature activation | +4.36e+00 |
Pos logit contributions | |
es | +0.024 |
again | +0.022 |
m | +0.021 |
le | +0.021 |
on | +0.021 |
Neg logit contributions | |
disl | -0.038 |
Cr | -0.028 |
Joey | -0.026 |
Fro | -0.026 |
Twe | -0.026 |
Token | red |
Token ID | 2266 |
Feature activation | +6.30e+00 |
Pos logit contributions | |
es | +0.041 |
again | +0.038 |
on | +0.036 |
le | +0.036 |
m | +0.036 |
Neg logit contributions | |
disl | -0.068 |
Cr | -0.051 |
Joey | -0.048 |
Fro | -0.047 |
Twe | -0.047 |
Token | rose |
Token ID | 8278 |
Feature activation | +1.03e+01 |
Pos logit contributions | |
es | +0.067 |
again | +0.059 |
le | +0.057 |
m | +0.056 |
ices | +0.055 |
Neg logit contributions | |
disl | -0.088 |
Cr | -0.064 |
Fro | -0.062 |
Twe | -0.061 |
Joey | -0.059 |
Token | replied |
Token ID | 8712 |
Feature activation | +7.47e+00 |
Pos logit contributions | |
es | +0.112 |
again | +0.100 |
le | +0.099 |
ices | +0.099 |
m | +0.098 |
Neg logit contributions | |
disl | -0.142 |
Cr | -0.101 |
Joey | -0.096 |
Fro | -0.096 |
Twe | -0.095 |
Token | " |
Token ID | 366 |
Feature activation | +5.38e+00 |
Pos logit contributions | |
es | +0.058 |
again | +0.053 |
on | +0.050 |
le | +0.048 |
y | +0.047 |
Neg logit contributions | |
disl | -0.130 |
Cr | -0.099 |
Joey | -0.095 |
Fro | -0.094 |
majesty | -0.093 |
Token | I |
Token ID | 40 |
Feature activation | +5.23e+00 |
Pos logit contributions | |
es | +0.051 |
again | +0.047 |
on | +0.045 |
le | +0.044 |
m | +0.044 |
Neg logit contributions | |
disl | -0.083 |
Cr | -0.062 |
Joey | -0.059 |
Fro | -0.058 |
Twe | -0.057 |
Token | 'm |
Token ID | 1101 |
Feature activation | +3.82e+00 |
Pos logit contributions | |
on | +0.053 |
es | +0.052 |
y | +0.051 |
m | +0.051 |
again | +0.050 |
Neg logit contributions | |
disl | -0.073 |
Cr | -0.055 |
icol | -0.054 |
Majesty | -0.053 |
majesty | -0.053 |
Token | bouncing |
Token ID | 30713 |
Feature activation | +8.81e+00 |
Pos logit contributions | |
on | +0.036 |
again | +0.027 |
and | +0.026 |
in | +0.023 |
under | +0.023 |
Neg logit contributions | |
disl | -0.067 |
icol | -0.048 |
roc | -0.047 |
majesty | -0.046 |
rightful | -0.046 |
Token | explored |
Token ID | 18782 |
Feature activation | +3.94e+00 |
Pos logit contributions | |
es | +0.004 |
on | +0.004 |
again | +0.004 |
y | +0.004 |
m | +0.004 |
Neg logit contributions | |
disl | -0.009 |
Cr | -0.006 |
majesty | -0.006 |
pleasure | -0.006 |
Majesty | -0.006 |
Token | all |
Token ID | 477 |
Feature activation | +8.21e-02 |
Pos logit contributions | |
es | +0.054 |
again | +0.050 |
le | +0.049 |
m | +0.049 |
on | +0.048 |
Neg logit contributions | |
disl | -0.044 |
Cr | -0.029 |
Joey | -0.027 |
Fro | -0.026 |
Twe | -0.026 |
Token | the |
Token ID | 262 |
Feature activation | +1.40e+00 |
Pos logit contributions | |
es | +0.001 |
again | +0.001 |
on | +0.001 |
y | +0.001 |
m | +0.001 |
Neg logit contributions | |
disl | -0.001 |
Cr | -0.001 |
majesty | -0.001 |
Fro | -0.001 |
icol | -0.001 |
Token | slides |
Token ID | 19392 |
Feature activation | +7.27e+00 |
Pos logit contributions | |
es | +0.018 |
again | +0.016 |
ities | +0.015 |
ier | +0.015 |
le | +0.015 |
Neg logit contributions | |
disl | -0.017 |
Joey | -0.011 |
talented | -0.010 |
Fre | -0.010 |
Twe | -0.010 |
Token | and |
Token ID | 290 |
Feature activation | -5.85e-02 |
Pos logit contributions | |
es | +0.052 |
ymes | +0.051 |
Will | +0.048 |
le | +0.047 |
ices | +0.047 |
Neg logit contributions | |
disl | -0.109 |
Twe | -0.091 |
Joey | -0.089 |
Fro | -0.088 |
J | -0.087 |
Token | swings |
Token ID | 26728 |
Feature activation | +5.79e+00 |
Pos logit contributions | |
disl | +0.001 |
Cr | +0.001 |
Joey | +0.001 |
Fro | +0.001 |
majesty | +0.001 |
Neg logit contributions | |
es | -0.001 |
again | -0.001 |
on | -0.001 |
m | -0.001 |
le | -0.001 |
Token | . |
Token ID | 13 |
Feature activation | -2.86e-02 |
Pos logit contributions | |
ymes | +0.042 |
es | +0.041 |
ologist | +0.041 |
ices | +0.040 |
ities | +0.039 |
Neg logit contributions | |
disl | -0.084 |
Twe | -0.073 |
Fro | -0.071 |
Sandy | -0.070 |
Cr | -0.070 |
Token | Meanwhile |
Token ID | 11214 |
Feature activation | +2.95e+00 |
Pos logit contributions | |
disl | +0.000 |
Cr | +0.000 |
majesty | +0.000 |
Fro | +0.000 |
Twe | +0.000 |
Neg logit contributions | |
es | -0.000 |
again | -0.000 |
on | -0.000 |
m | -0.000 |
y | -0.000 |
Token | Dan |
Token ID | 6035 |
Feature activation | +5.04e+00 |
Pos logit contributions | |
es | +0.022 |
again | +0.020 |
on | +0.019 |
le | +0.019 |
m | +0.019 |
Neg logit contributions | |
disl | -0.051 |
Cr | -0.039 |
Joey | -0.038 |
Fro | -0.037 |
Twe | -0.037 |
Token | grabbed |
Token ID | 13176 |
Feature activation | +3.02e+00 |
Pos logit contributions | |
es | +0.047 |
again | +0.042 |
on | +0.041 |
ymes | +0.041 |
le | +0.041 |
Neg logit contributions | |
disl | -0.074 |
Cr | -0.054 |
Joey | -0.053 |
Fro | -0.053 |
J | -0.051 |
Token | a |
Token ID | 257 |
Feature activation | +3.98e+00 |
Pos logit contributions | |
es | +0.034 |
on | +0.033 |
again | +0.032 |
le | +0.030 |
y | +0.030 |
Neg logit contributions | |
disl | -0.043 |
Cr | -0.029 |
majesty | -0.028 |
Twe | -0.027 |
Joey | -0.027 |
Token | l |
Token ID | 75 |
Feature activation | +4.74e+00 |
Pos logit contributions | |
es | +0.039 |
again | +0.036 |
m | +0.035 |
on | +0.033 |
ices | +0.033 |
Neg logit contributions | |
disl | -0.071 |
Cr | -0.053 |
Twe | -0.051 |
Joey | -0.050 |
Fro | -0.050 |
Token | aces |
Token ID | 2114 |
Feature activation | +7.13e+00 |
Pos logit contributions | |
Will | +0.051 |
Today | +0.050 |
m | +0.044 |
tighter | +0.043 |
Did | +0.043 |
Neg logit contributions | |
disl | -0.051 |
Twe | -0.039 |
This | -0.038 |
The | -0.034 |
Cr | -0.033 |
Token | and |
Token ID | 290 |
Feature activation | -1.72e+00 |
Pos logit contributions | |
es | +0.051 |
ymes | +0.050 |
ices | +0.047 |
le | +0.045 |
ud | +0.045 |
Neg logit contributions | |
disl | -0.110 |
Cr | -0.085 |
Twe | -0.085 |
Joey | -0.084 |
J | -0.081 |
Token | pretty |
Token ID | 2495 |
Feature activation | +1.69e+00 |
Pos logit contributions | |
disl | +0.027 |
Cr | +0.020 |
Joey | +0.019 |
Twe | +0.018 |
Fro | +0.018 |
Neg logit contributions | |
es | -0.016 |
again | -0.015 |
le | -0.014 |
m | -0.014 |
y | -0.014 |
Token | ear |
Token ID | 1027 |
Feature activation | +3.35e+00 |
Pos logit contributions | |
es | +0.015 |
m | +0.015 |
ing | +0.014 |
ymes | +0.013 |
ices | +0.013 |
Neg logit contributions | |
disl | -0.025 |
Twe | -0.018 |
majesty | -0.018 |
Cr | -0.017 |
Majesty | -0.017 |
Token | rings |
Token ID | 33173 |
Feature activation | +7.18e+00 |
Pos logit contributions | |
es | +0.029 |
m | +0.028 |
ices | +0.028 |
ymes | +0.028 |
le | +0.028 |
Neg logit contributions | |
disl | -0.046 |
Twe | -0.035 |
Cr | -0.034 |
majesty | -0.033 |
J | -0.033 |
Token | . |
Token ID | 13 |
Feature activation | -6.61e-01 |
Pos logit contributions | |
ymes | +0.057 |
ices | +0.054 |
ud | +0.054 |
Today | +0.050 |
le | +0.050 |
Neg logit contributions | |
disl | -0.104 |
Twe | -0.078 |
This | -0.077 |
pleasure | -0.077 |
Cr | -0.075 |
Token | She |
Token ID | 1375 |
Feature activation | +1.08e+00 |
Pos logit contributions | |
disl | +0.008 |
Cr | +0.006 |
Joey | +0.005 |
Twe | +0.005 |
Fro | +0.005 |
Neg logit contributions | |
es | -0.008 |
again | -0.008 |
le | -0.007 |
on | -0.007 |
y | -0.007 |
Token | worked |
Token ID | 3111 |
Feature activation | +2.55e+00 |
Pos logit contributions | |
es | +0.011 |
ing | +0.010 |
again | +0.010 |
m | +0.010 |
ymes | +0.010 |
Neg logit contributions | |
disl | -0.015 |
Cr | -0.010 |
Twe | -0.010 |
Fro | -0.010 |
Joey | -0.010 |
Token | very |
Token ID | 845 |
Feature activation | -8.10e-01 |
Pos logit contributions | |
es | +0.029 |
le | +0.027 |
ices | +0.027 |
ymes | +0.027 |
m | +0.027 |
Neg logit contributions | |
disl | -0.028 |
Cr | -0.021 |
Joey | -0.020 |
Twe | -0.020 |
J | -0.019 |
Token | hard |
Token ID | 1327 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
disl | +0.011 |
Cr | +0.007 |
Twe | +0.007 |
talented | +0.007 |
Joey | +0.007 |
Neg logit contributions | |
es | -0.009 |
m | -0.008 |
berries | -0.008 |
packs | -0.008 |
ices | -0.008 |
Token | play |
Token ID | 711 |
Feature activation | +4.66e+00 |
Pos logit contributions | |
on | +0.009 |
again | +0.009 |
es | +0.009 |
and | +0.008 |
while | +0.008 |
Neg logit contributions | |
disl | -0.015 |
Cr | -0.011 |
icol | -0.010 |
LL | -0.010 |
APP | -0.010 |
Token | neat |
Token ID | 15049 |
Feature activation | +6.28e+00 |
Pos logit contributions | |
es | +0.034 |
packs | +0.032 |
m | +0.032 |
y | +0.032 |
ing | +0.030 |
Neg logit contributions | |
disl | -0.075 |
Cr | -0.059 |
Fro | -0.056 |
Twe | -0.055 |
Joey | -0.055 |
Token | games |
Token ID | 1830 |
Feature activation | +7.98e+00 |
Pos logit contributions | |
es | +0.041 |
m | +0.041 |
Today | +0.038 |
again | +0.037 |
pr | +0.036 |
Neg logit contributions | |
disl | -0.108 |
Cr | -0.080 |
Twe | -0.078 |
Fro | -0.077 |
Joey | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | +1.49e+00 |
Pos logit contributions | |
ymes | +0.073 |
eness | +0.069 |
ices | +0.069 |
els | +0.068 |
les | +0.066 |
Neg logit contributions | |
disl | -0.097 |
Cr | -0.074 |
Jill | -0.074 |
Av | -0.074 |
Fro | -0.073 |
Token | |
Token ID | 220 |
Feature activation | -6.31e-02 |
Pos logit contributions | |
es | +0.016 |
again | +0.015 |
on | +0.014 |
m | +0.014 |
y | +0.014 |
Neg logit contributions | |
disl | -0.021 |
Cr | -0.015 |
Joey | -0.014 |
Fro | -0.014 |
majesty | -0.014 |
Token |
|
Token ID | 198 |
Feature activation | +1.34e+00 |
Pos logit contributions | |
disl | +0.001 |
Cr | +0.001 |
Joey | +0.001 |
Fro | +0.001 |
majesty | +0.001 |
Neg logit contributions | |
es | -0.001 |
again | -0.001 |
on | -0.001 |
m | -0.001 |
le | -0.001 |
Token |
|
Token ID | 198 |
Feature activation | +1.15e+00 |
Pos logit contributions | |
es | +0.018 |
le | +0.016 |
again | +0.016 |
ymes | +0.016 |
les | +0.016 |
Neg logit contributions | |
disl | -0.014 |
Cr | -0.010 |
Joey | -0.009 |
Fro | -0.009 |
Twe | -0.009 |
Token | One |
Token ID | 3198 |
Feature activation | +4.09e+00 |
Pos logit contributions | |
es | +0.010 |
ier | +0.009 |
again | +0.009 |
le | +0.009 |
les | +0.008 |
Neg logit contributions | |
disl | -0.019 |
Cr | -0.014 |
Twe | -0.014 |
LL | -0.013 |
This | -0.013 |
Token | day |
Token ID | 1110 |
Feature activation | +4.32e+00 |
Pos logit contributions | |
es | +0.039 |
again | +0.036 |
on | +0.034 |
le | +0.034 |
m | +0.033 |
Neg logit contributions | |
disl | -0.063 |
Cr | -0.047 |
Joey | -0.045 |
Fro | -0.044 |
Twe | -0.043 |
Token | , |
Token ID | 11 |
Feature activation | +2.41e+00 |
Pos logit contributions | |
es | +0.038 |
again | +0.034 |
le | +0.033 |
ymes | +0.033 |
m | +0.032 |
Neg logit contributions | |
disl | -0.067 |
Cr | -0.052 |
Joey | -0.050 |
Twe | -0.050 |
Fro | -0.049 |
Token | the |
Token ID | 262 |
Feature activation | +2.34e+00 |
Pos logit contributions | |
es | +0.024 |
again | +0.023 |
on | +0.023 |
m | +0.021 |
y | +0.021 |
Neg logit contributions | |
disl | -0.036 |
Cr | -0.026 |
Joey | -0.025 |
majesty | -0.024 |
Fro | -0.024 |
Token | . |
Token ID | 13 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
es | +0.022 |
ymes | +0.019 |
packs | +0.018 |
ices | +0.018 |
m | +0.018 |
Neg logit contributions | |
disl | -0.042 |
Twe | -0.037 |
Joey | -0.036 |
Sus | -0.034 |
Cr | -0.034 |
Token | |
Token ID | 220 |
Feature activation | -2.98e+00 |
Pos logit contributions | |
disl | +0.023 |
majesty | +0.016 |
Cr | +0.016 |
icol | +0.016 |
Majesty | +0.015 |
Neg logit contributions | |
es | -0.013 |
again | -0.013 |
m | -0.012 |
on | -0.012 |
Today | -0.011 |
Token |
|
Token ID | 198 |
Feature activation | -1.62e+00 |
Pos logit contributions | |
disl | +0.051 |
Cr | +0.038 |
icol | +0.037 |
majesty | +0.036 |
Fro | +0.035 |
Neg logit contributions | |
es | -0.026 |
again | -0.024 |
on | -0.022 |
m | -0.022 |
ing | -0.020 |
Token |
|
Token ID | 198 |
Feature activation | -1.43e+00 |
Pos logit contributions | |
disl | +0.028 |
Cr | +0.021 |
icol | +0.020 |
majesty | +0.020 |
Majesty | +0.020 |
Neg logit contributions | |
es | -0.013 |
again | -0.012 |
on | -0.012 |
m | -0.012 |
Today | -0.011 |
Token | G |
Token ID | 38 |
Feature activation | -1.42e+00 |
Pos logit contributions | |
disl | +0.026 |
Cr | +0.020 |
Joey | +0.019 |
pleasure | +0.019 |
majesty | +0.019 |
Neg logit contributions | |
es | -0.010 |
again | -0.009 |
on | -0.009 |
le | -0.009 |
m | -0.009 |
Token | lor |
Token ID | 4685 |
Feature activation | +3.55e+00 |
Pos logit contributions | |
disl | +0.021 |
Cr | +0.016 |
Joey | +0.015 |
Fro | +0.015 |
Twe | +0.014 |
Neg logit contributions | |
es | -0.014 |
again | -0.013 |
y | -0.013 |
le | -0.013 |
m | -0.013 |
Token | ia |
Token ID | 544 |
Feature activation | +3.03e+00 |
Pos logit contributions | |
es | +0.035 |
again | +0.033 |
le | +0.030 |
y | +0.030 |
on | +0.030 |
Neg logit contributions | |
disl | -0.058 |
Cr | -0.044 |
Joey | -0.040 |
pleasure | -0.040 |
Twe | -0.039 |
Token | was |
Token ID | 373 |
Feature activation | +8.28e-01 |
Pos logit contributions | |
es | +0.027 |
again | +0.024 |
on | +0.023 |
m | +0.023 |
le | +0.023 |
Neg logit contributions | |
disl | -0.047 |
Cr | -0.035 |
Joey | -0.034 |
Fro | -0.034 |
Twe | -0.033 |
Token | very |
Token ID | 845 |
Feature activation | -2.47e+00 |
Pos logit contributions | |
on | +0.008 |
again | +0.008 |
es | +0.007 |
m | +0.007 |
and | +0.006 |
Neg logit contributions | |
disl | -0.014 |
Cr | -0.010 |
icol | -0.010 |
majesty | -0.010 |
Joey | -0.009 |
Token | sad |
Token ID | 6507 |
Feature activation | +2.81e+00 |
Pos logit contributions | |
disl | +0.041 |
icol | +0.034 |
Cr | +0.033 |
majesty | +0.030 |
APP | +0.030 |
Neg logit contributions | |
on | -0.021 |
again | -0.019 |
m | -0.018 |
and | -0.017 |
y | -0.017 |
Token | . |
Token ID | 13 |
Feature activation | -1.05e-01 |
Pos logit contributions | |
es | +0.022 |
ymes | +0.021 |
le | +0.018 |
ices | +0.018 |
m | +0.018 |
Neg logit contributions | |
disl | -0.045 |
Joey | -0.035 |
Cr | -0.034 |
Twe | -0.034 |
Fro | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -5.97e-01 |
Pos logit contributions | |
es | +0.007 |
again | +0.007 |
on | +0.006 |
le | +0.006 |
y | +0.006 |
Neg logit contributions | |
disl | -0.019 |
Cr | -0.015 |
Joey | -0.014 |
Fro | -0.014 |
majesty | -0.014 |
Token | I |
Token ID | 314 |
Feature activation | +2.58e+00 |
Pos logit contributions | |
disl | +0.008 |
icol | +0.005 |
Cr | +0.005 |
LL | +0.005 |
APP | +0.005 |
Neg logit contributions | |
again | -0.007 |
on | -0.007 |
es | -0.007 |
m | -0.006 |
and | -0.006 |
Token | have |
Token ID | 423 |
Feature activation | +1.29e+00 |
Pos logit contributions | |
es | +0.026 |
on | +0.025 |
m | +0.024 |
again | +0.024 |
y | +0.023 |
Neg logit contributions | |
disl | -0.039 |
Cr | -0.029 |
Joey | -0.028 |
majesty | -0.027 |
Twe | -0.027 |
Token | a |
Token ID | 257 |
Feature activation | +2.51e+00 |
Pos logit contributions | |
on | +0.012 |
again | +0.011 |
es | +0.010 |
pieces | +0.009 |
and | +0.009 |
Neg logit contributions | |
disl | -0.022 |
Cr | -0.016 |
Madd | -0.015 |
Joey | -0.015 |
APP | -0.015 |
Token | lime |
Token ID | 28738 |
Feature activation | +8.33e+00 |
Pos logit contributions | |
es | +0.021 |
again | +0.021 |
on | +0.021 |
m | +0.019 |
y | +0.019 |
Neg logit contributions | |
disl | -0.040 |
Cr | -0.031 |
Joey | -0.028 |
Twe | -0.028 |
Fro | -0.028 |
Token | !" |
Token ID | 2474 |
Feature activation | +3.48e-01 |
Pos logit contributions | |
es | +0.086 |
again | +0.079 |
le | +0.076 |
on | +0.075 |
m | +0.075 |
Neg logit contributions | |
disl | -0.119 |
Cr | -0.087 |
Joey | -0.082 |
Fro | -0.082 |
Twe | -0.080 |
Token | Tom |
Token ID | 4186 |
Feature activation | +4.93e+00 |
Pos logit contributions | |
on | +0.004 |
again | +0.003 |
es | +0.003 |
and | +0.003 |
while | +0.003 |
Neg logit contributions | |
disl | -0.005 |
Majesty | -0.004 |
majesty | -0.004 |
pleasure | -0.004 |
icol | -0.004 |
Token | said |
Token ID | 531 |
Feature activation | +5.06e+00 |
Pos logit contributions | |
es | +0.058 |
again | +0.054 |
le | +0.052 |
ymes | +0.052 |
on | +0.051 |
Neg logit contributions | |
disl | -0.062 |
Cr | -0.045 |
Fro | -0.043 |
Joey | -0.043 |
Twe | -0.041 |
Token | . |
Token ID | 13 |
Feature activation | +6.94e-01 |
Pos logit contributions | |
es | +0.026 |
again | +0.021 |
le | +0.020 |
m | +0.020 |
on | +0.019 |
Neg logit contributions | |
disl | -0.099 |
Cr | -0.080 |
Joey | -0.077 |
Fro | -0.076 |
Twe | -0.076 |
Token | He |
Token ID | 679 |
Feature activation | +4.39e+00 |
Pos logit contributions | |
es | +0.008 |
again | +0.007 |
on | +0.007 |
m | +0.007 |
y | +0.007 |
Neg logit contributions | |
disl | -0.010 |
Cr | -0.007 |
majesty | -0.006 |
Majesty | -0.006 |
Joey | -0.006 |
Token | took |
Token ID | 1718 |
Feature activation | +3.61e+00 |
Pos logit contributions | |
es | +0.041 |
again | +0.038 |
le | +0.036 |
on | +0.036 |
m | +0.035 |
Neg logit contributions | |
disl | -0.067 |
Cr | -0.050 |
Joey | -0.048 |
Fro | -0.048 |
Twe | -0.047 |
Token | writing |
Token ID | 3597 |
Feature activation | +2.06e+00 |
Pos logit contributions | |
disl | +0.009 |
Cr | +0.006 |
Joey | +0.006 |
J | +0.006 |
talented | +0.005 |
Neg logit contributions | |
es | -0.007 |
m | -0.006 |
le | -0.006 |
y | -0.006 |
again | -0.006 |
Token | adventures |
Token ID | 17545 |
Feature activation | +2.25e+00 |
Pos logit contributions | |
es | +0.013 |
m | +0.012 |
le | +0.011 |
again | +0.011 |
y | +0.011 |
Neg logit contributions | |
disl | -0.037 |
Cr | -0.028 |
Joey | -0.027 |
J | -0.027 |
Fro | -0.027 |
Token | together |
Token ID | 1978 |
Feature activation | +5.71e-01 |
Pos logit contributions | |
es | +0.013 |
m | +0.011 |
le | +0.011 |
ices | +0.011 |
again | +0.010 |
Neg logit contributions | |
disl | -0.041 |
Cr | -0.032 |
Joey | -0.031 |
Twe | -0.030 |
J | -0.030 |
Token | . |
Token ID | 13 |
Feature activation | -2.99e+00 |
Pos logit contributions | |
es | +0.004 |
m | +0.003 |
ymes | +0.003 |
le | +0.003 |
ices | +0.003 |
Neg logit contributions | |
disl | -0.010 |
Joey | -0.008 |
Cr | -0.008 |
J | -0.007 |
pleasure | -0.007 |
Token | <|endoftext|> |
Token ID | 50256 |
Feature activation | +2.36e+00 |
Pos logit contributions | |
disl | +0.045 |
majesty | +0.031 |
Cr | +0.030 |
Majesty | +0.029 |
Joey | +0.029 |
Neg logit contributions | |
es | -0.029 |
again | -0.029 |
on | -0.029 |
m | -0.027 |
Today | -0.026 |
Token | One |
Token ID | 3198 |
Feature activation | +1.85e-01 |
Pos logit contributions | |
es | +0.027 |
le | +0.027 |
ymes | +0.025 |
again | +0.025 |
pr | +0.025 |
Neg logit contributions | |
disl | -0.026 |
Cr | -0.020 |
Joey | -0.019 |
Fro | -0.019 |
J | -0.018 |
Token | day |
Token ID | 1110 |
Feature activation | +1.83e-01 |
Pos logit contributions | |
on | +0.001 |
again | +0.001 |
y | +0.001 |
m | +0.001 |
es | +0.001 |
Neg logit contributions | |
disl | -0.003 |
Cr | -0.003 |
icol | -0.003 |
majesty | -0.003 |
Twe | -0.003 |
Token | , |
Token ID | 11 |
Feature activation | -3.03e-01 |
Pos logit contributions | |
es | +0.001 |
on | +0.001 |
again | +0.001 |
y | +0.001 |
ing | +0.001 |
Neg logit contributions | |
disl | -0.004 |
Cr | -0.003 |
majesty | -0.003 |
pleasure | -0.003 |
Majesty | -0.003 |
Token | Little |
Token ID | 7703 |
Feature activation | +1.30e+00 |
Pos logit contributions | |
disl | +0.005 |
majesty | +0.004 |
Majesty | +0.004 |
Cr | +0.003 |
icol | +0.003 |
Neg logit contributions | |
on | -0.003 |
es | -0.003 |
y | -0.003 |
again | -0.003 |
m | -0.002 |
Token | Joe |
Token ID | 5689 |
Feature activation | +2.74e+00 |
Pos logit contributions | |
es | +0.019 |
again | +0.019 |
on | +0.019 |
m | +0.018 |
y | +0.018 |
Neg logit contributions | |
disl | -0.013 |
Cr | -0.008 |
majesty | -0.007 |
Fro | -0.006 |
Majesty | -0.006 |
Token | was |
Token ID | 373 |
Feature activation | +6.40e-01 |
Pos logit contributions | |
es | +0.018 |
again | +0.017 |
on | +0.016 |
y | +0.016 |
le | +0.015 |
Neg logit contributions | |
disl | -0.050 |
Cr | -0.040 |
Fro | -0.037 |
majesty | -0.037 |
pleasure | -0.037 |
Token | A |
Token ID | 317 |
Feature activation | -6.73e+00 |
Pos logit contributions | |
disl | +0.145 |
majesty | +0.098 |
Cr | +0.097 |
icol | +0.093 |
talented | +0.092 |
Neg logit contributions | |
es | -0.104 |
again | -0.101 |
on | -0.093 |
y | -0.090 |
m | -0.088 |
Token | few |
Token ID | 1178 |
Feature activation | -8.46e+00 |
Pos logit contributions | |
disl | +0.091 |
Cr | +0.065 |
Joey | +0.063 |
Fro | +0.062 |
pleasure | +0.060 |
Neg logit contributions | |
es | -0.076 |
again | -0.068 |
le | -0.068 |
m | -0.066 |
y | -0.065 |
Token | weeks |
Token ID | 2745 |
Feature activation | -5.87e+00 |
Pos logit contributions | |
disl | +0.132 |
Joey | +0.099 |
Cr | +0.095 |
majesty | +0.094 |
Madd | +0.093 |
Neg logit contributions | |
es | -0.062 |
m | -0.060 |
y | -0.058 |
again | -0.056 |
Today | -0.055 |
Token | later |
Token ID | 1568 |
Feature activation | -7.02e+00 |
Pos logit contributions | |
disl | +0.099 |
Cr | +0.078 |
Joey | +0.078 |
Twe | +0.075 |
Jon | +0.074 |
Neg logit contributions | |
es | -0.040 |
ymes | -0.037 |
again | -0.035 |
le | -0.035 |
y | -0.034 |
Token | , |
Token ID | 11 |
Feature activation | -6.82e+00 |
Pos logit contributions | |
disl | +0.119 |
Cr | +0.091 |
Joey | +0.087 |
Fro | +0.086 |
Twe | +0.085 |
Neg logit contributions | |
es | -0.056 |
again | -0.050 |
on | -0.048 |
le | -0.047 |
m | -0.047 |
Token | Adam |
Token ID | 7244 |
Feature activation | -3.99e+00 |
Pos logit contributions | |
disl | +0.092 |
Cr | +0.065 |
Joey | +0.061 |
Fro | +0.060 |
Twe | +0.059 |
Neg logit contributions | |
es | -0.078 |
again | -0.073 |
on | -0.071 |
le | -0.069 |
m | -0.069 |
Token | heard |
Token ID | 2982 |
Feature activation | -5.81e+00 |
Pos logit contributions | |
disl | +0.067 |
Cr | +0.051 |
Joey | +0.048 |
Fro | +0.048 |
Twe | +0.047 |
Neg logit contributions | |
es | -0.033 |
again | -0.030 |
on | -0.028 |
le | -0.028 |
m | -0.027 |
Token | about |
Token ID | 546 |
Feature activation | -6.59e+00 |
Pos logit contributions | |
disl | +0.077 |
Cr | +0.054 |
Joey | +0.050 |
Fro | +0.050 |
Twe | +0.049 |
Neg logit contributions | |
es | -0.068 |
again | -0.064 |
on | -0.061 |
le | -0.061 |
m | -0.060 |
Token | a |
Token ID | 257 |
Feature activation | -4.62e+00 |
Pos logit contributions | |
disl | +0.082 |
Cr | +0.056 |
Joey | +0.053 |
Fro | +0.051 |
Twe | +0.050 |
Neg logit contributions | |
es | -0.082 |
again | -0.075 |
le | -0.074 |
m | -0.074 |
y | -0.073 |
Token | new |
Token ID | 649 |
Feature activation | -5.06e+00 |
Pos logit contributions | |
disl | +0.057 |
Cr | +0.038 |
Joey | +0.037 |
Fro | +0.037 |
pleasure | +0.036 |
Neg logit contributions | |
es | -0.059 |
le | -0.053 |
again | -0.052 |
y | -0.051 |
m | -0.051 |
Token | doctor |
Token ID | 6253 |
Feature activation | +3.38e-01 |
Pos logit contributions | |
disl | +0.077 |
Cr | +0.056 |
Joey | +0.054 |
Fro | +0.053 |
Twe | +0.052 |
Neg logit contributions | |
es | -0.050 |
again | -0.044 |
m | -0.043 |
le | -0.043 |
on | -0.043 |
Token | was |
Token ID | 373 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
disl | +0.122 |
Cr | +0.091 |
Joey | +0.088 |
Twe | +0.086 |
Fro | +0.086 |
Neg logit contributions | |
es | -0.061 |
again | -0.055 |
m | -0.053 |
on | -0.052 |
le | -0.052 |
Token | healthy |
Token ID | 5448 |
Feature activation | -6.64e+00 |
Pos logit contributions | |
disl | +0.158 |
Cr | +0.118 |
Fro | +0.111 |
majesty | +0.107 |
Joey | +0.106 |
Neg logit contributions | |
again | -0.104 |
es | -0.103 |
on | -0.102 |
y | -0.092 |
m | -0.091 |
Token | again |
Token ID | 757 |
Feature activation | -7.84e+00 |
Pos logit contributions | |
disl | +0.114 |
Joey | +0.092 |
pleasure | +0.089 |
Cr | +0.087 |
Twe | +0.087 |
Neg logit contributions | |
es | -0.041 |
ymes | -0.037 |
ices | -0.034 |
pr | -0.033 |
le | -0.032 |
Token | . |
Token ID | 13 |
Feature activation | -9.75e+00 |
Pos logit contributions | |
disl | +0.153 |
Cr | +0.119 |
Joey | +0.118 |
Fro | +0.115 |
Twe | +0.115 |
Neg logit contributions | |
es | -0.041 |
le | -0.032 |
again | -0.031 |
m | -0.030 |
ymes | -0.030 |
Token | So |
Token ID | 1406 |
Feature activation | -8.76e+00 |
Pos logit contributions | |
disl | +0.143 |
majesty | +0.099 |
Cr | +0.095 |
icol | +0.094 |
Majesty | +0.092 |
Neg logit contributions | |
again | -0.097 |
es | -0.095 |
on | -0.085 |
y | -0.084 |
Today | -0.083 |
Token | , |
Token ID | 11 |
Feature activation | -8.74e+00 |
Pos logit contributions | |
disl | +0.145 |
Cr | +0.105 |
majesty | +0.100 |
Fro | +0.099 |
pleasure | +0.096 |
Neg logit contributions | |
es | -0.077 |
again | -0.076 |
on | -0.074 |
y | -0.066 |
le | -0.066 |
Token | the |
Token ID | 262 |
Feature activation | -9.27e+00 |
Pos logit contributions | |
disl | +0.121 |
Cr | +0.081 |
majesty | +0.078 |
Fro | +0.076 |
pleasure | +0.074 |
Neg logit contributions | |
es | -0.099 |
again | -0.097 |
on | -0.095 |
le | -0.088 |
y | -0.087 |
Token | little |
Token ID | 1310 |
Feature activation | -9.36e+00 |
Pos logit contributions | |
disl | +0.127 |
Cr | +0.090 |
Joey | +0.087 |
Twe | +0.084 |
pleasure | +0.084 |
Neg logit contributions | |
es | -0.108 |
again | -0.094 |
le | -0.093 |
y | -0.091 |
ices | -0.091 |
Token | girl |
Token ID | 2576 |
Feature activation | -4.18e+00 |
Pos logit contributions | |
disl | +0.159 |
Cr | +0.124 |
Joey | +0.121 |
Twe | +0.118 |
Fro | +0.117 |
Neg logit contributions | |
es | -0.075 |
again | -0.062 |
m | -0.059 |
le | -0.059 |
on | -0.059 |
Token | and |
Token ID | 290 |
Feature activation | -8.09e+00 |
Pos logit contributions | |
disl | +0.067 |
Cr | +0.051 |
Joey | +0.049 |
Fro | +0.049 |
Twe | +0.048 |
Neg logit contributions | |
es | -0.034 |
again | -0.031 |
m | -0.030 |
le | -0.030 |
on | -0.029 |
Token | her |
Token ID | 607 |
Feature activation | -6.65e+00 |
Pos logit contributions | |
disl | +0.107 |
Cr | +0.069 |
majesty | +0.068 |
icol | +0.066 |
pleasure | +0.065 |
Neg logit contributions | |
es | -0.099 |
again | -0.097 |
on | -0.095 |
y | -0.089 |
m | -0.086 |
Token | was |
Token ID | 373 |
Feature activation | -7.78e+00 |
Pos logit contributions | |
disl | +0.075 |
Cr | +0.057 |
Joey | +0.054 |
Fro | +0.053 |
Twe | +0.053 |
Neg logit contributions | |
es | -0.038 |
again | -0.035 |
on | -0.033 |
le | -0.032 |
m | -0.032 |
Token | surprised |
Token ID | 6655 |
Feature activation | -7.23e+00 |
Pos logit contributions | |
disl | +0.122 |
Cr | +0.089 |
majesty | +0.085 |
icol | +0.083 |
Joey | +0.080 |
Neg logit contributions | |
again | -0.079 |
on | -0.078 |
es | -0.075 |
m | -0.069 |
y | -0.065 |
Token | , |
Token ID | 11 |
Feature activation | -6.57e+00 |
Pos logit contributions | |
disl | +0.132 |
Cr | +0.104 |
Joey | +0.101 |
Fro | +0.099 |
Twe | +0.098 |
Neg logit contributions | |
es | -0.049 |
again | -0.039 |
on | -0.038 |
le | -0.038 |
m | -0.038 |
Token | but |
Token ID | 475 |
Feature activation | -7.94e+00 |
Pos logit contributions | |
disl | +0.129 |
majesty | +0.102 |
Cr | +0.102 |
Majesty | +0.098 |
Fro | +0.097 |
Neg logit contributions | |
again | -0.036 |
on | -0.034 |
es | -0.030 |
and | -0.028 |
m | -0.026 |
Token | asked |
Token ID | 1965 |
Feature activation | -5.65e+00 |
Pos logit contributions | |
disl | +0.124 |
Cr | +0.087 |
majesty | +0.086 |
icol | +0.083 |
pleasure | +0.082 |
Neg logit contributions | |
again | -0.079 |
es | -0.077 |
on | -0.077 |
m | -0.068 |
ing | -0.066 |
Token | the |
Token ID | 262 |
Feature activation | -8.80e+00 |
Pos logit contributions | |
disl | +0.073 |
Cr | +0.051 |
Joey | +0.047 |
Fro | +0.047 |
Twe | +0.046 |
Neg logit contributions | |
es | -0.068 |
again | -0.064 |
on | -0.062 |
le | -0.061 |
m | -0.061 |
Token | old |
Token ID | 1468 |
Feature activation | -9.35e+00 |
Pos logit contributions | |
disl | +0.133 |
Cr | +0.098 |
Joey | +0.094 |
Fro | +0.093 |
pleasure | +0.091 |
Neg logit contributions | |
es | -0.092 |
le | -0.077 |
again | -0.075 |
y | -0.075 |
on | -0.074 |
Token | man |
Token ID | 582 |
Feature activation | -2.89e+00 |
Pos logit contributions | |
disl | +0.154 |
Cr | +0.117 |
Fro | +0.110 |
majesty | +0.110 |
Joey | +0.110 |
Neg logit contributions | |
again | -0.076 |
es | -0.075 |
on | -0.069 |
m | -0.067 |
y | -0.067 |
Token | if |
Token ID | 611 |
Feature activation | -6.46e+00 |
Pos logit contributions | |
disl | +0.044 |
Cr | +0.033 |
Joey | +0.032 |
Fro | +0.031 |
Twe | +0.030 |
Neg logit contributions | |
es | -0.027 |
le | -0.023 |
ymes | -0.023 |
m | -0.023 |
again | -0.023 |
Token | he |
Token ID | 339 |
Feature activation | -4.81e+00 |
Pos logit contributions | |
disl | +0.102 |
majesty | +0.072 |
icol | +0.072 |
Cr | +0.071 |
pleasure | +0.070 |
Neg logit contributions | |
again | -0.060 |
es | -0.060 |
on | -0.059 |
ing | -0.052 |
m | -0.052 |
Token | was |
Token ID | 373 |
Feature activation | -6.48e+00 |
Pos logit contributions | |
disl | +0.068 |
Cr | +0.049 |
Joey | +0.049 |
Fro | +0.047 |
Twe | +0.047 |
Neg logit contributions | |
es | -0.047 |
ices | -0.043 |
again | -0.043 |
ymes | -0.043 |
ing | -0.043 |
Token | with |
Token ID | 351 |
Feature activation | -1.00e+01 |
Pos logit contributions | |
disl | +0.172 |
Cr | +0.136 |
Joey | +0.129 |
Fro | +0.128 |
Twe | +0.128 |
Neg logit contributions | |
es | -0.058 |
again | -0.048 |
m | -0.047 |
le | -0.046 |
y | -0.046 |
Token | it |
Token ID | 340 |
Feature activation | -5.57e+00 |
Pos logit contributions | |
disl | +0.119 |
Cr | +0.079 |
Fro | +0.074 |
Joey | +0.072 |
majesty | +0.071 |
Neg logit contributions | |
es | -0.132 |
again | -0.129 |
on | -0.124 |
le | -0.117 |
y | -0.115 |
Token | , |
Token ID | 11 |
Feature activation | -8.76e+00 |
Pos logit contributions | |
disl | +0.076 |
Twe | +0.060 |
Cr | +0.058 |
my | +0.057 |
your | +0.057 |
Neg logit contributions | |
es | -0.051 |
ices | -0.050 |
ymes | -0.047 |
m | -0.045 |
ities | -0.044 |
Token | but |
Token ID | 475 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
disl | +0.153 |
Cr | +0.117 |
Joey | +0.111 |
Fro | +0.111 |
majesty | +0.110 |
Neg logit contributions | |
es | -0.065 |
again | -0.063 |
on | -0.060 |
le | -0.054 |
y | -0.053 |
Token | we |
Token ID | 356 |
Feature activation | -7.84e+00 |
Pos logit contributions | |
disl | +0.132 |
icol | +0.085 |
Cr | +0.085 |
LL | +0.080 |
APP | +0.080 |
Neg logit contributions | |
again | -0.125 |
es | -0.123 |
on | -0.122 |
y | -0.108 |
m | -0.107 |
Token | can |
Token ID | 460 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
disl | +0.127 |
Cr | +0.097 |
icol | +0.096 |
majesty | +0.092 |
Fro | +0.092 |
Neg logit contributions | |
es | -0.066 |
again | -0.064 |
on | -0.063 |
le | -0.060 |
y | -0.059 |
Token | learn |
Token ID | 2193 |
Feature activation | -8.51e+00 |
Pos logit contributions | |
disl | +0.144 |
Cr | +0.104 |
Fro | +0.099 |
Joey | +0.097 |
icol | +0.097 |
Neg logit contributions | |
again | -0.107 |
es | -0.107 |
on | -0.100 |
le | -0.100 |
m | -0.096 |
Token | about |
Token ID | 546 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
disl | +0.123 |
Cr | +0.088 |
Twe | +0.084 |
Joey | +0.080 |
Fro | +0.079 |
Neg logit contributions | |
es | -0.085 |
m | -0.082 |
le | -0.079 |
y | -0.077 |
ices | -0.077 |
Token | it |
Token ID | 340 |
Feature activation | -4.45e+00 |
Pos logit contributions | |
disl | +0.118 |
Cr | +0.086 |
Fro | +0.082 |
Joey | +0.082 |
majesty | +0.078 |
Neg logit contributions | |
es | -0.088 |
again | -0.084 |
on | -0.079 |
le | -0.075 |
y | -0.074 |
Token | ," |
Token ID | 553 |
Feature activation | -8.66e+00 |
Pos logit contributions | |
disl | +0.067 |
Cr | +0.049 |
your | +0.049 |
my | +0.049 |
Twe | +0.049 |
Neg logit contributions | |
ices | -0.034 |
m | -0.033 |
ud | -0.032 |
ymes | -0.031 |
es | -0.030 |
Token | she |
Token ID | 673 |
Feature activation | -7.53e+00 |
Pos logit contributions | |
disl | +0.124 |
icol | +0.090 |
majesty | +0.089 |
pleasure | +0.087 |
Majesty | +0.085 |
Neg logit contributions | |
again | -0.091 |
es | -0.090 |
on | -0.086 |
m | -0.081 |
y | -0.078 |
Token | on |
Token ID | 319 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
disl | +0.071 |
Cr | +0.056 |
Joey | +0.055 |
Twe | +0.054 |
Fro | +0.053 |
Neg logit contributions | |
es | -0.021 |
again | -0.018 |
m | -0.018 |
ices | -0.017 |
ymes | -0.017 |
Token | it |
Token ID | 340 |
Feature activation | -6.68e+00 |
Pos logit contributions | |
disl | +0.134 |
Cr | +0.090 |
Fro | +0.083 |
majesty | +0.082 |
Joey | +0.080 |
Neg logit contributions | |
es | -0.138 |
again | -0.135 |
on | -0.131 |
le | -0.126 |
y | -0.125 |
Token | ! |
Token ID | 0 |
Feature activation | -9.47e+00 |
Pos logit contributions | |
disl | +0.127 |
Cr | +0.101 |
Joey | +0.099 |
Twe | +0.097 |
Fro | +0.096 |
Neg logit contributions | |
es | -0.035 |
m | -0.028 |
again | -0.028 |
le | -0.028 |
ymes | -0.027 |
Token | |
Token ID | 220 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
disl | +0.138 |
majesty | +0.093 |
Majesty | +0.088 |
icol | +0.087 |
Cr | +0.086 |
Neg logit contributions | |
es | -0.100 |
again | -0.097 |
on | -0.090 |
m | -0.084 |
Today | -0.083 |
Token |
|
Token ID | 198 |
Feature activation | -9.18e+00 |
Pos logit contributions | |
disl | +0.187 |
Cr | +0.141 |
icol | +0.139 |
majesty | +0.135 |
Majesty | +0.133 |
Neg logit contributions | |
es | -0.093 |
again | -0.079 |
on | -0.076 |
m | -0.072 |
ing | -0.071 |
Token |
|
Token ID | 198 |
Feature activation | -8.83e+00 |
Pos logit contributions | |
disl | +0.148 |
Cr | +0.108 |
majesty | +0.105 |
icol | +0.104 |
Majesty | +0.102 |
Neg logit contributions | |
es | -0.084 |
again | -0.078 |
m | -0.074 |
on | -0.073 |
Today | -0.069 |
Token | J |
Token ID | 41 |
Feature activation | -8.82e+00 |
Pos logit contributions | |
disl | +0.147 |
Cr | +0.111 |
majesty | +0.107 |
Joey | +0.105 |
icol | +0.105 |
Neg logit contributions | |
es | -0.073 |
again | -0.066 |
on | -0.062 |
m | -0.062 |
y | -0.060 |
Token | ill |
Token ID | 359 |
Feature activation | -5.20e+00 |
Pos logit contributions | |
disl | +0.152 |
Cr | +0.117 |
Joey | +0.112 |
Fro | +0.111 |
Twe | +0.110 |
Neg logit contributions | |
es | -0.068 |
again | -0.062 |
on | -0.058 |
y | -0.057 |
m | -0.057 |
Token | quickly |
Token ID | 2952 |
Feature activation | -5.39e+00 |
Pos logit contributions | |
disl | +0.084 |
Cr | +0.063 |
Joey | +0.061 |
Fro | +0.060 |
Twe | +0.059 |
Neg logit contributions | |
es | -0.044 |
again | -0.039 |
on | -0.038 |
m | -0.037 |
le | -0.037 |
Token | glued |
Token ID | 39783 |
Feature activation | -3.01e+00 |
Pos logit contributions | |
disl | +0.084 |
Cr | +0.062 |
Joey | +0.059 |
Fro | +0.058 |
Twe | +0.057 |
Neg logit contributions | |
es | -0.051 |
again | -0.047 |
on | -0.045 |
le | -0.044 |
y | -0.044 |
Token | the |
Token ID | 262 |
Feature activation | -6.53e+00 |
Pos logit contributions | |
disl | +0.033 |
Cr | +0.021 |
Joey | +0.019 |
Fro | +0.019 |
Twe | +0.019 |
Neg logit contributions | |
es | -0.042 |
again | -0.039 |
le | -0.038 |
m | -0.038 |
on | -0.038 |
Token | smiled |
Token ID | 13541 |
Feature activation | -7.27e+00 |
Pos logit contributions | |
disl | +0.061 |
Joey | +0.046 |
Cr | +0.044 |
J | +0.044 |
Fro | +0.044 |
Neg logit contributions | |
es | -0.044 |
ymes | -0.041 |
ices | -0.041 |
packs | -0.039 |
le | -0.039 |
Token | and |
Token ID | 290 |
Feature activation | -9.06e+00 |
Pos logit contributions | |
disl | +0.136 |
Cr | +0.110 |
Joey | +0.109 |
Twe | +0.106 |
Fro | +0.105 |
Neg logit contributions | |
es | -0.040 |
ymes | -0.031 |
ices | -0.031 |
m | -0.029 |
boards | -0.029 |
Token | said |
Token ID | 531 |
Feature activation | -6.13e+00 |
Pos logit contributions | |
disl | +0.159 |
Cr | +0.120 |
majesty | +0.116 |
Majesty | +0.113 |
Fro | +0.112 |
Neg logit contributions | |
es | -0.073 |
again | -0.071 |
on | -0.069 |
y | -0.057 |
ing | -0.057 |
Token | , |
Token ID | 11 |
Feature activation | -7.36e+00 |
Pos logit contributions | |
disl | +0.114 |
Cr | +0.089 |
Fro | +0.086 |
majesty | +0.085 |
Joey | +0.084 |
Neg logit contributions | |
es | -0.043 |
again | -0.041 |
on | -0.038 |
ing | -0.034 |
y | -0.032 |
Token | " |
Token ID | 366 |
Feature activation | -7.92e+00 |
Pos logit contributions | |
disl | +0.092 |
Cr | +0.062 |
Fro | +0.057 |
majesty | +0.057 |
Joey | +0.056 |
Neg logit contributions | |
es | -0.091 |
again | -0.089 |
on | -0.086 |
m | -0.082 |
y | -0.081 |
Token | Yes |
Token ID | 5297 |
Feature activation | -7.97e+00 |
Pos logit contributions | |
disl | +0.123 |
Cr | +0.091 |
majesty | +0.088 |
Fro | +0.087 |
Joey | +0.087 |
Neg logit contributions | |
es | -0.072 |
again | -0.069 |
m | -0.066 |
y | -0.065 |
on | -0.065 |
Token | , |
Token ID | 11 |
Feature activation | -8.84e+00 |
Pos logit contributions | |
disl | +0.150 |
Cr | +0.118 |
Fro | +0.112 |
Joey | +0.109 |
majesty | +0.108 |
Neg logit contributions | |
again | -0.051 |
es | -0.050 |
on | -0.045 |
le | -0.042 |
ing | -0.041 |
Token | it |
Token ID | 340 |
Feature activation | -5.47e+00 |
Pos logit contributions | |
disl | +0.115 |
Cr | +0.081 |
Fro | +0.075 |
Joey | +0.072 |
majesty | +0.071 |
Neg logit contributions | |
es | -0.103 |
again | -0.103 |
on | -0.099 |
le | -0.094 |
ing | -0.093 |
Token | is |
Token ID | 318 |
Feature activation | -7.50e+00 |
Pos logit contributions | |
disl | +0.083 |
Cr | +0.058 |
Joey | +0.057 |
majesty | +0.057 |
Fro | +0.055 |
Neg logit contributions | |
es | -0.050 |
again | -0.047 |
on | -0.045 |
m | -0.045 |
y | -0.044 |
Token | . |
Token ID | 13 |
Feature activation | -7.96e+00 |
Pos logit contributions | |
disl | +0.130 |
Cr | +0.102 |
Fro | +0.097 |
majesty | +0.093 |
Joey | +0.091 |
Neg logit contributions | |
es | -0.057 |
again | -0.057 |
on | -0.057 |
y | -0.050 |
le | -0.049 |
Token | Did |
Token ID | 7731 |
Feature activation | -8.33e+00 |
Pos logit contributions | |
disl | +0.103 |
Fro | +0.068 |
majesty | +0.066 |
Cr | +0.066 |
Majesty | +0.064 |
Neg logit contributions | |
es | -0.085 |
again | -0.080 |
on | -0.077 |
Will | -0.075 |
ing | -0.074 |
Token | that |
Token ID | 326 |
Feature activation | -8.98e+00 |
Pos logit contributions | |
disl | +0.167 |
Cr | +0.130 |
Fro | +0.124 |
Joey | +0.123 |
majesty | +0.122 |
Neg logit contributions | |
es | -0.067 |
again | -0.063 |
on | -0.059 |
y | -0.056 |
le | -0.055 |
Token | the |
Token ID | 262 |
Feature activation | -1.07e+01 |
Pos logit contributions | |
disl | +0.127 |
Cr | +0.090 |
majesty | +0.086 |
Fro | +0.086 |
icol | +0.083 |
Neg logit contributions | |
es | -0.097 |
again | -0.096 |
on | -0.092 |
m | -0.084 |
y | -0.084 |
Token | bad |
Token ID | 2089 |
Feature activation | -9.81e+00 |
Pos logit contributions | |
disl | +0.156 |
Cr | +0.114 |
Joey | +0.108 |
Fro | +0.107 |
Twe | +0.105 |
Neg logit contributions | |
es | -0.109 |
again | -0.100 |
on | -0.096 |
le | -0.095 |
m | -0.094 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.01e+01 |
Pos logit contributions | |
disl | +0.153 |
Cr | +0.116 |
Fro | +0.110 |
Joey | +0.108 |
Twe | +0.107 |
Neg logit contributions | |
es | -0.087 |
again | -0.085 |
on | -0.080 |
le | -0.077 |
y | -0.077 |
Token | in |
Token ID | 259 |
Feature activation | -8.44e+00 |
Pos logit contributions | |
disl | +0.177 |
Cr | +0.144 |
Twe | +0.136 |
Joey | +0.135 |
Fro | +0.134 |
Neg logit contributions | |
es | -0.054 |
again | -0.050 |
packs | -0.046 |
boards | -0.046 |
on | -0.045 |
Token | oc |
Token ID | 420 |
Feature activation | -1.96e+01 |
Pos logit contributions | |
disl | +0.130 |
Cr | +0.097 |
Joey | +0.092 |
Fro | +0.091 |
Twe | +0.090 |
Neg logit contributions | |
es | -0.079 |
again | -0.072 |
on | -0.069 |
le | -0.068 |
m | -0.067 |
Token | eros |
Token ID | 27498 |
Feature activation | -5.42e+00 |
Pos logit contributions | |
disl | +0.233 |
Cr | +0.155 |
Joey | +0.144 |
Fro | +0.142 |
Twe | +0.138 |
Neg logit contributions | |
es | -0.256 |
again | -0.242 |
on | -0.233 |
le | -0.231 |
m | -0.230 |
Token | was |
Token ID | 373 |
Feature activation | -9.62e+00 |
Pos logit contributions | |
disl | +0.085 |
Cr | +0.063 |
Joey | +0.061 |
Fro | +0.060 |
Twe | +0.059 |
Neg logit contributions | |
es | -0.048 |
again | -0.043 |
m | -0.041 |
le | -0.041 |
on | -0.041 |
Token | now |
Token ID | 783 |
Feature activation | -9.06e+00 |
Pos logit contributions | |
disl | +0.146 |
Cr | +0.107 |
icol | +0.103 |
majesty | +0.103 |
Fro | +0.102 |
Neg logit contributions | |
again | -0.100 |
on | -0.099 |
es | -0.090 |
m | -0.083 |
y | -0.080 |
Token | nice |
Token ID | 3621 |
Feature activation | -5.90e+00 |
Pos logit contributions | |
disl | +0.136 |
Cr | +0.102 |
Fro | +0.096 |
Joey | +0.094 |
majesty | +0.093 |
Neg logit contributions | |
es | -0.088 |
again | -0.085 |
on | -0.082 |
y | -0.077 |
m | -0.077 |
Token | . |
Token ID | 13 |
Feature activation | -8.76e+00 |
Pos logit contributions | |
disl | +0.106 |
Joey | +0.084 |
Cr | +0.083 |
Fro | +0.081 |
pleasure | +0.080 |
Neg logit contributions | |
es | -0.038 |
le | -0.032 |
ymes | -0.031 |
m | -0.030 |
ices | -0.029 |
Token | give |
Token ID | 1577 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
disl | +0.170 |
icol | +0.137 |
Cr | +0.133 |
pleasure | +0.124 |
majesty | +0.123 |
Neg logit contributions | |
again | -0.116 |
on | -0.114 |
le | -0.104 |
es | -0.104 |
and | -0.099 |
Token | to |
Token ID | 284 |
Feature activation | -9.64e+00 |
Pos logit contributions | |
disl | +0.151 |
Cr | +0.108 |
majesty | +0.103 |
Fro | +0.101 |
icol | +0.100 |
Neg logit contributions | |
es | -0.117 |
again | -0.115 |
on | -0.112 |
le | -0.106 |
y | -0.103 |
Token | the |
Token ID | 262 |
Feature activation | -1.11e+01 |
Pos logit contributions | |
disl | +0.130 |
icol | +0.103 |
LL | +0.101 |
Cr | +0.097 |
Fre | +0.093 |
Neg logit contributions | |
again | -0.099 |
es | -0.093 |
on | -0.091 |
and | -0.084 |
my | -0.081 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.09e+01 |
Pos logit contributions | |
disl | +0.171 |
Cr | +0.127 |
Joey | +0.121 |
Fro | +0.120 |
Twe | +0.119 |
Neg logit contributions | |
es | -0.105 |
again | -0.094 |
le | -0.091 |
on | -0.090 |
y | -0.089 |
Token | in |
Token ID | 259 |
Feature activation | -7.94e+00 |
Pos logit contributions | |
disl | +0.186 |
Cr | +0.151 |
Fro | +0.142 |
Twe | +0.140 |
majesty | +0.139 |
Neg logit contributions | |
es | -0.061 |
again | -0.056 |
on | -0.056 |
boards | -0.051 |
Today | -0.051 |
Token | oc |
Token ID | 420 |
Feature activation | -2.13e+01 |
Pos logit contributions | |
disl | +0.132 |
Cr | +0.099 |
Joey | +0.095 |
Fro | +0.093 |
majesty | +0.093 |
Neg logit contributions | |
es | -0.067 |
again | -0.063 |
on | -0.060 |
y | -0.057 |
le | -0.057 |
Token | eros |
Token ID | 27498 |
Feature activation | -6.56e+00 |
Pos logit contributions | |
disl | +0.249 |
Cr | +0.164 |
Joey | +0.153 |
Fro | +0.151 |
Twe | +0.146 |
Neg logit contributions | |
es | -0.281 |
again | -0.267 |
on | -0.255 |
le | -0.253 |
y | -0.251 |
Token | . |
Token ID | 13 |
Feature activation | -9.04e+00 |
Pos logit contributions | |
disl | +0.115 |
Cr | +0.089 |
Joey | +0.084 |
Fro | +0.084 |
majesty | +0.083 |
Neg logit contributions | |
es | -0.049 |
again | -0.045 |
on | -0.042 |
le | -0.040 |
y | -0.040 |
Token | Lily |
Token ID | 20037 |
Feature activation | -4.85e+00 |
Pos logit contributions | |
disl | +0.120 |
majesty | +0.078 |
Cr | +0.075 |
talented | +0.074 |
pleasure | +0.074 |
Neg logit contributions | |
es | -0.101 |
again | -0.098 |
on | -0.091 |
y | -0.087 |
m | -0.087 |
Token | walked |
Token ID | 6807 |
Feature activation | -4.41e+00 |
Pos logit contributions | |
disl | +0.087 |
Cr | +0.069 |
Joey | +0.065 |
pleasure | +0.064 |
Twe | +0.064 |
Neg logit contributions | |
es | -0.035 |
again | -0.032 |
on | -0.029 |
y | -0.028 |
le | -0.028 |
Token | to |
Token ID | 284 |
Feature activation | -7.65e+00 |
Pos logit contributions | |
disl | +0.062 |
Cr | +0.051 |
Joey | +0.050 |
Fro | +0.049 |
J | +0.047 |
Neg logit contributions | |
es | -0.042 |
ymes | -0.038 |
ities | -0.036 |
ices | -0.036 |
le | -0.036 |
Token | quiet |
Token ID | 5897 |
Feature activation | -1.60e+01 |
Pos logit contributions | |
es | +0.050 |
again | +0.049 |
on | +0.046 |
y | +0.044 |
le | +0.043 |
Neg logit contributions | |
disl | -0.106 |
Cr | -0.080 |
Joey | -0.075 |
Fro | -0.075 |
Twe | -0.074 |
Token | compared |
Token ID | 3688 |
Feature activation | -1.39e+01 |
Pos logit contributions | |
disl | +0.322 |
Cr | +0.257 |
Joey | +0.249 |
Fro | +0.247 |
Twe | +0.244 |
Neg logit contributions | |
es | -0.075 |
again | -0.062 |
on | -0.056 |
le | -0.055 |
m | -0.054 |
Token | to |
Token ID | 284 |
Feature activation | -1.12e+01 |
Pos logit contributions | |
disl | +0.205 |
Cr | +0.150 |
Joey | +0.142 |
Fro | +0.141 |
Twe | +0.138 |
Neg logit contributions | |
es | -0.139 |
again | -0.130 |
on | -0.124 |
le | -0.122 |
m | -0.121 |
Token | the |
Token ID | 262 |
Feature activation | -1.24e+01 |
Pos logit contributions | |
disl | +0.146 |
Cr | +0.108 |
Fro | +0.097 |
Joey | +0.096 |
Twe | +0.095 |
Neg logit contributions | |
es | -0.130 |
again | -0.126 |
on | -0.123 |
le | -0.117 |
y | -0.115 |
Token | noisy |
Token ID | 31210 |
Feature activation | -1.13e+01 |
Pos logit contributions | |
disl | +0.186 |
Cr | +0.134 |
Joey | +0.130 |
Fro | +0.127 |
majesty | +0.126 |
Neg logit contributions | |
es | -0.125 |
again | -0.111 |
le | -0.107 |
m | -0.106 |
y | -0.105 |
Token | se |
Token ID | 384 |
Feature activation | -1.99e+01 |
Pos logit contributions | |
disl | +0.180 |
Cr | +0.132 |
Joey | +0.128 |
Fro | +0.125 |
Twe | +0.124 |
Neg logit contributions | |
es | -0.104 |
again | -0.091 |
m | -0.088 |
le | -0.088 |
on | -0.087 |
Token | ag |
Token ID | 363 |
Feature activation | -1.17e+01 |
Pos logit contributions | |
disl | +0.329 |
Cr | +0.260 |
Joey | +0.252 |
Fro | +0.248 |
Twe | +0.246 |
Neg logit contributions | |
es | -0.160 |
le | -0.148 |
again | -0.145 |
y | -0.139 |
les | -0.137 |
Token | ull |
Token ID | 724 |
Feature activation | -4.67e+00 |
Pos logit contributions | |
disl | +0.190 |
Cr | +0.148 |
pleasure | +0.139 |
Twe | +0.138 |
icol | +0.138 |
Neg logit contributions | |
es | -0.106 |
y | -0.094 |
on | -0.093 |
again | -0.092 |
le | -0.089 |
Token | s |
Token ID | 82 |
Feature activation | -9.84e+00 |
Pos logit contributions | |
disl | +0.089 |
Cr | +0.069 |
Joey | +0.067 |
Fro | +0.067 |
Twe | +0.066 |
Neg logit contributions | |
es | -0.027 |
again | -0.023 |
on | -0.021 |
le | -0.021 |
m | -0.021 |
Token | outside |
Token ID | 2354 |
Feature activation | -8.91e+00 |
Pos logit contributions | |
disl | +0.175 |
Cr | +0.131 |
Joey | +0.130 |
pleasure | +0.129 |
majesty | +0.127 |
Neg logit contributions | |
es | -0.065 |
le | -0.057 |
m | -0.055 |
again | -0.053 |
ymes | -0.053 |
Token | . |
Token ID | 13 |
Feature activation | -1.02e+01 |
Pos logit contributions | |
disl | +0.168 |
Cr | +0.132 |
Joey | +0.129 |
Fro | +0.126 |
Twe | +0.126 |
Neg logit contributions | |
es | -0.052 |
again | -0.042 |
le | -0.041 |
m | -0.040 |
on | -0.038 |
Token | he |
Token ID | 339 |
Feature activation | -8.32e+00 |
Pos logit contributions | |
disl | +0.184 |
Cr | +0.134 |
Fro | +0.125 |
majesty | +0.124 |
Joey | +0.123 |
Neg logit contributions | |
es | -0.119 |
again | -0.114 |
on | -0.110 |
y | -0.104 |
le | -0.104 |
Token | would |
Token ID | 561 |
Feature activation | -9.38e+00 |
Pos logit contributions | |
disl | +0.141 |
Cr | +0.108 |
Joey | +0.103 |
Fro | +0.102 |
Twe | +0.101 |
Neg logit contributions | |
es | -0.066 |
again | -0.060 |
on | -0.056 |
le | -0.055 |
m | -0.055 |
Token | take |
Token ID | 1011 |
Feature activation | -8.43e+00 |
Pos logit contributions | |
disl | +0.127 |
Cr | +0.091 |
Fro | +0.084 |
Joey | +0.084 |
Twe | +0.082 |
Neg logit contributions | |
es | -0.106 |
again | -0.100 |
on | -0.097 |
le | -0.095 |
y | -0.093 |
Token | the |
Token ID | 262 |
Feature activation | -9.85e+00 |
Pos logit contributions | |
disl | +0.111 |
Cr | +0.077 |
Joey | +0.072 |
Fro | +0.071 |
Twe | +0.069 |
Neg logit contributions | |
es | -0.100 |
again | -0.094 |
on | -0.091 |
le | -0.089 |
m | -0.088 |
Token | av |
Token ID | 1196 |
Feature activation | -1.19e+01 |
Pos logit contributions | |
disl | +0.141 |
Cr | +0.103 |
Joey | +0.102 |
pleasure | +0.101 |
Fro | +0.098 |
Neg logit contributions | |
es | -0.107 |
again | -0.089 |
le | -0.087 |
m | -0.087 |
y | -0.086 |
Token | oc |
Token ID | 420 |
Feature activation | -2.14e+01 |
Pos logit contributions | |
disl | +0.169 |
Cr | +0.127 |
Joey | +0.119 |
Fro | +0.117 |
Twe | +0.117 |
Neg logit contributions | |
es | -0.117 |
again | -0.111 |
m | -0.104 |
on | -0.104 |
le | -0.102 |
Token | ados |
Token ID | 22484 |
Feature activation | -4.04e+00 |
Pos logit contributions | |
disl | +0.325 |
Cr | +0.240 |
Joey | +0.227 |
Fro | +0.227 |
Twe | +0.221 |
Neg logit contributions | |
es | -0.208 |
again | -0.192 |
on | -0.182 |
le | -0.180 |
y | -0.179 |
Token | and |
Token ID | 290 |
Feature activation | -9.13e+00 |
Pos logit contributions | |
disl | +0.057 |
Cr | +0.044 |
Joey | +0.044 |
Fro | +0.041 |
Twe | +0.041 |
Neg logit contributions | |
es | -0.038 |
le | -0.034 |
ymes | -0.034 |
m | -0.033 |
ices | -0.033 |
Token | scatter |
Token ID | 41058 |
Feature activation | -6.61e+00 |
Pos logit contributions | |
disl | +0.136 |
Cr | +0.100 |
Fro | +0.096 |
Joey | +0.092 |
majesty | +0.092 |
Neg logit contributions | |
es | -0.091 |
again | -0.086 |
on | -0.084 |
y | -0.077 |
le | -0.077 |
Token | them |
Token ID | 606 |
Feature activation | -5.69e+00 |
Pos logit contributions | |
disl | +0.093 |
Cr | +0.069 |
Joey | +0.066 |
Twe | +0.063 |
Fro | +0.063 |
Neg logit contributions | |
es | -0.070 |
again | -0.064 |
m | -0.062 |
le | -0.061 |
on | -0.060 |
Token | around |
Token ID | 1088 |
Feature activation | -8.31e+00 |
Pos logit contributions | |
disl | +0.093 |
Joey | +0.073 |
Cr | +0.072 |
Twe | +0.069 |
Fro | +0.068 |
Neg logit contributions | |
es | -0.040 |
m | -0.037 |
ices | -0.036 |
ymes | -0.036 |
le | -0.035 |
Token | am |
Token ID | 716 |
Feature activation | -1.03e+01 |
Pos logit contributions | |
disl | +0.147 |
Cr | +0.112 |
Joey | +0.105 |
Fro | +0.104 |
majesty | +0.103 |
Neg logit contributions | |
es | -0.083 |
again | -0.083 |
on | -0.079 |
le | -0.077 |
m | -0.076 |
Token | taking |
Token ID | 2263 |
Feature activation | -1.05e+01 |
Pos logit contributions | |
disl | +0.152 |
icol | +0.115 |
Cr | +0.109 |
Fro | +0.099 |
Joey | +0.098 |
Neg logit contributions | |
on | -0.114 |
again | -0.106 |
es | -0.099 |
and | -0.090 |
. | -0.089 |
Token | the |
Token ID | 262 |
Feature activation | -1.10e+01 |
Pos logit contributions | |
disl | +0.139 |
Cr | +0.097 |
Joey | +0.090 |
Fro | +0.090 |
majesty | +0.087 |
Neg logit contributions | |
es | -0.125 |
again | -0.119 |
on | -0.117 |
le | -0.112 |
y | -0.108 |
Token | rh |
Token ID | 9529 |
Feature activation | -1.08e+01 |
Pos logit contributions | |
disl | +0.158 |
Cr | +0.115 |
Joey | +0.111 |
Fro | +0.109 |
Twe | +0.108 |
Neg logit contributions | |
es | -0.117 |
again | -0.103 |
le | -0.099 |
m | -0.098 |
y | -0.097 |
Token | in |
Token ID | 259 |
Feature activation | -8.88e+00 |
Pos logit contributions | |
disl | +0.186 |
Cr | +0.152 |
Twe | +0.144 |
Fro | +0.144 |
Joey | +0.142 |
Neg logit contributions | |
es | -0.061 |
again | -0.057 |
on | -0.051 |
boards | -0.050 |
Today | -0.049 |
Token | oc |
Token ID | 420 |
Feature activation | -2.19e+01 |
Pos logit contributions | |
disl | +0.130 |
Cr | +0.097 |
Joey | +0.091 |
Fro | +0.090 |
Twe | +0.090 |
Neg logit contributions | |
es | -0.089 |
again | -0.080 |
le | -0.077 |
m | -0.076 |
on | -0.076 |
Token | eros |
Token ID | 27498 |
Feature activation | -6.73e+00 |
Pos logit contributions | |
disl | +0.258 |
Cr | +0.170 |
Joey | +0.158 |
Fro | +0.156 |
Twe | +0.150 |
Neg logit contributions | |
es | -0.287 |
again | -0.273 |
on | -0.261 |
le | -0.259 |
y | -0.258 |
Token | to |
Token ID | 284 |
Feature activation | -1.06e+01 |
Pos logit contributions | |
disl | +0.110 |
Cr | +0.083 |
Joey | +0.079 |
Fro | +0.078 |
Twe | +0.077 |
Neg logit contributions | |
es | -0.057 |
again | -0.052 |
on | -0.049 |
le | -0.049 |
m | -0.048 |
Token | a |
Token ID | 257 |
Feature activation | -8.28e+00 |
Pos logit contributions | |
disl | +0.150 |
icol | +0.108 |
Cr | +0.102 |
Madd | +0.099 |
APP | +0.099 |
Neg logit contributions | |
again | -0.111 |
on | -0.106 |
es | -0.100 |
and | -0.093 |
later | -0.090 |
Token | new |
Token ID | 649 |
Feature activation | -8.96e+00 |
Pos logit contributions | |
disl | +0.116 |
Cr | +0.083 |
Joey | +0.078 |
Fro | +0.077 |
majesty | +0.075 |
Neg logit contributions | |
es | -0.088 |
again | -0.086 |
on | -0.082 |
le | -0.079 |
y | -0.079 |
Token | home |
Token ID | 1363 |
Feature activation | -6.03e+00 |
Pos logit contributions | |
disl | +0.134 |
Cr | +0.099 |
Joey | +0.094 |
Fro | +0.092 |
Twe | +0.091 |
Neg logit contributions | |
es | -0.089 |
again | -0.082 |
on | -0.078 |
le | -0.078 |
m | -0.077 |