TOP ACTIVATIONS
MAX = 0.545

a political dial ogue .
. There is undeniable arist ocratic leaning in Nietzsche
hell he would ever paraph rase that back to ownership ,"
going to have to paraph rase here that the reason
t capture how hor rid the patient s
Acceler ator Mass Spect rom etry ( AMS ) tests of
service from 2017 . Nom inal service life is 25 years
Soul ful , Trans cend ental , Kn ows value of
salt trucks because the grid lock was too thick to navigate
ple tes glucose and glyc ogen rapidly , forcing the body
to use cannabis . Ed ibles , vapor izers
live far away . Gam ers from all over the country
that holds a " nom inal interest " in White Marsh
while everyone was in grid lock , they couldn
the til ap ia fil lets are the same exact size
rac etr ack bass driver ,
: 14 games over Gam ers 2 and Titan , adding
terms ; for James Fraz er , all of myth
traditionally the realm of metaph ysics or the transcend ent ,
urga on , Far id abad and other districts of H

MIN ACTIVATIONS
MIN = -0.537

linked to Obama 's chair manship of the Chicago Ann enberg
Gay Away ser mons , the man who once
the Department of Education recons iders the guidance provided to schools
in the agreement . Analy sts that have followed the process
u will lose her chair manship . Throughout the campaign ,
Balk an countries . Analy sts say supplies could in theory
group . Analy sts said the rupture was due
counterparts . Analy sts say that the Kremlin
as He sed uced her through abduction .
and his genius for sales manship to convince NASA to marry
the allegations . Mc Donald 's did not comment
Restaurant manager apolog ises to homophobic customers
Post reading " ISIS Ur ges Jihad ists To Attack Canadians
(* mark locations as Sear ched *) Table [ index State
but the AI January analy zes your actions at length ,
F ED state ) accompl ishes all of these , very
of the company 's enroll ments allegedly involved overriding a system
will receive the income uncond itionally while others will have conditions
No major out bur sts marked the SB 6 hearing
h iked in rain fore sts , in deserts , and

INTERVAL 0.274 - 0.545
CONTAINS 0.032%

ple tes glucose and glyc ogen rapidly , forcing the body
receiver with an internal fer rite rod antenna and start moving
summer s euph oria has vanished . So far
The one kilomet re to go mark was the
in court on the inter lock violation on May 26 .

INTERVAL 0.004 - 0.274
CONTAINS 45.650%

, something Ro eth lis berger definitely has at his disposal
is wrong , and they lack the lead - in character
Virginia undergrad who served 18 months behind bars in the her
but would keep riding aggressively . The legs are
were left struggling to f athom the origin of their daughter

INTERVAL -0.267 - 0.004
CONTAINS 54.285%

3 s )} 52 . Q xf 7 + { (
Film ography [ edit ] Al bum [ edit
. It also makes it mandatory for all operators
blur the boundary lines between sovereign Israel and the settlements in
have been MS F 's statement a month ago that they

INTERVAL -0.537 - -0.267
CONTAINS 0.032%

S pen cer said that ads pretending to
tele metry channel that inexpl icably switched into an unsc hed
u will lose her chair manship . Throughout the campaign ,
un earth a few barg ains along the way .
2000 spears , 300 arm ours and 500 shields , were
Token a
Token ID257
Feature activation+2.02e-02

Pos logit contributions
utonium+0.070
puter+0.065
APH+0.058
awei+0.057
izoph+0.056
Neg logit contributions
xual-0.064
blank-0.064
 relativity-0.063
 Ples-0.062
manship-0.062
Token political
Token ID1964
Feature activation+3.67e-02

Pos logit contributions
utonium+0.062
puter+0.058
APH+0.052
awei+0.051
ritten+0.050
Neg logit contributions
xual-0.050
blank-0.049
 relativity-0.049
manship-0.048
 Ples-0.048
Token
Token ID564
Feature activation+6.69e-02

Pos logit contributions
utonium+0.119
puter+0.112
APH+0.101
awei+0.100
ritten+0.099
Neg logit contributions
xual-0.085
blank-0.083
 relativity-0.082
 Ples-0.080
manship-0.080
Token
Token ID246
Feature activation+6.76e-03

Pos logit contributions
utonium+0.168
puter+0.156
awei+0.133
APH+0.133
ritten+0.130
Neg logit contributions
xual-0.205
 relativity-0.203
blank-0.201
 Ples-0.199
manship-0.198
Tokendial
Token ID38969
Feature activation-6.00e-02

Pos logit contributions
utonium+0.021
puter+0.020
APH+0.018
awei+0.017
ritten+0.017
Neg logit contributions
 relativity-0.017
xual-0.017
 Ples-0.016
blank-0.016
 Lovecraft-0.016
Tokenogue
Token ID5119
Feature activation+5.45e-01

Pos logit contributions
xual+0.209
 relativity+0.208
blank+0.206
 Ples+0.204
manship+0.203
Neg logit contributions
utonium-0.126
puter-0.116
awei-0.095
APH-0.095
ordable-0.092
Token
Token ID447
Feature activation+3.10e-02

Pos logit contributions
utonium+1.659
puter+1.579
APH+1.405
awei+1.370
ordable+1.356
Neg logit contributions
xual-1.325
blank-1.316
 relativity-1.311
 Ples-1.277
 Lovecraft-1.260
Token
Token ID247
Feature activation+3.16e-02

Pos logit contributions
utonium+0.073
puter+0.066
awei+0.056
APH+0.056
ritten+0.055
Neg logit contributions
xual-0.100
 relativity-0.100
blank-0.099
 Ples-0.098
manship-0.097
Token.
Token ID13
Feature activation+2.08e-02

Pos logit contributions
utonium+0.098
puter+0.093
APH+0.083
awei+0.082
ritten+0.081
Neg logit contributions
xual-0.077
 relativity-0.076
blank-0.075
 Ples-0.073
manship-0.073
Token
Token ID198
Feature activation+2.31e-02

Pos logit contributions
utonium+0.066
puter+0.061
APH+0.056
awei+0.054
izoph+0.053
Neg logit contributions
xual-0.050
 relativity-0.049
blank-0.049
manship-0.047
 Ples-0.046
Token
Token ID198
Feature activation+2.62e-02

Pos logit contributions
utonium+0.078
puter+0.074
awei+0.066
APH+0.066
izoph+0.065
Neg logit contributions
xual-0.051
blank-0.050
 relativity-0.050
manship-0.049
 Ples-0.049
Token.
Token ID13
Feature activation+4.15e-02

Pos logit contributions
utonium+0.089
puter+0.084
awei+0.075
APH+0.075
izoph+0.073
Neg logit contributions
xual-0.065
 relativity-0.064
blank-0.064
manship-0.062
 Ples-0.062
Token There
Token ID1318
Feature activation-3.66e-02

Pos logit contributions
utonium+0.134
puter+0.126
APH+0.114
awei+0.112
izoph+0.110
Neg logit contributions
xual-0.098
 relativity-0.096
blank-0.095
manship-0.092
 Ples-0.091
Token is
Token ID318
Feature activation+2.02e-02

Pos logit contributions
xual+0.086
 relativity+0.085
blank+0.084
 Ples+0.082
manship+0.081
Neg logit contributions
utonium-0.118
puter-0.110
awei-0.099
APH-0.098
ritten-0.097
Token undeniable
Token ID36332
Feature activation+1.02e-01

Pos logit contributions
utonium+0.057
puter+0.053
APH+0.046
awei+0.046
ritten+0.046
Neg logit contributions
xual-0.055
blank-0.055
 relativity-0.054
 Ples-0.054
manship-0.053
Token arist
Token ID28631
Feature activation+4.35e-02

Pos logit contributions
utonium+0.323
puter+0.302
APH+0.273
awei+0.272
ritten+0.270
Neg logit contributions
xual-0.240
blank-0.237
 relativity-0.231
 Ples-0.228
manship-0.226
Tokenocratic
Token ID15405
Feature activation+5.26e-01

Pos logit contributions
utonium+0.120
puter+0.110
APH+0.096
awei+0.096
ritten+0.095
Neg logit contributions
xual-0.123
 relativity-0.122
blank-0.121
 Ples-0.119
manship-0.118
Token leaning
Token ID21804
Feature activation+7.64e-02

Pos logit contributions
utonium+1.671
puter+1.562
APH+1.422
awei+1.417
ritten+1.392
Neg logit contributions
xual-1.232
blank-1.212
 Ples-1.173
 relativity-1.168
manship-1.136
Token in
Token ID287
Feature activation-3.90e-02

Pos logit contributions
utonium+0.233
puter+0.219
APH+0.195
awei+0.195
ritten+0.191
Neg logit contributions
xual-0.190
blank-0.188
 relativity-0.187
 Ples-0.182
manship-0.178
Token Nietzsche
Token ID40258
Feature activation+8.05e-03

Pos logit contributions
xual+0.089
blank+0.087
 relativity+0.086
manship+0.084
 Ples+0.083
Neg logit contributions
utonium-0.128
puter-0.121
APH-0.109
awei-0.108
ritten-0.106
Token
Token ID447
Feature activation-1.30e-03

Pos logit contributions
utonium+0.030
puter+0.028
APH+0.026
awei+0.025
ritten+0.025
Neg logit contributions
xual-0.015
 relativity-0.015
blank-0.015
 Ples-0.014
manship-0.014
Token
Token ID247
Feature activation+1.56e-02

Pos logit contributions
xual+0.005
 relativity+0.005
blank+0.005
manship+0.005
 Ples+0.005
Neg logit contributions
utonium-0.002
puter-0.002
awei-0.002
APH-0.002
izoph-0.002
Token hell
Token ID5968
Feature activation+3.14e-02

Pos logit contributions
utonium+0.047
puter+0.044
awei+0.039
APH+0.039
ritten+0.039
Neg logit contributions
xual-0.033
 relativity-0.032
blank-0.032
manship-0.031
 Ples-0.031
Token he
Token ID339
Feature activation+2.44e-02

Pos logit contributions
utonium+0.096
puter+0.090
awei+0.080
APH+0.079
ordable+0.078
Neg logit contributions
xual-0.079
 relativity-0.077
blank-0.077
 Ples-0.075
manship-0.075
Token would
Token ID561
Feature activation+1.97e-02

Pos logit contributions
utonium+0.079
puter+0.074
awei+0.066
APH+0.066
ritten+0.065
Neg logit contributions
xual-0.057
 relativity-0.056
blank-0.056
 Ples-0.054
manship-0.054
Token ever
Token ID1683
Feature activation-6.39e-02

Pos logit contributions
utonium+0.061
puter+0.058
awei+0.051
APH+0.051
ritten+0.050
Neg logit contributions
xual-0.048
 relativity-0.048
blank-0.047
 Ples-0.046
manship-0.046
Token paraph
Token ID38624
Feature activation-2.10e-02

Pos logit contributions
xual+0.156
 relativity+0.154
blank+0.152
 Ples+0.149
manship+0.149
Neg logit contributions
utonium-0.200
puter-0.189
awei-0.167
APH-0.166
ritten-0.164
Tokenrase
Token ID22789
Feature activation+4.83e-01

Pos logit contributions
xual+0.079
 relativity+0.078
blank+0.078
manship+0.077
 Ples+0.077
Neg logit contributions
utonium-0.039
puter-0.034
awei-0.028
APH-0.027
izoph-0.026
Token that
Token ID326
Feature activation+1.49e-02

Pos logit contributions
utonium+1.390
puter+1.310
APH+1.148
awei+1.145
ritten+1.140
Neg logit contributions
xual-1.267
blank-1.214
 relativity-1.208
 Ples-1.198
manship-1.192
Token back
Token ID736
Feature activation+1.66e-02

Pos logit contributions
utonium+0.048
puter+0.046
APH+0.041
awei+0.041
izoph+0.040
Neg logit contributions
xual-0.034
 relativity-0.033
blank-0.033
manship-0.033
 Ples-0.032
Token to
Token ID284
Feature activation-4.91e-02

Pos logit contributions
utonium+0.049
puter+0.046
APH+0.041
awei+0.040
ritten+0.040
Neg logit contributions
xual-0.044
 relativity-0.043
blank-0.042
 Ples-0.041
manship-0.041
Token ownership
Token ID9238
Feature activation-1.02e-02

Pos logit contributions
xual+0.127
 relativity+0.124
blank+0.123
manship+0.121
 Ples+0.120
Neg logit contributions
utonium-0.147
puter-0.138
awei-0.122
APH-0.121
ritten-0.119
Token,"
Token ID553
Feature activation-4.87e-02

Pos logit contributions
xual+0.024
 relativity+0.023
blank+0.023
 Ples+0.023
manship+0.023
Neg logit contributions
utonium-0.033
puter-0.031
APH-0.027
awei-0.027
ritten-0.027
Token going
Token ID1016
Feature activation-3.87e-02

Pos logit contributions
utonium+0.153
puter+0.144
awei+0.127
APH+0.127
ordable+0.124
Neg logit contributions
xual-0.117
 relativity-0.114
blank-0.113
manship-0.110
 Ples-0.110
Token to
Token ID284
Feature activation-1.41e-03

Pos logit contributions
xual+0.096
 relativity+0.095
blank+0.094
manship+0.093
 Ples+0.091
Neg logit contributions
utonium-0.120
puter-0.113
APH-0.100
awei-0.100
ritten-0.098
Token have
Token ID423
Feature activation-6.12e-03

Pos logit contributions
xual+0.004
 relativity+0.003
blank+0.003
manship+0.003
 Ples+0.003
Neg logit contributions
utonium-0.004
puter-0.004
APH-0.004
awei-0.004
ritten-0.004
Token to
Token ID284
Feature activation+1.63e-02

Pos logit contributions
xual+0.016
 relativity+0.015
blank+0.015
manship+0.015
 Ples+0.015
Neg logit contributions
utonium-0.018
puter-0.017
APH-0.015
awei-0.015
ordable-0.015
Token paraph
Token ID38624
Feature activation-2.52e-02

Pos logit contributions
utonium+0.050
puter+0.047
awei+0.042
APH+0.042
izoph+0.041
Neg logit contributions
xual-0.040
 relativity-0.040
blank-0.039
manship-0.038
 Ples-0.038
Tokenrase
Token ID22789
Feature activation+4.75e-01

Pos logit contributions
xual+0.094
 relativity+0.093
blank+0.093
manship+0.092
 Ples+0.091
Neg logit contributions
utonium-0.046
puter-0.042
awei-0.033
APH-0.033
izoph-0.032
Token here
Token ID994
Feature activation+1.53e-03

Pos logit contributions
utonium+1.400
puter+1.305
APH+1.168
awei+1.151
ritten+1.142
Neg logit contributions
xual-1.224
 relativity-1.176
blank-1.175
manship-1.151
 Ples-1.142
Token
Token ID851
Feature activation+4.64e-03

Pos logit contributions
utonium+0.005
puter+0.005
APH+0.004
awei+0.004
ritten+0.004
Neg logit contributions
xual-0.004
 relativity-0.003
blank-0.003
 Ples-0.003
manship-0.003
Token that
Token ID326
Feature activation-3.74e-03

Pos logit contributions
utonium+0.014
puter+0.013
APH+0.011
awei+0.011
ordable+0.011
Neg logit contributions
xual-0.012
 relativity-0.012
blank-0.012
manship-0.012
 Ples-0.012
Token the
Token ID262
Feature activation+3.60e-02

Pos logit contributions
xual+0.010
blank+0.010
 relativity+0.010
manship+0.009
 Ples+0.009
Neg logit contributions
utonium-0.011
puter-0.010
APH-0.009
awei-0.009
izoph-0.009
Token reason
Token ID1738
Feature activation-6.89e-02

Pos logit contributions
utonium+0.111
puter+0.103
APH+0.092
awei+0.091
izoph+0.090
Neg logit contributions
xual-0.091
 relativity-0.088
blank-0.088
manship-0.087
 Ples-0.085
Token
Token ID247
Feature activation-2.42e-02

Pos logit contributions
xual+0.079
 relativity+0.079
blank+0.078
manship+0.077
 Ples+0.077
Neg logit contributions
utonium-0.045
puter-0.041
awei-0.034
APH-0.034
izoph-0.032
Tokent
Token ID83
Feature activation-3.94e-02

Pos logit contributions
 relativity+0.051
xual+0.051
blank+0.050
manship+0.049
 Ples+0.049
Neg logit contributions
utonium-0.083
puter-0.078
APH-0.070
awei-0.070
ordable-0.070
Token capture
Token ID8006
Feature activation-4.29e-02

Pos logit contributions
xual+0.096
blank+0.093
 relativity+0.093
 Ples+0.091
manship+0.091
Neg logit contributions
utonium-0.123
puter-0.115
APH-0.103
awei-0.103
ordable-0.101
Token how
Token ID703
Feature activation+4.85e-02

Pos logit contributions
xual+0.112
 relativity+0.110
blank+0.109
manship+0.107
 Ples+0.107
Neg logit contributions
utonium-0.127
puter-0.119
APH-0.106
awei-0.105
ordable-0.103
Token hor
Token ID3076
Feature activation-4.56e-02

Pos logit contributions
utonium+0.148
puter+0.138
APH+0.123
awei+0.123
izoph+0.120
Neg logit contributions
xual-0.123
 relativity-0.120
blank-0.120
manship-0.117
 Ples-0.117
Tokenrid
Token ID6058
Feature activation+4.54e-01

Pos logit contributions
xual+0.151
 relativity+0.150
blank+0.147
manship+0.146
 Ples+0.145
Neg logit contributions
utonium-0.104
puter-0.095
APH-0.081
awei-0.081
izoph-0.079
Token the
Token ID262
Feature activation-4.19e-03

Pos logit contributions
utonium+1.304
puter+1.211
APH+1.078
awei+1.059
ordable+1.050
Neg logit contributions
xual-1.224
 relativity-1.187
blank-1.184
manship-1.152
 Ples-1.152
Token patient
Token ID5827
Feature activation+4.80e-02

Pos logit contributions
xual+0.011
 relativity+0.010
blank+0.010
manship+0.010
 Ples+0.010
Neg logit contributions
utonium-0.013
puter-0.012
APH-0.011
awei-0.011
izoph-0.011
Token
Token ID447
Feature activation+6.44e-04

Pos logit contributions
utonium+0.159
puter+0.150
APH+0.135
awei+0.134
ritten+0.132
Neg logit contributions
xual-0.109
 relativity-0.107
blank-0.106
manship-0.103
 Ples-0.102
Token
Token ID247
Feature activation-3.92e-03

Pos logit contributions
utonium+0.001
puter+0.001
awei+0.001
APH+0.001
izoph+0.001
Neg logit contributions
xual-0.003
 relativity-0.003
blank-0.002
manship-0.002
 Ples-0.002
Tokens
Token ID82
Feature activation+6.08e-03

Pos logit contributions
xual+0.007
 relativity+0.007
blank+0.007
manship+0.006
 Ples+0.006
Neg logit contributions
utonium-0.015
puter-0.014
awei-0.013
APH-0.013
ritten-0.013
Token Acceler
Token ID29805
Feature activation-3.86e-02

Pos logit contributions
xual+0.095
blank+0.093
 relativity+0.092
 Ples+0.089
manship+0.088
Neg logit contributions
utonium-0.119
puter-0.111
APH-0.100
awei-0.099
ritten-0.097
Tokenator
Token ID1352
Feature activation-3.68e-03

Pos logit contributions
xual+0.100
 relativity+0.098
blank+0.096
 Ples+0.094
manship+0.094
Neg logit contributions
utonium-0.118
puter-0.110
APH-0.098
awei-0.097
ritten-0.095
Token Mass
Token ID5674
Feature activation-1.30e-01

Pos logit contributions
xual+0.009
 relativity+0.009
blank+0.009
manship+0.009
 Ples+0.009
Neg logit contributions
utonium-0.011
puter-0.011
APH-0.009
awei-0.009
ritten-0.009
Token Spect
Token ID13058
Feature activation+9.74e-02

Pos logit contributions
xual+0.339
blank+0.327
 relativity+0.325
manship+0.318
 Ples+0.314
Neg logit contributions
utonium-0.388
puter-0.365
APH-0.322
awei-0.319
ritten-0.311
Tokenrom
Token ID398
Feature activation-5.64e-02

Pos logit contributions
utonium+0.209
puter+0.189
APH+0.160
awei+0.159
ordable+0.155
Neg logit contributions
xual-0.338
 relativity-0.333
blank-0.330
manship-0.323
 Ples-0.321
Tokenetry
Token ID11973
Feature activation+4.47e-01

Pos logit contributions
xual+0.133
 relativity+0.131
blank+0.129
manship+0.127
 Ples+0.126
Neg logit contributions
utonium-0.183
puter-0.172
APH-0.154
awei-0.154
ordable-0.152
Token (
Token ID357
Feature activation-1.57e-02

Pos logit contributions
utonium+1.395
puter+1.302
APH+1.172
awei+1.157
ordable+1.129
Neg logit contributions
xual-1.103
blank-1.063
 relativity-1.039
manship-1.023
 Lovecraft-1.013
TokenAMS
Token ID40834
Feature activation-1.30e-02

Pos logit contributions
xual+0.045
 relativity+0.044
blank+0.044
 Ples+0.043
manship+0.043
Neg logit contributions
utonium-0.043
puter-0.039
APH-0.035
awei-0.034
ordable-0.033
Token)
Token ID8
Feature activation+1.83e-02

Pos logit contributions
xual+0.028
blank+0.027
 relativity+0.027
 Ples+0.026
manship+0.026
Neg logit contributions
utonium-0.045
puter-0.043
APH-0.039
awei-0.039
ordable-0.038
Token tests
Token ID5254
Feature activation-1.10e-02

Pos logit contributions
utonium+0.056
puter+0.052
APH+0.046
awei+0.046
ordable+0.045
Neg logit contributions
xual-0.046
blank-0.045
 relativity-0.045
manship-0.044
 Ples-0.044
Token of
Token ID286
Feature activation-1.22e-02

Pos logit contributions
xual+0.027
blank+0.027
 relativity+0.027
 Ples+0.026
 Lovecraft+0.026
Neg logit contributions
utonium-0.034
puter-0.032
awei-0.029
APH-0.029
ordable-0.028
Token service
Token ID2139
Feature activation-3.26e-02

Pos logit contributions
utonium+0.137
puter+0.128
awei+0.113
APH+0.113
izoph+0.110
Neg logit contributions
xual-0.125
 relativity-0.123
blank-0.123
manship-0.120
 Ples-0.119
Token from
Token ID422
Feature activation+5.11e-02

Pos logit contributions
xual+0.080
 relativity+0.079
blank+0.078
manship+0.076
 Ples+0.076
Neg logit contributions
utonium-0.102
puter-0.096
awei-0.085
APH-0.085
ordable-0.083
Token 2017
Token ID2177
Feature activation-6.93e-02

Pos logit contributions
utonium+0.152
puter+0.142
awei+0.125
APH+0.125
izoph+0.122
Neg logit contributions
xual-0.134
 relativity-0.131
blank-0.131
manship-0.128
 Ples-0.127
Token.
Token ID13
Feature activation+1.26e-02

Pos logit contributions
xual+0.165
 relativity+0.162
blank+0.160
manship+0.156
 Ples+0.155
Neg logit contributions
utonium-0.223
puter-0.209
APH-0.187
awei-0.187
ordable-0.183
Token Nom
Token ID21198
Feature activation-8.80e-02

Pos logit contributions
utonium+0.040
puter+0.037
APH+0.033
awei+0.033
ordable+0.032
Neg logit contributions
xual-0.031
 relativity-0.030
blank-0.030
manship-0.029
 Lovecraft-0.028
Tokeninal
Token ID1292
Feature activation+4.42e-01

Pos logit contributions
xual+0.240
 relativity+0.234
blank+0.232
manship+0.228
 Ples+0.226
Neg logit contributions
utonium-0.256
puter-0.240
awei-0.209
APH-0.208
ordable-0.205
Token service
Token ID2139
Feature activation-3.88e-02

Pos logit contributions
utonium+1.309
puter+1.214
awei+1.066
APH+1.063
ordable+1.048
Neg logit contributions
xual-1.189
blank-1.145
 relativity-1.131
manship-1.115
 Lovecraft-1.092
Token life
Token ID1204
Feature activation-4.93e-03

Pos logit contributions
xual+0.094
blank+0.091
 relativity+0.090
manship+0.087
 Ples+0.087
Neg logit contributions
utonium-0.125
puter-0.117
APH-0.104
awei-0.104
ordable-0.102
Token is
Token ID318
Feature activation+1.17e-02

Pos logit contributions
xual+0.011
blank+0.010
 relativity+0.010
manship+0.010
 Ples+0.010
Neg logit contributions
utonium-0.017
puter-0.016
awei-0.014
APH-0.014
ordable-0.014
Token 25
Token ID1679
Feature activation-3.82e-02

Pos logit contributions
utonium+0.030
puter+0.028
awei+0.024
APH+0.024
izoph+0.023
Neg logit contributions
xual-0.035
 relativity-0.035
blank-0.035
manship-0.034
 Ples-0.034
Token years
Token ID812
Feature activation+5.81e-02

Pos logit contributions
xual+0.117
 relativity+0.115
blank+0.115
manship+0.112
 Ples+0.112
Neg logit contributions
utonium-0.096
puter-0.089
awei-0.076
APH-0.076
ordable-0.074
Token Soul
Token ID8653
Feature activation-3.65e-03

Pos logit contributions
utonium+0.069
puter+0.065
APH+0.057
awei+0.057
izoph+0.057
Neg logit contributions
xual-0.061
 relativity-0.060
blank-0.059
manship-0.058
 Ples-0.057
Tokenful
Token ID913
Feature activation-1.01e-01

Pos logit contributions
xual+0.009
 relativity+0.009
blank+0.009
manship+0.009
 Ples+0.009
Neg logit contributions
utonium-0.011
puter-0.011
APH-0.009
awei-0.009
izoph-0.009
Token,
Token ID11
Feature activation+1.00e-02

Pos logit contributions
xual+0.226
 relativity+0.224
blank+0.222
 Ples+0.216
manship+0.215
Neg logit contributions
utonium-0.335
puter-0.318
APH-0.283
awei-0.281
izoph-0.279
Token Trans
Token ID3602
Feature activation+2.32e-02

Pos logit contributions
utonium+0.030
puter+0.028
APH+0.025
awei+0.025
izoph+0.025
Neg logit contributions
xual-0.026
 relativity-0.025
blank-0.025
manship-0.024
 Ples-0.024
Tokencend
Token ID15695
Feature activation-1.35e-01

Pos logit contributions
utonium+0.069
puter+0.066
awei+0.056
izoph+0.056
APH+0.056
Neg logit contributions
 relativity-0.061
xual-0.060
blank-0.059
 Ples-0.059
manship-0.058
Tokenental
Token ID2470
Feature activation+4.27e-01

Pos logit contributions
 relativity+0.471
xual+0.470
blank+0.462
manship+0.457
 Ples+0.457
Neg logit contributions
utonium-0.284
puter-0.256
awei-0.213
APH-0.211
ritten-0.207
Token,
Token ID11
Feature activation+6.64e-03

Pos logit contributions
utonium+1.359
puter+1.293
APH+1.148
izoph+1.134
awei+1.128
Neg logit contributions
xual-0.991
 relativity-0.975
blank-0.973
manship-0.945
 Ples-0.943
Token Kn
Token ID6102
Feature activation+3.46e-02

Pos logit contributions
utonium+0.020
puter+0.019
APH+0.017
awei+0.016
izoph+0.016
Neg logit contributions
xual-0.017
 relativity-0.017
blank-0.017
manship-0.016
 Ples-0.016
Tokenows
Token ID1666
Feature activation-5.37e-02

Pos logit contributions
utonium+0.096
puter+0.088
awei+0.076
APH+0.075
ritten+0.075
Neg logit contributions
xual-0.100
 relativity-0.100
blank-0.098
manship-0.096
 Ples-0.096
Token value
Token ID1988
Feature activation+1.04e-01

Pos logit contributions
xual+0.133
 relativity+0.130
blank+0.129
 Ples+0.126
manship+0.123
Neg logit contributions
utonium-0.168
puter-0.157
awei-0.139
APH-0.138
ordable-0.136
Token of
Token ID286
Feature activation+1.32e-02

Pos logit contributions
utonium+0.327
puter+0.308
awei+0.275
APH+0.275
ordable+0.268
Neg logit contributions
xual-0.247
blank-0.241
 relativity-0.240
 Ples-0.238
manship-0.233
Token salt
Token ID8268
Feature activation-8.13e-02

Pos logit contributions
xual+0.104
 relativity+0.102
blank+0.101
manship+0.100
 Ples+0.099
Neg logit contributions
utonium-0.111
puter-0.105
awei-0.091
APH-0.091
izoph-0.089
Token trucks
Token ID13960
Feature activation+5.81e-02

Pos logit contributions
xual+0.202
 relativity+0.197
blank+0.193
manship+0.193
 Lovecraft+0.188
Neg logit contributions
utonium-0.253
puter-0.242
APH-0.212
awei-0.210
ordable-0.207
Token because
Token ID780
Feature activation-9.91e-03

Pos logit contributions
utonium+0.191
puter+0.180
awei+0.161
APH+0.161
ordable+0.158
Neg logit contributions
xual-0.133
 relativity-0.130
blank-0.129
manship-0.125
 Ples-0.125
Token the
Token ID262
Feature activation-7.92e-03

Pos logit contributions
xual+0.025
 relativity+0.024
blank+0.024
manship+0.023
 Ples+0.023
Neg logit contributions
utonium-0.031
puter-0.029
awei-0.026
APH-0.026
izoph-0.025
Token grid
Token ID10706
Feature activation-4.93e-02

Pos logit contributions
xual+0.022
 relativity+0.021
blank+0.021
manship+0.020
 Ples+0.020
Neg logit contributions
utonium-0.023
puter-0.021
awei-0.019
APH-0.019
izoph-0.018
Tokenlock
Token ID5354
Feature activation+4.21e-01

Pos logit contributions
xual+0.144
 relativity+0.141
blank+0.140
 Ples+0.137
manship+0.136
Neg logit contributions
utonium-0.133
puter-0.125
awei-0.107
APH-0.107
ritten-0.104
Token was
Token ID373
Feature activation+5.85e-03

Pos logit contributions
utonium+1.304
puter+1.239
APH+1.092
awei+1.087
ordable+1.066
Neg logit contributions
xual-1.032
 relativity-1.005
blank-0.999
 Ples-0.969
manship-0.965
Token too
Token ID1165
Feature activation-5.83e-02

Pos logit contributions
utonium+0.018
puter+0.017
APH+0.015
awei+0.015
izoph+0.014
Neg logit contributions
xual-0.015
 relativity-0.015
blank-0.015
manship-0.014
 Ples-0.014
Token thick
Token ID6546
Feature activation+2.47e-02

Pos logit contributions
xual+0.145
 relativity+0.141
blank+0.140
manship+0.138
 Ples+0.137
Neg logit contributions
utonium-0.181
puter-0.171
awei-0.152
APH-0.151
ordable-0.148
Token to
Token ID284
Feature activation-2.67e-02

Pos logit contributions
utonium+0.079
puter+0.074
APH+0.066
awei+0.066
ordable+0.065
Neg logit contributions
xual-0.059
 relativity-0.058
blank-0.057
 Ples-0.056
manship-0.055
Token navigate
Token ID16500
Feature activation+3.47e-02

Pos logit contributions
xual+0.065
 relativity+0.064
blank+0.063
manship+0.062
 Ples+0.061
Neg logit contributions
utonium-0.084
puter-0.079
APH-0.070
awei-0.070
izoph-0.069
Tokenple
Token ID1154
Feature activation+1.11e-01

Pos logit contributions
xual+0.141
 relativity+0.140
blank+0.138
manship+0.136
 Ples+0.136
Neg logit contributions
utonium-0.107
puter-0.098
APH-0.084
awei-0.084
ritten-0.081
Tokentes
Token ID4879
Feature activation+4.98e-02

Pos logit contributions
utonium+0.370
puter+0.348
ordable+0.310
APH+0.309
awei+0.308
Neg logit contributions
 relativity-0.251
xual-0.250
blank-0.246
manship-0.239
 Ples-0.234
Token glucose
Token ID15701
Feature activation-4.07e-02

Pos logit contributions
utonium+0.140
puter+0.131
APH+0.114
awei+0.114
ritten+0.112
Neg logit contributions
xual-0.138
 relativity-0.136
blank-0.135
manship-0.133
 Ples-0.131
Token and
Token ID290
Feature activation-1.52e-02

Pos logit contributions
xual+0.100
 relativity+0.099
blank+0.098
manship+0.096
 Ples+0.096
Neg logit contributions
utonium-0.127
puter-0.119
APH-0.106
awei-0.105
ordable-0.103
Token glyc
Token ID40232
Feature activation+7.52e-04

Pos logit contributions
xual+0.039
blank+0.038
 relativity+0.038
manship+0.037
 Ples+0.037
Neg logit contributions
utonium-0.046
puter-0.043
awei-0.038
APH-0.038
izoph-0.037
Tokenogen
Token ID6644
Feature activation+4.08e-01

Pos logit contributions
utonium+0.002
puter+0.002
awei+0.001
APH+0.001
ritten+0.001
Neg logit contributions
xual-0.002
 relativity-0.002
blank-0.002
manship-0.002
 Ples-0.002
Token rapidly
Token ID8902
Feature activation+3.67e-02

Pos logit contributions
utonium+1.270
puter+1.196
APH+1.061
awei+1.045
ordable+1.027
Neg logit contributions
xual-0.995
 relativity-0.974
blank-0.964
 Ples-0.951
manship-0.944
Token,
Token ID11
Feature activation-1.49e-02

Pos logit contributions
utonium+0.116
puter+0.108
APH+0.097
awei+0.096
ordable+0.094
Neg logit contributions
xual-0.088
 relativity-0.087
blank-0.086
manship-0.084
 Ples-0.084
Token forcing
Token ID10833
Feature activation+1.52e-02

Pos logit contributions
xual+0.038
 relativity+0.037
blank+0.037
manship+0.036
 Ples+0.036
Neg logit contributions
utonium-0.046
puter-0.043
APH-0.038
awei-0.038
ordable-0.037
Token the
Token ID262
Feature activation-1.58e-03

Pos logit contributions
utonium+0.043
puter+0.040
awei+0.035
APH+0.035
izoph+0.035
Neg logit contributions
xual-0.042
 relativity-0.041
blank-0.041
manship-0.040
 Ples-0.040
Token body
Token ID1767
Feature activation-1.05e-02

Pos logit contributions
xual+0.005
blank+0.004
 relativity+0.004
manship+0.004
 Ples+0.004
Neg logit contributions
utonium-0.004
puter-0.004
APH-0.003
awei-0.003
izoph-0.003
Token to
Token ID284
Feature activation+5.29e-02

Pos logit contributions
xual+0.157
 relativity+0.155
blank+0.154
 Ples+0.150
manship+0.149
Neg logit contributions
utonium-0.198
puter-0.186
APH-0.165
awei-0.164
ordable-0.161
Token use
Token ID779
Feature activation+2.14e-03

Pos logit contributions
utonium+0.164
puter+0.154
APH+0.137
awei+0.137
izoph+0.134
Neg logit contributions
xual-0.131
 relativity-0.129
blank-0.128
 Ples-0.125
manship-0.125
Token cannabis
Token ID9499
Feature activation+2.83e-02

Pos logit contributions
utonium+0.006
puter+0.006
APH+0.005
awei+0.005
izoph+0.005
Neg logit contributions
xual-0.006
 relativity-0.006
blank-0.006
 Ples-0.006
manship-0.006
Token.
Token ID13
Feature activation-6.12e-03

Pos logit contributions
utonium+0.092
puter+0.087
APH+0.078
awei+0.077
ordable+0.076
Neg logit contributions
xual-0.066
 relativity-0.065
blank-0.065
 Ples-0.063
manship-0.063
Token Ed
Token ID1717
Feature activation+6.45e-03

Pos logit contributions
xual+0.015
 relativity+0.015
blank+0.015
manship+0.014
 Ples+0.014
Neg logit contributions
utonium-0.019
puter-0.018
APH-0.016
awei-0.016
ordable-0.016
Tokenibles
Token ID18764
Feature activation+4.05e-01

Pos logit contributions
utonium+0.018
puter+0.017
APH+0.015
awei+0.015
ordable+0.014
Neg logit contributions
xual-0.018
 relativity-0.018
blank-0.018
manship-0.017
 Ples-0.017
Token,
Token ID11
Feature activation-9.34e-04

Pos logit contributions
utonium+1.288
puter+1.213
APH+1.083
awei+1.068
ordable+1.060
Neg logit contributions
xual-0.961
 relativity-0.945
blank-0.941
 Ples-0.919
manship-0.908
Token vapor
Token ID20199
Feature activation-9.75e-03

Pos logit contributions
xual+0.002
 relativity+0.002
blank+0.002
manship+0.002
 Ples+0.002
Neg logit contributions
utonium-0.003
puter-0.003
APH-0.002
awei-0.002
izoph-0.002
Tokenizers
Token ID11341
Feature activation+6.27e-02

Pos logit contributions
xual+0.033
 relativity+0.033
blank+0.032
manship+0.032
 Ples+0.032
Neg logit contributions
utonium-0.021
puter-0.020
APH-0.016
awei-0.016
izoph-0.016
Token
Token ID1399
Feature activation-7.75e-02

Pos logit contributions
utonium+0.208
puter+0.196
APH+0.175
awei+0.174
ordable+0.171
Neg logit contributions
xual-0.142
 relativity-0.140
blank-0.139
 Ples-0.135
manship-0.134
Token
Token ID198
Feature activation-4.52e-03

Pos logit contributions
xual+0.189
 relativity+0.187
blank+0.183
 Ples+0.180
manship+0.179
Neg logit contributions
utonium-0.244
puter-0.229
APH-0.204
awei-0.203
ordable-0.199
Token live
Token ID2107
Feature activation+4.44e-02

Pos logit contributions
utonium+0.008
puter+0.008
awei+0.007
APH+0.007
ordable+0.007
Neg logit contributions
xual-0.007
 relativity-0.007
blank-0.007
 Ples-0.007
manship-0.007
Token far
Token ID1290
Feature activation+3.92e-02

Pos logit contributions
utonium+0.132
puter+0.123
awei+0.109
APH+0.109
ordable+0.107
Neg logit contributions
xual-0.118
blank-0.113
 relativity-0.113
 Ples-0.111
manship-0.110
Token away
Token ID1497
Feature activation-4.81e-02

Pos logit contributions
utonium+0.148
puter+0.141
awei+0.128
APH+0.128
ritten+0.125
Neg logit contributions
xual-0.072
 relativity-0.068
blank-0.067
manship-0.066
 Ples-0.065
Token.
Token ID13
Feature activation+4.24e-02

Pos logit contributions
xual+0.119
 relativity+0.116
blank+0.115
manship+0.113
 Ples+0.112
Neg logit contributions
utonium-0.150
puter-0.141
awei-0.125
APH-0.125
ordable-0.122
Token Gam
Token ID14014
Feature activation+2.04e-03

Pos logit contributions
utonium+0.134
puter+0.126
APH+0.112
awei+0.112
ordable+0.109
Neg logit contributions
xual-0.103
 relativity-0.101
blank-0.100
manship-0.097
 Ples-0.096
Tokeners
Token ID364
Feature activation+3.98e-01

Pos logit contributions
utonium+0.008
puter+0.008
awei+0.007
APH+0.007
ritten+0.007
Neg logit contributions
xual-0.003
 relativity-0.003
blank-0.003
 Ples-0.003
 Lovecraft-0.003
Token from
Token ID422
Feature activation+2.52e-02

Pos logit contributions
utonium+1.445
puter+1.374
APH+1.237
awei+1.234
ritten+1.219
Neg logit contributions
xual-0.777
 relativity-0.755
blank-0.747
 Ples-0.727
manship-0.713
Token all
Token ID477
Feature activation+7.01e-03

Pos logit contributions
utonium+0.076
puter+0.071
awei+0.063
APH+0.063
ordable+0.062
Neg logit contributions
xual-0.065
 relativity-0.063
blank-0.063
manship-0.061
 Ples-0.061
Token over
Token ID625
Feature activation-1.55e-03

Pos logit contributions
utonium+0.021
puter+0.020
awei+0.018
APH+0.018
ordable+0.017
Neg logit contributions
xual-0.018
blank-0.018
 relativity-0.017
manship-0.017
 Ples-0.017
Token the
Token ID262
Feature activation+5.38e-02

Pos logit contributions
xual+0.004
blank+0.004
 relativity+0.004
manship+0.004
 Ples+0.004
Neg logit contributions
utonium-0.004
puter-0.004
awei-0.004
APH-0.004
ordable-0.003
Token country
Token ID1499
Feature activation+3.36e-02

Pos logit contributions
utonium+0.178
puter+0.169
awei+0.151
APH+0.150
ordable+0.147
Neg logit contributions
xual-0.122
 relativity-0.118
blank-0.118
manship-0.117
 Ples-0.115
Token that
Token ID326
Feature activation+3.02e-02

Pos logit contributions
utonium+0.077
puter+0.072
awei+0.064
APH+0.064
ritten+0.062
Neg logit contributions
xual-0.070
 relativity-0.069
blank-0.068
manship-0.066
 Ples-0.066
Token holds
Token ID6622
Feature activation+3.16e-02

Pos logit contributions
utonium+0.099
puter+0.093
awei+0.083
APH+0.083
ordable+0.081
Neg logit contributions
xual-0.071
 relativity-0.068
blank-0.068
manship-0.066
 Ples-0.066
Token a
Token ID257
Feature activation+1.99e-02

Pos logit contributions
utonium+0.088
puter+0.082
awei+0.072
APH+0.072
ordable+0.071
Neg logit contributions
xual-0.089
 relativity-0.086
blank-0.086
manship-0.084
 Ples-0.084
Token "
Token ID366
Feature activation+2.96e-02

Pos logit contributions
utonium+0.058
puter+0.054
awei+0.048
APH+0.048
ritten+0.047
Neg logit contributions
xual-0.053
 relativity-0.052
blank-0.052
manship-0.051
 Ples-0.050
Tokennom
Token ID26601
Feature activation-1.23e-01

Pos logit contributions
utonium+0.091
puter+0.086
awei+0.076
APH+0.076
ordable+0.074
Neg logit contributions
xual-0.075
 relativity-0.074
blank-0.071
 Ples-0.071
manship-0.071
Tokeninal
Token ID1292
Feature activation+3.94e-01

Pos logit contributions
xual+0.431
 relativity+0.426
blank+0.423
manship+0.417
 Ples+0.416
Neg logit contributions
utonium-0.256
puter-0.232
awei-0.192
APH-0.191
ordable-0.184
Token interest
Token ID1393
Feature activation-4.34e-02

Pos logit contributions
utonium+1.169
puter+1.091
awei+0.964
APH+0.962
ordable+0.950
Neg logit contributions
xual-1.044
 relativity-0.999
blank-0.998
manship-0.978
 Ples-0.971
Token"
Token ID1
Feature activation-1.92e-02

Pos logit contributions
xual+0.101
 relativity+0.098
blank+0.096
 Ples+0.094
manship+0.094
Neg logit contributions
utonium-0.143
puter-0.135
APH-0.120
awei-0.120
ordable-0.118
Token in
Token ID287
Feature activation-4.64e-02

Pos logit contributions
xual+0.049
 relativity+0.049
blank+0.048
manship+0.047
 Ples+0.047
Neg logit contributions
utonium-0.058
puter-0.054
awei-0.048
APH-0.048
ordable-0.047
Token White
Token ID2635
Feature activation+4.47e-02

Pos logit contributions
xual+0.127
 relativity+0.124
blank+0.123
manship+0.121
 Ples+0.120
Neg logit contributions
utonium-0.133
puter-0.124
APH-0.109
awei-0.109
ordable-0.106
Token Marsh
Token ID9786
Feature activation+6.24e-02

Pos logit contributions
utonium+0.145
puter+0.135
awei+0.121
APH+0.119
ritten+0.119
Neg logit contributions
xual-0.107
 relativity-0.104
blank-0.101
 Ples-0.099
manship-0.098
Token while
Token ID981
Feature activation-1.31e-02

Pos logit contributions
utonium+0.051
puter+0.048
awei+0.042
APH+0.042
izoph+0.041
Neg logit contributions
xual-0.040
 relativity-0.039
blank-0.039
manship-0.038
 Ples-0.037
Token everyone
Token ID2506
Feature activation+1.07e-02

Pos logit contributions
xual+0.035
 relativity+0.034
blank+0.034
manship+0.033
 Ples+0.033
Neg logit contributions
utonium-0.038
puter-0.036
APH-0.032
awei-0.032
ordable-0.031
Token was
Token ID373
Feature activation-1.87e-02

Pos logit contributions
utonium+0.036
puter+0.034
awei+0.030
APH+0.030
ordable+0.029
Neg logit contributions
xual-0.024
 relativity-0.023
blank-0.023
manship-0.023
 Ples-0.023
Token in
Token ID287
Feature activation-4.74e-03

Pos logit contributions
xual+0.047
 relativity+0.046
blank+0.046
manship+0.045
 Ples+0.045
Neg logit contributions
utonium-0.058
puter-0.054
awei-0.048
APH-0.048
ritten-0.047
Token grid
Token ID10706
Feature activation-5.64e-02

Pos logit contributions
xual+0.012
 relativity+0.012
blank+0.012
manship+0.012
 Ples+0.011
Neg logit contributions
utonium-0.014
puter-0.013
APH-0.012
awei-0.012
ordable-0.012
Tokenlock
Token ID5354
Feature activation+3.91e-01

Pos logit contributions
xual+0.166
 relativity+0.163
blank+0.162
manship+0.159
 Ples+0.159
Neg logit contributions
utonium-0.150
puter-0.139
APH-0.121
awei-0.120
izoph-0.117
Token,
Token ID11
Feature activation-8.46e-03

Pos logit contributions
utonium+1.249
puter+1.188
APH+1.052
awei+1.041
ordable+1.029
Neg logit contributions
xual-0.918
 relativity-0.899
blank-0.887
 Ples-0.867
manship-0.859
Token they
Token ID484
Feature activation-2.70e-03

Pos logit contributions
xual+0.022
 relativity+0.022
blank+0.022
manship+0.021
 Ples+0.021
Neg logit contributions
utonium-0.025
puter-0.024
APH-0.021
awei-0.021
ordable-0.020
Token couldn
Token ID3521
Feature activation-2.78e-02

Pos logit contributions
xual+0.007
 relativity+0.007
blank+0.006
manship+0.006
 Ples+0.006
Neg logit contributions
utonium-0.008
puter-0.008
APH-0.007
awei-0.007
ritten-0.007
Token
Token ID447
Feature activation-5.37e-03

Pos logit contributions
xual+0.061
 relativity+0.060
blank+0.060
manship+0.059
 Ples+0.058
Neg logit contributions
utonium-0.094
puter-0.089
awei-0.080
APH-0.079
izoph-0.078
Token
Token ID247
Feature activation-5.94e-03

Pos logit contributions
xual+0.020
 relativity+0.020
blank+0.020
manship+0.019
 Ples+0.019
Neg logit contributions
utonium-0.010
puter-0.009
awei-0.007
APH-0.007
izoph-0.007
Token the
Token ID262
Feature activation+9.30e-02

Pos logit contributions
utonium+0.108
puter+0.100
APH+0.089
awei+0.089
izoph+0.087
Neg logit contributions
xual-0.094
 relativity-0.093
blank-0.093
manship-0.091
 Ples-0.089
Token til
Token ID21502
Feature activation-7.40e-02

Pos logit contributions
utonium+0.280
puter+0.263
awei+0.234
APH+0.233
izoph+0.231
Neg logit contributions
xual-0.236
blank-0.232
 relativity-0.232
manship-0.226
 Ples-0.223
Tokenap
Token ID499
Feature activation+4.51e-02

Pos logit contributions
xual+0.249
 relativity+0.248
blank+0.242
 Ples+0.241
manship+0.240
Neg logit contributions
utonium-0.167
puter-0.151
APH-0.129
awei-0.127
izoph-0.125
Tokenia
Token ID544
Feature activation+5.49e-02

Pos logit contributions
utonium+0.138
puter+0.129
APH+0.115
izoph+0.114
awei+0.114
Neg logit contributions
xual-0.114
 relativity-0.113
blank-0.111
 Ples-0.109
manship-0.108
Token fil
Token ID1226
Feature activation+6.54e-02

Pos logit contributions
utonium+0.168
puter+0.157
APH+0.141
awei+0.139
ritten+0.137
Neg logit contributions
xual-0.137
 relativity-0.135
blank-0.135
 Ples-0.129
manship-0.129
Tokenlets
Token ID5289
Feature activation+3.89e-01

Pos logit contributions
utonium+0.196
puter+0.183
APH+0.160
ritten+0.159
ordable+0.159
Neg logit contributions
xual-0.171
 relativity-0.170
blank-0.165
manship-0.164
 Lovecraft-0.162
Token are
Token ID389
Feature activation+4.86e-02

Pos logit contributions
utonium+1.142
puter+1.059
APH+0.941
awei+0.932
ritten+0.924
Neg logit contributions
xual-1.025
 relativity-1.003
blank-0.997
 Ples-0.970
manship-0.963
Token the
Token ID262
Feature activation+4.46e-02

Pos logit contributions
utonium+0.152
puter+0.142
awei+0.127
APH+0.127
ritten+0.125
Neg logit contributions
xual-0.119
 relativity-0.117
blank-0.114
manship-0.113
 Ples-0.111
Token same
Token ID976
Feature activation-4.21e-02

Pos logit contributions
utonium+0.152
puter+0.143
awei+0.130
APH+0.129
izoph+0.127
Neg logit contributions
xual-0.096
 relativity-0.095
blank-0.093
manship-0.092
 Ples-0.090
Token exact
Token ID2748
Feature activation-2.86e-02

Pos logit contributions
xual+0.104
 relativity+0.104
blank+0.102
manship+0.100
 Ples+0.099
Neg logit contributions
utonium-0.129
puter-0.121
APH-0.108
awei-0.108
izoph-0.107
Token size
Token ID2546
Feature activation+6.28e-02

Pos logit contributions
xual+0.071
 relativity+0.070
blank+0.069
manship+0.068
 Ples+0.067
Neg logit contributions
utonium-0.088
puter-0.083
awei-0.074
APH-0.074
izoph-0.073
Token
Token ID251
Feature activation-1.53e-02

Pos logit contributions
xual+0.114
 relativity+0.113
blank+0.112
 Ples+0.110
manship+0.110
Neg logit contributions
utonium-0.093
puter-0.086
awei-0.074
APH-0.074
ordable-0.071
Token
Token ID564
Feature activation-4.63e-02

Pos logit contributions
xual+0.040
 relativity+0.039
blank+0.038
manship+0.038
 Ples+0.038
Neg logit contributions
utonium-0.046
puter-0.043
APH-0.039
awei-0.038
ordable-0.038
Token
Token ID250
Feature activation-4.31e-02

Pos logit contributions
xual+0.148
 relativity+0.146
blank+0.145
manship+0.143
 Ples+0.143
Neg logit contributions
utonium-0.111
puter-0.102
awei-0.087
APH-0.087
izoph-0.084
Tokenrac
Token ID11510
Feature activation+5.63e-02

Pos logit contributions
xual+0.115
 relativity+0.113
blank+0.111
manship+0.110
 Ples+0.109
Neg logit contributions
utonium-0.126
puter-0.118
APH-0.105
awei-0.104
ordable-0.102
Tokenetr
Token ID21879
Feature activation+1.22e-01

Pos logit contributions
utonium+0.206
puter+0.195
APH+0.176
awei+0.176
ordable+0.173
Neg logit contributions
xual-0.111
 relativity-0.109
blank-0.107
manship-0.104
 Ples-0.104
Tokenack
Token ID441
Feature activation+3.87e-01

Pos logit contributions
utonium+0.249
puter+0.222
awei+0.184
APH+0.184
izoph+0.176
Neg logit contributions
xual-0.441
 relativity-0.435
blank-0.429
manship-0.425
 Ples-0.425
Token
Token ID447
Feature activation-2.45e-02

Pos logit contributions
utonium+1.207
puter+1.146
APH+1.014
awei+1.014
ordable+0.994
Neg logit contributions
xual-0.955
 relativity-0.929
blank-0.918
manship-0.898
 Ples-0.896
Token
Token ID251
Feature activation-1.19e-02

Pos logit contributions
xual+0.084
 relativity+0.084
blank+0.083
 Ples+0.082
manship+0.082
Neg logit contributions
utonium-0.053
puter-0.048
awei-0.040
APH-0.040
izoph-0.038
Token bass
Token ID12702
Feature activation-6.12e-02

Pos logit contributions
xual+0.029
 relativity+0.029
blank+0.028
 Ples+0.028
manship+0.028
Neg logit contributions
utonium-0.037
puter-0.035
APH-0.031
awei-0.031
ordable-0.030
Token driver
Token ID4639
Feature activation-2.43e-02

Pos logit contributions
xual+0.145
 relativity+0.140
blank+0.138
manship+0.136
 Ples+0.136
Neg logit contributions
utonium-0.198
puter-0.190
APH-0.168
awei-0.166
ordable-0.164
Token,
Token ID11
Feature activation-4.72e-03

Pos logit contributions
xual+0.057
 relativity+0.056
blank+0.055
manship+0.054
 Ples+0.054
Neg logit contributions
utonium-0.079
puter-0.075
APH-0.067
awei-0.067
ordable-0.065
Token:
Token ID25
Feature activation-3.90e-02

Pos logit contributions
xual+0.094
 relativity+0.093
blank+0.091
 Ples+0.089
manship+0.088
Neg logit contributions
utonium-0.137
puter-0.130
APH-0.117
awei-0.116
ritten-0.116
Token14
Token ID1415
Feature activation-2.13e-02

Pos logit contributions
xual+0.096
 relativity+0.094
blank+0.093
manship+0.091
 Ples+0.091
Neg logit contributions
utonium-0.122
puter-0.115
awei-0.102
APH-0.102
ritten-0.100
Token games
Token ID1830
Feature activation-9.66e-04

Pos logit contributions
xual+0.054
 relativity+0.053
blank+0.052
manship+0.051
 Ples+0.051
Neg logit contributions
utonium-0.065
puter-0.061
APH-0.054
awei-0.054
ritten-0.053
Token over
Token ID625
Feature activation-2.23e-02

Pos logit contributions
xual+0.002
 relativity+0.002
blank+0.002
 Ples+0.002
manship+0.002
Neg logit contributions
utonium-0.003
puter-0.003
awei-0.003
APH-0.003
ordable-0.003
Token Gam
Token ID14014
Feature activation-2.14e-02

Pos logit contributions
xual+0.058
 relativity+0.056
blank+0.056
manship+0.055
 Ples+0.054
Neg logit contributions
utonium-0.067
puter-0.063
awei-0.056
APH-0.055
izoph-0.054
Tokeners
Token ID364
Feature activation+3.85e-01

Pos logit contributions
xual+0.055
 relativity+0.054
blank+0.053
 Ples+0.052
manship+0.052
Neg logit contributions
utonium-0.065
puter-0.061
awei-0.054
APH-0.054
izoph-0.053
Token2
Token ID17
Feature activation-1.39e-02

Pos logit contributions
utonium+1.190
puter+1.114
APH+1.001
awei+0.990
izoph+0.984
Neg logit contributions
xual-0.955
 relativity-0.932
blank-0.907
 Ples-0.904
manship-0.897
Token and
Token ID290
Feature activation-3.35e-02

Pos logit contributions
xual+0.033
 relativity+0.033
blank+0.032
manship+0.032
 Ples+0.031
Neg logit contributions
utonium-0.044
puter-0.042
awei-0.037
APH-0.037
izoph-0.036
Token Titan
Token ID11977
Feature activation+5.69e-03

Pos logit contributions
xual+0.085
 relativity+0.083
blank+0.083
manship+0.081
 Ples+0.080
Neg logit contributions
utonium-0.103
puter-0.096
awei-0.085
APH-0.085
izoph-0.084
Token,
Token ID11
Feature activation-4.85e-04

Pos logit contributions
utonium+0.018
puter+0.017
awei+0.016
APH+0.015
izoph+0.015
Neg logit contributions
xual-0.013
 relativity-0.013
blank-0.013
manship-0.013
 Ples-0.013
Token adding
Token ID4375
Feature activation+1.67e-02

Pos logit contributions
xual+0.001
 relativity+0.001
blank+0.001
manship+0.001
 Ples+0.001
Neg logit contributions
utonium-0.002
puter-0.001
awei-0.001
APH-0.001
ordable-0.001
Token terms
Token ID2846
Feature activation-2.35e-02

Pos logit contributions
xual+0.092
blank+0.089
 relativity+0.089
manship+0.087
 Ples+0.086
Neg logit contributions
utonium-0.108
puter-0.101
APH-0.090
awei-0.089
ritten-0.088
Token;
Token ID26
Feature activation+1.16e-03

Pos logit contributions
xual+0.053
 relativity+0.052
blank+0.052
 Ples+0.051
manship+0.050
Neg logit contributions
utonium-0.078
puter-0.073
APH-0.066
awei-0.065
ritten-0.064
Token for
Token ID329
Feature activation+8.25e-03

Pos logit contributions
utonium+0.004
puter+0.003
APH+0.003
awei+0.003
ritten+0.003
Neg logit contributions
xual-0.003
blank-0.003
 relativity-0.003
manship-0.003
 Ples-0.003
Token James
Token ID3700
Feature activation+4.25e-02

Pos logit contributions
utonium+0.027
puter+0.025
APH+0.022
awei+0.022
ritten+0.022
Neg logit contributions
xual-0.019
blank-0.019
 relativity-0.019
manship-0.018
 Ples-0.018
Token Fraz
Token ID36914
Feature activation+5.98e-02

Pos logit contributions
utonium+0.140
puter+0.131
APH+0.118
awei+0.117
ritten+0.115
Neg logit contributions
xual-0.098
 relativity-0.096
blank-0.095
manship-0.092
 Ples-0.091
Tokener
Token ID263
Feature activation+3.84e-01

Pos logit contributions
utonium+0.289
puter+0.277
awei+0.258
APH+0.257
izoph+0.254
Neg logit contributions
xual-0.046
 relativity-0.043
blank-0.042
manship-0.039
 Ples-0.038
Token,
Token ID11
Feature activation+9.76e-03

Pos logit contributions
utonium+1.343
puter+1.263
APH+1.146
awei+1.141
izoph+1.124
Neg logit contributions
xual-0.798
blank-0.765
 relativity-0.749
manship-0.743
 Ples-0.738
Token all
Token ID477
Feature activation+1.14e-02

Pos logit contributions
utonium+0.033
puter+0.031
APH+0.028
awei+0.028
izoph+0.027
Neg logit contributions
xual-0.022
blank-0.021
 relativity-0.021
manship-0.021
 Ples-0.020
Token of
Token ID286
Feature activation+3.13e-02

Pos logit contributions
utonium+0.041
puter+0.039
APH+0.035
awei+0.035
izoph+0.035
Neg logit contributions
xual-0.023
blank-0.022
 relativity-0.021
manship-0.021
 Ples-0.021
Token myth
Token ID7918
Feature activation+8.32e-02

Pos logit contributions
utonium+0.099
puter+0.092
APH+0.083
awei+0.082
izoph+0.081
Neg logit contributions
xual-0.076
blank-0.074
 relativity-0.073
manship-0.072
 Ples-0.071
Token
Token ID447
Feature activation+2.17e-02

Pos logit contributions
utonium+0.270
puter+0.253
APH+0.227
awei+0.224
ritten+0.221
Neg logit contributions
xual-0.196
blank-0.191
 relativity-0.190
 Ples-0.186
manship-0.185
Token traditionally
Token ID16083
Feature activation+1.45e-02

Pos logit contributions
utonium+0.095
puter+0.089
APH+0.080
awei+0.079
ritten+0.077
Neg logit contributions
xual-0.081
blank-0.079
 relativity-0.079
 Ples-0.077
manship-0.077
Token the
Token ID262
Feature activation-9.72e-03

Pos logit contributions
utonium+0.041
puter+0.038
APH+0.034
awei+0.034
ritten+0.033
Neg logit contributions
xual-0.040
blank-0.039
 relativity-0.038
 Ples-0.038
manship-0.038
Token realm
Token ID13360
Feature activation-9.38e-02

Pos logit contributions
xual+0.021
blank+0.020
 relativity+0.020
manship+0.020
 Ples+0.019
Neg logit contributions
utonium-0.034
puter-0.032
APH-0.029
awei-0.029
ritten-0.028
Token of
Token ID286
Feature activation+3.26e-02

Pos logit contributions
xual+0.185
 relativity+0.180
blank+0.179
 Ples+0.174
manship+0.173
Neg logit contributions
utonium-0.339
puter-0.321
APH-0.291
awei-0.289
ritten-0.285
Token metaph
Token ID13738
Feature activation+6.16e-02

Pos logit contributions
utonium+0.101
puter+0.095
APH+0.085
awei+0.084
ritten+0.083
Neg logit contributions
xual-0.080
blank-0.079
 relativity-0.078
 Ples-0.077
manship-0.077
Tokenysics
Token ID23154
Feature activation+3.80e-01

Pos logit contributions
utonium+0.189
puter+0.176
APH+0.157
awei+0.156
ordable+0.154
Neg logit contributions
xual-0.156
 relativity-0.154
blank-0.152
 Ples-0.149
manship-0.149
Token or
Token ID393
Feature activation-1.35e-02

Pos logit contributions
utonium+1.208
puter+1.144
APH+1.033
awei+1.010
ritten+0.998
Neg logit contributions
xual-0.897
blank-0.868
 relativity-0.863
 Ples-0.848
manship-0.836
Token the
Token ID262
Feature activation+3.65e-03

Pos logit contributions
xual+0.032
blank+0.031
 relativity+0.030
 Ples+0.030
manship+0.030
Neg logit contributions
utonium-0.043
puter-0.041
APH-0.037
awei-0.036
izoph-0.036
Token transcend
Token ID26231
Feature activation-3.21e-02

Pos logit contributions
utonium+0.013
puter+0.013
APH+0.012
awei+0.012
izoph+0.011
Neg logit contributions
xual-0.007
blank-0.007
 relativity-0.007
manship-0.007
 Ples-0.006
Tokenent
Token ID298
Feature activation+4.04e-02

Pos logit contributions
xual+0.108
 relativity+0.106
blank+0.106
 Ples+0.104
manship+0.104
Neg logit contributions
utonium-0.072
puter-0.066
APH-0.055
awei-0.055
ritten-0.054
Token,
Token ID11
Feature activation+9.99e-03

Pos logit contributions
utonium+0.142
puter+0.136
APH+0.123
awei+0.122
ritten+0.120
Neg logit contributions
xual-0.082
blank-0.080
 relativity-0.078
manship-0.077
 Ples-0.077
Tokenurga
Token ID45098
Feature activation+3.34e-02

Pos logit contributions
utonium+0.051
puter+0.047
awei+0.043
APH+0.043
izoph+0.042
Neg logit contributions
xual-0.041
 relativity-0.041
manship-0.040
blank-0.039
 Ples-0.039
Tokenon
Token ID261
Feature activation+2.23e-01

Pos logit contributions
utonium+0.101
puter+0.095
awei+0.084
APH+0.083
ritten+0.083
Neg logit contributions
xual-0.087
 relativity-0.084
blank-0.082
 Lovecraft-0.079
 Ples-0.079
Token,
Token ID11
Feature activation+8.08e-02

Pos logit contributions
utonium+0.706
puter+0.668
awei+0.599
APH+0.596
izoph+0.583
Neg logit contributions
xual-0.540
 relativity-0.517
blank-0.514
manship-0.501
 Ples-0.497
Token Far
Token ID6755
Feature activation-6.68e-02

Pos logit contributions
utonium+0.249
puter+0.234
awei+0.209
APH+0.208
ordable+0.204
Neg logit contributions
xual-0.203
 relativity-0.197
blank-0.196
manship-0.191
 Ples-0.187
Tokenid
Token ID312
Feature activation-6.14e-02

Pos logit contributions
xual+0.160
 relativity+0.157
blank+0.153
manship+0.151
 Ples+0.151
Neg logit contributions
utonium-0.216
puter-0.203
awei-0.181
APH-0.180
izoph-0.177
Tokenabad
Token ID17325
Feature activation+3.80e-01

Pos logit contributions
xual+0.194
 relativity+0.192
blank+0.187
 Ples+0.186
manship+0.185
Neg logit contributions
utonium-0.150
puter-0.139
awei-0.119
APH-0.117
ordable-0.114
Token and
Token ID290
Feature activation-2.26e-03

Pos logit contributions
utonium+1.195
puter+1.129
awei+1.009
APH+1.006
ritten+0.981
Neg logit contributions
xual-0.923
 relativity-0.887
blank-0.879
manship-0.857
 Ples-0.856
Token other
Token ID584
Feature activation+9.12e-03

Pos logit contributions
xual+0.006
 relativity+0.006
blank+0.006
manship+0.005
 Ples+0.005
Neg logit contributions
utonium-0.007
puter-0.007
awei-0.006
APH-0.006
ordable-0.006
Token districts
Token ID12815
Feature activation+8.48e-02

Pos logit contributions
utonium+0.028
puter+0.026
awei+0.023
APH+0.023
ordable+0.023
Neg logit contributions
xual-0.023
blank-0.023
 relativity-0.023
manship-0.022
 Ples-0.022
Token of
Token ID286
Feature activation-5.30e-02

Pos logit contributions
utonium+0.272
puter+0.255
APH+0.230
awei+0.229
ordable+0.225
Neg logit contributions
xual-0.202
 relativity-0.196
blank-0.193
 Ples-0.187
manship-0.186
Token H
Token ID367
Feature activation+6.21e-03

Pos logit contributions
xual+0.147
 relativity+0.143
blank+0.143
manship+0.140
 Ples+0.139
Neg logit contributions
utonium-0.149
puter-0.139
APH-0.122
awei-0.122
ritten-0.119
Token linked
Token ID6692
Feature activation-1.65e-02

Pos logit contributions
xual+0.028
blank+0.027
 relativity+0.027
 Ples+0.026
manship+0.026
Neg logit contributions
utonium-0.024
puter-0.022
APH-0.019
awei-0.019
ritten-0.019
Token to
Token ID284
Feature activation-1.12e-02

Pos logit contributions
xual+0.041
 relativity+0.041
blank+0.040
manship+0.039
 Ples+0.039
Neg logit contributions
utonium-0.051
puter-0.048
APH-0.043
awei-0.043
ritten-0.042
Token Obama
Token ID2486
Feature activation-6.83e-02

Pos logit contributions
xual+0.029
 relativity+0.029
blank+0.029
manship+0.028
 Ples+0.028
Neg logit contributions
utonium-0.033
puter-0.031
awei-0.028
APH-0.028
ritten-0.027
Token's
Token ID338
Feature activation-3.20e-02

Pos logit contributions
xual+0.136
 relativity+0.133
blank+0.131
 Ples+0.128
manship+0.126
Neg logit contributions
utonium-0.246
puter-0.234
awei-0.211
APH-0.211
ritten-0.207
Token chair
Token ID5118
Feature activation-4.37e-02

Pos logit contributions
xual+0.085
 relativity+0.082
blank+0.082
 Ples+0.080
manship+0.080
Neg logit contributions
utonium-0.095
puter-0.088
awei-0.078
APH-0.078
ordable-0.076
Tokenmanship
Token ID25428
Feature activation-5.37e-01

Pos logit contributions
xual+0.017
 relativity+0.014
blank+0.012
 Ples+0.011
 Lovecraft+0.009
Neg logit contributions
utonium-0.228
puter-0.220
awei-0.206
APH-0.205
ordable-0.203
Token of
Token ID286
Feature activation+1.42e-03

Pos logit contributions
xual+1.129
 relativity+1.107
blank+1.095
 Ples+1.062
manship+1.048
Neg logit contributions
utonium-1.874
puter-1.769
awei-1.601
APH-1.596
ritten-1.561
Token the
Token ID262
Feature activation-9.62e-04

Pos logit contributions
utonium+0.004
puter+0.004
awei+0.003
APH+0.003
ritten+0.003
Neg logit contributions
xual-0.004
 relativity-0.004
blank-0.004
 Ples-0.004
manship-0.004
Token Chicago
Token ID4842
Feature activation-4.19e-02

Pos logit contributions
xual+0.002
 relativity+0.002
blank+0.002
manship+0.002
 Ples+0.002
Neg logit contributions
utonium-0.003
puter-0.003
awei-0.003
APH-0.003
ritten-0.002
Token Ann
Token ID5506
Feature activation-3.77e-02

Pos logit contributions
xual+0.094
blank+0.090
 relativity+0.090
manship+0.087
 Ples+0.087
Neg logit contributions
utonium-0.141
puter-0.132
APH-0.120
awei-0.120
ritten-0.117
Tokenenberg
Token ID23140
Feature activation+6.71e-03

Pos logit contributions
xual+0.077
 relativity+0.073
blank+0.072
 Ples+0.070
manship+0.070
Neg logit contributions
utonium-0.137
puter-0.130
APH-0.116
awei-0.116
ordable-0.115
Token Gay
Token ID16013
Feature activation+4.06e-02

Pos logit contributions
utonium+0.032
puter+0.030
awei+0.026
APH+0.026
ritten+0.026
Neg logit contributions
xual-0.024
 relativity-0.024
blank-0.023
manship-0.023
 Ples-0.023
Token Away
Token ID21986
Feature activation-8.07e-02

Pos logit contributions
utonium+0.126
puter+0.118
APH+0.104
awei+0.104
ritten+0.103
Neg logit contributions
xual-0.100
 relativity-0.099
blank-0.098
manship-0.096
 Ples-0.095
Token
Token ID447
Feature activation+3.67e-02

Pos logit contributions
xual+0.193
 relativity+0.191
blank+0.188
 Ples+0.183
manship+0.183
Neg logit contributions
utonium-0.256
puter-0.241
APH-0.215
awei-0.215
ritten-0.211
Token
Token ID247
Feature activation+8.63e-04

Pos logit contributions
utonium+0.072
puter+0.063
awei+0.052
APH+0.052
ritten+0.050
Neg logit contributions
xual-0.133
 relativity-0.133
blank-0.132
 Ples-0.130
manship-0.129
Token ser
Token ID1055
Feature activation-2.77e-02

Pos logit contributions
utonium+0.003
puter+0.003
APH+0.002
awei+0.002
ritten+0.002
Neg logit contributions
xual-0.002
 relativity-0.002
blank-0.002
 Ples-0.002
manship-0.002
Tokenmons
Token ID11567
Feature activation-5.16e-01

Pos logit contributions
xual+0.045
 relativity+0.044
blank+0.042
 Ples+0.041
manship+0.041
Neg logit contributions
utonium-0.111
puter-0.105
APH-0.097
awei-0.097
ritten-0.095
Token,
Token ID11
Feature activation-3.82e-02

Pos logit contributions
xual+1.172
 relativity+1.153
blank+1.144
 Ples+1.113
manship+1.110
Neg logit contributions
utonium-1.713
puter-1.612
APH-1.444
awei-1.442
izoph-1.414
Token the
Token ID262
Feature activation-7.92e-03

Pos logit contributions
xual+0.094
 relativity+0.093
blank+0.092
manship+0.090
 Ples+0.090
Neg logit contributions
utonium-0.119
puter-0.111
APH-0.099
awei-0.099
ritten-0.097
Token man
Token ID582
Feature activation+2.07e-02

Pos logit contributions
xual+0.022
 relativity+0.021
blank+0.021
manship+0.021
 Ples+0.021
Neg logit contributions
utonium-0.023
puter-0.021
awei-0.018
APH-0.018
izoph-0.018
Token who
Token ID508
Feature activation+1.70e-03

Pos logit contributions
utonium+0.062
puter+0.058
awei+0.051
APH+0.051
ritten+0.050
Neg logit contributions
xual-0.054
 relativity-0.053
blank-0.052
 Ples-0.051
manship-0.051
Token once
Token ID1752
Feature activation+1.30e-02

Pos logit contributions
utonium+0.005
puter+0.005
APH+0.004
awei+0.004
ordable+0.004
Neg logit contributions
xual-0.004
 relativity-0.004
blank-0.004
 Ples-0.004
manship-0.004
Token the
Token ID262
Feature activation+2.64e-02

Pos logit contributions
utonium+0.103
puter+0.096
awei+0.085
APH+0.084
ordable+0.082
Neg logit contributions
xual-0.102
 relativity-0.101
blank-0.100
manship-0.098
 Ples-0.098
Token Department
Token ID2732
Feature activation+4.74e-02

Pos logit contributions
utonium+0.080
puter+0.075
awei+0.067
APH+0.067
ordable+0.065
Neg logit contributions
xual-0.067
 relativity-0.066
blank-0.065
manship-0.064
 Ples-0.064
Token of
Token ID286
Feature activation+2.25e-02

Pos logit contributions
utonium+0.171
puter+0.162
APH+0.146
awei+0.146
ordable+0.143
Neg logit contributions
xual-0.093
 relativity-0.092
blank-0.091
 Ples-0.087
manship-0.087
Token Education
Token ID7868
Feature activation-1.67e-02

Pos logit contributions
utonium+0.060
puter+0.056
APH+0.048
awei+0.048
ordable+0.048
Neg logit contributions
xual-0.066
 relativity-0.064
blank-0.064
 Ples-0.063
manship-0.062
Token recons
Token ID23898
Feature activation-3.27e-02

Pos logit contributions
xual+0.037
blank+0.036
 relativity+0.036
 Ples+0.034
 Lovecraft+0.034
Neg logit contributions
utonium-0.056
puter-0.053
awei-0.047
APH-0.047
ordable-0.046
Tokeniders
Token ID4157
Feature activation-5.08e-01

Pos logit contributions
xual+0.073
 relativity+0.072
blank+0.071
 Ples+0.069
manship+0.068
Neg logit contributions
utonium-0.110
puter-0.103
awei-0.093
APH-0.092
ordable-0.091
Token the
Token ID262
Feature activation+3.21e-02

Pos logit contributions
xual+1.290
 relativity+1.259
blank+1.257
manship+1.227
 Ples+1.227
Neg logit contributions
utonium-1.546
puter-1.447
APH-1.286
awei-1.284
ordable-1.256
Token guidance
Token ID11154
Feature activation+1.33e-02

Pos logit contributions
utonium+0.101
puter+0.095
awei+0.084
APH+0.084
izoph+0.083
Neg logit contributions
xual-0.078
 relativity-0.076
blank-0.076
manship-0.074
 Ples-0.074
Token provided
Token ID2810
Feature activation+2.84e-02

Pos logit contributions
utonium+0.043
puter+0.040
awei+0.036
APH+0.036
ritten+0.035
Neg logit contributions
xual-0.031
 relativity-0.031
blank-0.030
 Ples-0.030
manship-0.030
Token to
Token ID284
Feature activation+2.71e-02

Pos logit contributions
utonium+0.087
puter+0.081
awei+0.072
APH+0.072
ordable+0.071
Neg logit contributions
xual-0.071
 relativity-0.070
blank-0.070
 Ples-0.068
manship-0.068
Token schools
Token ID4266
Feature activation+4.48e-02

Pos logit contributions
utonium+0.079
puter+0.073
awei+0.065
APH+0.065
izoph+0.063
Neg logit contributions
xual-0.072
 relativity-0.071
blank-0.071
manship-0.069
 Ples-0.069
Token in
Token ID287
Feature activation-5.75e-02

Pos logit contributions
utonium+0.145
puter+0.136
awei+0.122
APH+0.122
ordable+0.120
Neg logit contributions
xual-0.111
 relativity-0.108
blank-0.106
 Ples-0.104
manship-0.103
Token the
Token ID262
Feature activation-8.59e-02

Pos logit contributions
xual+0.153
 relativity+0.148
blank+0.147
manship+0.145
 Ples+0.143
Neg logit contributions
utonium-0.169
puter-0.157
APH-0.139
awei-0.139
ordable-0.137
Token agreement
Token ID4381
Feature activation-6.10e-03

Pos logit contributions
xual+0.216
 relativity+0.209
blank+0.208
manship+0.204
 Ples+0.202
Neg logit contributions
utonium-0.266
puter-0.248
awei-0.221
APH-0.220
ordable-0.217
Token.
Token ID13
Feature activation-6.08e-02

Pos logit contributions
xual+0.014
 relativity+0.014
blank+0.014
 Ples+0.014
manship+0.013
Neg logit contributions
utonium-0.020
puter-0.019
awei-0.017
APH-0.017
ritten-0.016
Token Analy
Token ID16213
Feature activation-9.04e-02

Pos logit contributions
xual+0.151
 relativity+0.147
blank+0.143
manship+0.139
 Ples+0.137
Neg logit contributions
utonium-0.191
puter-0.179
APH-0.161
awei-0.159
ordable-0.156
Tokensts
Token ID6448
Feature activation-4.69e-01

Pos logit contributions
xual+0.189
 relativity+0.187
blank+0.185
 Ples+0.179
manship+0.179
Neg logit contributions
utonium-0.318
puter-0.298
awei-0.269
APH-0.269
ritten-0.265
Token that
Token ID326
Feature activation-4.17e-02

Pos logit contributions
xual+1.237
 relativity+1.221
blank+1.210
manship+1.185
 Ples+1.181
Neg logit contributions
utonium-1.387
puter-1.295
awei-1.143
APH-1.140
izoph-1.115
Token have
Token ID423
Feature activation-3.62e-02

Pos logit contributions
xual+0.110
 relativity+0.108
blank+0.107
manship+0.105
 Ples+0.105
Neg logit contributions
utonium-0.123
puter-0.115
awei-0.102
APH-0.102
izoph-0.099
Token followed
Token ID3940
Feature activation+1.52e-02

Pos logit contributions
xual+0.101
 relativity+0.099
blank+0.099
manship+0.096
 Ples+0.096
Neg logit contributions
utonium-0.102
puter-0.095
awei-0.083
APH-0.083
ritten-0.081
Token the
Token ID262
Feature activation-4.52e-02

Pos logit contributions
utonium+0.044
puter+0.041
APH+0.036
awei+0.036
ordable+0.035
Neg logit contributions
xual-0.041
blank-0.040
 relativity-0.040
 Ples-0.039
manship-0.039
Token process
Token ID1429
Feature activation-9.76e-02

Pos logit contributions
xual+0.111
 relativity+0.107
blank+0.107
manship+0.104
 Ples+0.104
Neg logit contributions
utonium-0.143
puter-0.133
awei-0.119
APH-0.119
ordable-0.117
Tokenu
Token ID84
Feature activation-5.21e-02

Pos logit contributions
utonium+0.165
puter+0.156
awei+0.141
APH+0.141
izoph+0.139
Neg logit contributions
xual-0.092
 relativity-0.090
blank-0.090
manship-0.087
 Ples-0.086
Token will
Token ID481
Feature activation-3.27e-02

Pos logit contributions
xual+0.113
 relativity+0.109
blank+0.108
 Ples+0.105
manship+0.104
Neg logit contributions
utonium-0.179
puter-0.168
APH-0.152
awei-0.152
ordable-0.148
Token lose
Token ID4425
Feature activation-1.09e-02

Pos logit contributions
xual+0.080
 relativity+0.078
blank+0.078
manship+0.076
 Ples+0.075
Neg logit contributions
utonium-0.102
puter-0.096
APH-0.085
awei-0.085
ritten-0.083
Token her
Token ID607
Feature activation-3.32e-03

Pos logit contributions
xual+0.028
 relativity+0.028
blank+0.027
manship+0.027
 Ples+0.027
Neg logit contributions
utonium-0.033
puter-0.031
awei-0.027
APH-0.027
ordable-0.027
Token chair
Token ID5118
Feature activation-1.47e-02

Pos logit contributions
xual+0.008
 relativity+0.008
blank+0.008
 Ples+0.008
manship+0.008
Neg logit contributions
utonium-0.010
puter-0.010
awei-0.009
APH-0.008
ordable-0.008
Tokenmanship
Token ID25428
Feature activation-4.59e-01

Pos logit contributions
xual+0.012
 relativity+0.011
blank+0.010
 Ples+0.009
 Lovecraft+0.009
Neg logit contributions
utonium-0.071
puter-0.068
APH-0.063
awei-0.063
ordable-0.063
Token.
Token ID13
Feature activation-8.28e-02

Pos logit contributions
xual+1.031
 relativity+1.013
blank+1.001
 Ples+0.974
manship+0.970
Neg logit contributions
utonium-1.537
puter-1.448
awei-1.299
APH-1.297
ordable-1.271
Token Throughout
Token ID24581
Feature activation-4.31e-02

Pos logit contributions
xual+0.204
 relativity+0.199
blank+0.196
manship+0.190
 Ples+0.187
Neg logit contributions
utonium-0.260
puter-0.244
APH-0.220
awei-0.216
ordable-0.213
Token the
Token ID262
Feature activation-3.44e-02

Pos logit contributions
xual+0.115
blank+0.112
 relativity+0.112
manship+0.108
 Ples+0.107
Neg logit contributions
utonium-0.126
puter-0.118
APH-0.105
awei-0.103
ordable-0.103
Token campaign
Token ID1923
Feature activation-2.27e-03

Pos logit contributions
xual+0.086
 relativity+0.084
blank+0.083
manship+0.081
 Ples+0.081
Neg logit contributions
utonium-0.106
puter-0.099
APH-0.088
awei-0.088
ordable-0.087
Token,
Token ID11
Feature activation-1.73e-02

Pos logit contributions
xual+0.005
 relativity+0.005
blank+0.005
manship+0.005
 Ples+0.005
Neg logit contributions
utonium-0.007
puter-0.007
APH-0.006
awei-0.006
ritten-0.006
Token Balk
Token ID29643
Feature activation-5.62e-02

Pos logit contributions
utonium+0.021
puter+0.020
APH+0.017
awei+0.017
ordable+0.017
Neg logit contributions
xual-0.017
 relativity-0.016
blank-0.016
manship-0.016
 Ples-0.016
Tokenan
Token ID272
Feature activation+8.30e-02

Pos logit contributions
xual+0.154
 relativity+0.152
blank+0.150
manship+0.148
 Lovecraft+0.146
Neg logit contributions
utonium-0.162
puter-0.150
awei-0.132
APH-0.131
ordable-0.130
Token countries
Token ID2678
Feature activation+4.52e-02

Pos logit contributions
utonium+0.246
puter+0.229
awei+0.202
APH+0.201
ordable+0.198
Neg logit contributions
xual-0.220
 relativity-0.214
blank-0.214
manship-0.208
 Ples-0.207
Token.
Token ID13
Feature activation-4.33e-02

Pos logit contributions
utonium+0.142
puter+0.133
awei+0.119
APH+0.118
ordable+0.116
Neg logit contributions
xual-0.111
 relativity-0.108
blank-0.107
manship-0.104
 Ples-0.103
Token Analy
Token ID16213
Feature activation-4.97e-02

Pos logit contributions
xual+0.107
 relativity+0.105
blank+0.104
manship+0.101
 Lovecraft+0.099
Neg logit contributions
utonium-0.136
puter-0.127
APH-0.114
awei-0.113
ordable-0.110
Tokensts
Token ID6448
Feature activation-4.46e-01

Pos logit contributions
xual+0.104
 relativity+0.104
blank+0.102
 Ples+0.099
manship+0.098
Neg logit contributions
utonium-0.174
puter-0.163
awei-0.147
APH-0.147
ritten-0.145
Token say
Token ID910
Feature activation+1.53e-02

Pos logit contributions
xual+1.172
 relativity+1.155
blank+1.146
manship+1.121
 Ples+1.118
Neg logit contributions
utonium-1.324
puter-1.237
awei-1.092
APH-1.090
izoph-1.065
Token supplies
Token ID9416
Feature activation+6.74e-02

Pos logit contributions
utonium+0.046
puter+0.043
awei+0.038
APH+0.037
ordable+0.037
Neg logit contributions
xual-0.040
blank-0.039
 relativity-0.039
manship-0.038
 Lovecraft-0.037
Token could
Token ID714
Feature activation+6.69e-03

Pos logit contributions
utonium+0.210
puter+0.196
APH+0.174
awei+0.173
ordable+0.170
Neg logit contributions
xual-0.168
blank-0.163
 relativity-0.163
 Ples-0.158
 Lovecraft-0.156
Token in
Token ID287
Feature activation+1.61e-03

Pos logit contributions
utonium+0.020
puter+0.019
APH+0.017
awei+0.016
ordable+0.016
Neg logit contributions
xual-0.017
 relativity-0.017
blank-0.017
manship-0.016
 Ples-0.016
Token theory
Token ID4583
Feature activation-4.78e-03

Pos logit contributions
utonium+0.005
puter+0.005
APH+0.004
awei+0.004
ritten+0.004
Neg logit contributions
xual-0.004
blank-0.004
 relativity-0.004
manship-0.004
 Ples-0.004
Token group
Token ID1448
Feature activation+2.10e-03

Pos logit contributions
xual+0.208
 relativity+0.205
blank+0.203
manship+0.198
 Ples+0.197
Neg logit contributions
utonium-0.247
puter-0.231
awei-0.206
APH-0.204
ritten-0.200
Token.
Token ID13
Feature activation-2.57e-03

Pos logit contributions
utonium+0.007
puter+0.006
awei+0.005
APH+0.005
ritten+0.005
Neg logit contributions
xual-0.005
 relativity-0.005
blank-0.005
manship-0.005
 Ples-0.005
Token
Token ID198
Feature activation-9.73e-03

Pos logit contributions
xual+0.006
 relativity+0.006
blank+0.006
manship+0.006
 Ples+0.006
Neg logit contributions
utonium-0.008
puter-0.007
APH-0.007
awei-0.007
ritten-0.006
Token
Token ID198
Feature activation+1.78e-03

Pos logit contributions
xual+0.021
 relativity+0.021
blank+0.021
manship+0.021
 Ples+0.020
Neg logit contributions
utonium-0.033
puter-0.031
awei-0.028
APH-0.028
izoph-0.027
TokenAnaly
Token ID37702
Feature activation-3.68e-02

Pos logit contributions
utonium+0.005
puter+0.005
APH+0.005
awei+0.004
ritten+0.004
Neg logit contributions
xual-0.005
 relativity-0.005
 Ples-0.004
blank-0.004
manship-0.004
Tokensts
Token ID6448
Feature activation-4.40e-01

Pos logit contributions
xual+0.077
 relativity+0.076
blank+0.075
 Ples+0.073
manship+0.073
Neg logit contributions
utonium-0.130
puter-0.122
APH-0.109
awei-0.109
ritten-0.108
Token said
Token ID531
Feature activation-1.41e-02

Pos logit contributions
xual+1.155
 relativity+1.137
blank+1.129
manship+1.103
 Ples+1.102
Neg logit contributions
utonium-1.306
puter-1.219
awei-1.077
APH-1.076
ritten-1.050
Token the
Token ID262
Feature activation-4.26e-03

Pos logit contributions
xual+0.038
blank+0.037
 relativity+0.037
manship+0.036
 Ples+0.036
Neg logit contributions
utonium-0.041
puter-0.038
awei-0.034
APH-0.034
ordable-0.033
Token rupture
Token ID46836
Feature activation+1.20e-02

Pos logit contributions
xual+0.011
 relativity+0.011
blank+0.011
manship+0.010
 Ples+0.010
Neg logit contributions
utonium-0.013
puter-0.012
awei-0.011
APH-0.011
izoph-0.010
Token was
Token ID373
Feature activation+5.24e-03

Pos logit contributions
utonium+0.039
puter+0.036
awei+0.032
APH+0.032
ordable+0.032
Neg logit contributions
xual-0.029
 relativity-0.028
blank-0.028
 Ples-0.027
 Lovecraft-0.027
Token due
Token ID2233
Feature activation+2.08e-02

Pos logit contributions
utonium+0.015
puter+0.014
awei+0.012
APH+0.012
ritten+0.012
Neg logit contributions
xual-0.014
blank-0.014
 relativity-0.014
 Ples-0.014
manship-0.013
Token counterparts
Token ID16054
Feature activation+3.79e-02

Pos logit contributions
xual+0.042
 relativity+0.041
blank+0.041
manship+0.040
 Ples+0.040
Neg logit contributions
utonium-0.048
puter-0.045
awei-0.040
APH-0.040
ritten-0.039
Token.
Token ID13
Feature activation+1.95e-02

Pos logit contributions
utonium+0.122
puter+0.115
awei+0.103
APH+0.103
ordable+0.100
Neg logit contributions
xual-0.090
 relativity-0.088
blank-0.087
 Ples-0.084
manship-0.084
Token
Token ID198
Feature activation+2.57e-02

Pos logit contributions
utonium+0.061
puter+0.057
APH+0.051
awei+0.051
ritten+0.049
Neg logit contributions
xual-0.049
 relativity-0.047
blank-0.046
manship-0.046
 Ples-0.045
Token
Token ID198
Feature activation+3.90e-02

Pos logit contributions
utonium+0.087
puter+0.082
awei+0.074
APH+0.073
izoph+0.073
Neg logit contributions
xual-0.056
blank-0.056
 relativity-0.056
manship-0.054
 Ples-0.054
TokenAnaly
Token ID37702
Feature activation-1.86e-02

Pos logit contributions
utonium+0.121
puter+0.114
APH+0.104
awei+0.101
ritten+0.100
Neg logit contributions
xual-0.098
 relativity-0.096
blank-0.092
manship-0.091
 Ples-0.091
Tokensts
Token ID6448
Feature activation-4.30e-01

Pos logit contributions
xual+0.039
 relativity+0.038
blank+0.038
 Ples+0.037
manship+0.037
Neg logit contributions
utonium-0.066
puter-0.062
APH-0.056
awei-0.056
ritten-0.055
Token say
Token ID910
Feature activation+2.85e-02

Pos logit contributions
xual+1.070
 relativity+1.053
blank+1.044
manship+1.020
 Ples+1.017
Neg logit contributions
utonium-1.337
puter-1.253
awei-1.113
APH-1.112
izoph-1.087
Token that
Token ID326
Feature activation+3.99e-03

Pos logit contributions
utonium+0.083
puter+0.078
awei+0.069
APH+0.069
ritten+0.067
Neg logit contributions
xual-0.076
 relativity-0.073
blank-0.073
manship-0.071
 Ples-0.071
Token the
Token ID262
Feature activation+2.45e-02

Pos logit contributions
utonium+0.012
puter+0.012
APH+0.010
awei+0.010
izoph+0.010
Neg logit contributions
xual-0.010
 relativity-0.010
blank-0.010
manship-0.009
 Ples-0.009
Token Kremlin
Token ID19077
Feature activation-1.96e-02

Pos logit contributions
utonium+0.076
puter+0.071
APH+0.063
awei+0.063
ritten+0.062
Neg logit contributions
xual-0.061
 relativity-0.059
blank-0.059
manship-0.058
 Ples-0.057
Token
Token ID447
Feature activation+2.46e-02

Pos logit contributions
xual+0.043
 relativity+0.042
blank+0.042
manship+0.041
 Ples+0.041
Neg logit contributions
utonium-0.066
puter-0.063
APH-0.056
awei-0.056
ritten-0.055
Token as
Token ID355
Feature activation-6.67e-03

Pos logit contributions
xual+0.052
 relativity+0.051
blank+0.050
 Ples+0.049
manship+0.049
Neg logit contributions
utonium-0.062
puter-0.057
APH-0.051
awei-0.051
ritten-0.050
Token
Token ID564
Feature activation+1.57e-02

Pos logit contributions
xual+0.017
 relativity+0.017
blank+0.017
manship+0.016
 Ples+0.016
Neg logit contributions
utonium-0.020
puter-0.019
APH-0.017
awei-0.017
izoph-0.016
Token
Token ID250
Feature activation-1.34e-02

Pos logit contributions
utonium+0.034
puter+0.031
awei+0.025
APH+0.025
ritten+0.024
Neg logit contributions
xual-0.054
 relativity-0.054
blank-0.053
manship-0.053
 Ples-0.053
TokenHe
Token ID1544
Feature activation-1.59e-02

Pos logit contributions
xual+0.031
 relativity+0.031
blank+0.030
 Ples+0.030
manship+0.030
Neg logit contributions
utonium-0.044
puter-0.041
APH-0.037
awei-0.037
ritten-0.036
Token sed
Token ID10081
Feature activation+1.50e-02

Pos logit contributions
xual+0.035
 relativity+0.035
blank+0.034
 Ples+0.034
manship+0.034
Neg logit contributions
utonium-0.053
puter-0.050
awei-0.045
APH-0.045
ritten-0.044
Tokenuced
Token ID19513
Feature activation-4.06e-01

Pos logit contributions
utonium+0.044
puter+0.042
awei+0.037
APH+0.036
ritten+0.036
Neg logit contributions
xual-0.039
 relativity-0.039
blank-0.039
manship-0.038
 Ples-0.038
Token her
Token ID607
Feature activation+4.52e-02

Pos logit contributions
xual+1.023
 relativity+1.008
blank+1.000
manship+0.975
 Ples+0.968
Neg logit contributions
utonium-1.248
puter-1.170
awei-1.038
APH-1.037
izoph-1.012
Token through
Token ID832
Feature activation+1.24e-02

Pos logit contributions
utonium+0.140
puter+0.132
APH+0.117
awei+0.116
ritten+0.114
Neg logit contributions
xual-0.112
 relativity-0.110
blank-0.108
 Ples-0.106
manship-0.106
Token abduction
Token ID39630
Feature activation-4.39e-02

Pos logit contributions
utonium+0.038
puter+0.036
APH+0.032
awei+0.032
izoph+0.031
Neg logit contributions
xual-0.030
 relativity-0.030
blank-0.030
manship-0.029
 Ples-0.029
Token.
Token ID13
Feature activation+1.47e-03

Pos logit contributions
xual+0.101
 relativity+0.100
blank+0.099
 Ples+0.096
manship+0.096
Neg logit contributions
utonium-0.142
puter-0.134
APH-0.121
awei-0.120
ritten-0.117
Token
Token ID447
Feature activation+9.67e-03

Pos logit contributions
utonium+0.004
puter+0.004
APH+0.004
awei+0.004
ritten+0.004
Neg logit contributions
xual-0.004
 relativity-0.004
blank-0.004
manship-0.004
 Ples-0.004
Token and
Token ID290
Feature activation+1.64e-03

Pos logit contributions
utonium+0.061
puter+0.057
APH+0.051
awei+0.050
ritten+0.049
Neg logit contributions
xual-0.049
blank-0.048
 relativity-0.047
 Ples-0.046
 Lovecraft-0.045
Token his
Token ID465
Feature activation-6.05e-02

Pos logit contributions
utonium+0.005
puter+0.005
awei+0.004
APH+0.004
ritten+0.004
Neg logit contributions
xual-0.004
blank-0.004
 relativity-0.004
 Ples-0.004
manship-0.004
Token genius
Token ID15632
Feature activation+3.10e-02

Pos logit contributions
xual+0.148
blank+0.144
 relativity+0.142
 Ples+0.140
manship+0.139
Neg logit contributions
utonium-0.190
puter-0.179
awei-0.159
APH-0.158
ritten-0.156
Token for
Token ID329
Feature activation-3.28e-02

Pos logit contributions
utonium+0.105
puter+0.100
awei+0.089
APH+0.089
ritten+0.087
Neg logit contributions
xual-0.068
blank-0.066
 relativity-0.065
 Ples-0.064
 Lovecraft-0.063
Token sales
Token ID4200
Feature activation-8.47e-02

Pos logit contributions
xual+0.087
blank+0.085
 relativity+0.084
manship+0.083
 Ples+0.083
Neg logit contributions
utonium-0.096
puter-0.090
awei-0.080
APH-0.079
ordable-0.077
Tokenmanship
Token ID25428
Feature activation-4.04e-01

Pos logit contributions
xual+0.197
blank+0.192
 relativity+0.192
 Ples+0.187
 Lovecraft+0.184
Neg logit contributions
utonium-0.273
puter-0.259
awei-0.233
APH-0.232
ordable-0.225
Token to
Token ID284
Feature activation-2.70e-02

Pos logit contributions
xual+0.929
 relativity+0.912
blank+0.906
 Ples+0.881
manship+0.878
Neg logit contributions
utonium-1.326
puter-1.248
awei-1.119
APH-1.117
ritten-1.090
Token convince
Token ID11508
Feature activation-3.14e-02

Pos logit contributions
xual+0.066
 relativity+0.065
blank+0.065
manship+0.063
 Ples+0.063
Neg logit contributions
utonium-0.084
puter-0.079
awei-0.070
APH-0.070
ordable-0.069
Token NASA
Token ID8884
Feature activation+2.55e-02

Pos logit contributions
xual+0.087
 relativity+0.085
blank+0.085
manship+0.083
 Ples+0.082
Neg logit contributions
utonium-0.088
puter-0.083
awei-0.072
APH-0.072
ordable-0.070
Token to
Token ID284
Feature activation-4.18e-03

Pos logit contributions
utonium+0.077
puter+0.073
awei+0.064
APH+0.064
ordable+0.063
Neg logit contributions
xual-0.065
 relativity-0.063
blank-0.063
 Ples-0.062
manship-0.061
Token marry
Token ID12479
Feature activation-2.07e-02

Pos logit contributions
xual+0.011
 relativity+0.011
blank+0.011
manship+0.010
 Ples+0.010
Neg logit contributions
utonium-0.012
puter-0.012
awei-0.010
APH-0.010
ordable-0.010
Token the
Token ID262
Feature activation-2.16e-02

Pos logit contributions
xual+0.091
blank+0.089
 relativity+0.089
manship+0.086
 Ples+0.086
Neg logit contributions
utonium-0.108
puter-0.102
awei-0.091
APH-0.090
ordable-0.089
Token allegations
Token ID7636
Feature activation+1.83e-02

Pos logit contributions
xual+0.050
blank+0.049
 relativity+0.049
manship+0.048
 Ples+0.048
Neg logit contributions
utonium-0.070
puter-0.066
awei-0.059
APH-0.059
izoph-0.058
Token.
Token ID13
Feature activation+2.91e-02

Pos logit contributions
utonium+0.059
puter+0.056
awei+0.050
APH+0.050
ordable+0.049
Neg logit contributions
xual-0.043
 relativity-0.042
blank-0.042
 Ples-0.040
manship-0.040
Token
Token ID198
Feature activation+2.00e-02

Pos logit contributions
utonium+0.091
puter+0.085
APH+0.076
awei+0.075
ordable+0.074
Neg logit contributions
xual-0.072
 relativity-0.071
blank-0.070
manship-0.068
 Ples-0.068
Token
Token ID198
Feature activation+1.19e-02

Pos logit contributions
utonium+0.068
puter+0.064
awei+0.058
APH+0.057
izoph+0.057
Neg logit contributions
xual-0.044
blank-0.044
 relativity-0.044
manship-0.042
 Ples-0.042
TokenMc
Token ID9742
Feature activation-3.95e-01

Pos logit contributions
utonium+0.036
puter+0.034
APH+0.031
awei+0.030
ritten+0.030
Neg logit contributions
xual-0.031
 relativity-0.030
 Ples-0.029
blank-0.029
 Lovecraft-0.028
TokenDonald
Token ID7371
Feature activation+1.01e-01

Pos logit contributions
blank+1.028
xual+1.027
 relativity+1.017
manship+0.993
 Ples+0.988
Neg logit contributions
utonium-1.170
puter-1.081
awei-0.958
APH-0.953
izoph-0.936
Token's
Token ID338
Feature activation-6.82e-03

Pos logit contributions
utonium+0.370
puter+0.352
awei+0.320
APH+0.317
ritten+0.315
Neg logit contributions
xual-0.193
 relativity-0.186
blank-0.184
manship-0.181
 Ples-0.179
Token did
Token ID750
Feature activation-2.17e-02

Pos logit contributions
xual+0.018
blank+0.017
 relativity+0.017
 Ples+0.017
manship+0.017
Neg logit contributions
utonium-0.020
puter-0.019
awei-0.017
APH-0.017
ordable-0.016
Token not
Token ID407
Feature activation-4.22e-02

Pos logit contributions
xual+0.067
blank+0.066
 relativity+0.066
manship+0.065
 Ples+0.065
Neg logit contributions
utonium-0.054
puter-0.050
APH-0.043
awei-0.042
ordable-0.042
Token comment
Token ID2912
Feature activation-5.98e-03

Pos logit contributions
xual+0.119
 relativity+0.116
blank+0.116
manship+0.114
 Ples+0.114
Neg logit contributions
utonium-0.115
puter-0.108
awei-0.094
APH-0.093
ordable-0.092
Token Restaurant
Token ID26078
Feature activation+2.67e-03

Pos logit contributions
xual+0.120
 relativity+0.119
blank+0.117
manship+0.115
 Ples+0.113
Neg logit contributions
utonium-0.144
puter-0.135
APH-0.120
awei-0.120
izoph-0.117
Token manager
Token ID4706
Feature activation-6.24e-02

Pos logit contributions
utonium+0.008
puter+0.008
awei+0.007
APH+0.007
ritten+0.007
Neg logit contributions
blank-0.006
xual-0.006
 relativity-0.006
manship-0.006
 Ples-0.006
Token
Token ID564
Feature activation-1.35e-02

Pos logit contributions
xual+0.143
blank+0.140
 relativity+0.140
manship+0.136
 Ples+0.136
Neg logit contributions
utonium-0.203
puter-0.191
awei-0.172
APH-0.170
ritten-0.168
Token
Token ID246
Feature activation-8.58e-02

Pos logit contributions
xual+0.043
 relativity+0.042
blank+0.042
manship+0.041
 Ples+0.041
Neg logit contributions
utonium-0.033
puter-0.030
awei-0.026
APH-0.026
ritten-0.025
Tokenapolog
Token ID46407
Feature activation-6.80e-02

Pos logit contributions
 relativity+0.197
xual+0.197
blank+0.189
 Ples+0.189
manship+0.186
Neg logit contributions
utonium-0.281
puter-0.266
awei-0.238
APH-0.237
ordable-0.233
Tokenises
Token ID2696
Feature activation-3.89e-01

Pos logit contributions
xual+0.159
 relativity+0.158
blank+0.158
manship+0.154
 Ples+0.154
Neg logit contributions
utonium-0.219
puter-0.205
awei-0.183
APH-0.182
ordable-0.180
Token
Token ID447
Feature activation-1.94e-02

Pos logit contributions
xual+0.929
 relativity+0.922
blank+0.921
manship+0.895
 Ples+0.894
Neg logit contributions
utonium-1.226
puter-1.154
awei-1.029
APH-1.028
ordable-1.007
Token
Token ID247
Feature activation-4.09e-02

Pos logit contributions
xual+0.071
 relativity+0.071
blank+0.070
 Ples+0.069
manship+0.069
Neg logit contributions
utonium-0.037
puter-0.033
awei-0.027
APH-0.027
ritten-0.026
Token to
Token ID284
Feature activation-7.16e-03

Pos logit contributions
 relativity+0.097
xual+0.097
blank+0.096
 Ples+0.094
manship+0.094
Neg logit contributions
utonium-0.128
puter-0.121
awei-0.108
APH-0.107
ordable-0.106
Token homophobic
Token ID36034
Feature activation-6.91e-04

Pos logit contributions
xual+0.018
 relativity+0.018
blank+0.018
manship+0.018
 Ples+0.018
Neg logit contributions
utonium-0.021
puter-0.020
APH-0.018
awei-0.018
ordable-0.017
Token customers
Token ID4297
Feature activation+1.92e-02

Pos logit contributions
xual+0.002
 relativity+0.002
blank+0.002
manship+0.002
 Ples+0.002
Neg logit contributions
utonium-0.002
puter-0.002
awei-0.002
APH-0.002
ritten-0.002
Token Post
Token ID2947
Feature activation-1.15e-01

Pos logit contributions
utonium+0.232
puter+0.217
awei+0.191
APH+0.190
ordable+0.187
Neg logit contributions
xual-0.207
 relativity-0.204
blank-0.201
manship-0.197
 Ples-0.197
Token reading
Token ID3555
Feature activation-8.39e-02

Pos logit contributions
xual+0.257
 relativity+0.255
blank+0.250
 Ples+0.244
manship+0.242
Neg logit contributions
utonium-0.385
puter-0.365
APH-0.326
awei-0.325
ritten-0.322
Token "
Token ID366
Feature activation-4.42e-02

Pos logit contributions
xual+0.220
 relativity+0.215
blank+0.214
 Ples+0.208
manship+0.206
Neg logit contributions
utonium-0.250
puter-0.234
APH-0.206
awei-0.205
izoph-0.203
TokenISIS
Token ID29322
Feature activation-5.41e-02

Pos logit contributions
xual+0.114
 relativity+0.113
blank+0.109
manship+0.108
 Ples+0.108
Neg logit contributions
utonium-0.133
puter-0.125
APH-0.112
awei-0.110
ordable-0.108
Token Ur
Token ID8799
Feature activation+1.13e-02

Pos logit contributions
xual+0.131
 relativity+0.129
blank+0.128
manship+0.124
 Ples+0.123
Neg logit contributions
utonium-0.170
puter-0.160
APH-0.144
awei-0.142
izoph-0.140
Tokenges
Token ID3212
Feature activation-3.83e-01

Pos logit contributions
utonium+0.028
puter+0.026
awei+0.022
APH+0.022
izoph+0.022
Neg logit contributions
xual-0.035
 relativity-0.035
blank-0.034
 Lovecraft-0.034
manship-0.034
Token Jihad
Token ID35243
Feature activation+1.20e-02

Pos logit contributions
xual+0.976
 relativity+0.964
blank+0.952
manship+0.929
 Ples+0.925
Neg logit contributions
utonium-1.165
puter-1.091
awei-0.965
APH-0.962
ordable-0.943
Tokenists
Token ID1023
Feature activation+4.58e-02

Pos logit contributions
utonium+0.040
puter+0.038
APH+0.034
awei+0.034
ordable+0.033
Neg logit contributions
xual-0.027
 relativity-0.027
blank-0.026
manship-0.026
 Ples-0.025
Token To
Token ID1675
Feature activation-1.95e-02

Pos logit contributions
utonium+0.140
puter+0.132
APH+0.116
awei+0.116
ordable+0.114
Neg logit contributions
xual-0.116
 relativity-0.114
blank-0.112
manship-0.109
 Ples-0.109
Token Attack
Token ID8307
Feature activation-4.87e-02

Pos logit contributions
xual+0.048
 relativity+0.047
blank+0.046
manship+0.045
 Ples+0.044
Neg logit contributions
utonium-0.061
puter-0.058
APH-0.051
awei-0.051
izoph-0.050
Token Canadians
Token ID14008
Feature activation-1.93e-02

Pos logit contributions
xual+0.124
 relativity+0.123
blank+0.120
manship+0.117
 Ples+0.115
Neg logit contributions
utonium-0.148
puter-0.139
awei-0.122
APH-0.122
ordable-0.121
Token (*
Token ID20789
Feature activation-2.68e-02

Pos logit contributions
xual+0.043
 relativity+0.042
blank+0.041
manship+0.041
 Ples+0.040
Neg logit contributions
utonium-0.053
puter-0.050
APH-0.044
awei-0.044
ritten-0.043
Token mark
Token ID1317
Feature activation-2.10e-02

Pos logit contributions
xual+0.067
 relativity+0.066
blank+0.065
 Ples+0.064
manship+0.064
Neg logit contributions
utonium-0.082
puter-0.078
APH-0.068
awei-0.068
ritten-0.067
Token locations
Token ID7064
Feature activation+1.10e-02

Pos logit contributions
xual+0.055
 relativity+0.054
blank+0.053
 Ples+0.052
manship+0.052
Neg logit contributions
utonium-0.062
puter-0.059
APH-0.051
awei-0.051
ritten-0.050
Token as
Token ID355
Feature activation-1.42e-02

Pos logit contributions
utonium+0.034
puter+0.032
APH+0.028
awei+0.028
ritten+0.028
Neg logit contributions
xual-0.028
 relativity-0.027
blank-0.027
 Ples-0.026
manship-0.026
Token Sear
Token ID42016
Feature activation-7.55e-02

Pos logit contributions
xual+0.038
 relativity+0.037
blank+0.037
manship+0.036
 Ples+0.036
Neg logit contributions
utonium-0.042
puter-0.039
awei-0.034
APH-0.034
ritten-0.034
Tokenched
Token ID1740
Feature activation-3.83e-01

Pos logit contributions
xual+0.226
 relativity+0.223
blank+0.220
manship+0.217
 Ples+0.214
Neg logit contributions
utonium-0.198
puter-0.183
APH-0.160
awei-0.158
ordable-0.155
Token *)
Token ID31936
Feature activation+1.84e-01

Pos logit contributions
xual+0.900
 relativity+0.885
blank+0.876
manship+0.857
 Ples+0.853
Neg logit contributions
utonium-1.240
puter-1.166
awei-1.041
APH-1.040
izoph-1.018
Token Table
Token ID8655
Feature activation+1.41e-02

Pos logit contributions
utonium+0.613
puter+0.579
awei+0.520
APH+0.517
izoph+0.508
Neg logit contributions
xual-0.414
 relativity-0.404
blank-0.399
manship-0.392
 Ples-0.391
Token[
Token ID58
Feature activation+3.53e-02

Pos logit contributions
utonium+0.043
puter+0.040
APH+0.036
awei+0.036
ritten+0.035
Neg logit contributions
xual-0.036
 relativity-0.036
blank-0.035
 Ples-0.034
manship-0.034
Token index
Token ID6376
Feature activation-3.75e-02

Pos logit contributions
utonium+0.105
puter+0.098
APH+0.087
awei+0.086
ritten+0.084
Neg logit contributions
xual-0.093
 relativity-0.091
blank-0.089
 Ples-0.088
manship-0.088
TokenState
Token ID9012
Feature activation+1.19e-02

Pos logit contributions
xual+0.091
 relativity+0.090
blank+0.087
manship+0.086
 Ples+0.086
Neg logit contributions
utonium-0.118
puter-0.111
APH-0.100
awei-0.099
ritten-0.097
Token but
Token ID475
Feature activation-2.07e-02

Pos logit contributions
xual+0.074
blank+0.072
 relativity+0.072
manship+0.071
 Ples+0.070
Neg logit contributions
utonium-0.109
puter-0.103
awei-0.092
APH-0.092
ritten-0.090
Token the
Token ID262
Feature activation-2.31e-03

Pos logit contributions
xual+0.053
blank+0.052
 relativity+0.052
manship+0.051
 Ples+0.050
Neg logit contributions
utonium-0.062
puter-0.058
awei-0.052
APH-0.052
ritten-0.050
Token AI
Token ID9552
Feature activation-2.71e-02

Pos logit contributions
xual+0.006
blank+0.005
 relativity+0.005
manship+0.005
 Ples+0.005
Neg logit contributions
utonium-0.007
puter-0.007
APH-0.006
awei-0.006
izoph-0.006
Token January
Token ID3269
Feature activation-3.98e-02

Pos logit contributions
xual+0.060
blank+0.059
 relativity+0.059
 Ples+0.058
manship+0.057
Neg logit contributions
utonium-0.090
puter-0.085
APH-0.077
awei-0.076
ritten-0.075
Token analy
Token ID4284
Feature activation-4.53e-02

Pos logit contributions
xual+0.089
 relativity+0.088
blank+0.086
manship+0.084
 Ples+0.084
Neg logit contributions
utonium-0.132
puter-0.125
APH-0.111
awei-0.111
ritten-0.109
Tokenzes
Token ID12271
Feature activation-3.81e-01

Pos logit contributions
 relativity+0.116
xual+0.116
blank+0.115
manship+0.112
 Ples+0.111
Neg logit contributions
utonium-0.136
puter-0.126
APH-0.111
awei-0.111
ritten-0.109
Token your
Token ID534
Feature activation-6.60e-02

Pos logit contributions
xual+0.968
 relativity+0.947
blank+0.945
 Ples+0.920
manship+0.920
Neg logit contributions
utonium-1.159
puter-1.087
awei-0.966
APH-0.965
ritten-0.943
Token actions
Token ID4028
Feature activation+5.33e-02

Pos logit contributions
xual+0.176
 relativity+0.172
blank+0.172
 Ples+0.167
manship+0.167
Neg logit contributions
utonium-0.193
puter-0.181
awei-0.159
APH-0.159
izoph-0.155
Token at
Token ID379
Feature activation-3.51e-03

Pos logit contributions
utonium+0.169
puter+0.159
APH+0.142
awei+0.141
ritten+0.138
Neg logit contributions
xual-0.128
 relativity-0.126
blank-0.125
 Ples-0.122
manship-0.121
Token length
Token ID4129
Feature activation+9.52e-02

Pos logit contributions
xual+0.009
blank+0.009
 relativity+0.009
manship+0.009
 Ples+0.009
Neg logit contributions
utonium-0.010
puter-0.010
APH-0.009
awei-0.008
ritten-0.008
Token,
Token ID11
Feature activation-2.21e-02

Pos logit contributions
utonium+0.306
puter+0.288
APH+0.258
awei+0.257
ritten+0.251
Neg logit contributions
xual-0.223
 relativity-0.218
blank-0.217
 Ples-0.212
manship-0.211
Token F
Token ID376
Feature activation+1.08e-01

Pos logit contributions
xual+0.017
 relativity+0.017
blank+0.017
manship+0.017
 Ples+0.017
Neg logit contributions
utonium-0.018
puter-0.017
APH-0.015
awei-0.015
izoph-0.014
TokenED
Token ID1961
Feature activation-1.41e-01

Pos logit contributions
utonium+0.198
puter+0.174
APH+0.145
awei+0.138
ritten+0.136
Neg logit contributions
xual-0.408
 relativity-0.402
blank-0.398
 Ples-0.397
manship-0.397
Token state
Token ID1181
Feature activation-4.95e-02

Pos logit contributions
xual+0.324
 relativity+0.316
blank+0.312
manship+0.306
 Ples+0.306
Neg logit contributions
utonium-0.467
puter-0.440
APH-0.399
awei-0.389
ritten-0.387
Token)
Token ID8
Feature activation-1.23e-02

Pos logit contributions
xual+0.106
 relativity+0.103
blank+0.102
 Ples+0.100
manship+0.099
Neg logit contributions
utonium-0.171
puter-0.162
APH-0.145
awei-0.144
ritten-0.142
Token accompl
Token ID6424
Feature activation-5.72e-02

Pos logit contributions
xual+0.027
 relativity+0.026
blank+0.026
manship+0.025
 Ples+0.025
Neg logit contributions
utonium-0.042
puter-0.039
awei-0.036
APH-0.035
ordable-0.035
Tokenishes
Token ID5614
Feature activation-3.76e-01

Pos logit contributions
xual+0.161
 relativity+0.160
blank+0.158
manship+0.156
 Ples+0.155
Neg logit contributions
utonium-0.159
puter-0.146
awei-0.129
APH-0.128
ordable-0.126
Token all
Token ID477
Feature activation+3.90e-03

Pos logit contributions
xual+0.967
 relativity+0.952
blank+0.945
manship+0.925
 Ples+0.922
Neg logit contributions
utonium-1.134
puter-1.059
awei-0.939
APH-0.936
izoph-0.916
Token of
Token ID286
Feature activation+5.60e-02

Pos logit contributions
utonium+0.013
puter+0.012
APH+0.011
awei+0.011
izoph+0.011
Neg logit contributions
xual-0.009
blank-0.009
 relativity-0.009
manship-0.008
 Ples-0.008
Token these
Token ID777
Feature activation+5.09e-02

Pos logit contributions
utonium+0.158
puter+0.146
APH+0.129
awei+0.128
izoph+0.125
Neg logit contributions
xual-0.156
 relativity-0.152
blank-0.152
 Ples-0.149
manship-0.149
Token,
Token ID11
Feature activation+7.34e-03

Pos logit contributions
utonium+0.165
puter+0.155
awei+0.139
APH+0.139
izoph+0.136
Neg logit contributions
xual-0.120
 relativity-0.117
blank-0.116
manship-0.114
 Ples-0.113
Token very
Token ID845
Feature activation+4.05e-03

Pos logit contributions
utonium+0.023
puter+0.022
APH+0.019
awei+0.019
ordable+0.019
Neg logit contributions
xual-0.018
 relativity-0.017
blank-0.017
manship-0.017
 Ples-0.017
Token of
Token ID286
Feature activation-3.81e-02

Pos logit contributions
xual+0.092
 relativity+0.091
blank+0.090
manship+0.087
 Ples+0.087
Neg logit contributions
utonium-0.180
puter-0.170
awei-0.154
APH-0.154
ordable-0.151
Token the
Token ID262
Feature activation-4.57e-02

Pos logit contributions
xual+0.109
 relativity+0.108
blank+0.107
manship+0.105
 Ples+0.104
Neg logit contributions
utonium-0.103
puter-0.096
awei-0.084
APH-0.084
ordable-0.081
Token company
Token ID1664
Feature activation+4.03e-03

Pos logit contributions
xual+0.126
 relativity+0.124
blank+0.124
manship+0.121
 Ples+0.120
Neg logit contributions
utonium-0.129
puter-0.121
awei-0.106
APH-0.105
ordable-0.102
Token's
Token ID338
Feature activation-1.70e-02

Pos logit contributions
utonium+0.015
puter+0.014
awei+0.013
APH+0.013
ordable+0.013
Neg logit contributions
xual-0.008
 relativity-0.007
blank-0.007
 Ples-0.007
manship-0.007
Token enroll
Token ID14627
Feature activation+1.27e-02

Pos logit contributions
xual+0.052
 relativity+0.052
blank+0.052
manship+0.050
 Ples+0.050
Neg logit contributions
utonium-0.042
puter-0.039
awei-0.034
APH-0.033
ordable-0.033
Tokenments
Token ID902
Feature activation-3.75e-01

Pos logit contributions
utonium+0.041
puter+0.039
awei+0.035
APH+0.034
ordable+0.034
Neg logit contributions
xual-0.030
 relativity-0.030
blank-0.029
 Ples-0.028
manship-0.028
Token allegedly
Token ID7910
Feature activation+2.56e-03

Pos logit contributions
xual+0.975
 relativity+0.963
blank+0.954
 Ples+0.931
manship+0.931
Neg logit contributions
utonium-1.121
puter-1.047
awei-0.926
APH-0.922
ordable-0.902
Token involved
Token ID2950
Feature activation-8.45e-02

Pos logit contributions
utonium+0.008
puter+0.007
awei+0.006
APH+0.006
ordable+0.006
Neg logit contributions
xual-0.007
 relativity-0.006
blank-0.006
 Ples-0.006
manship-0.006
Token overriding
Token ID44987
Feature activation-5.64e-02

Pos logit contributions
xual+0.233
 relativity+0.229
blank+0.227
manship+0.223
 Ples+0.221
Neg logit contributions
utonium-0.240
puter-0.224
awei-0.197
APH-0.196
ordable-0.191
Token a
Token ID257
Feature activation-1.52e-02

Pos logit contributions
xual+0.154
 relativity+0.150
blank+0.149
manship+0.146
 Lovecraft+0.145
Neg logit contributions
utonium-0.160
puter-0.150
awei-0.133
APH-0.131
ordable-0.130
Token system
Token ID1080
Feature activation+3.91e-02

Pos logit contributions
xual+0.041
 relativity+0.040
blank+0.040
manship+0.039
 Ples+0.039
Neg logit contributions
utonium-0.044
puter-0.041
awei-0.036
APH-0.036
ritten-0.035
Token will
Token ID481
Feature activation-1.91e-02

Pos logit contributions
xual+0.086
 relativity+0.085
blank+0.084
 Ples+0.082
manship+0.082
Neg logit contributions
utonium-0.124
puter-0.116
awei-0.103
APH-0.103
ordable-0.101
Token receive
Token ID3328
Feature activation-3.22e-02

Pos logit contributions
xual+0.047
 relativity+0.046
blank+0.045
manship+0.044
 Ples+0.044
Neg logit contributions
utonium-0.060
puter-0.056
awei-0.050
APH-0.050
ritten-0.049
Token the
Token ID262
Feature activation-2.43e-02

Pos logit contributions
xual+0.090
 relativity+0.088
blank+0.088
manship+0.086
 Ples+0.086
Neg logit contributions
utonium-0.090
puter-0.084
awei-0.074
APH-0.073
ordable-0.072
Token income
Token ID3739
Feature activation+6.09e-03

Pos logit contributions
xual+0.061
 relativity+0.060
blank+0.059
manship+0.059
 Ples+0.058
Neg logit contributions
utonium-0.074
puter-0.070
awei-0.062
APH-0.061
ordable-0.061
Token uncond
Token ID31776
Feature activation-3.06e-02

Pos logit contributions
utonium+0.019
puter+0.018
awei+0.016
APH+0.016
ordable+0.015
Neg logit contributions
xual-0.015
 relativity-0.015
blank-0.015
manship-0.014
 Ples-0.014
Tokenitionally
Token ID8736
Feature activation-3.65e-01

Pos logit contributions
xual+0.084
 relativity+0.083
blank+0.083
manship+0.081
 Ples+0.081
Neg logit contributions
utonium-0.087
puter-0.081
awei-0.071
APH-0.071
izoph-0.069
Token while
Token ID981
Feature activation-1.04e-02

Pos logit contributions
xual+0.825
 relativity+0.810
blank+0.803
 Ples+0.783
manship+0.782
Neg logit contributions
utonium-1.217
puter-1.143
awei-1.025
APH-1.025
ordable-1.005
Token others
Token ID1854
Feature activation+4.84e-02

Pos logit contributions
xual+0.027
 relativity+0.027
blank+0.027
manship+0.026
 Ples+0.026
Neg logit contributions
utonium-0.031
puter-0.029
awei-0.025
APH-0.025
ordable-0.025
Token will
Token ID481
Feature activation-1.94e-02

Pos logit contributions
utonium+0.160
puter+0.150
APH+0.134
awei+0.134
ordable+0.132
Neg logit contributions
xual-0.111
 relativity-0.108
blank-0.108
 Ples-0.105
manship-0.104
Token have
Token ID423
Feature activation-5.44e-02

Pos logit contributions
xual+0.048
 relativity+0.047
blank+0.047
manship+0.046
 Ples+0.046
Neg logit contributions
utonium-0.061
puter-0.057
APH-0.050
awei-0.050
ritten-0.050
Token conditions
Token ID3403
Feature activation-1.09e-02

Pos logit contributions
xual+0.139
 relativity+0.136
blank+0.135
 Ples+0.132
manship+0.132
Neg logit contributions
utonium-0.166
puter-0.155
awei-0.138
APH-0.137
ordable-0.135
Token
Token ID198
Feature activation+7.58e-03

Pos logit contributions
xual+0.008
blank+0.008
 relativity+0.008
manship+0.007
 Ples+0.007
Neg logit contributions
utonium-0.012
puter-0.011
awei-0.010
APH-0.010
izoph-0.010
TokenNo
Token ID2949
Feature activation-4.02e-03

Pos logit contributions
utonium+0.023
puter+0.022
APH+0.020
awei+0.019
ritten+0.019
Neg logit contributions
xual-0.019
 relativity-0.019
 Ples-0.018
manship-0.018
blank-0.018
Token major
Token ID1688
Feature activation-3.33e-02

Pos logit contributions
xual+0.010
 relativity+0.010
blank+0.010
manship+0.010
 Ples+0.010
Neg logit contributions
utonium-0.012
puter-0.012
APH-0.010
awei-0.010
ordable-0.010
Token out
Token ID503
Feature activation-1.19e-02

Pos logit contributions
xual+0.085
 relativity+0.083
blank+0.082
 Ples+0.081
manship+0.080
Neg logit contributions
utonium-0.101
puter-0.094
awei-0.084
APH-0.084
ordable-0.082
Tokenbur
Token ID6236
Feature activation+1.61e-02

Pos logit contributions
 relativity+0.027
xual+0.027
 Lovecraft+0.026
blank+0.026
 Ples+0.026
Neg logit contributions
utonium-0.039
puter-0.037
APH-0.033
awei-0.033
ordable-0.033
Tokensts
Token ID6448
Feature activation-3.63e-01

Pos logit contributions
utonium+0.057
puter+0.054
awei+0.049
APH+0.049
ritten+0.048
Neg logit contributions
xual-0.033
 relativity-0.032
blank-0.032
manship-0.031
 Ples-0.031
Token marked
Token ID7498
Feature activation+6.10e-02

Pos logit contributions
xual+0.926
 relativity+0.916
blank+0.900
 Ples+0.881
manship+0.872
Neg logit contributions
utonium-1.103
puter-1.031
awei-0.915
APH-0.912
ordable-0.896
Token the
Token ID262
Feature activation+7.41e-02

Pos logit contributions
utonium+0.176
puter+0.165
APH+0.147
awei+0.145
ritten+0.142
Neg logit contributions
xual-0.162
 relativity-0.161
blank-0.158
manship-0.155
 Ples-0.154
Token SB
Token ID18056
Feature activation-5.18e-02

Pos logit contributions
utonium+0.222
puter+0.206
APH+0.184
awei+0.183
ritten+0.179
Neg logit contributions
xual-0.193
 relativity-0.189
blank-0.187
manship-0.183
 Ples-0.182
Token6
Token ID21
Feature activation-1.98e-02

Pos logit contributions
xual+0.150
 relativity+0.148
blank+0.145
 Ples+0.144
manship+0.143
Neg logit contributions
utonium-0.140
puter-0.128
APH-0.114
awei-0.112
ordable-0.110
Token hearing
Token ID4854
Feature activation+1.24e-02

Pos logit contributions
xual+0.048
 relativity+0.048
blank+0.047
manship+0.047
 Ples+0.046
Neg logit contributions
utonium-0.061
puter-0.057
APH-0.051
awei-0.051
ritten-0.050
Token h
Token ID289
Feature activation-5.27e-03

Pos logit contributions
xual+0.073
 relativity+0.072
blank+0.071
manship+0.070
 Ples+0.069
Neg logit contributions
utonium-0.089
puter-0.084
awei-0.074
APH-0.074
ritten-0.072
Tokeniked
Token ID17951
Feature activation-1.00e-03

Pos logit contributions
xual+0.013
 relativity+0.012
blank+0.012
manship+0.012
 Ples+0.012
Neg logit contributions
utonium-0.017
puter-0.016
awei-0.014
APH-0.014
ritten-0.014
Token in
Token ID287
Feature activation+1.20e-02

Pos logit contributions
xual+0.003
 relativity+0.003
blank+0.003
manship+0.003
 Ples+0.002
Neg logit contributions
utonium-0.003
puter-0.003
APH-0.002
awei-0.002
ordable-0.002
Token rain
Token ID6290
Feature activation-5.41e-03

Pos logit contributions
utonium+0.035
puter+0.033
APH+0.029
awei+0.029
ordable+0.028
Neg logit contributions
xual-0.032
 relativity-0.031
blank-0.031
manship-0.030
 Ples-0.030
Tokenfore
Token ID754
Feature activation+1.55e-02

Pos logit contributions
xual+0.013
 relativity+0.013
blank+0.012
manship+0.012
 Ples+0.012
Neg logit contributions
utonium-0.017
puter-0.016
APH-0.014
awei-0.014
izoph-0.014
Tokensts
Token ID6448
Feature activation-3.62e-01

Pos logit contributions
utonium+0.055
puter+0.052
APH+0.047
awei+0.047
ritten+0.046
Neg logit contributions
xual-0.032
 relativity-0.031
blank-0.030
 Ples-0.030
manship-0.030
Token,
Token ID11
Feature activation+5.58e-03

Pos logit contributions
xual+0.852
 relativity+0.840
blank+0.830
manship+0.810
 Ples+0.808
Neg logit contributions
utonium-1.173
puter-1.102
APH-0.985
awei-0.985
izoph-0.963
Token in
Token ID287
Feature activation+2.72e-02

Pos logit contributions
utonium+0.017
puter+0.016
APH+0.015
awei+0.014
ordable+0.014
Neg logit contributions
xual-0.014
 relativity-0.014
blank-0.013
manship-0.013
 Ples-0.013
Token deserts
Token ID45288
Feature activation-9.14e-02

Pos logit contributions
utonium+0.083
puter+0.078
APH+0.069
awei+0.069
ordable+0.068
Neg logit contributions
xual-0.068
 relativity-0.067
blank-0.066
manship-0.065
 Ples-0.064
Token,
Token ID11
Feature activation-1.55e-02

Pos logit contributions
xual+0.211
 relativity+0.207
blank+0.203
manship+0.199
 Ples+0.198
Neg logit contributions
utonium-0.297
puter-0.281
APH-0.253
awei-0.251
izoph-0.247
Token and
Token ID290
Feature activation-2.11e-02

Pos logit contributions
xual+0.039
 relativity+0.039
blank+0.038
manship+0.038
 Ples+0.037
Neg logit contributions
utonium-0.047
puter-0.044
APH-0.040
awei-0.040
ordable-0.039
Tokenple
Token ID1154
Feature activation+1.11e-01

Pos logit contributions
xual+0.141
 relativity+0.140
blank+0.138
manship+0.136
 Ples+0.136
Neg logit contributions
utonium-0.107
puter-0.098
APH-0.084
awei-0.084
ritten-0.081
Tokentes
Token ID4879
Feature activation+4.98e-02

Pos logit contributions
utonium+0.370
puter+0.348
ordable+0.310
APH+0.309
awei+0.308
Neg logit contributions
 relativity-0.251
xual-0.250
blank-0.246
manship-0.239
 Ples-0.234
Token glucose
Token ID15701
Feature activation-4.07e-02

Pos logit contributions
utonium+0.140
puter+0.131
APH+0.114
awei+0.114
ritten+0.112
Neg logit contributions
xual-0.138
 relativity-0.136
blank-0.135
manship-0.133
 Ples-0.131
Token and
Token ID290
Feature activation-1.52e-02

Pos logit contributions
xual+0.100
 relativity+0.099
blank+0.098
manship+0.096
 Ples+0.096
Neg logit contributions
utonium-0.127
puter-0.119
APH-0.106
awei-0.105
ordable-0.103
Token glyc
Token ID40232
Feature activation+7.52e-04

Pos logit contributions
xual+0.039
blank+0.038
 relativity+0.038
manship+0.037
 Ples+0.037
Neg logit contributions
utonium-0.046
puter-0.043
awei-0.038
APH-0.038
izoph-0.037
Tokenogen
Token ID6644
Feature activation+4.08e-01

Pos logit contributions
utonium+0.002
puter+0.002
awei+0.001
APH+0.001
ritten+0.001
Neg logit contributions
xual-0.002
 relativity-0.002
blank-0.002
manship-0.002
 Ples-0.002
Token rapidly
Token ID8902
Feature activation+3.67e-02

Pos logit contributions
utonium+1.270
puter+1.196
APH+1.061
awei+1.045
ordable+1.027
Neg logit contributions
xual-0.995
 relativity-0.974
blank-0.964
 Ples-0.951
manship-0.944
Token,
Token ID11
Feature activation-1.49e-02

Pos logit contributions
utonium+0.116
puter+0.108
APH+0.097
awei+0.096
ordable+0.094
Neg logit contributions
xual-0.088
 relativity-0.087
blank-0.086
manship-0.084
 Ples-0.084
Token forcing
Token ID10833
Feature activation+1.52e-02

Pos logit contributions
xual+0.038
 relativity+0.037
blank+0.037
manship+0.036
 Ples+0.036
Neg logit contributions
utonium-0.046
puter-0.043
APH-0.038
awei-0.038
ordable-0.037
Token the
Token ID262
Feature activation-1.58e-03

Pos logit contributions
utonium+0.043
puter+0.040
awei+0.035
APH+0.035
izoph+0.035
Neg logit contributions
xual-0.042
 relativity-0.041
blank-0.041
manship-0.040
 Ples-0.040
Token body
Token ID1767
Feature activation-1.05e-02

Pos logit contributions
xual+0.005
blank+0.004
 relativity+0.004
manship+0.004
 Ples+0.004
Neg logit contributions
utonium-0.004
puter-0.004
APH-0.003
awei-0.003
izoph-0.003
Token receiver
Token ID9733
Feature activation-4.64e-02

Pos logit contributions
xual+0.299
 relativity+0.290
blank+0.287
 Ples+0.287
manship+0.286
Neg logit contributions
utonium-0.321
puter-0.303
APH-0.269
awei-0.265
ordable-0.259
Token with
Token ID351
Feature activation-3.71e-03

Pos logit contributions
xual+0.112
 relativity+0.109
blank+0.108
 Ples+0.106
manship+0.105
Neg logit contributions
utonium-0.148
puter-0.140
awei-0.124
APH-0.124
ritten-0.121
Token an
Token ID281
Feature activation-3.94e-03

Pos logit contributions
xual+0.010
blank+0.010
 relativity+0.010
manship+0.010
 Ples+0.010
Neg logit contributions
utonium-0.010
puter-0.010
awei-0.009
APH-0.009
ritten-0.008
Token internal
Token ID5387
Feature activation-6.88e-02

Pos logit contributions
xual+0.011
 relativity+0.010
blank+0.010
manship+0.010
 Ples+0.010
Neg logit contributions
utonium-0.011
puter-0.011
awei-0.010
APH-0.010
ordable-0.009
Token fer
Token ID11354
Feature activation-2.15e-03

Pos logit contributions
xual+0.170
 relativity+0.163
blank+0.162
manship+0.160
 Ples+0.158
Neg logit contributions
utonium-0.217
puter-0.205
awei-0.182
APH-0.181
ritten-0.177
Tokenrite
Token ID6525
Feature activation+3.26e-01

Pos logit contributions
xual+0.009
 relativity+0.009
blank+0.009
manship+0.009
 Ples+0.009
Neg logit contributions
utonium-0.003
puter-0.003
awei-0.002
APH-0.002
izoph-0.002
Token rod
Token ID15299
Feature activation+6.22e-02

Pos logit contributions
utonium+1.060
puter+0.999
APH+0.891
awei+0.887
ritten+0.869
Neg logit contributions
xual-0.774
 relativity-0.745
blank-0.728
manship-0.727
 Ples-0.721
Token antenna
Token ID20509
Feature activation-3.99e-02

Pos logit contributions
utonium+0.197
puter+0.187
awei+0.165
APH+0.165
ritten+0.161
Neg logit contributions
xual-0.151
 relativity-0.147
blank-0.146
 Ples-0.142
manship-0.142
Token and
Token ID290
Feature activation+7.14e-03

Pos logit contributions
xual+0.096
 relativity+0.094
blank+0.093
manship+0.091
 Ples+0.091
Neg logit contributions
utonium-0.127
puter-0.120
awei-0.106
APH-0.106
ordable-0.104
Token start
Token ID923
Feature activation-3.04e-02

Pos logit contributions
utonium+0.022
puter+0.020
APH+0.018
awei+0.018
ritten+0.018
Neg logit contributions
xual-0.018
blank-0.018
 relativity-0.018
manship-0.017
 Ples-0.017
Token moving
Token ID3867
Feature activation+6.94e-02

Pos logit contributions
xual+0.079
 relativity+0.078
blank+0.077
 Ples+0.075
manship+0.075
Neg logit contributions
utonium-0.091
puter-0.086
awei-0.075
APH-0.075
izoph-0.073
Token summer
Token ID3931
Feature activation+3.41e-02

Pos logit contributions
utonium+0.176
puter+0.165
APH+0.147
awei+0.147
ritten+0.145
Neg logit contributions
xual-0.135
blank-0.131
 relativity-0.131
manship-0.128
 Ples-0.127
Token
Token ID447
Feature activation+4.15e-02

Pos logit contributions
utonium+0.112
puter+0.106
APH+0.095
awei+0.095
ritten+0.093
Neg logit contributions
xual-0.077
 relativity-0.076
blank-0.075
 Ples-0.073
manship-0.073
Token
Token ID247
Feature activation+8.26e-03

Pos logit contributions
utonium+0.079
puter+0.070
awei+0.058
APH+0.057
izoph+0.055
Neg logit contributions
xual-0.153
 relativity-0.151
blank-0.151
 Ples-0.149
manship-0.148
Tokens
Token ID82
Feature activation-7.27e-03

Pos logit contributions
utonium+0.027
puter+0.025
APH+0.023
awei+0.023
ritten+0.022
Neg logit contributions
xual-0.019
 relativity-0.019
blank-0.018
 Ples-0.018
manship-0.018
Token euph
Token ID40381
Feature activation+3.77e-02

Pos logit contributions
xual+0.019
 relativity+0.018
blank+0.018
manship+0.018
 Ples+0.018
Neg logit contributions
utonium-0.022
puter-0.020
APH-0.018
awei-0.018
ritten-0.018
Tokenoria
Token ID7661
Feature activation+3.08e-01

Pos logit contributions
utonium+0.103
puter+0.096
APH+0.083
awei+0.083
ritten+0.081
Neg logit contributions
xual-0.108
 relativity-0.107
blank-0.106
manship-0.104
 Ples-0.103
Token has
Token ID468
Feature activation+2.54e-02

Pos logit contributions
utonium+1.007
puter+0.950
awei+0.854
APH+0.853
ritten+0.834
Neg logit contributions
xual-0.699
blank-0.688
 relativity-0.680
 Ples-0.662
manship-0.654
Token vanished
Token ID23717
Feature activation+2.28e-02

Pos logit contributions
utonium+0.076
puter+0.071
awei+0.063
APH+0.063
ritten+0.062
Neg logit contributions
xual-0.066
 relativity-0.064
blank-0.064
manship-0.062
 Ples-0.062
Token.
Token ID13
Feature activation+8.90e-03

Pos logit contributions
utonium+0.074
puter+0.070
awei+0.062
APH+0.062
ritten+0.061
Neg logit contributions
xual-0.053
 relativity-0.052
blank-0.052
manship-0.050
 Ples-0.050
Token So
Token ID1406
Feature activation+2.54e-02

Pos logit contributions
utonium+0.028
puter+0.026
APH+0.023
awei+0.023
izoph+0.023
Neg logit contributions
xual-0.022
 relativity-0.022
blank-0.021
manship-0.021
 Ples-0.020
Token far
Token ID1290
Feature activation+4.88e-02

Pos logit contributions
utonium+0.080
puter+0.075
APH+0.067
awei+0.066
izoph+0.065
Neg logit contributions
xual-0.062
 relativity-0.060
blank-0.060
 Ples-0.059
manship-0.059
Token
Token ID564
Feature activation+4.20e-02

Pos logit contributions
utonium+0.185
puter+0.173
APH+0.155
awei+0.154
ritten+0.150
Neg logit contributions
xual-0.147
 relativity-0.143
blank-0.141
manship-0.138
 Ples-0.136
Token
Token ID250
Feature activation+1.30e-02

Pos logit contributions
utonium+0.113
puter+0.105
awei+0.091
APH+0.091
izoph+0.089
Neg logit contributions
xual-0.121
 relativity-0.120
blank-0.119
 Ples-0.117
manship-0.116
TokenThe
Token ID464
Feature activation-1.49e-02

Pos logit contributions
utonium+0.039
puter+0.037
APH+0.033
awei+0.033
ritten+0.032
Neg logit contributions
xual-0.034
 relativity-0.033
blank-0.032
manship-0.031
 Ples-0.031
Token one
Token ID530
Feature activation+2.29e-03

Pos logit contributions
xual+0.038
 relativity+0.037
blank+0.037
manship+0.036
 Ples+0.035
Neg logit contributions
utonium-0.046
puter-0.043
awei-0.038
APH-0.038
ritten-0.037
Token kilomet
Token ID11866
Feature activation+7.28e-02

Pos logit contributions
utonium+0.008
puter+0.007
awei+0.007
APH+0.007
ritten+0.007
Neg logit contributions
xual-0.005
 relativity-0.005
blank-0.005
 Ples-0.005
manship-0.005
Tokenre
Token ID260
Feature activation+2.79e-01

Pos logit contributions
utonium+0.243
puter+0.230
APH+0.209
awei+0.205
ritten+0.202
Neg logit contributions
xual-0.161
 relativity-0.161
blank-0.156
manship-0.155
 Ples-0.153
Token to
Token ID284
Feature activation+3.02e-02

Pos logit contributions
utonium+0.853
puter+0.807
awei+0.715
APH+0.713
ritten+0.702
Neg logit contributions
xual-0.703
 relativity-0.677
blank-0.674
manship-0.658
 Ples-0.657
Token go
Token ID467
Feature activation+2.80e-02

Pos logit contributions
utonium+0.090
puter+0.085
awei+0.074
APH+0.074
ritten+0.073
Neg logit contributions
xual-0.079
 relativity-0.077
blank-0.076
manship-0.075
 Ples-0.074
Token mark
Token ID1317
Feature activation+4.52e-02

Pos logit contributions
utonium+0.089
puter+0.083
awei+0.074
APH+0.074
ritten+0.073
Neg logit contributions
xual-0.068
 relativity-0.066
blank-0.066
manship-0.064
 Ples-0.064
Token was
Token ID373
Feature activation+8.56e-03

Pos logit contributions
utonium+0.141
puter+0.134
awei+0.118
APH+0.118
ritten+0.116
Neg logit contributions
xual-0.110
 relativity-0.108
blank-0.107
 Ples-0.104
 Lovecraft-0.103
Token the
Token ID262
Feature activation+3.61e-02

Pos logit contributions
utonium+0.025
puter+0.024
APH+0.021
awei+0.021
ritten+0.021
Neg logit contributions
xual-0.022
 relativity-0.022
blank-0.022
manship-0.021
 Ples-0.021
Token in
Token ID287
Feature activation+1.78e-02

Pos logit contributions
utonium+0.045
puter+0.043
awei+0.038
APH+0.038
izoph+0.037
Neg logit contributions
xual-0.035
 relativity-0.035
blank-0.035
manship-0.034
 Ples-0.034
Token court
Token ID2184
Feature activation-2.59e-02

Pos logit contributions
utonium+0.044
puter+0.041
awei+0.035
APH+0.035
ordable+0.034
Neg logit contributions
xual-0.055
 relativity-0.054
blank-0.054
manship-0.053
 Ples-0.052
Token on
Token ID319
Feature activation-2.34e-02

Pos logit contributions
xual+0.064
 relativity+0.063
blank+0.062
manship+0.061
 Ples+0.060
Neg logit contributions
utonium-0.081
puter-0.076
awei-0.068
APH-0.068
izoph-0.066
Token the
Token ID262
Feature activation+9.88e-03

Pos logit contributions
xual+0.056
 relativity+0.055
blank+0.054
manship+0.053
 Ples+0.053
Neg logit contributions
utonium-0.075
puter-0.070
awei-0.063
APH-0.063
ritten-0.061
Token inter
Token ID987
Feature activation+5.20e-02

Pos logit contributions
utonium+0.030
puter+0.028
awei+0.025
APH+0.025
izoph+0.024
Neg logit contributions
xual-0.025
 relativity-0.025
blank-0.025
manship-0.024
 Ples-0.024
Tokenlock
Token ID5354
Feature activation+2.75e-01

Pos logit contributions
utonium+0.139
puter+0.130
awei+0.113
APH+0.112
ritten+0.110
Neg logit contributions
xual-0.151
 relativity-0.149
blank-0.147
 Ples-0.145
manship-0.145
Token violation
Token ID8747
Feature activation-1.68e-02

Pos logit contributions
utonium+0.884
puter+0.843
awei+0.752
APH+0.743
ritten+0.733
Neg logit contributions
xual-0.648
 relativity-0.626
blank-0.624
 Ples-0.606
manship-0.600
Token on
Token ID319
Feature activation-4.70e-03

Pos logit contributions
xual+0.037
 relativity+0.036
blank+0.036
 Ples+0.035
manship+0.034
Neg logit contributions
utonium-0.057
puter-0.054
APH-0.048
awei-0.048
ritten-0.047
Token May
Token ID1737
Feature activation+4.78e-03

Pos logit contributions
xual+0.011
 relativity+0.011
blank+0.011
manship+0.011
 Ples+0.011
Neg logit contributions
utonium-0.015
puter-0.014
awei-0.013
APH-0.013
ritten-0.012
Token 26
Token ID2608
Feature activation-3.70e-02

Pos logit contributions
utonium+0.010
puter+0.009
awei+0.008
APH+0.008
izoph+0.008
Neg logit contributions
xual-0.016
 relativity-0.016
blank-0.016
manship-0.016
 Ples-0.016
Token.
Token ID13
Feature activation-7.82e-03

Pos logit contributions
xual+0.097
 relativity+0.095
blank+0.094
 Ples+0.092
manship+0.092
Neg logit contributions
utonium-0.110
puter-0.103
APH-0.091
awei-0.090
ritten-0.089
Token,
Token ID11
Feature activation-2.69e-02

Pos logit contributions
xual+0.002
 relativity+0.002
blank+0.002
 Ples+0.002
manship+0.002
Neg logit contributions
utonium-0.002
puter-0.002
awei-0.002
APH-0.002
ordable-0.002
Token something
Token ID1223
Feature activation-1.38e-01

Pos logit contributions
xual+0.076
 relativity+0.075
blank+0.074
manship+0.073
 Ples+0.072
Neg logit contributions
utonium-0.074
puter-0.068
awei-0.060
APH-0.060
ordable-0.058
Token Ro
Token ID5564
Feature activation+6.18e-02

Pos logit contributions
xual+0.357
blank+0.344
 relativity+0.343
 Ples+0.334
manship+0.333
Neg logit contributions
utonium-0.413
puter-0.388
awei-0.341
APH-0.339
ordable-0.337
Tokeneth
Token ID2788
Feature activation-5.26e-02

Pos logit contributions
utonium+0.250
puter+0.239
awei+0.219
APH+0.217
izoph+0.215
Neg logit contributions
xual-0.094
 relativity-0.093
blank-0.092
 Ples-0.088
manship-0.087
Tokenlis
Token ID27999
Feature activation-3.30e-03

Pos logit contributions
xual+0.069
 relativity+0.068
blank+0.067
manship+0.064
 Ples+0.064
Neg logit contributions
utonium-0.224
puter-0.214
APH-0.198
awei-0.197
izoph-0.195
Tokenberger
Token ID21041
Feature activation+7.98e-02

Pos logit contributions
xual+0.008
blank+0.008
 relativity+0.008
manship+0.008
 Ples+0.008
Neg logit contributions
utonium-0.010
puter-0.009
awei-0.008
APH-0.008
izoph-0.008
Token definitely
Token ID4753
Feature activation-4.28e-02

Pos logit contributions
utonium+0.270
puter+0.252
awei+0.227
APH+0.226
ritten+0.223
Neg logit contributions
xual-0.176
 relativity-0.170
blank-0.170
 Ples-0.165
manship-0.163
Token has
Token ID468
Feature activation-6.10e-03

Pos logit contributions
xual+0.091
blank+0.088
 relativity+0.088
 Ples+0.086
manship+0.084
Neg logit contributions
utonium-0.148
puter-0.139
awei-0.125
APH-0.125
ordable-0.123
Token at
Token ID379
Feature activation-9.79e-03

Pos logit contributions
xual+0.016
blank+0.016
 relativity+0.015
 Ples+0.015
manship+0.015
Neg logit contributions
utonium-0.018
puter-0.017
awei-0.015
APH-0.015
ordable-0.015
Token his
Token ID465
Feature activation+1.10e-02

Pos logit contributions
xual+0.026
 relativity+0.025
blank+0.025
manship+0.025
 Ples+0.025
Neg logit contributions
utonium-0.029
puter-0.027
APH-0.024
awei-0.024
ordable-0.023
Token disposal
Token ID18264
Feature activation+4.17e-02

Pos logit contributions
utonium+0.027
puter+0.026
awei+0.022
APH+0.022
ordable+0.021
Neg logit contributions
xual-0.034
 relativity-0.034
blank-0.033
manship-0.033
 Ples-0.033
Token is
Token ID318
Feature activation+1.58e-02

Pos logit contributions
xual+0.225
 relativity+0.218
blank+0.217
 Ples+0.213
 Lovecraft+0.207
Neg logit contributions
utonium-0.306
puter-0.289
awei-0.257
APH-0.257
ritten-0.252
Token wrong
Token ID2642
Feature activation+4.71e-02

Pos logit contributions
utonium+0.045
puter+0.042
awei+0.037
APH+0.037
ritten+0.036
Neg logit contributions
xual-0.044
 relativity-0.042
blank-0.042
 Ples-0.041
manship-0.041
Token,
Token ID11
Feature activation-1.38e-02

Pos logit contributions
utonium+0.150
puter+0.141
APH+0.127
awei+0.126
ritten+0.124
Neg logit contributions
xual-0.113
 relativity-0.109
blank-0.109
 Ples-0.107
manship-0.106
Token and
Token ID290
Feature activation-4.02e-02

Pos logit contributions
xual+0.035
 relativity+0.034
blank+0.034
manship+0.034
 Ples+0.034
Neg logit contributions
utonium-0.042
puter-0.039
APH-0.035
awei-0.035
ritten-0.034
Token they
Token ID484
Feature activation-4.16e-02

Pos logit contributions
xual+0.103
blank+0.100
 relativity+0.099
 Ples+0.098
manship+0.097
Neg logit contributions
utonium-0.122
puter-0.114
APH-0.101
awei-0.101
ritten-0.098
Token lack
Token ID3092
Feature activation+3.33e-02

Pos logit contributions
xual+0.104
 relativity+0.100
blank+0.099
 Ples+0.099
manship+0.097
Neg logit contributions
utonium-0.129
puter-0.121
APH-0.108
awei-0.107
ritten-0.106
Token the
Token ID262
Feature activation-8.04e-02

Pos logit contributions
utonium+0.098
puter+0.091
APH+0.081
awei+0.080
ritten+0.079
Neg logit contributions
xual-0.088
blank-0.086
 relativity-0.086
 Ples-0.084
manship-0.084
Token lead
Token ID1085
Feature activation-3.37e-02

Pos logit contributions
xual+0.201
blank+0.196
 relativity+0.196
manship+0.191
 Ples+0.191
Neg logit contributions
utonium-0.248
puter-0.232
awei-0.207
APH-0.206
izoph-0.202
Token-
Token ID12
Feature activation+5.76e-02

Pos logit contributions
xual+0.078
 relativity+0.077
blank+0.075
 Ples+0.075
manship+0.073
Neg logit contributions
utonium-0.110
puter-0.103
APH-0.093
awei-0.092
ritten-0.091
Tokenin
Token ID259
Feature activation+3.61e-02

Pos logit contributions
utonium+0.187
puter+0.177
awei+0.157
APH+0.157
ritten+0.156
Neg logit contributions
xual-0.135
 relativity-0.133
 Ples-0.129
blank-0.128
 Lovecraft-0.127
Token character
Token ID2095
Feature activation+7.27e-02

Pos logit contributions
utonium+0.115
puter+0.107
awei+0.096
APH+0.096
ritten+0.094
Neg logit contributions
xual-0.087
 relativity-0.085
blank-0.084
 Ples-0.082
manship-0.081
Token Virginia
Token ID6025
Feature activation+4.87e-02

Pos logit contributions
xual+0.034
 relativity+0.033
blank+0.033
manship+0.032
 Ples+0.031
Neg logit contributions
utonium-0.046
puter-0.043
APH-0.039
awei-0.039
ordable-0.038
Token undergrad
Token ID43485
Feature activation+1.97e-02

Pos logit contributions
utonium+0.138
puter+0.129
APH+0.112
awei+0.112
ritten+0.109
Neg logit contributions
xual-0.135
blank-0.132
 relativity-0.130
 Ples-0.129
manship-0.129
Token who
Token ID508
Feature activation-4.85e-03

Pos logit contributions
utonium+0.064
puter+0.061
awei+0.054
APH+0.054
ritten+0.053
Neg logit contributions
xual-0.046
 relativity-0.045
blank-0.045
 Ples-0.044
manship-0.044
Token served
Token ID4983
Feature activation-5.43e-02

Pos logit contributions
xual+0.013
blank+0.012
 relativity+0.012
manship+0.012
 Ples+0.012
Neg logit contributions
utonium-0.015
puter-0.014
awei-0.012
APH-0.012
ritten-0.012
Token 18
Token ID1248
Feature activation+2.87e-02

Pos logit contributions
xual+0.151
blank+0.148
 relativity+0.147
manship+0.144
 Ples+0.143
Neg logit contributions
utonium-0.153
puter-0.142
awei-0.125
APH-0.124
ordable-0.121
Token months
Token ID1933
Feature activation+6.50e-02

Pos logit contributions
utonium+0.073
puter+0.066
APH+0.058
awei+0.057
ritten+0.056
Neg logit contributions
xual-0.088
 relativity-0.086
blank-0.085
 Ples-0.084
manship-0.084
Token behind
Token ID2157
Feature activation-4.14e-02

Pos logit contributions
utonium+0.200
puter+0.186
APH+0.166
awei+0.165
ritten+0.162
Neg logit contributions
xual-0.165
 relativity-0.159
blank-0.158
 Ples-0.155
manship-0.154
Token bars
Token ID9210
Feature activation+1.51e-01

Pos logit contributions
xual+0.104
 relativity+0.097
blank+0.097
manship+0.095
 Ples+0.094
Neg logit contributions
utonium-0.131
puter-0.123
ritten-0.108
awei-0.108
APH-0.108
Token in
Token ID287
Feature activation+3.71e-02

Pos logit contributions
utonium+0.481
puter+0.450
APH+0.399
awei+0.399
ritten+0.393
Neg logit contributions
xual-0.368
 relativity-0.357
blank-0.356
 Ples-0.348
 Lovecraft-0.343
Token the
Token ID262
Feature activation+2.68e-02

Pos logit contributions
utonium+0.110
puter+0.102
APH+0.089
awei+0.089
ritten+0.088
Neg logit contributions
xual-0.099
blank-0.094
 relativity-0.094
manship-0.093
 Ples-0.091
Token her
Token ID607
Feature activation+7.71e-02

Pos logit contributions
utonium+0.085
puter+0.078
awei+0.069
APH+0.069
ritten+0.069
Neg logit contributions
xual-0.067
blank-0.064
 relativity-0.063
manship-0.063
 Ples-0.061
Token but
Token ID475
Feature activation-1.85e-02

Pos logit contributions
xual+0.222
 relativity+0.215
blank+0.212
manship+0.208
 Ples+0.207
Neg logit contributions
utonium-0.305
puter-0.289
awei-0.257
APH-0.256
ritten-0.251
Token would
Token ID561
Feature activation-9.01e-03

Pos logit contributions
xual+0.046
 relativity+0.045
blank+0.045
manship+0.044
 Ples+0.044
Neg logit contributions
utonium-0.057
puter-0.054
awei-0.048
APH-0.048
ordable-0.047
Token keep
Token ID1394
Feature activation-2.01e-02

Pos logit contributions
xual+0.023
 relativity+0.023
blank+0.022
manship+0.022
 Ples+0.022
Neg logit contributions
utonium-0.027
puter-0.026
APH-0.023
awei-0.023
ritten-0.022
Token riding
Token ID10311
Feature activation-3.17e-03

Pos logit contributions
xual+0.054
blank+0.052
 relativity+0.052
manship+0.051
 Ples+0.051
Neg logit contributions
utonium-0.058
puter-0.054
awei-0.048
APH-0.048
ritten-0.047
Token aggressively
Token ID19855
Feature activation+5.26e-02

Pos logit contributions
xual+0.008
 relativity+0.007
blank+0.007
 Ples+0.007
manship+0.007
Neg logit contributions
utonium-0.010
puter-0.009
APH-0.008
awei-0.008
ritten-0.008
Token.
Token ID13
Feature activation+1.33e-02

Pos logit contributions
utonium+0.168
puter+0.158
APH+0.141
awei+0.140
ordable+0.137
Neg logit contributions
xual-0.126
 relativity-0.123
blank-0.121
 Ples-0.119
manship-0.118
Token
Token ID564
Feature activation+3.39e-02

Pos logit contributions
utonium+0.040
puter+0.037
APH+0.033
awei+0.033
ritten+0.032
Neg logit contributions
xual-0.035
 relativity-0.034
blank-0.034
manship-0.033
 Ples-0.032
Token
Token ID250
Feature activation+3.67e-04

Pos logit contributions
utonium+0.093
puter+0.086
awei+0.075
APH+0.074
izoph+0.073
Neg logit contributions
xual-0.096
 relativity-0.096
blank-0.095
 Ples-0.093
manship-0.093
TokenThe
Token ID464
Feature activation-2.46e-02

Pos logit contributions
utonium+0.001
puter+0.001
APH+0.001
awei+0.001
ritten+0.001
Neg logit contributions
xual-0.001
 relativity-0.001
blank-0.001
manship-0.001
 Ples-0.001
Token legs
Token ID7405
Feature activation-2.29e-02

Pos logit contributions
xual+0.061
blank+0.059
 relativity+0.059
manship+0.058
 Ples+0.057
Neg logit contributions
utonium-0.077
puter-0.072
awei-0.064
APH-0.064
ritten-0.063
Token are
Token ID389
Feature activation-4.44e-03

Pos logit contributions
xual+0.058
 relativity+0.056
blank+0.056
 Ples+0.054
 Lovecraft+0.053
Neg logit contributions
utonium-0.071
puter-0.067
APH-0.059
awei-0.059
ritten-0.058
Token were
Token ID547
Feature activation-7.04e-03

Pos logit contributions
utonium+0.051
puter+0.048
APH+0.042
awei+0.042
ritten+0.041
Neg logit contributions
xual-0.045
 relativity-0.044
blank-0.044
 Ples-0.043
manship-0.043
Token left
Token ID1364
Feature activation-1.97e-02

Pos logit contributions
xual+0.019
 relativity+0.018
blank+0.018
manship+0.018
 Ples+0.018
Neg logit contributions
utonium-0.021
puter-0.019
awei-0.017
APH-0.017
ritten-0.017
Token struggling
Token ID9648
Feature activation-5.03e-03

Pos logit contributions
xual+0.050
 relativity+0.049
blank+0.048
 Ples+0.047
manship+0.047
Neg logit contributions
utonium-0.061
puter-0.057
awei-0.050
APH-0.050
ordable-0.049
Token to
Token ID284
Feature activation+8.06e-03

Pos logit contributions
xual+0.013
 relativity+0.012
blank+0.012
 Ples+0.012
manship+0.012
Neg logit contributions
utonium-0.016
puter-0.015
APH-0.013
awei-0.013
ordable-0.013
Token f
Token ID277
Feature activation+4.64e-03

Pos logit contributions
utonium+0.026
puter+0.024
awei+0.022
APH+0.022
izoph+0.021
Neg logit contributions
xual-0.019
 relativity-0.019
blank-0.019
manship-0.018
 Ples-0.018
Tokenathom
Token ID32910
Feature activation+5.23e-02

Pos logit contributions
utonium+0.008
puter+0.007
awei+0.005
APH+0.005
izoph+0.005
Neg logit contributions
xual-0.018
 relativity-0.018
blank-0.018
manship-0.018
 Ples-0.018
Token the
Token ID262
Feature activation+2.27e-02

Pos logit contributions
utonium+0.167
puter+0.158
APH+0.141
awei+0.140
izoph+0.138
Neg logit contributions
xual-0.124
 relativity-0.121
blank-0.120
manship-0.117
 Ples-0.116
Token origin
Token ID8159
Feature activation-3.32e-02

Pos logit contributions
utonium+0.070
puter+0.066
APH+0.058
awei+0.058
izoph+0.057
Neg logit contributions
xual-0.057
 relativity-0.056
blank-0.056
manship-0.055
 Ples-0.054
Token of
Token ID286
Feature activation-2.55e-02

Pos logit contributions
xual+0.070
 relativity+0.067
blank+0.067
manship+0.065
 Lovecraft+0.064
Neg logit contributions
utonium-0.116
puter-0.109
APH-0.100
awei-0.098
izoph-0.097
Token their
Token ID511
Feature activation+2.94e-02

Pos logit contributions
xual+0.068
 relativity+0.067
blank+0.067
manship+0.065
 Ples+0.065
Neg logit contributions
utonium-0.074
puter-0.069
APH-0.061
awei-0.060
izoph-0.060
Token daughter
Token ID4957
Feature activation+8.66e-02

Pos logit contributions
utonium+0.090
puter+0.084
awei+0.075
APH+0.075
izoph+0.073
Neg logit contributions
xual-0.074
 relativity-0.073
blank-0.072
manship-0.071
 Ples-0.071
Token3
Token ID18
Feature activation+5.28e-02

Pos logit contributions
utonium+0.121
puter+0.113
APH+0.101
awei+0.101
ordable+0.099
Neg logit contributions
xual-0.093
 relativity-0.092
blank-0.089
 Ples-0.088
manship-0.088
Tokens
Token ID82
Feature activation+5.55e-03

Pos logit contributions
utonium+0.204
puter+0.192
APH+0.176
awei+0.175
ordable+0.173
Neg logit contributions
xual-0.092
 relativity-0.090
blank-0.088
manship-0.086
 Ples-0.085
Token)}
Token ID38165
Feature activation-1.28e-01

Pos logit contributions
utonium+0.018
puter+0.016
APH+0.015
awei+0.015
ordable+0.014
Neg logit contributions
xual-0.014
 relativity-0.013
blank-0.013
manship-0.013
 Ples-0.013
Token 52
Token ID6740
Feature activation+3.15e-02

Pos logit contributions
xual+0.349
 relativity+0.341
blank+0.339
manship+0.332
 Ples+0.329
Neg logit contributions
utonium-0.368
puter-0.343
APH-0.301
awei-0.300
ordable-0.293
Token.
Token ID13
Feature activation+6.02e-02

Pos logit contributions
utonium+0.107
puter+0.101
awei+0.091
APH+0.090
izoph+0.089
Neg logit contributions
xual-0.069
 relativity-0.068
blank-0.067
manship-0.066
 Ples-0.065
Token Q
Token ID1195
Feature activation-5.14e-02

Pos logit contributions
utonium+0.177
puter+0.166
APH+0.146
awei+0.145
ordable+0.142
Neg logit contributions
xual-0.161
 relativity-0.156
blank-0.155
manship-0.153
 Ples-0.149
Tokenxf
Token ID26152
Feature activation-4.38e-02

Pos logit contributions
xual+0.117
 relativity+0.116
blank+0.112
manship+0.111
 Ples+0.111
Neg logit contributions
utonium-0.170
puter-0.161
APH-0.144
awei-0.143
ordable-0.141
Token7
Token ID22
Feature activation-9.47e-04

Pos logit contributions
xual+0.097
 relativity+0.097
blank+0.093
 Ples+0.092
manship+0.092
Neg logit contributions
utonium-0.148
puter-0.139
APH-0.125
awei-0.124
ordable-0.122
Token+
Token ID10
Feature activation+1.22e-02

Pos logit contributions
xual+0.003
 relativity+0.003
blank+0.003
manship+0.003
 Ples+0.002
Neg logit contributions
utonium-0.003
puter-0.002
APH-0.002
awei-0.002
ordable-0.002
Token {
Token ID1391
Feature activation-2.37e-02

Pos logit contributions
utonium+0.034
puter+0.031
APH+0.027
awei+0.027
ordable+0.026
Neg logit contributions
xual-0.035
 relativity-0.034
blank-0.034
manship-0.033
 Ples-0.033
Token(
Token ID7
Feature activation+4.25e-02

Pos logit contributions
xual+0.048
 relativity+0.047
blank+0.045
 Ples+0.045
manship+0.045
Neg logit contributions
utonium-0.085
puter-0.080
APH-0.073
awei-0.072
ordable-0.071
TokenFilm
Token ID39750
Feature activation+2.72e-02

Pos logit contributions
utonium+0.048
puter+0.046
APH+0.042
awei+0.041
ritten+0.040
Neg logit contributions
xual-0.037
 relativity-0.036
 Ples-0.035
manship-0.035
blank-0.035
Tokenography
Token ID4867
Feature activation+5.07e-02

Pos logit contributions
utonium+0.082
puter+0.077
APH+0.068
awei+0.067
ritten+0.066
Neg logit contributions
xual-0.071
blank-0.069
 relativity-0.068
manship-0.066
 Ples-0.066
Token [
Token ID685
Feature activation-2.68e-02

Pos logit contributions
utonium+0.156
puter+0.146
APH+0.131
awei+0.129
ritten+0.127
Neg logit contributions
xual-0.128
 relativity-0.124
blank-0.124
manship-0.121
 Ples-0.120
Token edit
Token ID4370
Feature activation+8.33e-04

Pos logit contributions
xual+0.075
 relativity+0.074
blank+0.073
manship+0.072
 Ples+0.071
Neg logit contributions
utonium-0.075
puter-0.070
awei-0.061
APH-0.061
izoph-0.060
Token ]
Token ID2361
Feature activation-8.19e-02

Pos logit contributions
utonium+0.003
puter+0.003
APH+0.003
awei+0.003
ritten+0.003
Neg logit contributions
xual-0.002
 relativity-0.002
blank-0.002
manship-0.002
 Ples-0.002
Token
Token ID198
Feature activation-4.75e-02

Pos logit contributions
xual+0.187
 relativity+0.185
blank+0.183
manship+0.178
 Ples+0.178
Neg logit contributions
utonium-0.271
puter-0.254
awei-0.228
APH-0.227
izoph-0.223
Token
Token ID198
Feature activation-2.27e-02

Pos logit contributions
blank+0.102
xual+0.102
 relativity+0.101
manship+0.099
 Ples+0.098
Neg logit contributions
utonium-0.163
puter-0.154
awei-0.139
APH-0.137
izoph-0.136
TokenAl
Token ID2348
Feature activation+5.37e-02

Pos logit contributions
xual+0.058
 relativity+0.056
manship+0.054
 Ples+0.054
blank+0.054
Neg logit contributions
utonium-0.070
puter-0.066
APH-0.060
awei-0.058
ritten-0.058
Tokenbum
Token ID4435
Feature activation-1.01e-01

Pos logit contributions
utonium+0.178
puter+0.168
awei+0.147
APH+0.146
ritten+0.146
Neg logit contributions
xual-0.126
 relativity-0.123
blank-0.118
manship-0.118
eering-0.115
Token [
Token ID685
Feature activation-1.77e-02

Pos logit contributions
xual+0.239
 relativity+0.232
blank+0.231
 Ples+0.222
manship+0.221
Neg logit contributions
utonium-0.330
puter-0.310
APH-0.278
awei-0.277
ritten-0.273
Token edit
Token ID4370
Feature activation-2.53e-02

Pos logit contributions
xual+0.048
blank+0.047
 relativity+0.047
manship+0.046
 Lovecraft+0.045
Neg logit contributions
utonium-0.051
puter-0.048
awei-0.042
APH-0.041
izoph-0.041
Token.
Token ID13
Feature activation-8.62e-03

Pos logit contributions
utonium+0.147
puter+0.138
APH+0.124
awei+0.124
ordable+0.121
Neg logit contributions
xual-0.110
 relativity-0.108
blank-0.106
 Ples-0.105
manship-0.104
Token
Token ID198
Feature activation-1.00e-02

Pos logit contributions
xual+0.021
 relativity+0.021
blank+0.020
manship+0.020
 Ples+0.020
Neg logit contributions
utonium-0.027
puter-0.025
APH-0.023
awei-0.023
ordable-0.022
Token
Token ID198
Feature activation-7.17e-03

Pos logit contributions
xual+0.022
 relativity+0.022
blank+0.022
manship+0.021
 Ples+0.021
Neg logit contributions
utonium-0.034
puter-0.032
awei-0.029
APH-0.029
izoph-0.028
TokenIt
Token ID1026
Feature activation-2.42e-02

Pos logit contributions
xual+0.018
 relativity+0.017
 Ples+0.017
blank+0.017
manship+0.017
Neg logit contributions
utonium-0.022
puter-0.021
APH-0.019
awei-0.019
ritten-0.018
Token also
Token ID635
Feature activation+1.64e-02

Pos logit contributions
xual+0.059
 relativity+0.058
blank+0.057
 Ples+0.056
manship+0.056
Neg logit contributions
utonium-0.076
puter-0.071
awei-0.064
APH-0.064
ritten-0.063
Token makes
Token ID1838
Feature activation-2.58e-02

Pos logit contributions
utonium+0.050
puter+0.046
awei+0.041
APH+0.041
ritten+0.040
Neg logit contributions
xual-0.042
blank-0.041
 relativity-0.041
 Ples-0.040
manship-0.040
Token it
Token ID340
Feature activation+1.93e-02

Pos logit contributions
xual+0.073
 relativity+0.071
blank+0.071
manship+0.070
 Ples+0.070
Neg logit contributions
utonium-0.072
puter-0.067
awei-0.058
APH-0.058
izoph-0.057
Token mandatory
Token ID13677
Feature activation+9.03e-02

Pos logit contributions
utonium+0.054
puter+0.051
awei+0.044
APH+0.044
ordable+0.043
Neg logit contributions
xual-0.054
 relativity-0.053
blank-0.052
 Ples-0.051
manship-0.051
Token for
Token ID329
Feature activation-5.98e-02

Pos logit contributions
utonium+0.275
puter+0.260
awei+0.230
APH+0.229
ritten+0.223
Neg logit contributions
xual-0.229
 relativity-0.223
blank-0.222
 Ples-0.218
manship-0.217
Token all
Token ID477
Feature activation-3.07e-02

Pos logit contributions
xual+0.163
 relativity+0.160
blank+0.159
manship+0.156
 Ples+0.155
Neg logit contributions
utonium-0.171
puter-0.160
awei-0.141
APH-0.140
izoph-0.137
Token operators
Token ID12879
Feature activation+4.27e-02

Pos logit contributions
xual+0.090
 relativity+0.088
blank+0.088
manship+0.086
 Ples+0.085
Neg logit contributions
utonium-0.082
puter-0.076
awei-0.066
APH-0.066
ordable-0.064
Token blur
Token ID23671
Feature activation-1.01e-01

Pos logit contributions
utonium+0.069
puter+0.065
APH+0.058
awei+0.058
izoph+0.057
Neg logit contributions
xual-0.054
blank-0.052
 relativity-0.052
manship-0.051
 Ples-0.051
Token the
Token ID262
Feature activation+1.52e-02

Pos logit contributions
xual+0.269
 relativity+0.260
blank+0.260
manship+0.254
 Ples+0.253
Neg logit contributions
utonium-0.298
puter-0.278
APH-0.248
awei-0.244
ritten-0.242
Token boundary
Token ID18645
Feature activation+6.30e-02

Pos logit contributions
utonium+0.052
puter+0.049
APH+0.044
awei+0.044
ritten+0.044
Neg logit contributions
xual-0.033
blank-0.031
 relativity-0.031
manship-0.031
 Ples-0.030
Token lines
Token ID3951
Feature activation+9.15e-03

Pos logit contributions
utonium+0.193
puter+0.181
APH+0.160
awei+0.160
ritten+0.156
Neg logit contributions
xual-0.159
 relativity-0.154
blank-0.153
manship-0.149
 Lovecraft-0.149
Token between
Token ID1022
Feature activation-2.04e-02

Pos logit contributions
utonium+0.028
puter+0.026
APH+0.023
awei+0.023
ordable+0.023
Neg logit contributions
xual-0.023
 relativity-0.022
blank-0.022
 Ples-0.021
 Lovecraft-0.021
Token sovereign
Token ID18901
Feature activation-5.26e-04

Pos logit contributions
xual+0.053
 relativity+0.052
blank+0.052
manship+0.051
 Ples+0.050
Neg logit contributions
utonium-0.061
puter-0.057
APH-0.050
awei-0.050
ritten-0.049
Token Israel
Token ID2692
Feature activation-5.70e-02

Pos logit contributions
xual+0.001
 relativity+0.001
blank+0.001
 Ples+0.001
manship+0.001
Neg logit contributions
utonium-0.002
puter-0.001
APH-0.001
awei-0.001
ritten-0.001
Token and
Token ID290
Feature activation-4.29e-02

Pos logit contributions
xual+0.143
 relativity+0.140
blank+0.138
 Ples+0.135
manship+0.134
Neg logit contributions
utonium-0.176
puter-0.165
APH-0.147
awei-0.146
ritten-0.144
Token the
Token ID262
Feature activation-2.47e-02

Pos logit contributions
xual+0.116
 relativity+0.113
blank+0.112
manship+0.110
 Ples+0.109
Neg logit contributions
utonium-0.125
puter-0.116
APH-0.103
awei-0.102
ritten-0.100
Token settlements
Token ID18573
Feature activation-3.25e-02

Pos logit contributions
xual+0.065
 relativity+0.063
blank+0.062
manship+0.061
 Ples+0.061
Neg logit contributions
utonium-0.074
puter-0.069
APH-0.061
awei-0.061
izoph-0.059
Token in
Token ID287
Feature activation-4.14e-02

Pos logit contributions
xual+0.082
 relativity+0.079
blank+0.079
 Ples+0.077
 Lovecraft+0.076
Neg logit contributions
utonium-0.100
puter-0.093
APH-0.083
awei-0.082
ordable-0.081
Token have
Token ID423
Feature activation+1.81e-03

Pos logit contributions
utonium+0.147
puter+0.138
APH+0.123
awei+0.121
ritten+0.120
Neg logit contributions
xual-0.133
 relativity-0.131
blank-0.130
 Ples-0.127
manship-0.126
Token been
Token ID587
Feature activation-1.66e-02

Pos logit contributions
utonium+0.005
puter+0.004
awei+0.004
APH+0.004
ritten+0.004
Neg logit contributions
xual-0.005
 relativity-0.005
blank-0.005
 Ples-0.005
manship-0.005
Token MS
Token ID6579
Feature activation+1.78e-02

Pos logit contributions
xual+0.044
blank+0.043
 relativity+0.043
 Ples+0.042
manship+0.042
Neg logit contributions
utonium-0.049
puter-0.045
APH-0.040
awei-0.040
ritten-0.039
TokenF
Token ID37
Feature activation+8.13e-02

Pos logit contributions
utonium+0.050
puter+0.046
awei+0.041
izoph+0.040
APH+0.039
Neg logit contributions
xual-0.050
 relativity-0.049
blank-0.049
manship-0.048
 Ples-0.048
Token's
Token ID338
Feature activation+3.32e-02

Pos logit contributions
utonium+0.281
puter+0.265
APH+0.240
awei+0.239
ordable+0.234
Neg logit contributions
xual-0.173
 relativity-0.168
blank-0.168
 Ples-0.163
manship-0.162
Token statement
Token ID2643
Feature activation-1.00e-01

Pos logit contributions
utonium+0.102
puter+0.095
awei+0.085
APH+0.084
izoph+0.083
Neg logit contributions
xual-0.084
blank-0.082
 relativity-0.082
manship-0.080
 Ples-0.079
Token a
Token ID257
Feature activation-1.20e-02

Pos logit contributions
xual+0.255
 relativity+0.250
blank+0.248
 Ples+0.243
manship+0.243
Neg logit contributions
utonium-0.302
puter-0.282
awei-0.251
APH-0.250
ordable-0.245
Token month
Token ID1227
Feature activation-1.96e-02

Pos logit contributions
xual+0.031
 relativity+0.031
blank+0.030
manship+0.030
 Ples+0.030
Neg logit contributions
utonium-0.036
puter-0.033
APH-0.029
awei-0.029
ritten-0.029
Token ago
Token ID2084
Feature activation-2.35e-02

Pos logit contributions
xual+0.052
 relativity+0.051
blank+0.050
manship+0.049
 Ples+0.049
Neg logit contributions
utonium-0.058
puter-0.054
APH-0.048
awei-0.047
ritten-0.046
Token that
Token ID326
Feature activation+7.86e-04

Pos logit contributions
xual+0.060
 relativity+0.059
blank+0.058
 Ples+0.057
manship+0.057
Neg logit contributions
utonium-0.071
puter-0.066
awei-0.059
APH-0.059
ordable-0.058
Token they
Token ID484
Feature activation+5.07e-02

Pos logit contributions
utonium+0.002
puter+0.002
awei+0.002
APH+0.002
izoph+0.002
Neg logit contributions
xual-0.002
 relativity-0.002
blank-0.002
 Ples-0.002
manship-0.002
Token
Token ID251
Feature activation+3.27e-02

Pos logit contributions
utonium+0.012
puter+0.011
awei+0.010
APH+0.010
izoph+0.010
Neg logit contributions
xual-0.016
 relativity-0.016
blank-0.016
manship-0.015
 Ples-0.015
Token
Token ID198
Feature activation-1.24e-03

Pos logit contributions
utonium+0.103
puter+0.097
APH+0.087
awei+0.086
izoph+0.084
Neg logit contributions
xual-0.080
 relativity-0.079
blank-0.077
manship-0.075
 Ples-0.074
Token
Token ID198
Feature activation+3.00e-03

Pos logit contributions
xual+0.003
blank+0.003
 relativity+0.003
manship+0.003
 Ples+0.003
Neg logit contributions
utonium-0.004
puter-0.004
awei-0.004
APH-0.004
izoph-0.003
TokenS
Token ID50
Feature activation-1.08e-01

Pos logit contributions
utonium+0.009
puter+0.009
APH+0.008
awei+0.008
ritten+0.007
Neg logit contributions
xual-0.008
 relativity-0.008
manship-0.007
 Ples-0.007
blank-0.007
Tokenpen
Token ID3617
Feature activation+1.31e-01

Pos logit contributions
xual+0.235
 relativity+0.233
blank+0.226
manship+0.223
 Ples+0.222
Neg logit contributions
utonium-0.368
puter-0.346
APH-0.313
awei-0.313
ritten-0.307
Tokencer
Token ID2189
Feature activation-3.02e-01

Pos logit contributions
utonium+0.423
puter+0.389
APH+0.356
awei+0.352
ritten+0.348
Neg logit contributions
 relativity-0.312
xual-0.311
blank-0.298
 Ples-0.297
manship-0.293
Token said
Token ID531
Feature activation+1.17e-02

Pos logit contributions
xual+0.779
 relativity+0.767
blank+0.757
manship+0.741
 Ples+0.740
Neg logit contributions
utonium-0.913
puter-0.854
awei-0.759
APH-0.755
ritten-0.737
Token that
Token ID326
Feature activation+6.47e-02

Pos logit contributions
utonium+0.033
puter+0.031
awei+0.028
APH+0.027
ordable+0.027
Neg logit contributions
xual-0.032
 relativity-0.031
blank-0.030
manship-0.030
 Ples-0.030
Token ads
Token ID9011
Feature activation+2.36e-02

Pos logit contributions
utonium+0.188
puter+0.178
awei+0.158
APH+0.157
ordable+0.153
Neg logit contributions
xual-0.171
 relativity-0.167
blank-0.165
manship-0.162
 Ples-0.160
Token pretending
Token ID23662
Feature activation+1.48e-02

Pos logit contributions
utonium+0.071
puter+0.067
APH+0.059
awei+0.059
ordable+0.057
Neg logit contributions
xual-0.061
 relativity-0.060
blank-0.059
 Ples-0.058
manship-0.057
Token to
Token ID284
Feature activation+4.91e-03

Pos logit contributions
utonium+0.046
puter+0.043
APH+0.038
awei+0.038
ordable+0.038
Neg logit contributions
xual-0.037
 relativity-0.036
blank-0.036
 Ples-0.035
manship-0.035
Token tele
Token ID5735
Feature activation+8.00e-02

Pos logit contributions
utonium+0.028
puter+0.026
APH+0.023
awei+0.023
ritten+0.022
Neg logit contributions
xual-0.026
 relativity-0.025
blank-0.025
manship-0.024
 Ples-0.024
Tokenmetry
Token ID41935
Feature activation-1.76e-01

Pos logit contributions
utonium+0.197
puter+0.184
awei+0.156
APH+0.156
ordable+0.150
Neg logit contributions
xual-0.254
 relativity-0.248
 Ples-0.242
blank-0.242
manship-0.239
Token channel
Token ID6518
Feature activation+7.19e-02

Pos logit contributions
xual+0.415
 relativity+0.396
blank+0.395
manship+0.389
 Ples+0.386
Neg logit contributions
utonium-0.571
puter-0.541
APH-0.482
awei-0.481
izoph-0.472
Token that
Token ID326
Feature activation+5.54e-02

Pos logit contributions
utonium+0.230
puter+0.217
APH+0.193
awei+0.193
ritten+0.189
Neg logit contributions
xual-0.172
 relativity-0.168
blank-0.166
 Ples-0.163
manship-0.162
Token inexpl
Token ID33199
Feature activation+6.66e-02

Pos logit contributions
utonium+0.167
puter+0.157
awei+0.139
APH+0.138
izoph+0.134
Neg logit contributions
xual-0.144
 relativity-0.139
blank-0.138
manship-0.135
 Ples-0.134
Tokenicably
Token ID41685
Feature activation-3.08e-01

Pos logit contributions
utonium+0.172
puter+0.158
awei+0.137
APH+0.136
ritten+0.133
Neg logit contributions
xual-0.202
 relativity-0.199
blank-0.197
manship-0.194
 Ples-0.193
Token switched
Token ID15293
Feature activation+5.43e-02

Pos logit contributions
xual+0.800
 relativity+0.778
blank+0.772
manship+0.756
 Ples+0.752
Neg logit contributions
utonium-0.928
puter-0.869
awei-0.768
APH-0.767
ritten-0.750
Token into
Token ID656
Feature activation-4.09e-04

Pos logit contributions
utonium+0.164
puter+0.154
awei+0.136
APH+0.136
izoph+0.133
Neg logit contributions
xual-0.140
blank-0.135
 relativity-0.135
manship-0.132
 Ples-0.131
Token an
Token ID281
Feature activation+4.98e-03

Pos logit contributions
xual+0.001
 relativity+0.001
blank+0.001
manship+0.001
 Ples+0.001
Neg logit contributions
utonium-0.001
puter-0.001
APH-0.001
awei-0.001
izoph-0.001
Token unsc
Token ID28594
Feature activation+5.21e-02

Pos logit contributions
utonium+0.015
puter+0.014
awei+0.012
APH+0.012
izoph+0.012
Neg logit contributions
xual-0.013
 relativity-0.013
blank-0.013
manship-0.013
 Ples-0.012
Tokenhed
Token ID704
Feature activation-2.10e-02

Pos logit contributions
utonium+0.161
puter+0.151
awei+0.134
APH+0.134
ritten+0.131
Neg logit contributions
xual-0.130
 relativity-0.129
blank-0.127
manship-0.125
 Ples-0.125
Tokenu
Token ID84
Feature activation-5.21e-02

Pos logit contributions
utonium+0.165
puter+0.156
awei+0.141
APH+0.141
izoph+0.139
Neg logit contributions
xual-0.092
 relativity-0.090
blank-0.090
manship-0.087
 Ples-0.086
Token will
Token ID481
Feature activation-3.27e-02

Pos logit contributions
xual+0.113
 relativity+0.109
blank+0.108
 Ples+0.105
manship+0.104
Neg logit contributions
utonium-0.179
puter-0.168
APH-0.152
awei-0.152
ordable-0.148
Token lose
Token ID4425
Feature activation-1.09e-02

Pos logit contributions
xual+0.080
 relativity+0.078
blank+0.078
manship+0.076
 Ples+0.075
Neg logit contributions
utonium-0.102
puter-0.096
APH-0.085
awei-0.085
ritten-0.083
Token her
Token ID607
Feature activation-3.32e-03

Pos logit contributions
xual+0.028
 relativity+0.028
blank+0.027
manship+0.027
 Ples+0.027
Neg logit contributions
utonium-0.033
puter-0.031
awei-0.027
APH-0.027
ordable-0.027
Token chair
Token ID5118
Feature activation-1.47e-02

Pos logit contributions
xual+0.008
 relativity+0.008
blank+0.008
 Ples+0.008
manship+0.008
Neg logit contributions
utonium-0.010
puter-0.010
awei-0.009
APH-0.008
ordable-0.008
Tokenmanship
Token ID25428
Feature activation-4.59e-01

Pos logit contributions
xual+0.012
 relativity+0.011
blank+0.010
 Ples+0.009
 Lovecraft+0.009
Neg logit contributions
utonium-0.071
puter-0.068
APH-0.063
awei-0.063
ordable-0.063
Token.
Token ID13
Feature activation-8.28e-02

Pos logit contributions
xual+1.031
 relativity+1.013
blank+1.001
 Ples+0.974
manship+0.970
Neg logit contributions
utonium-1.537
puter-1.448
awei-1.299
APH-1.297
ordable-1.271
Token Throughout
Token ID24581
Feature activation-4.31e-02

Pos logit contributions
xual+0.204
 relativity+0.199
blank+0.196
manship+0.190
 Ples+0.187
Neg logit contributions
utonium-0.260
puter-0.244
APH-0.220
awei-0.216
ordable-0.213
Token the
Token ID262
Feature activation-3.44e-02

Pos logit contributions
xual+0.115
blank+0.112
 relativity+0.112
manship+0.108
 Ples+0.107
Neg logit contributions
utonium-0.126
puter-0.118
APH-0.105
awei-0.103
ordable-0.103
Token campaign
Token ID1923
Feature activation-2.27e-03

Pos logit contributions
xual+0.086
 relativity+0.084
blank+0.083
manship+0.081
 Ples+0.081
Neg logit contributions
utonium-0.106
puter-0.099
APH-0.088
awei-0.088
ordable-0.087
Token,
Token ID11
Feature activation-1.73e-02

Pos logit contributions
xual+0.005
 relativity+0.005
blank+0.005
manship+0.005
 Ples+0.005
Neg logit contributions
utonium-0.007
puter-0.007
APH-0.006
awei-0.006
ritten-0.006
Token un
Token ID555
Feature activation-8.67e-03

Pos logit contributions
xual+0.050
 relativity+0.048
blank+0.048
manship+0.047
 Ples+0.047
Neg logit contributions
utonium-0.067
puter-0.063
awei-0.056
APH-0.056
ordable-0.055
Tokenearth
Token ID16442
Feature activation-1.22e-01

Pos logit contributions
xual+0.021
 relativity+0.021
 Ples+0.020
blank+0.020
 Lovecraft+0.020
Neg logit contributions
utonium-0.028
puter-0.026
APH-0.023
awei-0.023
ritten-0.023
Token a
Token ID257
Feature activation-4.05e-02

Pos logit contributions
xual+0.333
 relativity+0.324
blank+0.323
 Ples+0.317
manship+0.314
Neg logit contributions
utonium-0.351
puter-0.325
awei-0.287
APH-0.285
ordable-0.281
Token few
Token ID1178
Feature activation-2.94e-02

Pos logit contributions
xual+0.099
 relativity+0.095
blank+0.095
 Ples+0.093
manship+0.093
Neg logit contributions
utonium-0.129
puter-0.120
awei-0.107
APH-0.106
ritten-0.105
Token barg
Token ID12828
Feature activation-8.33e-02

Pos logit contributions
xual+0.077
 relativity+0.074
blank+0.074
 Ples+0.073
manship+0.073
Neg logit contributions
utonium-0.088
puter-0.082
awei-0.073
APH-0.072
ordable-0.071
Tokenains
Token ID1299
Feature activation-3.01e-01

Pos logit contributions
 relativity+0.235
xual+0.235
blank+0.230
 Ples+0.229
manship+0.226
Neg logit contributions
utonium-0.234
puter-0.212
awei-0.190
ritten-0.186
ordable-0.185
Token along
Token ID1863
Feature activation-8.37e-02

Pos logit contributions
xual+0.732
 relativity+0.716
blank+0.711
 Ples+0.697
manship+0.686
Neg logit contributions
utonium-0.954
puter-0.894
awei-0.798
APH-0.794
ordable-0.783
Token the
Token ID262
Feature activation-6.32e-02

Pos logit contributions
xual+0.242
 relativity+0.233
blank+0.232
 Ples+0.229
manship+0.227
Neg logit contributions
utonium-0.228
puter-0.212
APH-0.184
awei-0.182
ritten-0.181
Token way
Token ID835
Feature activation-7.61e-02

Pos logit contributions
xual+0.158
 relativity+0.153
blank+0.152
manship+0.150
 Ples+0.149
Neg logit contributions
utonium-0.196
puter-0.184
awei-0.164
APH-0.163
ritten-0.161
Token.
Token ID13
Feature activation+1.26e-03

Pos logit contributions
xual+0.181
 relativity+0.176
blank+0.175
 Ples+0.172
manship+0.170
Neg logit contributions
utonium-0.244
puter-0.229
awei-0.205
APH-0.204
ordable-0.200
Token
Token ID198
Feature activation+1.51e-03

Pos logit contributions
utonium+0.004
puter+0.004
APH+0.003
awei+0.003
ordable+0.003
Neg logit contributions
xual-0.003
 relativity-0.003
blank-0.003
manship-0.003
 Ples-0.003
Token 2000
Token ID4751
Feature activation-7.16e-02

Pos logit contributions
xual+0.111
 relativity+0.109
blank+0.107
manship+0.105
 Ples+0.105
Neg logit contributions
utonium-0.119
puter-0.111
awei-0.099
APH-0.099
izoph-0.096
Token spears
Token ID46842
Feature activation-1.07e-01

Pos logit contributions
xual+0.167
 relativity+0.165
blank+0.160
 Ples+0.158
manship+0.157
Neg logit contributions
utonium-0.233
puter-0.218
awei-0.197
APH-0.196
izoph-0.192
Token,
Token ID11
Feature activation-2.47e-02

Pos logit contributions
xual+0.247
 relativity+0.242
blank+0.237
 Ples+0.233
manship+0.229
Neg logit contributions
utonium-0.350
puter-0.329
APH-0.296
awei-0.295
ritten-0.287
Token 300
Token ID5867
Feature activation-4.33e-03

Pos logit contributions
xual+0.074
 relativity+0.073
blank+0.072
manship+0.071
 Ples+0.070
Neg logit contributions
utonium-0.064
puter-0.060
awei-0.052
APH-0.052
izoph-0.050
Token arm
Token ID3211
Feature activation-5.65e-02

Pos logit contributions
xual+0.010
 relativity+0.010
blank+0.010
 Ples+0.010
manship+0.010
Neg logit contributions
utonium-0.014
puter-0.013
awei-0.012
APH-0.012
izoph-0.012
Tokenours
Token ID4662
Feature activation-3.29e-01

Pos logit contributions
xual+0.127
 relativity+0.124
blank+0.119
 Ples+0.117
 Lovecraft+0.116
Neg logit contributions
utonium-0.191
puter-0.182
awei-0.165
APH-0.163
ordable-0.158
Token and
Token ID290
Feature activation-2.29e-02

Pos logit contributions
xual+0.755
 relativity+0.744
blank+0.730
 Ples+0.715
manship+0.707
Neg logit contributions
utonium-1.081
puter-1.018
awei-0.917
APH-0.917
ritten-0.888
Token 500
Token ID5323
Feature activation-6.90e-02

Pos logit contributions
xual+0.067
 relativity+0.066
blank+0.066
manship+0.064
 Ples+0.064
Neg logit contributions
utonium-0.060
puter-0.056
awei-0.049
APH-0.049
izoph-0.047
Token shields
Token ID21132
Feature activation+2.71e-03

Pos logit contributions
xual+0.163
 relativity+0.160
blank+0.156
 Ples+0.153
manship+0.153
Neg logit contributions
utonium-0.223
puter-0.208
awei-0.189
APH-0.187
izoph-0.184
Token,
Token ID11
Feature activation+9.94e-03

Pos logit contributions
utonium+0.009
puter+0.008
awei+0.007
APH+0.007
ordable+0.007
Neg logit contributions
xual-0.007
 relativity-0.007
blank-0.006
 Ples-0.006
manship-0.006
Token were
Token ID547
Feature activation-4.25e-02

Pos logit contributions
utonium+0.030
puter+0.028
awei+0.025
APH+0.025
ordable+0.024
Neg logit contributions
xual-0.026
 relativity-0.025
blank-0.025
manship-0.024
 Ples-0.024