TOP ACTIVATIONS
MAX = 0.721

Cook . Vict ory , however , would put
t weet / <|endoftext|> Story highlights Secretary of Defense Chuck Hag
s sec rets .
vote accordingly . <|endoftext|> Story highlights Police chief vows wanted suspect
the problem . <|endoftext|> Haw aii Congress woman Tuls i G
instead of going through std :: ist ream . I also
The alleged offenses were drug possession and possession of drug parap
of the del ayed unfolding of independence
` represent able :( I
+ : Struct uring Prosper ity for Yourself and the Nation
full story <|endoftext|> Asia Health Correspond ent A lake
an aer obic pathogens ( Prev ot ella , Pe pt
PS 4 Release Date Del ayed Until At Le ast March
Brom wich Albion and Stoke City achieved without players such as
offenses were drug possession and possession of drug parap hern alia
us B ully / Vict im Question naire [ M imeo
, the legacy of Antiqu ity to the so -
Communications Commission chairman Aj it Pai , a Trump appoint ee
explore a proced urally generated universe Col on ize
tradition reaches back to Antiqu ity itself , and even then

MIN ACTIVATIONS
MIN = -0.699

might be Jar red Cos art , who has allowed four
, the coalition said its raids in Syria and Iraq and
23 ] Di agn osis [ edit ]
take measures to stop these raids , Turkey would defend itself
with S ich uan pe pperc orns ( which I couldn
[ a big ] enough premium to pay the claims over
YouTube spokeswoman . Newsletter Sign Up Continue reading the
claims against Israel over the raid and that the countries would
and Ch ado Ralph Ru cci and portraits of world -
2010 after an Israeli naval raid on a Gaza - bound
, and triggered Thursday 's raids . " Air
fingerprints are all over Obamacare premium increases ," May 5 ).
image . Draw String ($ art ext [ $ i -
ed via pipes to e art hen storage reservoirs . From
didnt apply for summer intern ships until February . By that
and winning his first k art ing races he was tipped
remove the damaged skin and graft skin from another area of
C it ib ank fore closed on Andrew W ied er
popular FX series Sons of Anarchy he was most recently seen
says . " Getting the premium in the health insurance business

INTERVAL 0.366 - 0.721
CONTAINS 0.228%

Yes , the real - estate boom raised rents beyond the
m ote ( O mega Pharma - Quick step ) s
being shot , so B ass ' later insistence that he
even fix a breach in Tal os - 1
be used in all game modes or you can choose to

INTERVAL 0.011 - 0.366
CONTAINS 43.352%

claimed that he was forced to sign the document by Joseph
Pittsburgh , they hadn t scored in two games
the movement , moving up into the feminist movement , as
If you find the above method too troublesome , just
s collapse requires active involvement of international organisations that

INTERVAL -0.344 - 0.011
CONTAINS 56.072%

MIC AS instrument was a design success , but the ultraviolet
ating the y aku za as a trans national
rist own , N . J . Early - 19 th
per animal for the farmer . But the people
the National Review Institute in Washington on January 20 , 2015

INTERVAL -0.699 - -0.344
CONTAINS 0.348%

other in the Ham pt ons , and their children attended
. Coord ination on this front is not a small thing
be taken seriously by audi oph iles ? For their imaging
m ose , an Ike a manager . " The use
have done a bit more clearly . It 's
Token Cook
Token ID8261
Feature activation-1.32e-01

Pos logit contributions
SSL+0.687
fox+0.681
SPONSORED+0.666
 �+0.613
 ‎+0.611
Neg logit contributions
UTERS-0.636
inent-0.584
 Detail-0.571
Interstitial-0.568
idences-0.565
Token.
Token ID13
Feature activation-3.32e-02

Pos logit contributions
SSL+0.260
fox+0.257
SPONSORED+0.254
 �+0.229
 ‎+0.228
Neg logit contributions
UTERS-0.274
inent-0.256
 Detail-0.251
Interstitial-0.246
iege-0.246
Token
Token ID198
Feature activation-8.97e-02

Pos logit contributions
SSL+0.069
fox+0.068
SPONSORED+0.067
 ‎+0.062
 �+0.062
Neg logit contributions
UTERS-0.066
inent-0.062
Interstitial-0.059
 Detail-0.059
idences-0.059
Token
Token ID198
Feature activation-9.75e-02

Pos logit contributions
SSL+0.131
fox+0.129
SPONSORED+0.127
 ‎+0.111
 �+0.110
Neg logit contributions
UTERS-0.235
inent-0.223
 Detail-0.219
Interstitial-0.216
iege-0.216
TokenVict
Token ID21944
Feature activation-1.24e-01

Pos logit contributions
SSL+0.211
SPONSORED+0.207
fox+0.207
 ‎+0.186
 �+0.185
Neg logit contributions
UTERS-0.187
inent-0.175
 Detail-0.172
idences-0.167
iege-0.167
Tokenory
Token ID652
Feature activation+7.21e-01

Pos logit contributions
SSL+0.222
fox+0.221
SPONSORED+0.215
 �+0.194
 ‎+0.193
Neg logit contributions
UTERS-0.283
inent-0.261
 Detail-0.257
Interstitial-0.257
iege-0.252
Token,
Token ID11
Feature activation-4.70e-02

Pos logit contributions
UTERS+1.486
inent+1.386
 Detail+1.359
idences+1.332
iege+1.327
Neg logit contributions
SSL-1.437
fox-1.416
SPONSORED-1.406
 �-1.257
cens-1.249
Token however
Token ID2158
Feature activation+2.15e-02

Pos logit contributions
SSL+0.091
fox+0.090
SPONSORED+0.089
 ‎+0.082
 �+0.081
Neg logit contributions
UTERS-0.100
inent-0.093
 Detail-0.090
Interstitial-0.090
iege-0.089
Token,
Token ID11
Feature activation-3.17e-02

Pos logit contributions
UTERS+0.039
inent+0.036
 Detail+0.035
Interstitial+0.035
iege+0.035
Neg logit contributions
SSL-0.048
fox-0.047
SPONSORED-0.047
-0.042
cens-0.042
Token would
Token ID561
Feature activation+1.64e-02

Pos logit contributions
SSL+0.056
fox+0.055
SPONSORED+0.055
 �+0.048
 ‎+0.048
Neg logit contributions
UTERS-0.073
inent-0.068
 Detail-0.067
Interstitial-0.066
iege-0.066
Token put
Token ID1234
Feature activation-8.11e-02

Pos logit contributions
UTERS+0.034
inent+0.031
 Detail+0.031
Interstitial+0.030
iege+0.030
Neg logit contributions
SSL-0.033
fox-0.033
SPONSORED-0.032
 �-0.029
 ‎-0.029
Tokent
Token ID83
Feature activation-5.49e-04

Pos logit contributions
SSL+0.109
fox+0.108
SPONSORED+0.107
 �+0.096
 ‎+0.096
Neg logit contributions
UTERS-0.122
inent-0.113
 Detail-0.112
Interstitial-0.110
iege-0.109
Tokenweet
Token ID7277
Feature activation+9.36e-02

Pos logit contributions
SSL+0.001
fox+0.001
SPONSORED+0.001
 �+0.001
 ‎+0.001
Neg logit contributions
UTERS-0.001
inent-0.001
 Detail-0.001
Interstitial-0.001
iege-0.001
Token/
Token ID14
Feature activation-1.08e-01

Pos logit contributions
UTERS+0.208
inent+0.194
 Detail+0.191
Interstitial+0.187
iege+0.187
Neg logit contributions
SSL-0.173
fox-0.169
SPONSORED-0.168
 �-0.150
 ‎-0.148
Token<|endoftext|>
Token ID50256
Feature activation-5.47e-02

Pos logit contributions
SSL+0.179
fox+0.176
SPONSORED+0.173
 �+0.154
 ‎+0.152
Neg logit contributions
UTERS-0.258
inent-0.243
 Detail-0.239
Interstitial-0.235
iege-0.234
TokenStory
Token ID11605
Feature activation-8.46e-02

Pos logit contributions
SSL+0.119
fox+0.117
SPONSORED+0.116
 �+0.105
 ‎+0.105
Neg logit contributions
UTERS-0.104
inent-0.096
 Detail-0.095
iege-0.092
idences-0.092
Token highlights
Token ID11330
Feature activation+7.03e-01

Pos logit contributions
SSL+0.156
fox+0.155
SPONSORED+0.150
 �+0.137
 ‎+0.137
Neg logit contributions
UTERS-0.187
inent-0.175
Interstitial-0.170
 Detail-0.169
iege-0.168
Token Secretary
Token ID4986
Feature activation+4.67e-02

Pos logit contributions
UTERS+1.335
inent+1.227
 Detail+1.210
Interstitial+1.181
iege+1.176
Neg logit contributions
SSL-1.519
fox-1.502
SPONSORED-1.486
 �-1.352
 ‎-1.344
Token of
Token ID286
Feature activation-4.30e-02

Pos logit contributions
UTERS+0.107
inent+0.100
 Detail+0.098
Interstitial+0.097
iege+0.096
Neg logit contributions
SSL-0.083
fox-0.082
SPONSORED-0.081
 �-0.072
 ‎-0.072
Token Defense
Token ID5947
Feature activation+1.22e-01

Pos logit contributions
SSL+0.102
fox+0.101
SPONSORED+0.099
 �+0.092
 ‎+0.091
Neg logit contributions
UTERS-0.073
inent-0.067
 Detail-0.065
Interstitial-0.064
iege-0.064
Token Chuck
Token ID14663
Feature activation+1.32e-01

Pos logit contributions
UTERS+0.249
inent+0.233
Interstitial+0.226
idences+0.224
iege+0.224
Neg logit contributions
SSL-0.245
fox-0.245
SPONSORED-0.239
 ‎-0.220
 �-0.218
Token Hag
Token ID21375
Feature activation-7.31e-03

Pos logit contributions
UTERS+0.363
inent+0.347
Interstitial+0.342
iege+0.335
idences+0.334
Neg logit contributions
SSL-0.173
fox-0.173
SPONSORED-0.162
 �-0.147
 ‎-0.145
Token
Token ID247
Feature activation-6.50e-02

Pos logit contributions
UTERS+0.030
inent+0.027
 Detail+0.026
Interstitial+0.026
idences+0.025
Neg logit contributions
SSL-0.051
fox-0.051
SPONSORED-0.050
 �-0.046
 ‎-0.046
Tokens
Token ID82
Feature activation-6.35e-02

Pos logit contributions
SSL+0.094
fox+0.093
SPONSORED+0.091
 �+0.080
 ‎+0.079
Neg logit contributions
UTERS-0.170
inent-0.160
 Detail-0.157
Interstitial-0.156
iege-0.155
Token
Token ID564
Feature activation+8.18e-02

Pos logit contributions
SSL+0.137
fox+0.135
SPONSORED+0.133
 �+0.123
 ‎+0.122
Neg logit contributions
UTERS-0.121
inent-0.112
 Detail-0.109
Interstitial-0.108
iege-0.107
Token
Token ID250
Feature activation-8.04e-02

Pos logit contributions
UTERS+0.085
inent+0.073
 Detail+0.070
Interstitial+0.068
iege+0.067
Neg logit contributions
SSL-0.247
fox-0.245
SPONSORED-0.243
 �-0.228
 ‎-0.228
Tokensec
Token ID2363
Feature activation-6.71e-02

Pos logit contributions
SSL+0.155
fox+0.153
SPONSORED+0.150
 �+0.136
 ‎+0.136
Neg logit contributions
UTERS-0.172
inent-0.160
 Detail-0.157
Interstitial-0.155
iege-0.154
Tokenrets
Token ID8004
Feature activation+6.86e-01

Pos logit contributions
SSL+0.116
fox+0.115
SPONSORED+0.113
 ‎+0.101
 �+0.101
Neg logit contributions
UTERS-0.156
inent-0.146
 Detail-0.144
Interstitial-0.143
iege-0.141
Token
Token ID447
Feature activation+6.62e-02

Pos logit contributions
UTERS+1.403
inent+1.307
 Detail+1.285
iege+1.254
idences+1.254
Neg logit contributions
SSL-1.374
fox-1.358
SPONSORED-1.337
 �-1.200
cens-1.190
Token
Token ID251
Feature activation-1.35e-02

Pos logit contributions
UTERS+0.100
inent+0.091
 Detail+0.088
Interstitial+0.086
iege+0.086
Neg logit contributions
SSL-0.169
fox-0.167
SPONSORED-0.165
 �-0.153
 ‎-0.152
Token.
Token ID13
Feature activation+4.75e-03

Pos logit contributions
SSL+0.027
fox+0.027
SPONSORED+0.026
 �+0.024
 ‎+0.024
Neg logit contributions
UTERS-0.028
inent-0.026
 Detail-0.025
Interstitial-0.025
iege-0.025
Token
Token ID198
Feature activation-2.03e-02

Pos logit contributions
UTERS+0.011
inent+0.010
 Detail+0.010
Interstitial+0.010
iege+0.010
Neg logit contributions
SSL-0.009
fox-0.009
SPONSORED-0.008
 �-0.008
 ‎-0.008
Token
Token ID198
Feature activation-4.25e-02

Pos logit contributions
SSL+0.030
fox+0.030
SPONSORED+0.029
 �+0.025
 ‎+0.025
Neg logit contributions
UTERS-0.053
inent-0.050
 Detail-0.049
Interstitial-0.049
iege-0.048
Token vote
Token ID3015
Feature activation+2.00e-01

Pos logit contributions
UTERS+0.049
inent+0.045
 Detail+0.044
Interstitial+0.044
idences+0.043
Neg logit contributions
SSL-0.049
fox-0.048
SPONSORED-0.048
 �-0.044
 ‎-0.043
Token accordingly
Token ID16062
Feature activation+2.28e-01

Pos logit contributions
UTERS+0.413
inent+0.384
 Detail+0.375
Interstitial+0.373
iege+0.371
Neg logit contributions
SSL-0.399
fox-0.396
SPONSORED-0.389
 �-0.357
 ‎-0.355
Token.
Token ID13
Feature activation+6.57e-02

Pos logit contributions
UTERS+0.447
inent+0.414
 Detail+0.407
Interstitial+0.396
iege+0.396
Neg logit contributions
SSL-0.480
fox-0.473
SPONSORED-0.467
 �-0.423
 ‎-0.421
Token<|endoftext|>
Token ID50256
Feature activation-2.30e-02

Pos logit contributions
UTERS+0.152
inent+0.143
 Detail+0.140
Interstitial+0.138
iege+0.137
Neg logit contributions
SSL-0.115
fox-0.113
SPONSORED-0.112
 �-0.100
 ‎-0.099
TokenStory
Token ID11605
Feature activation-1.93e-01

Pos logit contributions
SSL+0.050
fox+0.049
SPONSORED+0.049
 �+0.044
 ‎+0.044
Neg logit contributions
UTERS-0.044
inent-0.040
 Detail-0.040
iege-0.039
idences-0.039
Token highlights
Token ID11330
Feature activation+6.81e-01

Pos logit contributions
SSL+0.355
fox+0.353
SPONSORED+0.341
 �+0.312
 ‎+0.312
Neg logit contributions
UTERS-0.428
inent-0.402
Interstitial-0.389
 Detail-0.387
iege-0.387
Token Police
Token ID4287
Feature activation+1.81e-01

Pos logit contributions
UTERS+1.293
inent+1.188
 Detail+1.172
Interstitial+1.143
iege+1.138
Neg logit contributions
SSL-1.474
fox-1.457
SPONSORED-1.442
 �-1.312
 ‎-1.304
Token chief
Token ID4039
Feature activation+9.15e-02

Pos logit contributions
UTERS+0.372
inent+0.346
Interstitial+0.337
 Detail+0.334
idences+0.332
Neg logit contributions
SSL-0.362
fox-0.362
SPONSORED-0.351
 ‎-0.323
 �-0.321
Token vows
Token ID36605
Feature activation-1.15e-01

Pos logit contributions
UTERS+0.182
inent+0.168
Interstitial+0.164
 Detail+0.164
idences+0.162
Neg logit contributions
SSL-0.190
fox-0.189
SPONSORED-0.185
 �-0.170
 ‎-0.170
Token wanted
Token ID2227
Feature activation+9.49e-02

Pos logit contributions
SSL+0.238
fox+0.237
SPONSORED+0.232
 ‎+0.214
 �+0.213
Neg logit contributions
UTERS-0.229
inent-0.213
Interstitial-0.206
 Detail-0.206
idences-0.204
Token suspect
Token ID4099
Feature activation+6.07e-02

Pos logit contributions
UTERS+0.191
inent+0.177
 Detail+0.173
Interstitial+0.172
iege+0.170
Neg logit contributions
SSL-0.194
fox-0.193
SPONSORED-0.189
 ‎-0.172
 �-0.172
Token the
Token ID262
Feature activation+5.43e-03

Pos logit contributions
UTERS+0.189
inent+0.172
 Detail+0.170
Interstitial+0.169
iege+0.165
Neg logit contributions
SSL-0.238
fox-0.236
SPONSORED-0.232
 ‎-0.217
 �-0.216
Token problem
Token ID1917
Feature activation-4.84e-04

Pos logit contributions
UTERS+0.010
inent+0.009
Interstitial+0.009
 Detail+0.009
idences+0.009
Neg logit contributions
SSL-0.012
fox-0.012
SPONSORED-0.011
 ‎-0.011
 �-0.011
Token.
Token ID13
Feature activation-1.04e-03

Pos logit contributions
SSL+0.001
fox+0.001
SPONSORED+0.001
 �+0.001
 ‎+0.001
Neg logit contributions
UTERS-0.001
inent-0.001
 Detail-0.001
Interstitial-0.001
iege-0.001
Token<|endoftext|>
Token ID50256
Feature activation+8.64e-02

Pos logit contributions
SSL+0.002
fox+0.002
SPONSORED+0.002
cens+0.001
 �+0.001
Neg logit contributions
UTERS-0.002
inent-0.002
 Detail-0.002
Interstitial-0.002
iege-0.002
TokenHaw
Token ID33055
Feature activation+2.30e-01

Pos logit contributions
UTERS+0.164
inent+0.152
 Detail+0.149
Interstitial+0.146
iege+0.146
Neg logit contributions
SSL-0.187
fox-0.185
SPONSORED-0.182
 �-0.166
 ‎-0.165
Tokenaii
Token ID42648
Feature activation+6.64e-01

Pos logit contributions
UTERS+0.542
inent+0.509
 Detail+0.500
Interstitial+0.494
iege+0.491
Neg logit contributions
SSL-0.392
fox-0.386
SPONSORED-0.380
 �-0.338
 ‎-0.336
Token Congress
Token ID3162
Feature activation-7.52e-02

Pos logit contributions
UTERS+1.341
inent+1.245
 Detail+1.227
Interstitial+1.197
iege+1.197
Neg logit contributions
SSL-1.350
fox-1.332
SPONSORED-1.316
 �-1.190
 ‎-1.184
Tokenwoman
Token ID8580
Feature activation-7.52e-02

Pos logit contributions
SSL+0.132
fox+0.131
SPONSORED+0.129
 �+0.116
 ‎+0.115
Neg logit contributions
UTERS-0.173
inent-0.162
 Detail-0.158
Interstitial-0.157
idences-0.157
Token Tuls
Token ID33219
Feature activation+2.31e-01

Pos logit contributions
SSL+0.140
fox+0.140
SPONSORED+0.137
 �+0.124
 ‎+0.124
Neg logit contributions
UTERS-0.165
inent-0.153
 Detail-0.150
Interstitial-0.150
iege-0.148
Tokeni
Token ID72
Feature activation+1.04e-01

Pos logit contributions
UTERS+0.591
inent+0.546
Interstitial+0.539
 Detail+0.537
idences+0.529
Neg logit contributions
fox-0.357
SSL-0.355
SPONSORED-0.343
 ‎-0.311
 �-0.308
Token G
Token ID402
Feature activation-1.04e-01

Pos logit contributions
UTERS+0.202
Interstitial+0.184
inent+0.184
idences+0.180
 Detail+0.178
Neg logit contributions
SSL-0.222
fox-0.221
SPONSORED-0.215
 ‎-0.205
 �-0.200
Token instead
Token ID2427
Feature activation+1.05e-01

Pos logit contributions
SSL+0.029
fox+0.028
SPONSORED+0.028
 �+0.025
 ‎+0.025
Neg logit contributions
UTERS-0.030
inent-0.028
Interstitial-0.027
 Detail-0.027
iege-0.027
Token of
Token ID286
Feature activation-8.58e-03

Pos logit contributions
UTERS+0.227
inent+0.212
 Detail+0.209
iege+0.205
idences+0.204
Neg logit contributions
SSL-0.199
fox-0.198
SPONSORED-0.194
 ‎-0.173
 �-0.172
Token going
Token ID1016
Feature activation+1.06e-02

Pos logit contributions
SSL+0.018
fox+0.017
SPONSORED+0.017
 �+0.016
 ‎+0.016
Neg logit contributions
UTERS-0.017
inent-0.016
Interstitial-0.016
 Detail-0.016
iege-0.016
Token through
Token ID832
Feature activation-4.42e-02

Pos logit contributions
UTERS+0.022
inent+0.021
 Detail+0.020
Interstitial+0.020
iege+0.020
Neg logit contributions
SSL-0.021
fox-0.021
SPONSORED-0.020
 �-0.019
 ‎-0.019
Token std
Token ID14367
Feature activation+1.40e-01

Pos logit contributions
SSL+0.088
fox+0.087
SPONSORED+0.085
 �+0.077
 ‎+0.077
Neg logit contributions
UTERS-0.092
inent-0.086
 Detail-0.084
Interstitial-0.083
iege-0.082
Token::
Token ID3712
Feature activation+6.61e-01

Pos logit contributions
UTERS+0.280
inent+0.259
 Detail+0.254
Interstitial+0.252
idences+0.248
Neg logit contributions
SSL-0.291
fox-0.287
SPONSORED-0.281
 �-0.257
 ‎-0.255
Tokenist
Token ID396
Feature activation-2.38e-02

Pos logit contributions
UTERS+1.354
inent+1.259
 Detail+1.233
Interstitial+1.212
iege+1.209
Neg logit contributions
SSL-1.327
fox-1.312
SPONSORED-1.299
 �-1.175
 ‎-1.169
Tokenream
Token ID1476
Feature activation+3.02e-01

Pos logit contributions
SSL+0.043
fox+0.042
SPONSORED+0.041
 �+0.037
 ‎+0.037
Neg logit contributions
UTERS-0.054
inent-0.051
 Detail-0.050
Interstitial-0.049
iege-0.049
Token.
Token ID13
Feature activation+1.78e-02

Pos logit contributions
UTERS+0.640
inent+0.596
 Detail+0.585
Interstitial+0.576
iege+0.573
Neg logit contributions
SSL-0.584
fox-0.578
SPONSORED-0.569
 �-0.514
 ‎-0.511
Token I
Token ID314
Feature activation-1.42e-02

Pos logit contributions
UTERS+0.036
inent+0.033
 Detail+0.032
Interstitial+0.032
idences+0.031
Neg logit contributions
SSL-0.037
fox-0.036
SPONSORED-0.036
 �-0.033
 ‎-0.033
Token also
Token ID635
Feature activation+2.41e-02

Pos logit contributions
SSL+0.026
fox+0.025
SPONSORED+0.025
 �+0.023
 ‎+0.022
Neg logit contributions
UTERS-0.032
inent-0.030
 Detail-0.029
Interstitial-0.029
iege-0.029
TokenThe
Token ID464
Feature activation-5.12e-02

Pos logit contributions
UTERS+0.061
inent+0.057
 Detail+0.056
iege+0.055
idences+0.055
Neg logit contributions
SSL-0.067
fox-0.066
SPONSORED-0.065
 �-0.059
 ‎-0.059
Token alleged
Token ID4260
Feature activation-1.73e-01

Pos logit contributions
SSL+0.109
fox+0.108
SPONSORED+0.106
 �+0.097
 ‎+0.097
Neg logit contributions
UTERS-0.099
inent-0.091
 Detail-0.089
Interstitial-0.088
iege-0.087
Token offenses
Token ID18514
Feature activation-1.08e-01

Pos logit contributions
SSL+0.379
fox+0.376
SPONSORED+0.370
 ‎+0.340
 �+0.340
Neg logit contributions
UTERS-0.325
inent-0.298
 Detail-0.290
Interstitial-0.289
iege-0.285
Token were
Token ID547
Feature activation+9.77e-02

Pos logit contributions
SSL+0.225
fox+0.224
SPONSORED+0.222
 ‎+0.203
 �+0.202
Neg logit contributions
UTERS-0.211
inent-0.194
Interstitial-0.190
 Detail-0.188
iege-0.187
Token drug
Token ID2563
Feature activation-4.61e-02

Pos logit contributions
UTERS+0.202
inent+0.185
iege+0.182
 Detail+0.180
Interstitial+0.180
Neg logit contributions
SSL-0.196
fox-0.194
SPONSORED-0.191
 ‎-0.176
 �-0.173
Token possession
Token ID7797
Feature activation+6.53e-01

Pos logit contributions
SSL+0.105
fox+0.105
SPONSORED+0.104
 ‎+0.096
 �+0.095
Neg logit contributions
UTERS-0.082
inent-0.074
 Detail-0.072
iege-0.071
Interstitial-0.071
Token and
Token ID290
Feature activation+1.13e-01

Pos logit contributions
UTERS+1.321
inent+1.235
 Detail+1.208
Interstitial+1.183
idences+1.180
Neg logit contributions
SSL-1.331
fox-1.301
SPONSORED-1.282
 �-1.170
cens-1.155
Token possession
Token ID7797
Feature activation+6.10e-01

Pos logit contributions
UTERS+0.196
inent+0.178
 Detail+0.173
Interstitial+0.171
idences+0.170
Neg logit contributions
SSL-0.264
fox-0.262
SPONSORED-0.260
 ‎-0.239
 �-0.238
Token of
Token ID286
Feature activation+1.47e-01

Pos logit contributions
UTERS+1.283
inent+1.208
 Detail+1.167
iege+1.155
idences+1.144
Neg logit contributions
SSL-1.203
fox-1.163
SPONSORED-1.130
 �-1.046
cens-1.031
Token drug
Token ID2563
Feature activation-2.79e-02

Pos logit contributions
UTERS+0.290
inent+0.268
 Detail+0.261
Interstitial+0.259
idences+0.257
Neg logit contributions
SSL-0.306
fox-0.304
SPONSORED-0.300
 ‎-0.274
 �-0.274
Token parap
Token ID41406
Feature activation+3.41e-01

Pos logit contributions
SSL+0.055
fox+0.055
SPONSORED+0.054
 ‎+0.049
 �+0.049
Neg logit contributions
UTERS-0.058
inent-0.054
 Detail-0.052
Interstitial-0.052
iege-0.052
Token of
Token ID286
Feature activation+2.04e-02

Pos logit contributions
SSL+0.148
fox+0.146
SPONSORED+0.143
 �+0.128
 ‎+0.127
Neg logit contributions
UTERS-0.180
inent-0.168
 Detail-0.165
Interstitial-0.162
iege-0.162
Token the
Token ID262
Feature activation+1.16e-02

Pos logit contributions
UTERS+0.040
inent+0.037
 Detail+0.036
Interstitial+0.035
iege+0.035
Neg logit contributions
SSL-0.043
fox-0.043
SPONSORED-0.042
 �-0.038
 ‎-0.038
Token
Token ID564
Feature activation-1.08e-01

Pos logit contributions
UTERS+0.024
inent+0.022
 Detail+0.021
Interstitial+0.021
idences+0.021
Neg logit contributions
SSL-0.023
fox-0.023
SPONSORED-0.023
 �-0.021
 ‎-0.021
Token
Token ID246
Feature activation-1.12e-01

Pos logit contributions
SSL+0.281
fox+0.277
SPONSORED+0.273
 ‎+0.255
 �+0.255
Neg logit contributions
UTERS-0.161
inent-0.143
 Detail-0.143
idences-0.137
Interstitial-0.136
Tokendel
Token ID12381
Feature activation+2.07e-01

Pos logit contributions
SSL+0.203
fox+0.200
SPONSORED+0.197
 �+0.176
 ‎+0.176
Neg logit contributions
UTERS-0.251
inent-0.234
 Detail-0.230
Interstitial-0.226
idences-0.226
Tokenayed
Token ID16548
Feature activation+6.43e-01

Pos logit contributions
UTERS+0.505
inent+0.477
 Detail+0.467
iege+0.462
Interstitial+0.461
Neg logit contributions
SSL-0.335
fox-0.328
SPONSORED-0.323
 �-0.285
 ‎-0.283
Token unfolding
Token ID34502
Feature activation+1.36e-01

Pos logit contributions
UTERS+1.247
inent+1.156
 Detail+1.133
Interstitial+1.119
iege+1.107
Neg logit contributions
SSL-1.359
fox-1.345
SPONSORED-1.323
 �-1.200
cens-1.191
Token of
Token ID286
Feature activation+3.87e-02

Pos logit contributions
UTERS+0.298
inent+0.276
 Detail+0.273
Interstitial+0.271
iege+0.270
Neg logit contributions
SSL-0.256
fox-0.254
SPONSORED-0.246
 �-0.220
cens-0.219
Token independence
Token ID10404
Feature activation+1.91e-01

Pos logit contributions
UTERS+0.075
inent+0.070
 Detail+0.068
Interstitial+0.067
iege+0.067
Neg logit contributions
SSL-0.082
fox-0.081
SPONSORED-0.080
 �-0.072
cens-0.072
Token
Token ID447
Feature activation-8.42e-02

Pos logit contributions
UTERS+0.439
inent+0.411
 Detail+0.403
Interstitial+0.397
iege+0.396
Neg logit contributions
SSL-0.339
fox-0.335
SPONSORED-0.329
 �-0.293
 ‎-0.289
Token
Token ID247
Feature activation-7.07e-03

Pos logit contributions
SSL+0.220
fox+0.216
SPONSORED+0.215
 ‎+0.202
 �+0.201
Neg logit contributions
UTERS-0.123
inent-0.111
 Detail-0.108
idences-0.104
iege-0.102
Token`
Token ID63
Feature activation+2.93e-01

Pos logit contributions
SSL+0.366
fox+0.360
SPONSORED+0.356
 �+0.322
 ‎+0.321
Neg logit contributions
UTERS-0.380
inent-0.354
 Detail-0.345
Interstitial-0.341
idences-0.339
Token represent
Token ID2380
Feature activation+6.53e-02

Pos logit contributions
UTERS+0.581
inent+0.539
 Detail+0.527
Interstitial+0.519
idences+0.516
Neg logit contributions
SSL-0.607
fox-0.601
SPONSORED-0.594
 �-0.540
 ‎-0.538
Tokenable
Token ID540
Feature activation+1.03e-01

Pos logit contributions
UTERS+0.137
inent+0.128
 Detail+0.125
Interstitial+0.123
idences+0.123
Neg logit contributions
SSL-0.128
fox-0.127
SPONSORED-0.125
 �-0.114
 ‎-0.113
Token
Token ID198
Feature activation+1.39e-02

Pos logit contributions
UTERS+0.210
inent+0.195
 Detail+0.190
Interstitial+0.189
idences+0.187
Neg logit contributions
SSL-0.206
fox-0.205
SPONSORED-0.202
 �-0.184
 ‎-0.184
Token
Token ID198
Feature activation+9.71e-03

Pos logit contributions
UTERS+0.036
inent+0.034
 Detail+0.034
Interstitial+0.033
iege+0.033
Neg logit contributions
SSL-0.021
fox-0.020
SPONSORED-0.020
 �-0.017
 ‎-0.017
Token:(
Token ID37498
Feature activation+6.39e-01

Pos logit contributions
UTERS+0.018
inent+0.017
 Detail+0.017
idences+0.016
iege+0.016
Neg logit contributions
SSL-0.021
fox-0.021
SPONSORED-0.021
 ‎-0.019
cens-0.019
Token
Token ID198
Feature activation-1.55e-02

Pos logit contributions
UTERS+1.321
inent+1.228
 Detail+1.205
Interstitial+1.185
iege+1.179
Neg logit contributions
SSL-1.273
fox-1.259
SPONSORED-1.241
 �-1.123
 ‎-1.118
Token
Token ID198
Feature activation-1.28e-02

Pos logit contributions
SSL+0.023
fox+0.022
SPONSORED+0.022
 �+0.019
 ‎+0.019
Neg logit contributions
UTERS-0.040
inent-0.038
 Detail-0.038
Interstitial-0.037
iege-0.037
TokenI
Token ID40
Feature activation+6.47e-02

Pos logit contributions
SSL+0.027
fox+0.026
SPONSORED+0.026
 ‎+0.024
 �+0.024
Neg logit contributions
UTERS-0.025
inent-0.023
 Detail-0.023
idences-0.023
iege-0.022
Token
Token ID447
Feature activation-1.23e-01

Pos logit contributions
UTERS+0.137
inent+0.128
 Detail+0.125
Interstitial+0.123
iege+0.122
Neg logit contributions
SSL-0.126
fox-0.125
SPONSORED-0.123
 �-0.112
 ‎-0.111
Token
Token ID247
Feature activation-2.79e-02

Pos logit contributions
SSL+0.323
SPONSORED+0.318
fox+0.315
 �+0.295
 ‎+0.295
Neg logit contributions
UTERS-0.177
inent-0.161
 Detail-0.156
idences-0.152
Interstitial-0.149
Token+
Token ID10
Feature activation-2.82e-03

Pos logit contributions
UTERS+0.271
inent+0.251
 Detail+0.245
Interstitial+0.242
iege+0.241
Neg logit contributions
SSL-0.281
fox-0.278
SPONSORED-0.273
 �-0.249
 ‎-0.248
Token:
Token ID25
Feature activation+1.01e-02

Pos logit contributions
SSL+0.006
fox+0.006
SPONSORED+0.006
 �+0.005
 ‎+0.005
Neg logit contributions
UTERS-0.006
inent-0.005
 Detail-0.005
Interstitial-0.005
idences-0.005
Token Struct
Token ID32112
Feature activation-1.54e-01

Pos logit contributions
UTERS+0.019
inent+0.017
 Detail+0.017
Interstitial+0.017
iege+0.017
Neg logit contributions
SSL-0.022
fox-0.022
SPONSORED-0.022
 �-0.020
 ‎-0.020
Tokenuring
Token ID870
Feature activation+3.23e-01

Pos logit contributions
SSL+0.320
fox+0.316
SPONSORED+0.312
 �+0.284
 ‎+0.282
Neg logit contributions
UTERS-0.305
inent-0.283
 Detail-0.277
Interstitial-0.272
iege-0.271
Token Prosper
Token ID41342
Feature activation+3.55e-01

Pos logit contributions
UTERS+0.647
inent+0.600
 Detail+0.585
Interstitial+0.578
iege+0.574
Neg logit contributions
SSL-0.667
fox-0.660
SPONSORED-0.651
 �-0.592
 ‎-0.590
Tokenity
Token ID414
Feature activation+6.36e-01

Pos logit contributions
UTERS+0.590
inent+0.539
 Detail+0.526
Interstitial+0.513
iege+0.511
Neg logit contributions
SSL-0.852
fox-0.845
SPONSORED-0.834
 �-0.770
 ‎-0.765
Token for
Token ID329
Feature activation+3.90e-02

Pos logit contributions
UTERS+1.291
inent+1.199
 Detail+1.176
Interstitial+1.155
iege+1.150
Neg logit contributions
SSL-1.290
fox-1.275
SPONSORED-1.258
 �-1.141
 ‎-1.134
Token Yourself
Token ID42132
Feature activation+1.71e-02

Pos logit contributions
UTERS+0.078
inent+0.072
Interstitial+0.070
iege+0.069
 Detail+0.069
Neg logit contributions
SSL-0.081
fox-0.080
SPONSORED-0.079
 ‎-0.073
 �-0.072
Token and
Token ID290
Feature activation+4.01e-02

Pos logit contributions
UTERS+0.039
inent+0.036
 Detail+0.035
Interstitial+0.035
iege+0.035
Neg logit contributions
SSL-0.031
fox-0.031
SPONSORED-0.030
 �-0.027
 ‎-0.027
Token the
Token ID262
Feature activation+4.89e-02

Pos logit contributions
UTERS+0.077
inent+0.071
Interstitial+0.069
 Detail+0.069
iege+0.068
Neg logit contributions
SSL-0.086
fox-0.085
SPONSORED-0.084
 ‎-0.077
 �-0.077
Token Nation
Token ID8741
Feature activation+1.55e-01

Pos logit contributions
UTERS+0.088
inent+0.081
Interstitial+0.078
 Detail+0.077
iege+0.077
Neg logit contributions
SSL-0.110
fox-0.110
SPONSORED-0.108
 ‎-0.100
 �-0.100
Token full
Token ID1336
Feature activation+1.50e-01

Pos logit contributions
SSL+0.088
fox+0.088
SPONSORED+0.085
 �+0.078
 ‎+0.077
Neg logit contributions
UTERS-0.099
inent-0.093
 Detail-0.091
iege-0.090
Interstitial-0.090
Token story
Token ID1621
Feature activation+5.29e-03

Pos logit contributions
UTERS+0.384
inent+0.362
 Detail+0.354
Interstitial+0.353
iege+0.352
Neg logit contributions
SSL-0.225
fox-0.224
SPONSORED-0.219
 �-0.192
 ‎-0.191
Token<|endoftext|>
Token ID50256
Feature activation-2.34e-02

Pos logit contributions
UTERS+0.014
inent+0.013
 Detail+0.013
Interstitial+0.012
iege+0.012
Neg logit contributions
SSL-0.008
fox-0.008
SPONSORED-0.008
 �-0.007
 ‎-0.007
TokenAsia
Token ID38555
Feature activation-8.77e-02

Pos logit contributions
SSL+0.051
fox+0.050
SPONSORED+0.050
 �+0.045
 ‎+0.045
Neg logit contributions
UTERS-0.045
inent-0.041
 Detail-0.041
iege-0.040
idences-0.040
Token Health
Token ID3893
Feature activation+3.52e-01

Pos logit contributions
SSL+0.170
fox+0.168
SPONSORED+0.165
 �+0.150
 ‎+0.149
Neg logit contributions
UTERS-0.187
inent-0.174
 Detail-0.170
Interstitial-0.168
idences-0.167
Token Correspond
Token ID34428
Feature activation+6.31e-01

Pos logit contributions
UTERS+0.709
inent+0.658
 Detail+0.644
Interstitial+0.635
iege+0.631
Neg logit contributions
SSL-0.722
fox-0.714
SPONSORED-0.703
 �-0.640
 ‎-0.637
Tokenent
Token ID298
Feature activation+1.19e-01

Pos logit contributions
UTERS+0.950
inent+0.865
 Detail+0.839
iege+0.813
idences+0.812
Neg logit contributions
SSL-1.611
fox-1.596
SPONSORED-1.582
 �-1.457
 ‎-1.447
Token
Token ID198
Feature activation+5.11e-02

Pos logit contributions
UTERS+0.252
inent+0.235
 Detail+0.229
Interstitial+0.227
iege+0.226
Neg logit contributions
SSL-0.232
fox-0.230
SPONSORED-0.226
 �-0.205
 ‎-0.205
Token
Token ID198
Feature activation+5.26e-02

Pos logit contributions
UTERS+0.133
inent+0.127
 Detail+0.125
iege+0.123
idences+0.123
Neg logit contributions
SSL-0.075
fox-0.074
SPONSORED-0.073
 ‎-0.063
 �-0.063
TokenA
Token ID32
Feature activation-3.51e-02

Pos logit contributions
UTERS+0.098
inent+0.092
 Detail+0.091
iege+0.088
idences+0.088
Neg logit contributions
SSL-0.116
fox-0.114
SPONSORED-0.113
 �-0.102
 ‎-0.102
Token lake
Token ID13546
Feature activation+5.76e-02

Pos logit contributions
SSL+0.073
fox+0.073
SPONSORED+0.071
 �+0.065
 ‎+0.065
Neg logit contributions
UTERS-0.069
inent-0.064
 Detail-0.063
Interstitial-0.062
iege-0.062
Token an
Token ID281
Feature activation+9.88e-02

Pos logit contributions
UTERS+0.056
inent+0.051
 Detail+0.050
iege+0.050
Interstitial+0.049
Neg logit contributions
SSL-0.062
fox-0.061
SPONSORED-0.060
 ‎-0.056
 �-0.056
Tokenaer
Token ID25534
Feature activation+1.99e-01

Pos logit contributions
UTERS+0.180
inent+0.164
 Detail+0.161
idences+0.157
iege+0.156
Neg logit contributions
SSL-0.222
fox-0.219
SPONSORED-0.217
 �-0.200
 ‎-0.200
Tokenobic
Token ID20803
Feature activation-2.68e-01

Pos logit contributions
UTERS+0.418
inent+0.391
 Detail+0.382
Interstitial+0.376
iege+0.375
Neg logit contributions
SSL-0.389
fox-0.384
SPONSORED-0.380
 �-0.342
 ‎-0.341
Token pathogens
Token ID38366
Feature activation+2.11e-01

Pos logit contributions
SSL+0.574
fox+0.573
SPONSORED+0.566
 ‎+0.522
 �+0.520
Neg logit contributions
UTERS-0.513
inent-0.469
 Detail-0.456
iege-0.452
Interstitial-0.451
Token (
Token ID357
Feature activation+5.11e-02

Pos logit contributions
UTERS+0.441
inent+0.409
 Detail+0.402
Interstitial+0.396
iege+0.394
Neg logit contributions
SSL-0.414
fox-0.411
SPONSORED-0.408
 �-0.368
 ‎-0.368
TokenPrev
Token ID36854
Feature activation+6.29e-01

Pos logit contributions
UTERS+0.108
inent+0.100
 Detail+0.099
idences+0.097
iege+0.097
Neg logit contributions
SSL-0.100
fox-0.099
SPONSORED-0.097
 ‎-0.088
 �-0.087
Tokenot
Token ID313
Feature activation+5.26e-02

Pos logit contributions
UTERS+1.322
inent+1.221
 Detail+1.203
Interstitial+1.188
iege+1.179
Neg logit contributions
SSL-1.241
fox-1.225
SPONSORED-1.200
 �-1.092
cens-1.083
Tokenella
Token ID12627
Feature activation+1.30e-01

Pos logit contributions
UTERS+0.085
inent+0.074
 Detail+0.073
Interstitial+0.073
iege+0.071
Neg logit contributions
SSL-0.131
fox-0.130
SPONSORED-0.127
cens-0.118
 ‎-0.118
Token,
Token ID11
Feature activation+6.78e-02

Pos logit contributions
UTERS+0.260
inent+0.240
 Detail+0.235
Interstitial+0.232
iege+0.231
Neg logit contributions
SSL-0.268
fox-0.265
SPONSORED-0.261
 �-0.238
 ‎-0.237
Token Pe
Token ID2631
Feature activation-9.53e-03

Pos logit contributions
UTERS+0.122
inent+0.111
 Detail+0.107
Interstitial+0.107
iege+0.106
Neg logit contributions
SSL-0.154
fox-0.153
SPONSORED-0.151
 ‎-0.139
 �-0.139
Tokenpt
Token ID457
Feature activation-1.67e-01

Pos logit contributions
SSL+0.016
fox+0.016
SPONSORED+0.016
 �+0.014
 ‎+0.014
Neg logit contributions
UTERS-0.022
inent-0.021
 Detail-0.021
Interstitial-0.020
iege-0.020
Token PS
Token ID6599
Feature activation+1.59e-01

Pos logit contributions
SSL+0.011
fox+0.011
SPONSORED+0.010
 �+0.009
 ‎+0.009
Neg logit contributions
UTERS-0.013
inent-0.012
 Detail-0.011
Interstitial-0.011
idences-0.011
Token4
Token ID19
Feature activation+4.04e-01

Pos logit contributions
UTERS+0.345
inent+0.321
 Detail+0.316
Interstitial+0.311
iege+0.310
Neg logit contributions
SSL-0.298
fox-0.295
SPONSORED-0.291
 �-0.261
 ‎-0.260
Token Release
Token ID13868
Feature activation-2.49e-03

Pos logit contributions
UTERS+0.726
inent+0.670
 Detail+0.645
Interstitial+0.642
idences+0.637
Neg logit contributions
SSL-0.916
fox-0.905
SPONSORED-0.891
 �-0.825
 ‎-0.821
Token Date
Token ID7536
Feature activation-2.61e-01

Pos logit contributions
SSL+0.005
fox+0.005
SPONSORED+0.005
 �+0.005
 ‎+0.004
Neg logit contributions
UTERS-0.005
inent-0.005
Interstitial-0.005
idences-0.005
iege-0.005
Token Del
Token ID4216
Feature activation+2.80e-01

Pos logit contributions
SSL+0.570
fox+0.567
SPONSORED+0.552
 �+0.515
 ‎+0.512
Neg logit contributions
UTERS-0.489
inent-0.457
Interstitial-0.439
idences-0.433
iege-0.431
Tokenayed
Token ID16548
Feature activation+6.24e-01

Pos logit contributions
UTERS+0.666
inent+0.631
 Detail+0.617
iege+0.611
idences+0.611
Neg logit contributions
SSL-0.469
SPONSORED-0.460
fox-0.454
 �-0.401
 ‎-0.397
Token Until
Token ID14303
Feature activation-2.28e-01

Pos logit contributions
UTERS+1.345
inent+1.252
 Detail+1.238
Interstitial+1.211
iege+1.205
Neg logit contributions
SSL-1.188
fox-1.172
SPONSORED-1.157
 �-1.038
 ‎-1.031
Token At
Token ID1629
Feature activation-1.95e-02

Pos logit contributions
SSL+0.467
fox+0.459
SPONSORED+0.448
 ‎+0.420
 �+0.419
Neg logit contributions
UTERS-0.462
inent-0.430
Interstitial-0.415
iege-0.410
idences-0.410
Token Le
Token ID1004
Feature activation+1.75e-03

Pos logit contributions
SSL+0.036
fox+0.036
SPONSORED+0.035
 �+0.032
 ‎+0.032
Neg logit contributions
UTERS-0.043
inent-0.040
 Detail-0.039
Interstitial-0.039
idences-0.039
Tokenast
Token ID459
Feature activation+3.63e-02

Pos logit contributions
UTERS+0.004
inent+0.003
 Detail+0.003
Interstitial+0.003
idences+0.003
Neg logit contributions
SSL-0.004
fox-0.004
SPONSORED-0.003
 �-0.003
 ‎-0.003
Token March
Token ID2805
Feature activation-2.35e-02

Pos logit contributions
UTERS+0.070
inent+0.065
idences+0.062
Interstitial+0.062
iege+0.062
Neg logit contributions
SSL-0.078
fox-0.077
SPONSORED-0.075
 ‎-0.071
 �-0.071
Token Brom
Token ID31455
Feature activation-2.67e-02

Pos logit contributions
UTERS+0.318
inent+0.292
Interstitial+0.288
 Detail+0.283
iege+0.278
Neg logit contributions
fox-0.374
SSL-0.368
SPONSORED-0.357
 ‎-0.332
 �-0.330
Tokenwich
Token ID11451
Feature activation+3.31e-02

Pos logit contributions
SSL+0.041
fox+0.040
SPONSORED+0.039
 �+0.034
 ‎+0.034
Neg logit contributions
UTERS-0.068
inent-0.064
 Detail-0.063
Interstitial-0.062
iege-0.062
Token Albion
Token ID47995
Feature activation+9.62e-02

Pos logit contributions
UTERS+0.064
inent+0.059
 Detail+0.058
Interstitial+0.058
idences+0.056
Neg logit contributions
fox-0.071
SSL-0.071
SPONSORED-0.069
 ‎-0.063
 �-0.063
Token and
Token ID290
Feature activation+4.20e-02

Pos logit contributions
UTERS+0.200
inent+0.186
 Detail+0.182
idences+0.178
Interstitial+0.178
Neg logit contributions
SSL-0.191
fox-0.188
SPONSORED-0.186
 �-0.168
 ‎-0.166
Token Stoke
Token ID36178
Feature activation-8.83e-02

Pos logit contributions
UTERS+0.083
inent+0.078
Interstitial+0.076
 Detail+0.075
idences+0.074
Neg logit contributions
fox-0.087
SSL-0.087
SPONSORED-0.084
 ‎-0.079
 �-0.078
Token City
Token ID2254
Feature activation+6.15e-01

Pos logit contributions
fox+0.241
SSL+0.240
SPONSORED+0.235
 ‎+0.221
 �+0.220
Neg logit contributions
UTERS-0.119
inent-0.106
Interstitial-0.102
 Detail-0.101
idences-0.099
Token achieved
Token ID8793
Feature activation+1.08e-01

Pos logit contributions
UTERS+1.249
inent+1.159
 Detail+1.137
Interstitial+1.116
iege+1.111
Neg logit contributions
SSL-1.250
fox-1.234
SPONSORED-1.219
 �-1.105
 ‎-1.098
Token without
Token ID1231
Feature activation+3.33e-02

Pos logit contributions
UTERS+0.219
inent+0.204
 Detail+0.200
Interstitial+0.198
idences+0.196
Neg logit contributions
SSL-0.218
fox-0.216
SPONSORED-0.212
 �-0.194
 ‎-0.194
Token players
Token ID1938
Feature activation+1.44e-01

Pos logit contributions
UTERS+0.063
inent+0.059
 Detail+0.057
Interstitial+0.057
iege+0.056
Neg logit contributions
SSL-0.072
fox-0.071
SPONSORED-0.070
 ‎-0.065
 �-0.065
Token such
Token ID884
Feature activation-9.03e-02

Pos logit contributions
UTERS+0.261
inent+0.240
 Detail+0.233
Interstitial+0.232
idences+0.230
Neg logit contributions
SSL-0.325
fox-0.322
SPONSORED-0.319
 ‎-0.294
 �-0.293
Token as
Token ID355
Feature activation-6.98e-02

Pos logit contributions
SSL+0.161
fox+0.160
SPONSORED+0.157
 ‎+0.144
 �+0.143
Neg logit contributions
UTERS-0.206
inent-0.193
 Detail-0.189
Interstitial-0.188
idences-0.186
Token offenses
Token ID18514
Feature activation-1.08e-01

Pos logit contributions
SSL+0.379
fox+0.376
SPONSORED+0.370
 ‎+0.340
 �+0.340
Neg logit contributions
UTERS-0.325
inent-0.298
 Detail-0.290
Interstitial-0.289
iege-0.285
Token were
Token ID547
Feature activation+9.77e-02

Pos logit contributions
SSL+0.225
fox+0.224
SPONSORED+0.222
 ‎+0.203
 �+0.202
Neg logit contributions
UTERS-0.211
inent-0.194
Interstitial-0.190
 Detail-0.188
iege-0.187
Token drug
Token ID2563
Feature activation-4.61e-02

Pos logit contributions
UTERS+0.202
inent+0.185
iege+0.182
 Detail+0.180
Interstitial+0.180
Neg logit contributions
SSL-0.196
fox-0.194
SPONSORED-0.191
 ‎-0.176
 �-0.173
Token possession
Token ID7797
Feature activation+6.53e-01

Pos logit contributions
SSL+0.105
fox+0.105
SPONSORED+0.104
 ‎+0.096
 �+0.095
Neg logit contributions
UTERS-0.082
inent-0.074
 Detail-0.072
iege-0.071
Interstitial-0.071
Token and
Token ID290
Feature activation+1.13e-01

Pos logit contributions
UTERS+1.321
inent+1.235
 Detail+1.208
Interstitial+1.183
idences+1.180
Neg logit contributions
SSL-1.331
fox-1.301
SPONSORED-1.282
 �-1.170
cens-1.155
Token possession
Token ID7797
Feature activation+6.10e-01

Pos logit contributions
UTERS+0.196
inent+0.178
 Detail+0.173
Interstitial+0.171
idences+0.170
Neg logit contributions
SSL-0.264
fox-0.262
SPONSORED-0.260
 ‎-0.239
 �-0.238
Token of
Token ID286
Feature activation+1.47e-01

Pos logit contributions
UTERS+1.283
inent+1.208
 Detail+1.167
iege+1.155
idences+1.144
Neg logit contributions
SSL-1.203
fox-1.163
SPONSORED-1.130
 �-1.046
cens-1.031
Token drug
Token ID2563
Feature activation-2.79e-02

Pos logit contributions
UTERS+0.290
inent+0.268
 Detail+0.261
Interstitial+0.259
idences+0.257
Neg logit contributions
SSL-0.306
fox-0.304
SPONSORED-0.300
 ‎-0.274
 �-0.274
Token parap
Token ID41406
Feature activation+3.41e-01

Pos logit contributions
SSL+0.055
fox+0.055
SPONSORED+0.054
 ‎+0.049
 �+0.049
Neg logit contributions
UTERS-0.058
inent-0.054
 Detail-0.052
Interstitial-0.052
iege-0.052
Tokenhern
Token ID2881
Feature activation-2.14e-01

Pos logit contributions
UTERS+0.649
 Detail+0.600
Interstitial+0.594
inent+0.593
idences+0.572
Neg logit contributions
fox-0.729
SSL-0.728
SPONSORED-0.711
 ‎-0.662
 �-0.653
Tokenalia
Token ID9752
Feature activation+1.51e-02

Pos logit contributions
fox+0.551
SSL+0.544
SPONSORED+0.525
 ‎+0.499
css+0.497
Neg logit contributions
UTERS-0.330
 Detail-0.291
Interstitial-0.289
ALSE-0.277
inent-0.276
Tokenus
Token ID385
Feature activation+1.31e-01

Pos logit contributions
SSL+0.239
fox+0.236
SPONSORED+0.232
 �+0.208
 ‎+0.208
Neg logit contributions
UTERS-0.305
inent-0.285
 Detail-0.281
Interstitial-0.278
iege-0.275
Token B
Token ID347
Feature activation+4.56e-02

Pos logit contributions
UTERS+0.250
inent+0.231
 Detail+0.223
Interstitial+0.222
idences+0.219
Neg logit contributions
SSL-0.284
fox-0.283
SPONSORED-0.276
 �-0.255
 ‎-0.254
Tokenully
Token ID2132
Feature activation+1.05e-01

Pos logit contributions
UTERS+0.089
inent+0.082
 Detail+0.081
Interstitial+0.080
idences+0.079
Neg logit contributions
SSL-0.097
fox-0.095
SPONSORED-0.093
 �-0.085
 ‎-0.085
Token/
Token ID14
Feature activation+3.96e-02

Pos logit contributions
UTERS+0.193
inent+0.177
Interstitial+0.171
 Detail+0.171
idences+0.168
Neg logit contributions
SSL-0.235
fox-0.235
SPONSORED-0.229
 ‎-0.213
 �-0.212
TokenVict
Token ID21944
Feature activation+1.11e-02

Pos logit contributions
UTERS+0.079
inent+0.073
 Detail+0.072
Interstitial+0.070
idences+0.070
Neg logit contributions
SSL-0.082
fox-0.081
SPONSORED-0.080
 �-0.073
 ‎-0.073
Tokenim
Token ID320
Feature activation+5.98e-01

Pos logit contributions
UTERS+0.026
inent+0.024
Interstitial+0.024
 Detail+0.024
iege+0.024
Neg logit contributions
fox-0.019
SSL-0.019
SPONSORED-0.018
 ‎-0.016
 �-0.016
Token Question
Token ID18233
Feature activation+9.85e-02

Pos logit contributions
UTERS+1.045
inent+0.958
 Detail+0.931
Interstitial+0.919
iege+0.910
Neg logit contributions
SSL-1.383
fox-1.370
SPONSORED-1.351
 �-1.245
 ‎-1.240
Tokennaire
Token ID24042
Feature activation-4.60e-02

Pos logit contributions
UTERS+0.080
inent+0.064
 Detail+0.060
Interstitial+0.059
idences+0.057
Neg logit contributions
SSL-0.320
fox-0.319
SPONSORED-0.314
 �-0.298
 ‎-0.298
Token [
Token ID685
Feature activation-1.29e-01

Pos logit contributions
SSL+0.086
fox+0.085
SPONSORED+0.083
 �+0.075
 ‎+0.075
Neg logit contributions
UTERS-0.101
inent-0.094
 Detail-0.092
Interstitial-0.091
idences-0.091
TokenM
Token ID44
Feature activation+1.81e-01

Pos logit contributions
SSL+0.260
fox+0.257
SPONSORED+0.251
 �+0.230
 ‎+0.229
Neg logit contributions
UTERS-0.268
inent-0.247
 Detail-0.240
Interstitial-0.240
idences-0.238
Tokenimeo
Token ID47776
Feature activation+1.33e-01

Pos logit contributions
UTERS+0.350
inent+0.323
 Detail+0.317
Interstitial+0.311
iege+0.309
Neg logit contributions
SSL-0.387
fox-0.383
SPONSORED-0.378
 �-0.345
 ‎-0.343
Token,
Token ID11
Feature activation+2.58e-02

Pos logit contributions
SSL+0.317
fox+0.314
SPONSORED+0.309
 �+0.281
 ‎+0.280
Neg logit contributions
UTERS-0.351
inent-0.327
 Detail-0.319
Interstitial-0.316
iege-0.314
Token the
Token ID262
Feature activation+5.13e-02

Pos logit contributions
UTERS+0.055
inent+0.052
 Detail+0.051
Interstitial+0.050
iege+0.050
Neg logit contributions
SSL-0.049
fox-0.049
SPONSORED-0.048
 �-0.044
 ‎-0.043
Token legacy
Token ID10655
Feature activation+4.13e-02

Pos logit contributions
UTERS+0.102
inent+0.094
 Detail+0.092
Interstitial+0.091
idences+0.090
Neg logit contributions
SSL-0.106
fox-0.106
SPONSORED-0.103
 �-0.096
 ‎-0.096
Token of
Token ID286
Feature activation+1.05e-01

Pos logit contributions
UTERS+0.094
inent+0.088
 Detail+0.087
Interstitial+0.085
iege+0.085
Neg logit contributions
SSL-0.074
fox-0.073
SPONSORED-0.071
 �-0.064
 ‎-0.063
Token Antiqu
Token ID47789
Feature activation+3.15e-01

Pos logit contributions
UTERS+0.217
inent+0.202
 Detail+0.197
Interstitial+0.195
idences+0.193
Neg logit contributions
SSL-0.208
fox-0.206
SPONSORED-0.203
 �-0.185
 ‎-0.184
Tokenity
Token ID414
Feature activation+5.94e-01

Pos logit contributions
UTERS+0.532
inent+0.488
 Detail+0.474
Interstitial+0.463
iege+0.463
Neg logit contributions
SSL-0.749
fox-0.742
SPONSORED-0.733
 �-0.673
 ‎-0.671
Token
Token ID851
Feature activation+9.89e-02

Pos logit contributions
UTERS+1.483
inent+1.398
 Detail+1.378
iege+1.351
idences+1.350
Neg logit contributions
SSL-0.930
fox-0.913
SPONSORED-0.899
 �-0.773
 ‎-0.761
Token to
Token ID284
Feature activation+5.40e-02

Pos logit contributions
UTERS+0.197
inent+0.183
 Detail+0.178
iege+0.175
idences+0.174
Neg logit contributions
SSL-0.206
fox-0.203
SPONSORED-0.200
 �-0.180
cens-0.178
Token the
Token ID262
Feature activation+6.38e-02

Pos logit contributions
UTERS+0.109
inent+0.101
 Detail+0.098
Interstitial+0.098
iege+0.097
Neg logit contributions
SSL-0.110
fox-0.109
SPONSORED-0.108
 ‎-0.099
 �-0.098
Token so
Token ID523
Feature activation+1.95e-02

Pos logit contributions
UTERS+0.126
inent+0.117
 Detail+0.113
Interstitial+0.113
iege+0.111
Neg logit contributions
SSL-0.133
fox-0.132
SPONSORED-0.129
 ‎-0.120
 �-0.120
Token-
Token ID12
Feature activation-4.26e-02

Pos logit contributions
UTERS+0.043
inent+0.040
 Detail+0.039
iege+0.038
Interstitial+0.038
Neg logit contributions
SSL-0.037
fox-0.036
SPONSORED-0.036
 ‎-0.032
 �-0.032
Token Communications
Token ID14620
Feature activation-8.58e-02

Pos logit contributions
SSL+0.504
fox+0.501
SPONSORED+0.496
 �+0.453
 ‎+0.452
Neg logit contributions
UTERS-0.428
inent-0.399
 Detail-0.388
Interstitial-0.384
iege-0.378
Token Commission
Token ID4513
Feature activation-2.17e-01

Pos logit contributions
SSL+0.201
fox+0.199
SPONSORED+0.198
 ‎+0.184
 �+0.184
Neg logit contributions
UTERS-0.146
inent-0.134
Interstitial-0.131
 Detail-0.130
iege-0.128
Token chairman
Token ID8900
Feature activation+1.93e-02

Pos logit contributions
SSL+0.477
fox+0.474
SPONSORED+0.471
 ‎+0.428
 �+0.428
Neg logit contributions
UTERS-0.400
inent-0.371
 Detail-0.361
Interstitial-0.359
iege-0.355
Token Aj
Token ID22028
Feature activation+1.50e-01

Pos logit contributions
UTERS+0.033
inent+0.030
Interstitial+0.030
 Detail+0.030
idences+0.029
Neg logit contributions
fox-0.045
SSL-0.045
SPONSORED-0.044
 ‎-0.041
 �-0.041
Tokenit
Token ID270
Feature activation+6.65e-02

Pos logit contributions
UTERS+0.322
Interstitial+0.301
inent+0.294
ALSE+0.288
 Detail+0.287
Neg logit contributions
fox-0.294
SSL-0.290
SPONSORED-0.276
 ‎-0.265
 �-0.261
Token Pai
Token ID41626
Feature activation+5.85e-01

Pos logit contributions
UTERS+0.157
Interstitial+0.149
iege+0.145
inent+0.143
idences+0.143
Neg logit contributions
fox-0.118
SSL-0.114
SPONSORED-0.107
 ‎-0.107
 �-0.102
Token,
Token ID11
Feature activation+4.04e-02

Pos logit contributions
UTERS+1.265
inent+1.184
 Detail+1.166
iege+1.138
Interstitial+1.133
Neg logit contributions
SSL-1.101
fox-1.074
SPONSORED-1.056
 �-0.949
cens-0.945
Token a
Token ID257
Feature activation+5.00e-02

Pos logit contributions
UTERS+0.082
inent+0.076
 Detail+0.074
Interstitial+0.073
iege+0.073
Neg logit contributions
SSL-0.083
fox-0.082
SPONSORED-0.081
 �-0.074
 ‎-0.074
Token Trump
Token ID1301
Feature activation+6.20e-02

Pos logit contributions
UTERS+0.099
inent+0.090
Interstitial+0.090
 Detail+0.089
iege+0.088
Neg logit contributions
SSL-0.104
fox-0.104
SPONSORED-0.101
 ‎-0.095
 �-0.094
Token appoint
Token ID5393
Feature activation+2.39e-01

Pos logit contributions
UTERS+0.131
inent+0.121
 Detail+0.120
Interstitial+0.119
idences+0.117
Neg logit contributions
SSL-0.121
fox-0.120
SPONSORED-0.117
 �-0.107
 ‎-0.107
Tokenee
Token ID1453
Feature activation+1.02e-01

Pos logit contributions
UTERS+0.413
inent+0.371
 Detail+0.368
Interstitial+0.365
idences+0.357
Neg logit contributions
SSL-0.560
fox-0.557
SPONSORED-0.550
 ‎-0.509
 �-0.508
Token explore
Token ID7301
Feature activation-1.34e-01

Pos logit contributions
UTERS+0.064
inent+0.059
 Detail+0.058
Interstitial+0.057
idences+0.056
Neg logit contributions
SSL-0.072
fox-0.071
SPONSORED-0.070
 �-0.064
 ‎-0.064
Token a
Token ID257
Feature activation-1.88e-02

Pos logit contributions
SSL+0.256
fox+0.253
SPONSORED+0.250
 �+0.226
 ‎+0.225
Neg logit contributions
UTERS-0.289
inent-0.270
 Detail-0.264
Interstitial-0.261
iege-0.259
Token proced
Token ID5131
Feature activation-1.33e-01

Pos logit contributions
SSL+0.039
fox+0.039
SPONSORED+0.038
 �+0.035
 ‎+0.035
Neg logit contributions
UTERS-0.037
inent-0.034
 Detail-0.034
Interstitial-0.033
idences-0.033
Tokenurally
Token ID20221
Feature activation-8.36e-02

Pos logit contributions
fox+0.313
SSL+0.311
SPONSORED+0.308
 ‎+0.288
 �+0.285
Neg logit contributions
UTERS-0.227
 Detail-0.205
Interstitial-0.202
inent-0.202
iege-0.194
Token generated
Token ID7560
Feature activation+1.55e-01

Pos logit contributions
SSL+0.178
fox+0.176
SPONSORED+0.173
 �+0.158
 ‎+0.157
Neg logit contributions
UTERS-0.162
inent-0.150
 Detail-0.146
Interstitial-0.143
iege-0.143
Token universe
Token ID6881
Feature activation+5.81e-01

Pos logit contributions
UTERS+0.301
inent+0.276
Interstitial+0.269
 Detail+0.269
idences+0.266
Neg logit contributions
SSL-0.327
fox-0.325
SPONSORED-0.321
 �-0.296
 ‎-0.296
Token
Token ID198
Feature activation+6.52e-02

Pos logit contributions
UTERS+1.121
inent+1.039
 Detail+1.018
iege+0.998
Interstitial+0.993
Neg logit contributions
SSL-1.233
fox-1.217
SPONSORED-1.202
 �-1.088
 ‎-1.085
Token
Token ID198
Feature activation+5.36e-02

Pos logit contributions
UTERS+0.168
inent+0.159
 Detail+0.156
Interstitial+0.154
iege+0.154
Neg logit contributions
SSL-0.097
fox-0.096
SPONSORED-0.094
 �-0.082
 ‎-0.082
TokenCol
Token ID5216
Feature activation-1.21e-01

Pos logit contributions
UTERS+0.105
inent+0.098
 Detail+0.095
idences+0.094
iege+0.093
Neg logit contributions
SSL-0.114
fox-0.112
SPONSORED-0.111
 �-0.100
 ‎-0.100
Tokenon
Token ID261
Feature activation-8.07e-02

Pos logit contributions
SSL+0.273
fox+0.272
SPONSORED+0.265
 �+0.245
 ‎+0.245
Neg logit contributions
UTERS-0.217
inent-0.196
Interstitial-0.195
 Detail-0.195
iege-0.188
Tokenize
Token ID1096
Feature activation-1.19e-02

Pos logit contributions
SSL+0.152
fox+0.151
SPONSORED+0.148
 �+0.134
 ‎+0.133
Neg logit contributions
UTERS-0.175
inent-0.163
 Detail-0.160
Interstitial-0.158
idences-0.157
Token tradition
Token ID6761
Feature activation+3.02e-01

Pos logit contributions
SSL+0.216
fox+0.214
SPONSORED+0.211
 �+0.194
 ‎+0.193
Neg logit contributions
UTERS-0.205
inent-0.190
 Detail-0.184
Interstitial-0.184
idences-0.181
Token reaches
Token ID12229
Feature activation+1.03e-01

Pos logit contributions
UTERS+0.657
inent+0.615
 Detail+0.605
iege+0.591
Interstitial+0.591
Neg logit contributions
SSL-0.569
fox-0.561
SPONSORED-0.550
 �-0.494
 ‎-0.490
Token back
Token ID736
Feature activation+9.19e-02

Pos logit contributions
UTERS+0.229
inent+0.214
 Detail+0.210
Interstitial+0.207
iege+0.206
Neg logit contributions
SSL-0.188
fox-0.185
SPONSORED-0.183
 �-0.165
 ‎-0.164
Token to
Token ID284
Feature activation+6.49e-02

Pos logit contributions
UTERS+0.181
inent+0.168
 Detail+0.164
Interstitial+0.162
iege+0.161
Neg logit contributions
SSL-0.192
fox-0.190
SPONSORED-0.187
 �-0.170
 ‎-0.170
Token Antiqu
Token ID47789
Feature activation+3.41e-01

Pos logit contributions
UTERS+0.134
inent+0.124
 Detail+0.121
Interstitial+0.120
iege+0.119
Neg logit contributions
SSL-0.130
fox-0.129
SPONSORED-0.127
 �-0.116
 ‎-0.115
Tokenity
Token ID414
Feature activation+5.81e-01

Pos logit contributions
UTERS+0.591
inent+0.536
 Detail+0.530
Interstitial+0.524
iege+0.513
Neg logit contributions
SSL-0.793
fox-0.785
SPONSORED-0.774
 �-0.717
 ‎-0.717
Token itself
Token ID2346
Feature activation+8.90e-02

Pos logit contributions
UTERS+1.191
inent+1.106
 Detail+1.087
Interstitial+1.065
iege+1.060
Neg logit contributions
SSL-1.170
fox-1.155
SPONSORED-1.139
 �-1.027
 ‎-1.019
Token,
Token ID11
Feature activation+1.85e-02

Pos logit contributions
UTERS+0.180
inent+0.167
 Detail+0.163
Interstitial+0.161
iege+0.160
Neg logit contributions
SSL-0.182
fox-0.180
SPONSORED-0.177
 �-0.161
 ‎-0.160
Token and
Token ID290
Feature activation+4.45e-03

Pos logit contributions
UTERS+0.038
inent+0.035
 Detail+0.034
Interstitial+0.034
idences+0.034
Neg logit contributions
SSL-0.037
fox-0.037
SPONSORED-0.036
 �-0.033
 ‎-0.033
Token even
Token ID772
Feature activation+1.24e-01

Pos logit contributions
UTERS+0.009
inent+0.009
 Detail+0.008
Interstitial+0.008
idences+0.008
Neg logit contributions
SSL-0.009
fox-0.009
SPONSORED-0.008
 �-0.008
 ‎-0.008
Token then
Token ID788
Feature activation-8.27e-02

Pos logit contributions
UTERS+0.255
inent+0.237
 Detail+0.231
Interstitial+0.228
idences+0.227
Neg logit contributions
SSL-0.251
fox-0.248
SPONSORED-0.245
 �-0.223
 ‎-0.222
Token might
Token ID1244
Feature activation+9.31e-02

Pos logit contributions
SSL+0.029
fox+0.029
SPONSORED+0.028
 �+0.025
 ‎+0.025
Neg logit contributions
UTERS-0.036
inent-0.034
 Detail-0.033
Interstitial-0.033
iege-0.032
Token be
Token ID307
Feature activation+4.33e-03

Pos logit contributions
UTERS+0.194
inent+0.180
 Detail+0.177
Interstitial+0.173
iege+0.173
Neg logit contributions
SSL-0.184
fox-0.182
SPONSORED-0.180
 �-0.162
 ‎-0.161
Token Jar
Token ID15374
Feature activation+1.62e-01

Pos logit contributions
UTERS+0.009
inent+0.008
 Detail+0.008
Interstitial+0.008
idences+0.008
Neg logit contributions
SSL-0.009
fox-0.009
SPONSORED-0.009
 ‎-0.008
 �-0.008
Tokenred
Token ID445
Feature activation-1.32e-01

Pos logit contributions
UTERS+0.304
inent+0.275
 Detail+0.271
Interstitial+0.270
idences+0.264
Neg logit contributions
fox-0.360
SSL-0.356
SPONSORED-0.342
 ‎-0.320
 �-0.316
Token Cos
Token ID10437
Feature activation-2.13e-02

Pos logit contributions
SSL+0.183
fox+0.181
SPONSORED+0.175
 �+0.154
 ‎+0.154
Neg logit contributions
UTERS-0.355
inent-0.334
 Detail-0.329
Interstitial-0.328
iege-0.324
Tokenart
Token ID433
Feature activation-6.99e-01

Pos logit contributions
SSL+0.038
fox+0.038
SPONSORED+0.037
 �+0.034
 ‎+0.034
Neg logit contributions
UTERS-0.049
inent-0.045
 Detail-0.045
Interstitial-0.044
idences-0.043
Token,
Token ID11
Feature activation-6.66e-02

Pos logit contributions
SSL+1.368
fox+1.354
SPONSORED+1.326
 ‎+1.208
 �+1.208
Neg logit contributions
UTERS-1.470
inent-1.362
 Detail-1.344
Interstitial-1.319
idences-1.314
Token who
Token ID508
Feature activation-5.39e-02

Pos logit contributions
SSL+0.142
fox+0.141
SPONSORED+0.139
 �+0.127
 ‎+0.127
Neg logit contributions
UTERS-0.129
inent-0.119
 Detail-0.116
Interstitial-0.115
iege-0.114
Token has
Token ID468
Feature activation+5.04e-02

Pos logit contributions
SSL+0.102
fox+0.101
SPONSORED+0.099
 �+0.090
 ‎+0.089
Neg logit contributions
UTERS-0.117
inent-0.109
 Detail-0.107
Interstitial-0.106
iege-0.105
Token allowed
Token ID3142
Feature activation-8.25e-02

Pos logit contributions
UTERS+0.106
inent+0.099
 Detail+0.097
Interstitial+0.095
iege+0.095
Neg logit contributions
SSL-0.099
fox-0.097
SPONSORED-0.096
 �-0.087
 ‎-0.087
Token four
Token ID1440
Feature activation-4.98e-02

Pos logit contributions
SSL+0.147
fox+0.146
SPONSORED+0.143
 �+0.130
 ‎+0.130
Neg logit contributions
UTERS-0.189
inent-0.176
 Detail-0.172
Interstitial-0.171
iege-0.170
Token,
Token ID11
Feature activation+4.21e-02

Pos logit contributions
UTERS+0.024
inent+0.023
 Detail+0.022
iege+0.022
Interstitial+0.022
Neg logit contributions
SSL-0.025
fox-0.025
SPONSORED-0.024
 �-0.022
cens-0.022
Token the
Token ID262
Feature activation+3.53e-02

Pos logit contributions
UTERS+0.090
inent+0.084
 Detail+0.083
Interstitial+0.082
iege+0.081
Neg logit contributions
SSL-0.081
fox-0.080
SPONSORED-0.079
 �-0.071
 ‎-0.071
Token coalition
Token ID9906
Feature activation-1.31e-01

Pos logit contributions
UTERS+0.078
inent+0.073
 Detail+0.071
Interstitial+0.071
idences+0.070
Neg logit contributions
SSL-0.066
fox-0.065
SPONSORED-0.064
 ‎-0.057
 �-0.057
Token said
Token ID531
Feature activation-1.02e-01

Pos logit contributions
SSL+0.249
fox+0.246
SPONSORED+0.242
 ‎+0.219
 �+0.219
Neg logit contributions
UTERS-0.282
inent-0.263
 Detail-0.257
Interstitial-0.255
idences-0.253
Token its
Token ID663
Feature activation-2.34e-02

Pos logit contributions
SSL+0.206
fox+0.204
SPONSORED+0.200
 ‎+0.183
 �+0.183
Neg logit contributions
UTERS-0.209
inent-0.195
 Detail-0.190
Interstitial-0.189
idences-0.186
Token raids
Token ID20371
Feature activation-6.93e-01

Pos logit contributions
SSL+0.045
fox+0.045
SPONSORED+0.044
 ‎+0.040
 �+0.040
Neg logit contributions
UTERS-0.050
inent-0.047
Interstitial-0.046
 Detail-0.046
idences-0.045
Token in
Token ID287
Feature activation+4.97e-03

Pos logit contributions
fox+1.275
SSL+1.273
SPONSORED+1.256
 ‎+1.140
 �+1.125
Neg logit contributions
UTERS-1.528
inent-1.428
 Detail-1.402
Interstitial-1.394
idences-1.374
Token Syria
Token ID4392
Feature activation-1.23e-01

Pos logit contributions
UTERS+0.011
inent+0.010
 Detail+0.010
Interstitial+0.010
idences+0.010
Neg logit contributions
SSL-0.009
fox-0.009
SPONSORED-0.009
 ‎-0.008
 �-0.008
Token and
Token ID290
Feature activation+4.32e-02

Pos logit contributions
SSL+0.225
fox+0.223
SPONSORED+0.219
 ‎+0.197
 �+0.196
Neg logit contributions
UTERS-0.273
inent-0.256
 Detail-0.251
Interstitial-0.248
iege-0.246
Token Iraq
Token ID3908
Feature activation+2.54e-02

Pos logit contributions
UTERS+0.106
inent+0.100
 Detail+0.098
Interstitial+0.097
iege+0.097
Neg logit contributions
SSL-0.069
fox-0.068
SPONSORED-0.067
 �-0.059
 ‎-0.059
Token and
Token ID290
Feature activation-4.28e-03

Pos logit contributions
UTERS+0.057
inent+0.053
 Detail+0.052
Interstitial+0.052
iege+0.051
Neg logit contributions
SSL-0.046
fox-0.046
SPONSORED-0.045
 ‎-0.040
 �-0.040
Token23
Token ID1954
Feature activation+1.11e-01

Pos logit contributions
SSL+0.084
fox+0.083
SPONSORED+0.081
 �+0.072
 ‎+0.072
Neg logit contributions
UTERS-0.108
inent-0.101
 Detail-0.099
Interstitial-0.098
iege-0.097
Token]
Token ID60
Feature activation-1.07e-02

Pos logit contributions
UTERS+0.184
inent+0.169
 Detail+0.165
Interstitial+0.160
idences+0.159
Neg logit contributions
SSL-0.269
fox-0.264
SPONSORED-0.261
 �-0.242
 ‎-0.241
Token
Token ID198
Feature activation-6.89e-02

Pos logit contributions
SSL+0.018
fox+0.018
SPONSORED+0.018
 �+0.016
 ‎+0.016
Neg logit contributions
UTERS-0.025
inent-0.024
 Detail-0.023
Interstitial-0.023
iege-0.023
Token
Token ID198
Feature activation-6.19e-02

Pos logit contributions
SSL+0.101
fox+0.100
SPONSORED+0.098
 �+0.086
 ‎+0.086
Neg logit contributions
UTERS-0.179
inent-0.170
 Detail-0.167
Interstitial-0.165
iege-0.164
TokenDi
Token ID18683
Feature activation-4.25e-02

Pos logit contributions
SSL+0.131
fox+0.130
SPONSORED+0.129
 ‎+0.116
 �+0.115
Neg logit contributions
UTERS-0.121
inent-0.112
 Detail-0.111
iege-0.108
idences-0.107
Tokenagn
Token ID4660
Feature activation-6.84e-01

Pos logit contributions
SSL+0.063
fox+0.062
SPONSORED+0.061
 �+0.054
 ‎+0.053
Neg logit contributions
UTERS-0.109
inent-0.103
 Detail-0.101
Interstitial-0.100
iege-0.100
Tokenosis
Token ID5958
Feature activation+1.98e-02

Pos logit contributions
SSL+1.891
fox+1.877
SPONSORED+1.849
 ‎+1.733
 �+1.732
Neg logit contributions
UTERS-0.885
inent-0.764
 Detail-0.757
Interstitial-0.743
iege-0.717
Token [
Token ID685
Feature activation-2.11e-02

Pos logit contributions
UTERS+0.048
inent+0.045
 Detail+0.045
Interstitial+0.044
iege+0.044
Neg logit contributions
SSL-0.032
fox-0.032
SPONSORED-0.031
 �-0.028
 ‎-0.027
Token edit
Token ID4370
Feature activation-3.19e-02

Pos logit contributions
SSL+0.032
fox+0.031
SPONSORED+0.031
 �+0.027
 ‎+0.027
Neg logit contributions
UTERS-0.054
inent-0.051
 Detail-0.050
Interstitial-0.050
iege-0.049
Token ]
Token ID2361
Feature activation-7.56e-02

Pos logit contributions
SSL+0.072
fox+0.072
SPONSORED+0.070
 �+0.065
 ‎+0.065
Neg logit contributions
UTERS-0.058
inent-0.053
 Detail-0.052
Interstitial-0.052
idences-0.051
Token
Token ID198
Feature activation-4.14e-02

Pos logit contributions
SSL+0.110
fox+0.108
SPONSORED+0.106
 ‎+0.093
 �+0.093
Neg logit contributions
UTERS-0.198
inent-0.187
 Detail-0.184
Interstitial-0.182
iege-0.181
Token take
Token ID1011
Feature activation+4.30e-02

Pos logit contributions
UTERS+0.036
inent+0.033
 Detail+0.032
Interstitial+0.032
idences+0.032
Neg logit contributions
SSL-0.040
fox-0.040
SPONSORED-0.039
 ‎-0.036
 �-0.036
Token measures
Token ID5260
Feature activation+1.23e-01

Pos logit contributions
UTERS+0.090
inent+0.084
 Detail+0.083
Interstitial+0.082
iege+0.081
Neg logit contributions
SSL-0.084
fox-0.083
SPONSORED-0.082
 �-0.075
 ‎-0.074
Token to
Token ID284
Feature activation+2.26e-02

Pos logit contributions
UTERS+0.253
inent+0.235
 Detail+0.230
Interstitial+0.226
iege+0.226
Neg logit contributions
SSL-0.248
fox-0.245
SPONSORED-0.241
 �-0.219
 ‎-0.217
Token stop
Token ID2245
Feature activation+4.35e-02

Pos logit contributions
UTERS+0.041
inent+0.038
 Detail+0.037
Interstitial+0.037
idences+0.036
Neg logit contributions
SSL-0.050
fox-0.050
SPONSORED-0.049
 ‎-0.046
 �-0.045
Token these
Token ID777
Feature activation-1.41e-01

Pos logit contributions
UTERS+0.092
inent+0.086
 Detail+0.084
Interstitial+0.083
iege+0.082
Neg logit contributions
SSL-0.085
fox-0.084
SPONSORED-0.083
 ‎-0.075
 �-0.075
Token raids
Token ID20371
Feature activation-6.73e-01

Pos logit contributions
SSL+0.293
fox+0.291
SPONSORED+0.287
 ‎+0.262
 �+0.261
Neg logit contributions
UTERS-0.281
inent-0.261
 Detail-0.255
Interstitial-0.251
idences-0.249
Token,
Token ID11
Feature activation+2.94e-02

Pos logit contributions
SSL+1.335
fox+1.324
SPONSORED+1.306
 ‎+1.186
 �+1.185
Neg logit contributions
UTERS-1.395
inent-1.295
 Detail-1.274
Interstitial-1.257
iege-1.243
Token Turkey
Token ID7137
Feature activation-1.03e-01

Pos logit contributions
UTERS+0.061
inent+0.057
 Detail+0.056
Interstitial+0.055
iege+0.054
Neg logit contributions
SSL-0.058
fox-0.058
SPONSORED-0.057
 �-0.051
 ‎-0.051
Token would
Token ID561
Feature activation-4.49e-02

Pos logit contributions
SSL+0.157
fox+0.153
SPONSORED+0.151
 �+0.131
cens+0.129
Neg logit contributions
UTERS-0.259
inent-0.244
 Detail-0.240
iege-0.237
idences-0.236
Token defend
Token ID4404
Feature activation-1.61e-01

Pos logit contributions
SSL+0.094
fox+0.093
SPONSORED+0.091
 �+0.084
 ‎+0.083
Neg logit contributions
UTERS-0.089
inent-0.082
 Detail-0.081
Interstitial-0.079
idences-0.079
Token itself
Token ID2346
Feature activation-4.40e-02

Pos logit contributions
SSL+0.273
fox+0.269
SPONSORED+0.265
 ‎+0.237
 �+0.236
Neg logit contributions
UTERS-0.381
inent-0.357
 Detail-0.352
Interstitial-0.348
idences-0.345
Token with
Token ID351
Feature activation-4.79e-03

Pos logit contributions
SSL+0.001
fox+0.001
SPONSORED+0.001
 �+0.001
 ‎+0.001
Neg logit contributions
UTERS-0.001
inent-0.001
 Detail-0.001
iege-0.001
Interstitial-0.001
Token S
Token ID311
Feature activation-1.63e-02

Pos logit contributions
SSL+0.009
fox+0.009
SPONSORED+0.009
 �+0.008
 ‎+0.008
Neg logit contributions
UTERS-0.010
inent-0.009
 Detail-0.009
Interstitial-0.009
iege-0.009
Tokenich
Token ID488
Feature activation-5.68e-02

Pos logit contributions
SSL+0.034
fox+0.033
SPONSORED+0.033
 �+0.030
 ‎+0.030
Neg logit contributions
UTERS-0.032
inent-0.030
 Detail-0.030
Interstitial-0.029
idences-0.029
Tokenuan
Token ID7258
Feature activation+1.54e-01

Pos logit contributions
SSL+0.154
fox+0.153
SPONSORED+0.151
 �+0.141
 ‎+0.141
Neg logit contributions
UTERS-0.077
inent-0.067
 Detail-0.066
Interstitial-0.065
idences-0.063
Token pe
Token ID613
Feature activation+3.02e-01

Pos logit contributions
UTERS+0.341
inent+0.318
 Detail+0.313
Interstitial+0.308
iege+0.306
Neg logit contributions
SSL-0.286
fox-0.283
SPONSORED-0.278
 �-0.250
 ‎-0.249
Tokenpperc
Token ID39921
Feature activation-6.55e-01

Pos logit contributions
UTERS+0.549
inent+0.505
 Detail+0.493
Interstitial+0.484
iege+0.481
Neg logit contributions
SSL-0.679
fox-0.672
SPONSORED-0.664
 �-0.609
 ‎-0.606
Tokenorns
Token ID19942
Feature activation+2.37e-02

Pos logit contributions
SSL+1.348
fox+1.335
SPONSORED+1.294
cens+1.202
 ‎+1.196
Neg logit contributions
UTERS-1.315
Interstitial-1.183
 Detail-1.180
inent-1.171
iege-1.143
Token (
Token ID357
Feature activation+2.23e-02

Pos logit contributions
UTERS+0.049
inent+0.046
 Detail+0.045
Interstitial+0.044
iege+0.044
Neg logit contributions
SSL-0.047
fox-0.046
SPONSORED-0.045
 �-0.041
 ‎-0.041
Tokenwhich
Token ID4758
Feature activation+4.07e-02

Pos logit contributions
UTERS+0.049
inent+0.046
 Detail+0.045
Interstitial+0.044
idences+0.044
Neg logit contributions
SSL-0.042
fox-0.041
SPONSORED-0.041
 �-0.036
 ‎-0.036
Token I
Token ID314
Feature activation+7.13e-02

Pos logit contributions
UTERS+0.088
inent+0.082
 Detail+0.080
Interstitial+0.079
iege+0.079
Neg logit contributions
SSL-0.078
fox-0.077
SPONSORED-0.076
 �-0.069
 ‎-0.068
Token couldn
Token ID3521
Feature activation-1.54e-02

Pos logit contributions
UTERS+0.156
inent+0.145
 Detail+0.142
Interstitial+0.140
idences+0.139
Neg logit contributions
SSL-0.134
fox-0.134
SPONSORED-0.131
 �-0.119
 ‎-0.118
Token [
Token ID685
Feature activation+3.75e-02

Pos logit contributions
SSL+0.350
fox+0.348
SPONSORED+0.343
 ‎+0.312
 �+0.310
Neg logit contributions
UTERS-0.385
inent-0.362
 Detail-0.351
Interstitial-0.347
iege-0.344
Tokena
Token ID64
Feature activation-1.08e-01

Pos logit contributions
UTERS+0.081
inent+0.076
 Detail+0.075
Interstitial+0.073
iege+0.073
Neg logit contributions
SSL-0.071
fox-0.070
SPONSORED-0.069
 �-0.062
 ‎-0.062
Token big
Token ID1263
Feature activation+1.05e-02

Pos logit contributions
SSL+0.208
fox+0.207
SPONSORED+0.203
 ‎+0.184
 �+0.183
Neg logit contributions
UTERS-0.232
inent-0.216
 Detail-0.211
Interstitial-0.210
iege-0.207
Token]
Token ID60
Feature activation-4.20e-02

Pos logit contributions
UTERS+0.022
inent+0.020
 Detail+0.020
Interstitial+0.020
idences+0.020
Neg logit contributions
SSL-0.021
fox-0.021
SPONSORED-0.020
 ‎-0.019
 �-0.019
Token enough
Token ID1576
Feature activation+1.45e-01

Pos logit contributions
SSL+0.081
fox+0.081
SPONSORED+0.079
 ‎+0.072
 �+0.072
Neg logit contributions
UTERS-0.089
inent-0.084
 Detail-0.081
Interstitial-0.080
idences-0.080
Token premium
Token ID8683
Feature activation-6.41e-01

Pos logit contributions
UTERS+0.310
inent+0.291
 Detail+0.280
Interstitial+0.280
idences+0.277
Neg logit contributions
SSL-0.278
fox-0.277
SPONSORED-0.272
 ‎-0.248
 �-0.248
Token to
Token ID284
Feature activation-4.07e-02

Pos logit contributions
fox+1.204
SSL+1.202
SPONSORED+1.183
 ‎+1.089
 �+1.075
Neg logit contributions
UTERS-1.396
inent-1.311
Interstitial-1.279
idences-1.255
 Detail-1.245
Token pay
Token ID1414
Feature activation-2.40e-02

Pos logit contributions
fox+0.080
SSL+0.080
SPONSORED+0.079
 ‎+0.073
 �+0.072
Neg logit contributions
UTERS-0.086
inent-0.080
Interstitial-0.077
 Detail-0.077
idences-0.075
Token the
Token ID262
Feature activation-2.46e-02

Pos logit contributions
SSL+0.046
fox+0.046
SPONSORED+0.045
 ‎+0.041
 �+0.041
Neg logit contributions
UTERS-0.052
inent-0.048
 Detail-0.047
Interstitial-0.047
iege-0.046
Token claims
Token ID3667
Feature activation-2.92e-01

Pos logit contributions
SSL+0.042
fox+0.042
SPONSORED+0.041
 ‎+0.037
 �+0.037
Neg logit contributions
UTERS-0.058
inent-0.054
 Detail-0.053
Interstitial-0.052
idences-0.052
Token over
Token ID625
Feature activation+1.08e-02

Pos logit contributions
SSL+0.544
fox+0.542
SPONSORED+0.534
 ‎+0.487
 �+0.485
Neg logit contributions
UTERS-0.645
inent-0.597
Interstitial-0.584
 Detail-0.583
idences-0.571
Token YouTube
Token ID7444
Feature activation+9.62e-02

Pos logit contributions
SSL+0.087
fox+0.086
SPONSORED+0.084
 ‎+0.077
 �+0.077
Neg logit contributions
UTERS-0.096
inent-0.089
Interstitial-0.087
 Detail-0.087
iege-0.086
Token spokeswoman
Token ID12262
Feature activation+2.58e-02

Pos logit contributions
UTERS+0.190
inent+0.176
 Detail+0.172
Interstitial+0.170
idences+0.169
Neg logit contributions
SSL-0.201
fox-0.199
SPONSORED-0.196
 ‎-0.179
 �-0.179
Token.
Token ID13
Feature activation+8.15e-02

Pos logit contributions
UTERS+0.050
inent+0.046
 Detail+0.045
iege+0.044
Interstitial+0.044
Neg logit contributions
SSL-0.055
fox-0.055
SPONSORED-0.054
 �-0.049
 ‎-0.049
Token
Token ID198
Feature activation+7.82e-04

Pos logit contributions
UTERS+0.189
inent+0.178
 Detail+0.174
Interstitial+0.172
iege+0.172
Neg logit contributions
SSL-0.142
fox-0.140
SPONSORED-0.137
 ‎-0.123
 �-0.123
Token
Token ID198
Feature activation+3.01e-03

Pos logit contributions
UTERS+0.002
inent+0.002
 Detail+0.002
Interstitial+0.002
iege+0.002
Neg logit contributions
SSL-0.001
fox-0.001
SPONSORED-0.001
 �-0.001
 ‎-0.001
TokenNewsletter
Token ID33031
Feature activation-6.28e-01

Pos logit contributions
UTERS+0.006
inent+0.005
 Detail+0.005
iege+0.005
idences+0.005
Neg logit contributions
SSL-0.007
fox-0.007
SPONSORED-0.007
 ‎-0.006
 �-0.006
Token Sign
Token ID5865
Feature activation-1.34e-01

Pos logit contributions
SSL+1.331
fox+1.321
SPONSORED+1.267
 ‎+1.204
 �+1.199
Neg logit contributions
UTERS-1.234
inent-1.123
iege-1.094
idences-1.087
Interstitial-1.075
Token Up
Token ID3205
Feature activation+1.19e-01

Pos logit contributions
SSL+0.174
fox+0.169
SPONSORED+0.160
 ‎+0.145
 �+0.145
Neg logit contributions
UTERS-0.372
inent-0.351
idences-0.342
 Detail-0.341
Interstitial-0.341
Token Continue
Token ID10054
Feature activation-7.52e-04

Pos logit contributions
UTERS+0.216
inent+0.202
idences+0.194
iege+0.193
 defic+0.191
Neg logit contributions
SSL-0.268
fox-0.261
SPONSORED-0.259
 �-0.246
 ‎-0.245
Token reading
Token ID3555
Feature activation-4.12e-02

Pos logit contributions
SSL+0.001
fox+0.001
SPONSORED+0.001
 �+0.001
 ‎+0.001
Neg logit contributions
UTERS-0.002
inent-0.002
idences-0.002
iege-0.002
 Detail-0.002
Token the
Token ID262
Feature activation+4.55e-02

Pos logit contributions
SSL+0.075
fox+0.074
SPONSORED+0.073
 ‎+0.066
 �+0.066
Neg logit contributions
UTERS-0.093
inent-0.087
iege-0.085
 Detail-0.085
idences-0.084
Token claims
Token ID3667
Feature activation-2.32e-01

Pos logit contributions
UTERS+0.219
inent+0.204
 Detail+0.200
Interstitial+0.198
iege+0.196
Neg logit contributions
SSL-0.203
fox-0.201
SPONSORED-0.199
 �-0.180
 ‎-0.180
Token against
Token ID1028
Feature activation-8.26e-02

Pos logit contributions
SSL+0.441
fox+0.435
SPONSORED+0.429
 �+0.387
 ‎+0.385
Neg logit contributions
UTERS-0.504
inent-0.470
 Detail-0.461
Interstitial-0.455
iege-0.452
Token Israel
Token ID2692
Feature activation-1.16e-01

Pos logit contributions
SSL+0.140
fox+0.138
SPONSORED+0.136
 �+0.120
 ‎+0.119
Neg logit contributions
UTERS-0.195
inent-0.183
 Detail-0.180
Interstitial-0.177
iege-0.177
Token over
Token ID625
Feature activation+1.40e-02

Pos logit contributions
SSL+0.222
fox+0.219
SPONSORED+0.216
 �+0.195
 ‎+0.195
Neg logit contributions
UTERS-0.249
inent-0.232
 Detail-0.228
Interstitial-0.225
iege-0.224
Token the
Token ID262
Feature activation-3.69e-02

Pos logit contributions
UTERS+0.030
inent+0.028
 Detail+0.028
Interstitial+0.028
idences+0.027
Neg logit contributions
SSL-0.026
fox-0.026
SPONSORED-0.026
 �-0.023
 ‎-0.023
Token raid
Token ID9513
Feature activation-6.27e-01

Pos logit contributions
SSL+0.083
fox+0.082
SPONSORED+0.081
 ‎+0.075
 �+0.075
Neg logit contributions
UTERS-0.067
inent-0.062
 Detail-0.060
Interstitial-0.060
idences-0.059
Token and
Token ID290
Feature activation+1.18e-02

Pos logit contributions
SSL+1.223
fox+1.215
SPONSORED+1.199
 �+1.088
 ‎+1.088
Neg logit contributions
UTERS-1.317
inent-1.227
 Detail-1.200
Interstitial-1.187
iege-1.178
Token that
Token ID326
Feature activation-7.55e-03

Pos logit contributions
UTERS+0.025
inent+0.024
 Detail+0.023
Interstitial+0.023
idences+0.023
Neg logit contributions
SSL-0.023
fox-0.022
SPONSORED-0.022
 �-0.020
 ‎-0.020
Token the
Token ID262
Feature activation-3.05e-02

Pos logit contributions
SSL+0.014
fox+0.014
SPONSORED+0.013
 �+0.012
 ‎+0.012
Neg logit contributions
UTERS-0.017
inent-0.016
 Detail-0.015
Interstitial-0.015
iege-0.015
Token countries
Token ID2678
Feature activation-7.55e-02

Pos logit contributions
SSL+0.052
fox+0.051
SPONSORED+0.050
 ‎+0.045
 �+0.045
Neg logit contributions
UTERS-0.072
inent-0.068
 Detail-0.066
Interstitial-0.066
idences-0.065
Token would
Token ID561
Feature activation-7.10e-02

Pos logit contributions
SSL+0.113
fox+0.111
SPONSORED+0.109
 �+0.096
 ‎+0.095
Neg logit contributions
UTERS-0.194
inent-0.183
 Detail-0.180
Interstitial-0.178
iege-0.177
Token and
Token ID290
Feature activation-1.13e-02

Pos logit contributions
SSL+0.033
fox+0.033
SPONSORED+0.032
 �+0.029
 ‎+0.029
Neg logit contributions
UTERS-0.035
inent-0.033
 Detail-0.032
Interstitial-0.032
iege-0.032
Token Ch
Token ID609
Feature activation+6.11e-03

Pos logit contributions
SSL+0.022
fox+0.022
SPONSORED+0.022
 �+0.020
 ‎+0.020
Neg logit contributions
UTERS-0.023
inent-0.022
 Detail-0.021
Interstitial-0.021
iege-0.021
Tokenado
Token ID4533
Feature activation+1.74e-01

Pos logit contributions
UTERS+0.012
inent+0.011
 Detail+0.011
Interstitial+0.011
iege+0.010
Neg logit contributions
SSL-0.013
fox-0.013
SPONSORED-0.013
 �-0.012
 ‎-0.012
Token Ralph
Token ID20993
Feature activation-1.56e-02

Pos logit contributions
UTERS+0.355
inent+0.330
 Detail+0.325
Interstitial+0.318
iege+0.317
Neg logit contributions
SSL-0.353
fox-0.349
SPONSORED-0.345
 �-0.311
 ‎-0.310
Token Ru
Token ID11667
Feature activation+1.87e-01

Pos logit contributions
SSL+0.029
fox+0.029
SPONSORED+0.028
 �+0.026
 ‎+0.026
Neg logit contributions
UTERS-0.034
inent-0.032
 Detail-0.031
Interstitial-0.031
iege-0.030
Tokencci
Token ID35764
Feature activation-6.25e-01

Pos logit contributions
UTERS+0.399
inent+0.371
 Detail+0.364
Interstitial+0.359
iege+0.356
Neg logit contributions
SSL-0.363
fox-0.358
SPONSORED-0.353
 �-0.318
 ‎-0.317
Token and
Token ID290
Feature activation-6.11e-02

Pos logit contributions
SSL+1.236
fox+1.220
SPONSORED+1.196
 ‎+1.098
 �+1.096
Neg logit contributions
UTERS-1.300
inent-1.210
 Detail-1.175
Interstitial-1.172
iege-1.164
Token portraits
Token ID31725
Feature activation-1.93e-01

Pos logit contributions
SSL+0.120
fox+0.119
SPONSORED+0.117
 �+0.106
 ‎+0.106
Neg logit contributions
UTERS-0.128
inent-0.119
 Detail-0.116
Interstitial-0.115
iege-0.115
Token of
Token ID286
Feature activation-1.42e-01

Pos logit contributions
SSL+0.376
fox+0.371
SPONSORED+0.366
 �+0.331
 ‎+0.329
Neg logit contributions
UTERS-0.407
inent-0.379
 Detail-0.372
Interstitial-0.366
iege-0.364
Token world
Token ID995
Feature activation-4.04e-02

Pos logit contributions
SSL+0.284
fox+0.281
SPONSORED+0.277
 �+0.253
 ‎+0.252
Neg logit contributions
UTERS-0.292
inent-0.270
 Detail-0.264
Interstitial-0.262
iege-0.261
Token-
Token ID12
Feature activation-5.87e-02

Pos logit contributions
SSL+0.080
fox+0.079
SPONSORED+0.078
 �+0.071
 ‎+0.070
Neg logit contributions
UTERS-0.084
inent-0.078
 Detail-0.077
Interstitial-0.075
iege-0.075
Token 2010
Token ID3050
Feature activation-5.79e-02

Pos logit contributions
UTERS+0.223
inent+0.206
 Detail+0.200
Interstitial+0.200
idences+0.197
Neg logit contributions
SSL-0.252
fox-0.250
SPONSORED-0.246
 ‎-0.228
 �-0.227
Token after
Token ID706
Feature activation+1.79e-02

Pos logit contributions
SSL+0.117
fox+0.116
SPONSORED+0.114
 ‎+0.104
 �+0.104
Neg logit contributions
UTERS-0.118
inent-0.110
 Detail-0.108
Interstitial-0.106
iege-0.105
Token an
Token ID281
Feature activation+7.03e-02

Pos logit contributions
UTERS+0.040
inent+0.038
 Detail+0.037
Interstitial+0.036
idences+0.036
Neg logit contributions
SSL-0.033
fox-0.032
SPONSORED-0.032
 �-0.028
 ‎-0.028
Token Israeli
Token ID6085
Feature activation-1.57e-01

Pos logit contributions
UTERS+0.152
inent+0.143
 Detail+0.140
idences+0.138
Interstitial+0.138
Neg logit contributions
SSL-0.133
fox-0.131
SPONSORED-0.129
 ‎-0.117
 �-0.117
Token naval
Token ID19014
Feature activation+1.45e-02

Pos logit contributions
SSL+0.324
fox+0.321
SPONSORED+0.314
 ‎+0.288
 �+0.287
Neg logit contributions
UTERS-0.312
inent-0.291
 Detail-0.283
idences-0.281
Interstitial-0.280
Token raid
Token ID9513
Feature activation-6.17e-01

Pos logit contributions
UTERS+0.027
inent+0.024
Interstitial+0.024
 Detail+0.024
idences+0.024
Neg logit contributions
SSL-0.032
fox-0.032
SPONSORED-0.031
 ‎-0.029
 �-0.029
Token on
Token ID319
Feature activation+1.31e-01

Pos logit contributions
SSL+1.194
fox+1.192
SPONSORED+1.178
 ‎+1.064
 �+1.063
Neg logit contributions
UTERS-1.301
inent-1.208
 Detail-1.191
Interstitial-1.178
idences-1.174
Token a
Token ID257
Feature activation+7.31e-02

Pos logit contributions
UTERS+0.284
inent+0.265
 Detail+0.260
Interstitial+0.256
iege+0.255
Neg logit contributions
SSL-0.247
fox-0.244
SPONSORED-0.240
 �-0.216
 ‎-0.215
Token Gaza
Token ID11010
Feature activation-2.07e-01

Pos logit contributions
UTERS+0.164
inent+0.153
Interstitial+0.150
 Detail+0.150
idences+0.148
Neg logit contributions
SSL-0.134
fox-0.132
SPONSORED-0.128
 ‎-0.117
 �-0.116
Token-
Token ID12
Feature activation+4.63e-02

Pos logit contributions
SSL+0.445
fox+0.439
SPONSORED+0.428
 ‎+0.400
 �+0.396
Neg logit contributions
UTERS-0.394
inent-0.369
Interstitial-0.360
 Detail-0.355
idences-0.354
Tokenbound
Token ID7784
Feature activation+1.21e-01

Pos logit contributions
UTERS+0.098
inent+0.091
 Detail+0.089
Interstitial+0.088
idences+0.088
Neg logit contributions
SSL-0.091
fox-0.090
SPONSORED-0.088
 ‎-0.080
cens-0.079
Token,
Token ID11
Feature activation+3.53e-03

Pos logit contributions
SSL+0.099
fox+0.098
SPONSORED+0.097
 �+0.088
 ‎+0.088
Neg logit contributions
UTERS-0.101
inent-0.094
 Detail-0.092
Interstitial-0.090
iege-0.090
Token and
Token ID290
Feature activation+1.65e-02

Pos logit contributions
UTERS+0.008
inent+0.008
 Detail+0.007
Interstitial+0.007
iege+0.007
Neg logit contributions
SSL-0.006
fox-0.006
SPONSORED-0.006
 ‎-0.006
 �-0.006
Token triggered
Token ID13973
Feature activation+4.49e-02

Pos logit contributions
UTERS+0.034
inent+0.032
 Detail+0.031
Interstitial+0.031
iege+0.031
Neg logit contributions
SSL-0.033
fox-0.032
SPONSORED-0.032
 ‎-0.029
 �-0.029
Token Thursday
Token ID3635
Feature activation-9.88e-03

Pos logit contributions
UTERS+0.096
inent+0.090
 Detail+0.088
Interstitial+0.087
idences+0.087
Neg logit contributions
SSL-0.086
fox-0.085
SPONSORED-0.084
 ‎-0.076
 �-0.076
Token's
Token ID338
Feature activation+5.54e-02

Pos logit contributions
SSL+0.020
fox+0.019
SPONSORED+0.019
 �+0.017
 ‎+0.017
Neg logit contributions
UTERS-0.021
inent-0.019
 Detail-0.019
iege-0.018
idences-0.018
Token raids
Token ID20371
Feature activation-6.07e-01

Pos logit contributions
UTERS+0.110
inent+0.102
 Detail+0.100
Interstitial+0.099
idences+0.098
Neg logit contributions
SSL-0.115
fox-0.114
SPONSORED-0.112
 ‎-0.102
 �-0.102
Token.
Token ID13
Feature activation-1.29e-02

Pos logit contributions
SSL+1.193
fox+1.191
SPONSORED+1.175
 ‎+1.066
 �+1.062
Neg logit contributions
UTERS-1.261
inent-1.173
 Detail-1.151
Interstitial-1.140
idences-1.133
Token
Token ID198
Feature activation-3.67e-02

Pos logit contributions
SSL+0.022
fox+0.021
SPONSORED+0.021
 �+0.019
cens+0.018
Neg logit contributions
UTERS-0.031
 Detail-0.029
inent-0.029
iege-0.028
Interstitial-0.028
Token
Token ID198
Feature activation-2.88e-02

Pos logit contributions
SSL+0.053
fox+0.052
SPONSORED+0.051
 ‎+0.045
 �+0.045
Neg logit contributions
UTERS-0.097
inent-0.092
 Detail-0.090
Interstitial-0.090
idences-0.089
Token"
Token ID1
Feature activation-4.20e-02

Pos logit contributions
SSL+0.064
SPONSORED+0.063
fox+0.062
 ‎+0.056
cens+0.055
Neg logit contributions
UTERS-0.053
inent-0.050
 Detail-0.050
idences-0.049
iege-0.048
TokenAir
Token ID16170
Feature activation+1.97e-01

Pos logit contributions
SSL+0.092
fox+0.091
SPONSORED+0.090
 ‎+0.081
 �+0.081
Neg logit contributions
UTERS-0.079
inent-0.074
 Detail-0.073
idences-0.072
iege-0.070
Token fingerprints
Token ID34290
Feature activation-2.49e-01

Pos logit contributions
SSL+0.123
fox+0.122
SPONSORED+0.121
 �+0.110
 ‎+0.110
Neg logit contributions
UTERS-0.116
inent-0.108
 Detail-0.104
idences-0.103
Interstitial-0.102
Token are
Token ID389
Feature activation-1.02e-02

Pos logit contributions
SSL+0.543
fox+0.537
SPONSORED+0.533
 �+0.494
 ‎+0.491
Neg logit contributions
UTERS-0.467
inent-0.431
Interstitial-0.418
 Detail-0.416
iege-0.409
Token all
Token ID477
Feature activation-5.80e-02

Pos logit contributions
SSL+0.020
fox+0.020
SPONSORED+0.019
 �+0.018
 ‎+0.018
Neg logit contributions
UTERS-0.022
inent-0.020
 Detail-0.020
iege-0.019
Interstitial-0.019
Token over
Token ID625
Feature activation+4.30e-02

Pos logit contributions
SSL+0.089
fox+0.087
SPONSORED+0.086
 �+0.075
 ‎+0.075
Neg logit contributions
UTERS-0.147
inent-0.139
 Detail-0.136
Interstitial-0.135
idences-0.134
Token Obamacare
Token ID12439
Feature activation-1.50e-01

Pos logit contributions
UTERS+0.089
inent+0.083
 Detail+0.081
Interstitial+0.080
iege+0.079
Neg logit contributions
SSL-0.086
fox-0.085
SPONSORED-0.084
 ‎-0.076
 �-0.076
Token premium
Token ID8683
Feature activation-6.06e-01

Pos logit contributions
SSL+0.357
fox+0.354
SPONSORED+0.347
 ‎+0.324
 �+0.323
Neg logit contributions
UTERS-0.255
inent-0.236
Interstitial-0.227
 Detail-0.224
iege-0.223
Token increases
Token ID5732
Feature activation-2.35e-02

Pos logit contributions
fox+1.076
SSL+1.071
SPONSORED+1.068
 �+0.964
 ‎+0.954
Neg logit contributions
UTERS-1.377
inent-1.310
Interstitial-1.278
 Detail-1.251
idences-1.235
Token,"
Token ID553
Feature activation+5.62e-02

Pos logit contributions
SSL+0.054
fox+0.053
SPONSORED+0.053
 ‎+0.049
 �+0.049
Neg logit contributions
UTERS-0.042
inent-0.038
 Detail-0.037
Interstitial-0.037
iege-0.037
Token May
Token ID1737
Feature activation-5.36e-02

Pos logit contributions
UTERS+0.116
inent+0.108
 Detail+0.105
Interstitial+0.105
iege+0.104
Neg logit contributions
SSL-0.112
fox-0.112
SPONSORED-0.110
 �-0.100
 ‎-0.100
Token 5
Token ID642
Feature activation+2.35e-02

Pos logit contributions
SSL+0.103
fox+0.102
SPONSORED+0.100
 ‎+0.090
 �+0.090
Neg logit contributions
UTERS-0.115
inent-0.107
 Detail-0.105
Interstitial-0.104
iege-0.103
Token).
Token ID737
Feature activation+3.45e-03

Pos logit contributions
UTERS+0.042
inent+0.038
 Detail+0.037
Interstitial+0.037
iege+0.037
Neg logit contributions
SSL-0.054
fox-0.053
SPONSORED-0.052
 �-0.048
 ‎-0.048
Tokenimage
Token ID9060
Feature activation-2.62e-01

Pos logit contributions
SSL+0.051
fox+0.051
SPONSORED+0.050
 �+0.046
 ‎+0.045
Neg logit contributions
UTERS-0.046
inent-0.043
 Detail-0.042
Interstitial-0.041
iege-0.041
Token.
Token ID13
Feature activation-1.73e-01

Pos logit contributions
SSL+0.566
fox+0.561
SPONSORED+0.551
 �+0.505
 ‎+0.504
Neg logit contributions
UTERS-0.497
inent-0.457
 Detail-0.451
iege-0.442
Interstitial-0.442
TokenDraw
Token ID25302
Feature activation-4.83e-01

Pos logit contributions
SSL+0.416
fox+0.412
SPONSORED+0.408
 �+0.377
 ‎+0.375
Neg logit contributions
UTERS-0.284
inent-0.259
 Detail-0.253
Interstitial-0.249
iege-0.247
TokenString
Token ID10100
Feature activation-2.27e-01

Pos logit contributions
SSL+1.147
fox+1.140
SPONSORED+1.125
 �+1.038
 ‎+1.034
Neg logit contributions
UTERS-0.810
inent-0.739
 Detail-0.723
Interstitial-0.712
iege-0.703
Token($
Token ID16763
Feature activation+1.11e-01

Pos logit contributions
SSL+0.308
fox+0.300
SPONSORED+0.297
 �+0.255
 ‎+0.248
Neg logit contributions
UTERS-0.614
inent-0.590
 Detail-0.573
idences-0.570
iege-0.567
Tokenart
Token ID433
Feature activation-5.98e-01

Pos logit contributions
UTERS+0.261
 Detail+0.240
inent+0.239
Interstitial+0.235
idences+0.234
Neg logit contributions
fox-0.194
SSL-0.192
SPONSORED-0.185
css-0.167
 ‎-0.167
Tokenext
Token ID2302
Feature activation-8.21e-02

Pos logit contributions
fox+0.553
SSL+0.516
SPONSORED+0.493
 ‎+0.404
css+0.402
Neg logit contributions
UTERS-1.904
 Detail-1.787
 defic-1.786
inent-1.770
Interstitial-1.770
Token[
Token ID58
Feature activation-2.16e-01

Pos logit contributions
SSL+0.114
fox+0.113
SPONSORED+0.112
 ‎+0.096
 �+0.095
Neg logit contributions
UTERS-0.220
inent-0.209
 Detail-0.205
idences-0.203
iege-0.202
Token$
Token ID3
Feature activation-9.57e-02

Pos logit contributions
SSL+0.326
fox+0.323
SPONSORED+0.313
 �+0.270
 ‎+0.270
Neg logit contributions
UTERS-0.560
inent-0.526
 Detail-0.525
iege-0.513
idences-0.512
Tokeni
Token ID72
Feature activation-6.10e-02

Pos logit contributions
fox+0.149
SSL+0.149
SPONSORED+0.144
 �+0.126
 ‎+0.126
Neg logit contributions
UTERS-0.242
 Detail-0.224
inent-0.224
Interstitial-0.220
idences-0.218
Token-
Token ID12
Feature activation-1.86e-01

Pos logit contributions
SSL+0.099
fox+0.098
SPONSORED+0.096
 ‎+0.085
 �+0.084
Neg logit contributions
UTERS-0.149
inent-0.141
 Detail-0.139
iege-0.137
idences-0.136
Tokened
Token ID276
Feature activation+8.85e-02

Pos logit contributions
SSL+0.245
fox+0.243
SPONSORED+0.240
 �+0.217
 ‎+0.216
Neg logit contributions
UTERS-0.262
inent-0.243
 Detail-0.239
Interstitial-0.236
idences-0.235
Token via
Token ID2884
Feature activation+1.13e-01

Pos logit contributions
UTERS+0.180
inent+0.167
 Detail+0.163
Interstitial+0.161
iege+0.160
Neg logit contributions
SSL-0.180
fox-0.178
SPONSORED-0.176
 �-0.160
 ‎-0.159
Token pipes
Token ID19860
Feature activation+1.44e-01

Pos logit contributions
UTERS+0.236
inent+0.220
 Detail+0.215
Interstitial+0.212
iege+0.211
Neg logit contributions
SSL-0.223
fox-0.221
SPONSORED-0.218
 �-0.197
 ‎-0.196
Token to
Token ID284
Feature activation+5.92e-02

Pos logit contributions
UTERS+0.291
inent+0.270
 Detail+0.265
Interstitial+0.261
iege+0.259
Neg logit contributions
SSL-0.294
fox-0.291
SPONSORED-0.287
 �-0.261
 ‎-0.260
Token e
Token ID304
Feature activation-4.32e-02

Pos logit contributions
UTERS+0.123
inent+0.115
 Detail+0.112
Interstitial+0.111
iege+0.110
Neg logit contributions
SSL-0.117
fox-0.116
SPONSORED-0.114
 �-0.104
 ‎-0.103
Tokenart
Token ID433
Feature activation-5.98e-01

Pos logit contributions
SSL+0.081
fox+0.080
SPONSORED+0.079
 �+0.071
 ‎+0.071
Neg logit contributions
UTERS-0.094
inent-0.089
 Detail-0.087
Interstitial-0.086
iege-0.085
Tokenhen
Token ID831
Feature activation-1.85e-01

Pos logit contributions
fox+1.383
SSL+1.380
SPONSORED+1.337
 �+1.255
 ‎+1.246
Neg logit contributions
UTERS-1.048
inent-0.943
Interstitial-0.923
 Detail-0.923
iege-0.898
Token storage
Token ID6143
Feature activation-6.66e-02

Pos logit contributions
SSL+0.367
fox+0.362
SPONSORED+0.357
 �+0.326
 ‎+0.324
Neg logit contributions
UTERS-0.386
inent-0.360
 Detail-0.353
iege-0.344
Interstitial-0.344
Token reservoirs
Token ID46637
Feature activation+1.88e-01

Pos logit contributions
SSL+0.136
fox+0.135
SPONSORED+0.133
 �+0.122
 ‎+0.122
Neg logit contributions
UTERS-0.134
inent-0.125
 Detail-0.122
Interstitial-0.120
iege-0.119
Token.
Token ID13
Feature activation+2.10e-02

Pos logit contributions
UTERS+0.387
inent+0.359
 Detail+0.352
Interstitial+0.347
iege+0.345
Neg logit contributions
SSL-0.375
fox-0.371
SPONSORED-0.366
 �-0.332
 ‎-0.330
Token From
Token ID3574
Feature activation+3.28e-02

Pos logit contributions
UTERS+0.046
inent+0.043
Interstitial+0.042
 Detail+0.042
idences+0.042
Neg logit contributions
SSL-0.040
fox-0.039
SPONSORED-0.039
 ‎-0.035
 �-0.035
Token didnt
Token ID42547
Feature activation-1.23e-02

Pos logit contributions
UTERS+0.001
inent+0.001
 Detail+0.001
Interstitial+0.001
iege+0.001
Neg logit contributions
fox-0.001
SSL-0.001
SPONSORED-0.001
 �-0.001
 ‎-0.001
Token apply
Token ID4174
Feature activation+1.04e-01

Pos logit contributions
SSL+0.026
fox+0.026
SPONSORED+0.025
 �+0.024
 ‎+0.023
Neg logit contributions
UTERS-0.024
inent-0.022
 Detail-0.022
Interstitial-0.021
iege-0.021
Token for
Token ID329
Feature activation-4.79e-02

Pos logit contributions
UTERS+0.214
inent+0.199
 Detail+0.194
Interstitial+0.193
idences+0.191
Neg logit contributions
SSL-0.209
fox-0.206
SPONSORED-0.201
 �-0.186
 ‎-0.185
Token summer
Token ID3931
Feature activation-1.92e-01

Pos logit contributions
SSL+0.093
fox+0.092
SPONSORED+0.089
 ‎+0.082
 �+0.082
Neg logit contributions
UTERS-0.102
inent-0.096
Interstitial-0.093
 Detail-0.092
iege-0.092
Token intern
Token ID1788
Feature activation-4.57e-03

Pos logit contributions
SSL+0.423
fox+0.419
SPONSORED+0.402
 �+0.377
 ‎+0.375
Neg logit contributions
UTERS-0.362
inent-0.338
Interstitial-0.332
 Detail-0.326
iege-0.323
Tokenships
Token ID26313
Feature activation-5.91e-01

Pos logit contributions
SSL+0.010
fox+0.010
SPONSORED+0.010
 �+0.009
 ‎+0.009
Neg logit contributions
UTERS-0.008
inent-0.008
 Detail-0.008
Interstitial-0.008
iege-0.007
Token until
Token ID1566
Feature activation-1.93e-01

Pos logit contributions
SSL+1.167
fox+1.160
SPONSORED+1.133
 �+1.047
 ‎+1.047
Neg logit contributions
UTERS-1.226
inent-1.139
 Detail-1.115
Interstitial-1.112
idences-1.100
Token February
Token ID3945
Feature activation-8.64e-02

Pos logit contributions
SSL+0.365
fox+0.360
SPONSORED+0.354
 �+0.323
 ‎+0.323
Neg logit contributions
UTERS-0.418
inent-0.391
 Detail-0.379
Interstitial-0.379
iege-0.377
Token.
Token ID13
Feature activation-5.10e-02

Pos logit contributions
SSL+0.170
fox+0.168
SPONSORED+0.165
 �+0.151
 ‎+0.150
Neg logit contributions
UTERS-0.182
inent-0.169
 Detail-0.165
Interstitial-0.164
iege-0.162
Token By
Token ID2750
Feature activation-1.49e-01

Pos logit contributions
SSL+0.110
fox+0.109
SPONSORED+0.106
 �+0.099
 ‎+0.099
Neg logit contributions
UTERS-0.098
inent-0.092
Interstitial-0.087
idences-0.087
iege-0.087
Token that
Token ID326
Feature activation-6.12e-02

Pos logit contributions
SSL+0.297
fox+0.294
SPONSORED+0.285
 �+0.266
 ‎+0.265
Neg logit contributions
UTERS-0.307
inent-0.287
Interstitial-0.280
 Detail-0.278
iege-0.276
Token and
Token ID290
Feature activation-1.24e-01

Pos logit contributions
SSL+0.245
fox+0.242
SPONSORED+0.239
 �+0.217
 ‎+0.216
Neg logit contributions
UTERS-0.245
inent-0.228
 Detail-0.223
Interstitial-0.220
iege-0.218
Token winning
Token ID5442
Feature activation-3.41e-02

Pos logit contributions
SSL+0.255
fox+0.252
SPONSORED+0.249
 �+0.226
 ‎+0.226
Neg logit contributions
UTERS-0.249
inent-0.231
 Detail-0.226
Interstitial-0.223
idences-0.222
Token his
Token ID465
Feature activation+5.68e-02

Pos logit contributions
SSL+0.067
fox+0.066
SPONSORED+0.065
 �+0.059
 ‎+0.059
Neg logit contributions
UTERS-0.072
inent-0.067
 Detail-0.065
Interstitial-0.064
iege-0.064
Token first
Token ID717
Feature activation-7.66e-02

Pos logit contributions
UTERS+0.124
inent+0.114
 Detail+0.112
Interstitial+0.112
iege+0.110
Neg logit contributions
SSL-0.108
fox-0.107
SPONSORED-0.104
 �-0.095
 ‎-0.095
Token k
Token ID479
Feature activation-2.08e-01

Pos logit contributions
SSL+0.172
fox+0.170
SPONSORED+0.167
 ‎+0.155
 �+0.155
Neg logit contributions
UTERS-0.140
inent-0.128
 Detail-0.125
Interstitial-0.124
idences-0.123
Tokenart
Token ID433
Feature activation-5.88e-01

Pos logit contributions
SSL+0.380
fox+0.377
SPONSORED+0.362
 �+0.331
 ‎+0.329
Neg logit contributions
UTERS-0.468
inent-0.434
 Detail-0.431
Interstitial-0.425
idences-0.417
Tokening
Token ID278
Feature activation-1.09e-01

Pos logit contributions
SSL+1.216
fox+1.203
SPONSORED+1.172
 �+1.082
 ‎+1.078
Neg logit contributions
UTERS-1.177
inent-1.081
 Detail-1.068
Interstitial-1.051
idences-1.048
Token races
Token ID9558
Feature activation-8.12e-04

Pos logit contributions
SSL+0.214
fox+0.211
SPONSORED+0.208
 ‎+0.190
 �+0.189
Neg logit contributions
UTERS-0.230
inent-0.214
 Detail-0.210
Interstitial-0.208
idences-0.207
Token he
Token ID339
Feature activation+1.18e-02

Pos logit contributions
SSL+0.002
fox+0.002
SPONSORED+0.002
 �+0.001
 ‎+0.001
Neg logit contributions
UTERS-0.002
inent-0.002
 Detail-0.002
Interstitial-0.002
iege-0.001
Token was
Token ID373
Feature activation-5.69e-02

Pos logit contributions
UTERS+0.025
inent+0.024
 Detail+0.023
Interstitial+0.023
iege+0.023
Neg logit contributions
SSL-0.023
fox-0.022
SPONSORED-0.022
 �-0.020
 ‎-0.020
Token tipped
Token ID28395
Feature activation+5.03e-02

Pos logit contributions
SSL+0.114
fox+0.113
SPONSORED+0.111
 �+0.101
 ‎+0.101
Neg logit contributions
UTERS-0.118
inent-0.109
 Detail-0.107
Interstitial-0.106
idences-0.106
Token remove
Token ID4781
Feature activation-2.16e-01

Pos logit contributions
SSL+0.058
fox+0.057
SPONSORED+0.056
 �+0.052
 ‎+0.051
Neg logit contributions
UTERS-0.052
inent-0.048
 Detail-0.047
Interstitial-0.046
iege-0.046
Token the
Token ID262
Feature activation-2.92e-02

Pos logit contributions
SSL+0.391
fox+0.386
SPONSORED+0.380
 �+0.341
 ‎+0.339
Neg logit contributions
UTERS-0.485
inent-0.454
 Detail-0.446
Interstitial-0.440
iege-0.438
Token damaged
Token ID9694
Feature activation-1.66e-03

Pos logit contributions
SSL+0.063
fox+0.062
SPONSORED+0.061
 �+0.056
 ‎+0.056
Neg logit contributions
UTERS-0.056
inent-0.052
 Detail-0.050
Interstitial-0.050
idences-0.049
Token skin
Token ID4168
Feature activation+3.58e-03

Pos logit contributions
SSL+0.004
fox+0.004
SPONSORED+0.004
 �+0.003
 ‎+0.003
Neg logit contributions
UTERS-0.003
inent-0.003
 Detail-0.003
Interstitial-0.003
iege-0.003
Token and
Token ID290
Feature activation-7.34e-02

Pos logit contributions
UTERS+0.007
inent+0.007
 Detail+0.007
Interstitial+0.007
iege+0.006
Neg logit contributions
SSL-0.007
fox-0.007
SPONSORED-0.007
 �-0.006
 ‎-0.006
Token graft
Token ID38455
Feature activation-5.87e-01

Pos logit contributions
SSL+0.150
fox+0.148
SPONSORED+0.146
 �+0.133
 ‎+0.133
Neg logit contributions
UTERS-0.149
inent-0.138
 Detail-0.135
Interstitial-0.133
iege-0.133
Token skin
Token ID4168
Feature activation-2.12e-02

Pos logit contributions
SSL+1.126
fox+1.113
SPONSORED+1.090
 �+0.998
 ‎+0.992
Neg logit contributions
UTERS-1.259
inent-1.170
 Detail-1.145
Interstitial-1.128
iege-1.127
Token from
Token ID422
Feature activation-3.62e-02

Pos logit contributions
SSL+0.046
fox+0.046
SPONSORED+0.045
 �+0.042
 ‎+0.041
Neg logit contributions
UTERS-0.040
inent-0.037
 Detail-0.036
Interstitial-0.035
iege-0.035
Token another
Token ID1194
Feature activation-3.24e-02

Pos logit contributions
SSL+0.063
fox+0.062
SPONSORED+0.061
 �+0.055
 ‎+0.054
Neg logit contributions
UTERS-0.084
inent-0.079
 Detail-0.077
Interstitial-0.076
iege-0.076
Token area
Token ID1989
Feature activation-3.18e-01

Pos logit contributions
SSL+0.067
fox+0.067
SPONSORED+0.066
 ‎+0.061
 �+0.061
Neg logit contributions
UTERS-0.064
inent-0.059
 Detail-0.057
Interstitial-0.057
idences-0.057
Token of
Token ID286
Feature activation-2.17e-02

Pos logit contributions
SSL+0.607
fox+0.601
SPONSORED+0.593
 �+0.535
 ‎+0.534
Neg logit contributions
UTERS-0.684
inent-0.638
 Detail-0.626
Interstitial-0.618
iege-0.614
TokenC
Token ID34
Feature activation-6.60e-02

Pos logit contributions
SSL+0.011
fox+0.011
SPONSORED+0.011
 �+0.010
 ‎+0.010
Neg logit contributions
UTERS-0.010
inent-0.009
 Detail-0.009
iege-0.009
idences-0.009
Tokenit
Token ID270
Feature activation+2.28e-02

Pos logit contributions
SSL+0.145
fox+0.144
SPONSORED+0.141
 �+0.129
 ‎+0.129
Neg logit contributions
UTERS-0.123
inent-0.113
 Detail-0.112
Interstitial-0.110
iege-0.108
Tokenib
Token ID571
Feature activation-6.94e-02

Pos logit contributions
UTERS+0.050
inent+0.047
 Detail+0.046
Interstitial+0.045
iege+0.045
Neg logit contributions
SSL-0.042
fox-0.042
SPONSORED-0.041
 �-0.037
 ‎-0.037
Tokenank
Token ID962
Feature activation-1.67e-01

Pos logit contributions
SSL+0.156
fox+0.155
SPONSORED+0.151
 �+0.140
 ‎+0.138
Neg logit contributions
UTERS-0.126
inent-0.114
 Detail-0.113
Interstitial-0.112
idences-0.110
Token fore
Token ID1674
Feature activation-8.90e-03

Pos logit contributions
SSL+0.333
fox+0.328
SPONSORED+0.321
 �+0.294
 ‎+0.293
Neg logit contributions
UTERS-0.347
inent-0.324
 Detail-0.315
Interstitial-0.314
idences-0.311
Tokenclosed
Token ID20225
Feature activation-5.83e-01

Pos logit contributions
SSL+0.017
fox+0.017
SPONSORED+0.016
 �+0.015
 ‎+0.015
Neg logit contributions
UTERS-0.019
inent-0.018
 Detail-0.018
Interstitial-0.018
idences-0.017
Token on
Token ID319
Feature activation+3.66e-02

Pos logit contributions
SSL+1.063
fox+1.058
SPONSORED+1.027
 ‎+0.945
 �+0.942
Neg logit contributions
UTERS-1.301
inent-1.218
Interstitial-1.192
 Detail-1.180
idences-1.170
Token Andrew
Token ID6858
Feature activation+2.42e-02

Pos logit contributions
UTERS+0.077
inent+0.071
 Detail+0.070
Interstitial+0.069
iege+0.068
Neg logit contributions
SSL-0.072
fox-0.071
SPONSORED-0.070
 �-0.064
 ‎-0.064
Token W
Token ID370
Feature activation-1.99e-01

Pos logit contributions
UTERS+0.048
inent+0.044
Interstitial+0.043
 Detail+0.043
iege+0.042
Neg logit contributions
SSL-0.051
fox-0.050
SPONSORED-0.049
 �-0.045
 ‎-0.045
Tokenied
Token ID798
Feature activation+1.47e-02

Pos logit contributions
SSL+0.411
fox+0.409
SPONSORED+0.398
 �+0.365
 ‎+0.363
Neg logit contributions
UTERS-0.399
inent-0.365
 Detail-0.360
Interstitial-0.356
idences-0.351
Tokener
Token ID263
Feature activation-1.07e-02

Pos logit contributions
UTERS+0.026
inent+0.023
 Detail+0.023
Interstitial+0.022
idences+0.022
Neg logit contributions
SSL-0.034
fox-0.034
SPONSORED-0.033
 �-0.031
 ‎-0.031
Token popular
Token ID2968
Feature activation-5.34e-02

Pos logit contributions
SSL+0.139
fox+0.138
SPONSORED+0.134
 �+0.125
 ‎+0.124
Neg logit contributions
UTERS-0.130
inent-0.120
Interstitial-0.116
 Detail-0.116
iege-0.115
Token FX
Token ID19534
Feature activation-2.75e-02

Pos logit contributions
SSL+0.112
fox+0.112
SPONSORED+0.108
 �+0.101
 ‎+0.100
Neg logit contributions
UTERS-0.106
inent-0.097
 Detail-0.094
Interstitial-0.094
idences-0.094
Token series
Token ID2168
Feature activation-1.04e-01

Pos logit contributions
fox+0.060
SSL+0.060
SPONSORED+0.058
 �+0.053
 ‎+0.053
Neg logit contributions
UTERS-0.052
inent-0.048
 Detail-0.047
idences-0.046
Interstitial-0.046
Token Sons
Token ID27989
Feature activation+2.87e-02

Pos logit contributions
SSL+0.221
fox+0.221
SPONSORED+0.214
 �+0.198
 ‎+0.197
Neg logit contributions
UTERS-0.204
inent-0.188
Interstitial-0.181
 Detail-0.181
idences-0.180
Token of
Token ID286
Feature activation-1.16e-01

Pos logit contributions
UTERS+0.063
inent+0.059
 Detail+0.058
iege+0.057
idences+0.057
Neg logit contributions
SSL-0.054
fox-0.052
SPONSORED-0.052
 �-0.047
 ‎-0.046
Token Anarchy
Token ID38899
Feature activation-5.83e-01

Pos logit contributions
fox+0.237
SSL+0.235
SPONSORED+0.231
 ‎+0.212
 �+0.212
Neg logit contributions
UTERS-0.234
inent-0.216
Interstitial-0.211
idences-0.206
iege-0.204
Token he
Token ID339
Feature activation-8.38e-02

Pos logit contributions
fox+1.122
SSL+1.122
SPONSORED+1.088
 �+0.991
 ‎+0.987
Neg logit contributions
UTERS-1.243
inent-1.154
 Detail-1.123
Interstitial-1.120
idences-1.108
Token was
Token ID373
Feature activation-7.52e-02

Pos logit contributions
SSL+0.158
fox+0.156
SPONSORED+0.154
 �+0.138
 ‎+0.137
Neg logit contributions
UTERS-0.182
inent-0.170
 Detail-0.167
Interstitial-0.164
iege-0.164
Token most
Token ID749
Feature activation-4.48e-02

Pos logit contributions
fox+0.138
SSL+0.138
SPONSORED+0.134
 ‎+0.121
 �+0.121
Neg logit contributions
UTERS-0.168
inent-0.157
Interstitial-0.153
 Detail-0.153
iege-0.152
Token recently
Token ID2904
Feature activation-1.03e-01

Pos logit contributions
SSL+0.090
fox+0.090
SPONSORED+0.088
 �+0.080
 ‎+0.080
Neg logit contributions
UTERS-0.091
inent-0.085
 Detail-0.083
Interstitial-0.082
iege-0.081
Token seen
Token ID1775
Feature activation-2.49e-02

Pos logit contributions
SSL+0.196
fox+0.196
SPONSORED+0.190
 ‎+0.174
 �+0.173
Neg logit contributions
UTERS-0.222
inent-0.206
 Detail-0.202
Interstitial-0.200
iege-0.200
Token says
Token ID1139
Feature activation+1.61e-01

Pos logit contributions
SSL+0.352
fox+0.344
SPONSORED+0.342
 �+0.313
cens+0.309
Neg logit contributions
UTERS-0.295
inent-0.272
 Detail-0.266
iege-0.261
idences-0.261
Token.
Token ID13
Feature activation+4.32e-03

Pos logit contributions
UTERS+0.295
inent+0.270
 Detail+0.265
iege+0.260
idences+0.258
Neg logit contributions
SSL-0.361
fox-0.352
SPONSORED-0.352
 �-0.322
-0.317
Token "
Token ID366
Feature activation+1.40e-02

Pos logit contributions
UTERS+0.008
inent+0.008
 Detail+0.008
Interstitial+0.008
iege+0.008
Neg logit contributions
SSL-0.009
fox-0.009
SPONSORED-0.009
 �-0.008
cens-0.008
TokenGetting
Token ID20570
Feature activation-3.39e-02

Pos logit contributions
UTERS+0.027
inent+0.025
 Detail+0.024
idences+0.024
iege+0.024
Neg logit contributions
SSL-0.031
fox-0.030
SPONSORED-0.030
 ‎-0.027
 �-0.027
Token the
Token ID262
Feature activation+3.41e-03

Pos logit contributions
SSL+0.067
fox+0.066
SPONSORED+0.065
 ‎+0.060
 �+0.059
Neg logit contributions
UTERS-0.071
inent-0.067
 Detail-0.065
Interstitial-0.064
iege-0.063
Token premium
Token ID8683
Feature activation-5.83e-01

Pos logit contributions
UTERS+0.007
inent+0.007
 Detail+0.007
Interstitial+0.007
iege+0.006
Neg logit contributions
SSL-0.007
fox-0.007
SPONSORED-0.006
 �-0.006
 ‎-0.006
Token in
Token ID287
Feature activation-2.17e-02

Pos logit contributions
SSL+1.021
fox+1.013
SPONSORED+0.999
 ‎+0.899
 �+0.897
Neg logit contributions
UTERS-1.345
inent-1.270
Interstitial-1.230
 Detail-1.227
iege-1.209
Token the
Token ID262
Feature activation-2.13e-03

Pos logit contributions
SSL+0.043
fox+0.042
SPONSORED+0.042
 �+0.038
 ‎+0.038
Neg logit contributions
UTERS-0.046
inent-0.043
 Detail-0.041
Interstitial-0.041
idences-0.041
Token health
Token ID1535
Feature activation+1.01e-01

Pos logit contributions
SSL+0.004
fox+0.004
SPONSORED+0.004
 ‎+0.004
 �+0.004
Neg logit contributions
UTERS-0.004
inent-0.004
 Detail-0.004
Interstitial-0.004
idences-0.004
Token insurance
Token ID5096
Feature activation-1.24e-01

Pos logit contributions
UTERS+0.219
inent+0.204
 Detail+0.200
Interstitial+0.197
idences+0.196
Neg logit contributions
SSL-0.191
fox-0.190
SPONSORED-0.187
 �-0.169
 ‎-0.168
Token business
Token ID1597
Feature activation-5.26e-03

Pos logit contributions
SSL+0.222
fox+0.221
SPONSORED+0.220
 ‎+0.197
 �+0.197
Neg logit contributions
UTERS-0.282
inent-0.265
 Detail-0.257
Interstitial-0.256
idences-0.253
TokenYes
Token ID5297
Feature activation-8.10e-02

Pos logit contributions
UTERS+0.036
inent+0.034
 Detail+0.033
idences+0.032
iege+0.032
Neg logit contributions
SSL-0.043
SPONSORED-0.042
fox-0.042
 ‎-0.038
 �-0.038
Token,
Token ID11
Feature activation+6.99e-02

Pos logit contributions
SSL+0.167
fox+0.165
SPONSORED+0.163
 �+0.148
 ‎+0.147
Neg logit contributions
UTERS-0.162
inent-0.150
 Detail-0.147
Interstitial-0.144
iege-0.143
Token the
Token ID262
Feature activation+4.72e-02

Pos logit contributions
UTERS+0.141
inent+0.132
Interstitial+0.128
 Detail+0.128
iege+0.125
Neg logit contributions
fox-0.143
SSL-0.142
SPONSORED-0.139
 ‎-0.128
 �-0.128
Token real
Token ID1103
Feature activation+1.14e-01

Pos logit contributions
UTERS+0.090
inent+0.083
 Detail+0.081
Interstitial+0.081
iege+0.079
Neg logit contributions
SSL-0.102
fox-0.101
SPONSORED-0.099
 ‎-0.092
 �-0.091
Token-
Token ID12
Feature activation+7.32e-03

Pos logit contributions
UTERS+0.212
inent+0.195
 Detail+0.190
Interstitial+0.188
iege+0.186
Neg logit contributions
SSL-0.252
fox-0.250
SPONSORED-0.247
 ‎-0.226
 �-0.226
Tokenestate
Token ID44146
Feature activation+5.44e-01

Pos logit contributions
UTERS+0.010
inent+0.009
 Detail+0.009
Interstitial+0.009
iege+0.009
Neg logit contributions
SSL-0.020
fox-0.019
SPONSORED-0.019
 �-0.018
 ‎-0.018
Token boom
Token ID14166
Feature activation-1.51e-03

Pos logit contributions
UTERS+1.141
inent+1.064
 Detail+1.046
Interstitial+1.024
iege+1.023
Neg logit contributions
SSL-1.063
fox-1.048
SPONSORED-1.038
 �-0.931
 ‎-0.923
Token raised
Token ID4376
Feature activation-7.05e-02

Pos logit contributions
SSL+0.003
fox+0.003
SPONSORED+0.003
 �+0.003
 ‎+0.003
Neg logit contributions
UTERS-0.003
inent-0.003
 Detail-0.003
Interstitial-0.003
iege-0.003
Token rents
Token ID28393
Feature activation+3.96e-03

Pos logit contributions
SSL+0.141
fox+0.140
SPONSORED+0.139
 ‎+0.127
 �+0.126
Neg logit contributions
UTERS-0.145
inent-0.136
 Detail-0.131
Interstitial-0.130
iege-0.129
Token beyond
Token ID3675
Feature activation+1.60e-01

Pos logit contributions
UTERS+0.008
inent+0.007
 Detail+0.007
Interstitial+0.007
iege+0.007
Neg logit contributions
SSL-0.008
fox-0.008
SPONSORED-0.008
 �-0.007
 ‎-0.007
Token the
Token ID262
Feature activation-7.16e-03

Pos logit contributions
UTERS+0.319
inent+0.295
 Detail+0.289
Interstitial+0.285
iege+0.283
Neg logit contributions
SSL-0.331
fox-0.328
SPONSORED-0.324
 �-0.295
 ‎-0.294
Tokenm
Token ID76
Feature activation+1.19e-01

Pos logit contributions
fox+0.265
SSL+0.263
SPONSORED+0.255
 �+0.231
 ‎+0.230
Neg logit contributions
UTERS-0.336
inent-0.313
 Detail-0.308
Interstitial-0.305
idences-0.301
Tokenote
Token ID1258
Feature activation-6.99e-02

Pos logit contributions
UTERS+0.255
inent+0.237
 Detail+0.234
Interstitial+0.231
idences+0.228
Neg logit contributions
SSL-0.227
fox-0.225
SPONSORED-0.219
 �-0.199
 ‎-0.198
Token (
Token ID357
Feature activation-8.70e-02

Pos logit contributions
SPONSORED+0.105
SSL+0.104
fox+0.101
 ‎+0.085
 �+0.085
Neg logit contributions
UTERS-0.180
inent-0.171
 Detail-0.168
iege-0.167
idences-0.164
TokenO
Token ID46
Feature activation+1.33e-01

Pos logit contributions
SSL+0.179
fox+0.177
SPONSORED+0.173
 �+0.156
 ‎+0.156
Neg logit contributions
UTERS-0.175
inent-0.166
 Detail-0.162
idences-0.159
Interstitial-0.159
Tokenmega
Token ID13731
Feature activation-1.58e-02

Pos logit contributions
UTERS+0.307
inent+0.287
 Detail+0.282
Interstitial+0.278
iege+0.277
Neg logit contributions
SSL-0.234
fox-0.231
SPONSORED-0.228
 �-0.203
 ‎-0.202
Token Pharma
Token ID41845
Feature activation+3.70e-01

Pos logit contributions
SSL+0.039
fox+0.039
SPONSORED+0.038
 ‎+0.036
 �+0.036
Neg logit contributions
UTERS-0.025
inent-0.023
Interstitial-0.022
 Detail-0.022
idences-0.022
Token -
Token ID532
Feature activation-1.32e-01

Pos logit contributions
UTERS+0.928
inent+0.881
Interstitial+0.857
idences+0.856
 Detail+0.855
Neg logit contributions
SSL-0.577
fox-0.574
SPONSORED-0.546
 ‎-0.507
 �-0.503
Token Quick
Token ID12029
Feature activation+2.97e-02

Pos logit contributions
SSL+0.272
fox+0.269
SPONSORED+0.258
 ‎+0.245
 �+0.244
Neg logit contributions
UTERS-0.268
inent-0.252
Interstitial-0.244
idences-0.244
iege-0.241
Tokenstep
Token ID9662
Feature activation-9.99e-02

Pos logit contributions
UTERS+0.055
inent+0.050
 Detail+0.050
Interstitial+0.049
idences+0.049
Neg logit contributions
fox-0.066
SSL-0.066
SPONSORED-0.064
 ‎-0.059
 �-0.059
Token)
Token ID8
Feature activation-3.30e-02

Pos logit contributions
SSL+0.225
fox+0.224
SPONSORED+0.218
 �+0.203
 ‎+0.202
Neg logit contributions
UTERS-0.182
inent-0.171
 Detail-0.164
Interstitial-0.163
idences-0.162
Token s
Token ID264
Feature activation+1.97e-01

Pos logit contributions
SPONSORED+0.058
SSL+0.058
fox+0.057
cens+0.050
 ‎+0.048
Neg logit contributions
UTERS-0.076
inent-0.071
 Detail-0.071
iege-0.069
idences-0.069
Token being
Token ID852
Feature activation-6.83e-02

Pos logit contributions
SSL+0.047
fox+0.046
SPONSORED+0.045
 ‎+0.041
 �+0.041
Neg logit contributions
UTERS-0.052
inent-0.048
 Detail-0.047
idences-0.047
Interstitial-0.047
Token shot
Token ID2823
Feature activation+4.66e-02

Pos logit contributions
SSL+0.131
fox+0.130
SPONSORED+0.127
 �+0.115
 ‎+0.115
Neg logit contributions
UTERS-0.147
inent-0.137
 Detail-0.134
Interstitial-0.132
idences-0.132
Token,
Token ID11
Feature activation-2.66e-03

Pos logit contributions
UTERS+0.094
inent+0.087
 Detail+0.085
Interstitial+0.084
iege+0.084
Neg logit contributions
SSL-0.095
fox-0.094
SPONSORED-0.093
 �-0.084
 ‎-0.084
Token so
Token ID523
Feature activation-8.29e-02

Pos logit contributions
SSL+0.005
fox+0.005
SPONSORED+0.005
 �+0.005
 ‎+0.005
Neg logit contributions
UTERS-0.005
inent-0.005
 Detail-0.005
Interstitial-0.005
idences-0.005
TokenB
Token ID33
Feature activation-1.36e-01

Pos logit contributions
fox+0.169
SSL+0.169
SPONSORED+0.165
 ‎+0.150
 �+0.150
Neg logit contributions
UTERS-0.167
inent-0.155
 Detail-0.151
Interstitial-0.150
iege-0.149
Tokenass
Token ID562
Feature activation+4.22e-01

Pos logit contributions
SSL+0.334
fox+0.330
SPONSORED+0.324
 ‎+0.300
 �+0.300
Neg logit contributions
UTERS-0.221
 Detail-0.198
inent-0.197
Interstitial-0.194
iege-0.189
Token'
Token ID6
Feature activation-7.29e-02

Pos logit contributions
UTERS+0.910
inent+0.852
 Detail+0.837
iege+0.820
Interstitial+0.820
Neg logit contributions
SSL-0.801
fox-0.786
SPONSORED-0.779
 �-0.699
 ‎-0.694
Token later
Token ID1568
Feature activation-3.41e-02

Pos logit contributions
SSL+0.153
fox+0.152
SPONSORED+0.149
 �+0.136
 ‎+0.136
Neg logit contributions
UTERS-0.143
inent-0.132
 Detail-0.129
Interstitial-0.127
iege-0.127
Token insistence
Token ID30696
Feature activation-4.76e-02

Pos logit contributions
SSL+0.067
fox+0.067
SPONSORED+0.066
 �+0.060
 ‎+0.060
Neg logit contributions
UTERS-0.071
inent-0.066
 Detail-0.064
Interstitial-0.064
iege-0.063
Token that
Token ID326
Feature activation+1.18e-02

Pos logit contributions
SSL+0.098
fox+0.097
SPONSORED+0.096
 �+0.087
 ‎+0.087
Neg logit contributions
UTERS-0.095
inent-0.089
 Detail-0.087
Interstitial-0.085
iege-0.085
Token he
Token ID339
Feature activation-3.76e-02

Pos logit contributions
UTERS+0.024
inent+0.022
 Detail+0.022
Interstitial+0.021
iege+0.021
Neg logit contributions
SSL-0.024
fox-0.024
SPONSORED-0.024
 �-0.021
 ‎-0.021
Token even
Token ID772
Feature activation+1.08e-01

Pos logit contributions
UTERS+0.083
inent+0.077
 Detail+0.075
idences+0.074
Interstitial+0.074
Neg logit contributions
SSL-0.087
fox-0.086
SPONSORED-0.084
 �-0.078
 ‎-0.078
Token fix
Token ID4259
Feature activation+3.59e-02

Pos logit contributions
UTERS+0.213
inent+0.198
 Detail+0.193
Interstitial+0.189
idences+0.189
Neg logit contributions
SSL-0.225
fox-0.224
SPONSORED-0.220
 �-0.203
 ‎-0.201
Token a
Token ID257
Feature activation+2.74e-02

Pos logit contributions
UTERS+0.075
inent+0.069
 Detail+0.068
Interstitial+0.067
idences+0.067
Neg logit contributions
SSL-0.071
fox-0.071
SPONSORED-0.069
 �-0.063
 ‎-0.063
Token breach
Token ID13694
Feature activation+1.14e-01

Pos logit contributions
UTERS+0.055
inent+0.051
 Detail+0.050
Interstitial+0.049
idences+0.049
Neg logit contributions
SSL-0.056
fox-0.056
SPONSORED-0.054
 �-0.050
 ‎-0.050
Token in
Token ID287
Feature activation+4.95e-02

Pos logit contributions
UTERS+0.237
inent+0.221
 Detail+0.217
Interstitial+0.214
idences+0.212
Neg logit contributions
SSL-0.225
fox-0.223
SPONSORED-0.218
 �-0.200
 ‎-0.199
Token Tal
Token ID7193
Feature activation+4.97e-01

Pos logit contributions
UTERS+0.105
inent+0.098
 Detail+0.096
Interstitial+0.095
iege+0.094
Neg logit contributions
SSL-0.096
fox-0.095
SPONSORED-0.094
 �-0.085
 ‎-0.084
Tokenos
Token ID418
Feature activation+2.19e-02

Pos logit contributions
UTERS+1.106
inent+1.037
 Detail+1.018
iege+0.999
Interstitial+0.999
Neg logit contributions
SSL-0.909
fox-0.896
SPONSORED-0.886
 �-0.793
 ‎-0.788
Token-
Token ID12
Feature activation+6.39e-02

Pos logit contributions
UTERS+0.045
inent+0.042
 Detail+0.041
Interstitial+0.040
idences+0.040
Neg logit contributions
SSL-0.044
fox-0.044
SPONSORED-0.043
 �-0.039
 ‎-0.039
Token1
Token ID16
Feature activation-9.04e-02

Pos logit contributions
UTERS+0.129
inent+0.120
 Detail+0.118
Interstitial+0.115
idences+0.115
Neg logit contributions
SSL-0.131
fox-0.130
SPONSORED-0.127
 ‎-0.115
 �-0.115
Token
Token ID447
Feature activation+2.10e-02

Pos logit contributions
SSL+0.168
fox+0.166
SPONSORED+0.162
 �+0.147
 ‎+0.147
Neg logit contributions
UTERS-0.199
inent-0.186
 Detail-0.183
Interstitial-0.180
iege-0.179
Token
Token ID247
Feature activation+4.20e-02

Pos logit contributions
UTERS+0.029
inent+0.026
 Detail+0.025
Interstitial+0.024
iege+0.024
Neg logit contributions
SSL-0.057
fox-0.056
SPONSORED-0.056
 �-0.052
 ‎-0.052
Token be
Token ID307
Feature activation+1.23e-01

Pos logit contributions
SSL+0.095
fox+0.094
SPONSORED+0.093
 �+0.084
 ‎+0.083
Neg logit contributions
UTERS-0.104
inent-0.097
 Detail-0.095
Interstitial-0.094
iege-0.093
Token used
Token ID973
Feature activation+6.42e-02

Pos logit contributions
UTERS+0.264
inent+0.246
 Detail+0.240
Interstitial+0.238
idences+0.237
Neg logit contributions
SSL-0.235
fox-0.233
SPONSORED-0.228
 �-0.207
 ‎-0.206
Token in
Token ID287
Feature activation-6.68e-03

Pos logit contributions
UTERS+0.134
inent+0.124
 Detail+0.121
Interstitial+0.121
idences+0.120
Neg logit contributions
SSL-0.127
fox-0.127
SPONSORED-0.123
 �-0.113
 ‎-0.112
Token all
Token ID477
Feature activation+7.14e-03

Pos logit contributions
SSL+0.014
fox+0.014
SPONSORED+0.013
 �+0.012
 ‎+0.012
Neg logit contributions
UTERS-0.013
inent-0.013
Interstitial-0.012
 Detail-0.012
idences-0.012
Token game
Token ID983
Feature activation+5.98e-02

Pos logit contributions
UTERS+0.015
inent+0.013
Interstitial+0.013
 Detail+0.013
iege+0.013
Neg logit contributions
fox-0.014
SSL-0.014
SPONSORED-0.014
 �-0.013
 ‎-0.013
Token modes
Token ID12881
Feature activation+3.94e-01

Pos logit contributions
UTERS+0.133
inent+0.124
 Detail+0.121
Interstitial+0.121
iege+0.120
Neg logit contributions
SSL-0.110
fox-0.109
SPONSORED-0.106
 �-0.096
 ‎-0.096
Token or
Token ID393
Feature activation+2.40e-02

Pos logit contributions
UTERS+0.810
inent+0.752
 Detail+0.736
Interstitial+0.728
idences+0.722
Neg logit contributions
SSL-0.793
fox-0.785
SPONSORED-0.771
 �-0.702
 ‎-0.698
Token you
Token ID345
Feature activation+3.25e-02

Pos logit contributions
UTERS+0.051
inent+0.048
Interstitial+0.046
 Detail+0.046
idences+0.046
Neg logit contributions
SSL-0.046
fox-0.046
SPONSORED-0.045
 �-0.041
 ‎-0.041
Token can
Token ID460
Feature activation-1.32e-02

Pos logit contributions
UTERS+0.068
inent+0.063
 Detail+0.061
Interstitial+0.061
idences+0.060
Neg logit contributions
SSL-0.065
fox-0.064
SPONSORED-0.063
 �-0.057
 ‎-0.057
Token choose
Token ID3853
Feature activation-1.72e-01

Pos logit contributions
SSL+0.026
fox+0.026
SPONSORED+0.025
 �+0.023
 ‎+0.023
Neg logit contributions
UTERS-0.028
inent-0.026
 Detail-0.025
Interstitial-0.025
idences-0.025
Token to
Token ID284
Feature activation-2.83e-02

Pos logit contributions
SSL+0.342
fox+0.340
SPONSORED+0.333
 �+0.304
 ‎+0.303
Neg logit contributions
UTERS-0.358
inent-0.332
 Detail-0.321
Interstitial-0.321
idences-0.320
Token claimed
Token ID4752
Feature activation-6.77e-02

Pos logit contributions
UTERS+0.171
inent+0.159
 Detail+0.156
Interstitial+0.154
idences+0.152
Neg logit contributions
SSL-0.164
fox-0.163
SPONSORED-0.160
 �-0.146
 ‎-0.146
Token that
Token ID326
Feature activation+1.79e-01

Pos logit contributions
SSL+0.142
fox+0.140
SPONSORED+0.138
 �+0.127
 ‎+0.127
Neg logit contributions
UTERS-0.133
inent-0.123
 Detail-0.120
Interstitial-0.119
idences-0.118
Token he
Token ID339
Feature activation+5.92e-02

Pos logit contributions
UTERS+0.364
inent+0.339
 Detail+0.329
Interstitial+0.328
iege+0.324
Neg logit contributions
SSL-0.364
fox-0.359
SPONSORED-0.353
 ‎-0.325
 �-0.323
Token was
Token ID373
Feature activation+9.39e-02

Pos logit contributions
UTERS+0.136
inent+0.128
 Detail+0.125
Interstitial+0.123
iege+0.123
Neg logit contributions
SSL-0.104
fox-0.103
SPONSORED-0.101
 �-0.090
 ‎-0.090
Token forced
Token ID4137
Feature activation+1.34e-01

Pos logit contributions
UTERS+0.190
inent+0.176
 Detail+0.173
Interstitial+0.170
iege+0.170
Neg logit contributions
SSL-0.192
fox-0.190
SPONSORED-0.187
 ‎-0.170
 �-0.170
Token to
Token ID284
Feature activation+3.57e-02

Pos logit contributions
UTERS+0.251
inent+0.232
 Detail+0.226
Interstitial+0.222
iege+0.221
Neg logit contributions
SSL-0.294
fox-0.289
SPONSORED-0.286
 �-0.261
 ‎-0.259
Token sign
Token ID1051
Feature activation-1.15e-01

Pos logit contributions
UTERS+0.070
inent+0.065
Interstitial+0.063
 Detail+0.063
idences+0.062
Neg logit contributions
SSL-0.075
fox-0.075
SPONSORED-0.073
 ‎-0.068
 �-0.068
Token the
Token ID262
Feature activation+9.52e-02

Pos logit contributions
SSL+0.223
fox+0.221
SPONSORED+0.217
 �+0.197
 ‎+0.196
Neg logit contributions
UTERS-0.245
inent-0.228
 Detail-0.223
Interstitial-0.221
iege-0.219
Token document
Token ID3188
Feature activation+7.17e-02

Pos logit contributions
UTERS+0.193
inent+0.178
 Detail+0.173
Interstitial+0.172
idences+0.171
Neg logit contributions
SSL-0.193
fox-0.191
SPONSORED-0.189
 �-0.174
 ‎-0.173
Token by
Token ID416
Feature activation+4.70e-03

Pos logit contributions
UTERS+0.142
inent+0.131
 Detail+0.128
Interstitial+0.128
iege+0.126
Neg logit contributions
SSL-0.149
fox-0.149
SPONSORED-0.146
 �-0.134
 ‎-0.134
Token Joseph
Token ID7212
Feature activation+2.07e-01

Pos logit contributions
UTERS+0.009
inent+0.009
Interstitial+0.008
 Detail+0.008
iege+0.008
Neg logit contributions
SSL-0.010
fox-0.010
SPONSORED-0.009
 �-0.009
 ‎-0.009
Token Pittsburgh
Token ID12767
Feature activation+1.53e-01

Pos logit contributions
UTERS+0.015
inent+0.014
 Detail+0.014
Interstitial+0.014
idences+0.014
Neg logit contributions
SSL-0.015
fox-0.015
SPONSORED-0.014
 �-0.013
 ‎-0.013
Token,
Token ID11
Feature activation-3.25e-02

Pos logit contributions
UTERS+0.318
inent+0.296
 Detail+0.290
Interstitial+0.285
iege+0.284
Neg logit contributions
SSL-0.302
fox-0.298
SPONSORED-0.293
 �-0.265
 ‎-0.263
Token they
Token ID484
Feature activation-2.48e-03

Pos logit contributions
SSL+0.066
fox+0.065
SPONSORED+0.064
 ‎+0.059
 �+0.059
Neg logit contributions
UTERS-0.066
inent-0.061
 Detail-0.060
Interstitial-0.059
iege-0.059
Token hadn
Token ID8020
Feature activation+1.05e-01

Pos logit contributions
SSL+0.005
fox+0.005
SPONSORED+0.005
 �+0.004
 ‎+0.004
Neg logit contributions
UTERS-0.005
inent-0.005
 Detail-0.005
Interstitial-0.005
iege-0.005
Token
Token ID447
Feature activation+4.62e-02

Pos logit contributions
UTERS+0.264
inent+0.250
 Detail+0.246
iege+0.242
idences+0.241
Neg logit contributions
SSL-0.163
fox-0.160
SPONSORED-0.158
 �-0.140
 ‎-0.138
Token
Token ID247
Feature activation+6.95e-02

Pos logit contributions
UTERS+0.066
inent+0.060
 Detail+0.058
Interstitial+0.057
idences+0.056
Neg logit contributions
SSL-0.121
SPONSORED-0.120
fox-0.119
 ‎-0.111
 �-0.111
Tokent
Token ID83
Feature activation-8.62e-05

Pos logit contributions
UTERS+0.168
inent+0.158
 Detail+0.155
Interstitial+0.154
iege+0.153
Neg logit contributions
SSL-0.115
fox-0.113
SPONSORED-0.111
 �-0.100
 ‎-0.099
Token scored
Token ID7781
Feature activation-3.25e-01

Pos logit contributions
SSL+0.000
fox+0.000
SPONSORED+0.000
 ‎+0.000
 �+0.000
Neg logit contributions
UTERS-0.000
inent-0.000
 Detail-0.000
Interstitial-0.000
iege-0.000
Token in
Token ID287
Feature activation+6.61e-03

Pos logit contributions
SSL+0.611
fox+0.602
SPONSORED+0.587
 ‎+0.544
 �+0.538
Neg logit contributions
UTERS-0.711
inent-0.660
 Detail-0.649
Interstitial-0.647
idences-0.637
Token two
Token ID734
Feature activation-1.39e-02

Pos logit contributions
UTERS+0.015
inent+0.014
 Detail+0.013
Interstitial+0.013
idences+0.013
Neg logit contributions
SSL-0.012
fox-0.012
SPONSORED-0.012
 ‎-0.011
 �-0.011
Token games
Token ID1830
Feature activation-6.80e-02

Pos logit contributions
SSL+0.028
fox+0.028
SPONSORED+0.028
 ‎+0.025
 �+0.025
Neg logit contributions
UTERS-0.028
inent-0.026
 Detail-0.026
Interstitial-0.025
iege-0.025
Token the
Token ID262
Feature activation+1.73e-02

Pos logit contributions
UTERS+0.041
inent+0.038
 Detail+0.037
Interstitial+0.037
iege+0.037
Neg logit contributions
SSL-0.037
fox-0.037
SPONSORED-0.036
 ‎-0.033
 �-0.033
Token movement
Token ID3356
Feature activation-2.45e-01

Pos logit contributions
UTERS+0.029
inent+0.026
 Detail+0.025
Interstitial+0.025
idences+0.025
Neg logit contributions
SSL-0.042
fox-0.041
SPONSORED-0.041
 ‎-0.038
 �-0.038
Token,
Token ID11
Feature activation+5.39e-02

Pos logit contributions
SSL+0.496
fox+0.491
SPONSORED+0.484
 �+0.441
 ‎+0.439
Neg logit contributions
UTERS-0.499
inent-0.462
 Detail-0.454
Interstitial-0.449
iege-0.445
Token moving
Token ID3867
Feature activation+5.51e-02

Pos logit contributions
UTERS+0.113
inent+0.104
 Detail+0.102
Interstitial+0.101
idences+0.100
Neg logit contributions
SSL-0.106
fox-0.106
SPONSORED-0.105
 �-0.095
 ‎-0.095
Token up
Token ID510
Feature activation+1.02e-01

Pos logit contributions
UTERS+0.114
inent+0.106
 Detail+0.104
Interstitial+0.103
iege+0.102
Neg logit contributions
SSL-0.109
fox-0.108
SPONSORED-0.107
 �-0.098
 ‎-0.097
Token into
Token ID656
Feature activation+8.05e-02

Pos logit contributions
UTERS+0.210
inent+0.195
 Detail+0.191
Interstitial+0.188
iege+0.187
Neg logit contributions
SSL-0.204
fox-0.202
SPONSORED-0.199
 �-0.180
 ‎-0.179
Token the
Token ID262
Feature activation+8.23e-02

Pos logit contributions
UTERS+0.168
inent+0.155
 Detail+0.151
Interstitial+0.150
iege+0.149
Neg logit contributions
SSL-0.160
fox-0.158
SPONSORED-0.157
 ‎-0.142
 �-0.142
Token feminist
Token ID14314
Feature activation+8.10e-02

Pos logit contributions
UTERS+0.157
inent+0.144
 Detail+0.139
Interstitial+0.139
idences+0.138
Neg logit contributions
SSL-0.177
fox-0.175
SPONSORED-0.173
 ‎-0.161
 �-0.160
Token movement
Token ID3356
Feature activation-3.56e-01

Pos logit contributions
UTERS+0.152
inent+0.140
 Detail+0.136
Interstitial+0.135
idences+0.133
Neg logit contributions
SSL-0.177
fox-0.175
SPONSORED-0.173
 �-0.159
 ‎-0.159
Token,
Token ID11
Feature activation+6.28e-02

Pos logit contributions
SSL+0.705
fox+0.697
SPONSORED+0.690
 �+0.626
 ‎+0.625
Neg logit contributions
UTERS-0.737
inent-0.684
 Detail-0.672
Interstitial-0.665
iege-0.658
Token as
Token ID355
Feature activation+1.07e-01

Pos logit contributions
UTERS+0.133
inent+0.123
 Detail+0.121
Interstitial+0.119
idences+0.118
Neg logit contributions
SSL-0.123
fox-0.121
SPONSORED-0.120
 �-0.109
 ‎-0.109
Token
Token ID198
Feature activation+1.37e-02

Pos logit contributions
UTERS+0.071
inent+0.068
 Detail+0.066
Interstitial+0.066
iege+0.065
Neg logit contributions
SSL-0.041
fox-0.041
SPONSORED-0.040
 �-0.035
 ‎-0.035
TokenIf
Token ID1532
Feature activation+5.84e-02

Pos logit contributions
UTERS+0.026
inent+0.024
 Detail+0.024
idences+0.023
iege+0.023
Neg logit contributions
SSL-0.030
fox-0.030
SPONSORED-0.029
 �-0.026
cens-0.026
Token you
Token ID345
Feature activation-4.57e-03

Pos logit contributions
UTERS+0.123
inent+0.114
 Detail+0.110
Interstitial+0.110
iege+0.109
Neg logit contributions
SSL-0.115
fox-0.113
SPONSORED-0.110
 �-0.102
 ‎-0.101
Token find
Token ID1064
Feature activation+1.34e-01

Pos logit contributions
SSL+0.009
fox+0.009
SPONSORED+0.009
 �+0.008
 ‎+0.008
Neg logit contributions
UTERS-0.009
inent-0.009
Interstitial-0.009
 Detail-0.008
idences-0.008
Token the
Token ID262
Feature activation+1.83e-02

Pos logit contributions
UTERS+0.279
inent+0.259
Interstitial+0.251
iege+0.248
 Detail+0.248
Neg logit contributions
SSL-0.266
fox-0.264
SPONSORED-0.259
 �-0.238
 ‎-0.238
Token above
Token ID2029
Feature activation+7.42e-02

Pos logit contributions
UTERS+0.037
inent+0.034
Interstitial+0.033
 Detail+0.032
iege+0.032
Neg logit contributions
SSL-0.038
fox-0.038
SPONSORED-0.037
 �-0.034
 ‎-0.034
Token method
Token ID2446
Feature activation+2.33e-01

Pos logit contributions
UTERS+0.155
inent+0.145
 Detail+0.139
Interstitial+0.138
iege+0.138
Neg logit contributions
SSL-0.147
fox-0.147
SPONSORED-0.144
 �-0.131
 ‎-0.130
Token too
Token ID1165
Feature activation+2.45e-01

Pos logit contributions
UTERS+0.480
inent+0.448
 Detail+0.435
Interstitial+0.433
idences+0.429
Neg logit contributions
SSL-0.467
fox-0.462
SPONSORED-0.458
 �-0.416
 ‎-0.412
Token troublesome
Token ID35778
Feature activation-1.24e-01

Pos logit contributions
UTERS+0.458
inent+0.422
 Detail+0.409
Interstitial+0.407
idences+0.406
Neg logit contributions
SSL-0.542
fox-0.535
SPONSORED-0.529
 �-0.486
 ‎-0.482
Token,
Token ID11
Feature activation-5.11e-03

Pos logit contributions
SSL+0.244
fox+0.242
SPONSORED+0.238
 �+0.217
 ‎+0.215
Neg logit contributions
UTERS-0.262
inent-0.243
 Detail-0.237
Interstitial-0.234
idences-0.233
Token just
Token ID655
Feature activation-6.48e-03

Pos logit contributions
SSL+0.010
fox+0.010
SPONSORED+0.010
 �+0.009
 ‎+0.009
Neg logit contributions
UTERS-0.011
inent-0.010
 Detail-0.010
Interstitial-0.010
idences-0.009
Token
Token ID447
Feature activation+1.39e-02

Pos logit contributions
UTERS+0.079
inent+0.074
 Detail+0.072
Interstitial+0.071
iege+0.071
Neg logit contributions
SSL-0.066
fox-0.065
SPONSORED-0.064
 �-0.057
 ‎-0.057
Token
Token ID247
Feature activation+8.23e-02

Pos logit contributions
UTERS+0.020
inent+0.018
 Detail+0.018
idences+0.017
iege+0.017
Neg logit contributions
SSL-0.036
fox-0.036
SPONSORED-0.036
 �-0.033
 ‎-0.033
Tokens
Token ID82
Feature activation-5.81e-03

Pos logit contributions
UTERS+0.227
inent+0.215
 Detail+0.212
Interstitial+0.209
idences+0.209
Neg logit contributions
SSL-0.107
fox-0.105
SPONSORED-0.103
 �-0.087
 ‎-0.086
Token collapse
Token ID9807
Feature activation-3.68e-02

Pos logit contributions
SSL+0.013
fox+0.013
SPONSORED+0.013
 ‎+0.012
 �+0.012
Neg logit contributions
UTERS-0.011
inent-0.010
 Detail-0.010
Interstitial-0.010
idences-0.009
Token requires
Token ID4433
Feature activation-2.11e-02

Pos logit contributions
SSL+0.067
fox+0.066
SPONSORED+0.065
 �+0.058
 ‎+0.058
Neg logit contributions
UTERS-0.083
inent-0.077
 Detail-0.076
Interstitial-0.075
iege-0.074
Token active
Token ID4075
Feature activation+1.22e-01

Pos logit contributions
SSL+0.044
fox+0.043
SPONSORED+0.043
 �+0.039
 ‎+0.039
Neg logit contributions
UTERS-0.042
inent-0.039
 Detail-0.038
Interstitial-0.037
iege-0.037
Token involvement
Token ID9750
Feature activation-2.26e-02

Pos logit contributions
UTERS+0.235
inent+0.217
 Detail+0.213
Interstitial+0.210
iege+0.208
Neg logit contributions
SSL-0.259
fox-0.256
SPONSORED-0.252
 �-0.230
 ‎-0.230
Token of
Token ID286
Feature activation+7.81e-02

Pos logit contributions
SSL+0.046
fox+0.045
SPONSORED+0.045
 �+0.040
cens+0.040
Neg logit contributions
UTERS-0.046
inent-0.043
 Detail-0.042
iege-0.041
idences-0.041
Token international
Token ID3230
Feature activation-4.77e-02

Pos logit contributions
UTERS+0.159
inent+0.148
 Detail+0.145
Interstitial+0.143
iege+0.142
Neg logit contributions
SSL-0.158
fox-0.156
SPONSORED-0.154
 �-0.140
 ‎-0.140
Token organisations
Token ID16435
Feature activation+7.29e-02

Pos logit contributions
SSL+0.092
fox+0.091
SPONSORED+0.090
 ‎+0.082
 �+0.081
Neg logit contributions
UTERS-0.102
inent-0.094
 Detail-0.093
Interstitial-0.092
iege-0.091
Token that
Token ID326
Feature activation+4.46e-03

Pos logit contributions
UTERS+0.141
inent+0.131
 Detail+0.128
Interstitial+0.126
iege+0.125
Neg logit contributions
SSL-0.155
fox-0.153
SPONSORED-0.151
 �-0.138
 ‎-0.137
Token MIC
Token ID35878
Feature activation+1.63e-01

Pos logit contributions
UTERS+0.106
inent+0.097
Interstitial+0.094
 Detail+0.094
idences+0.093
Neg logit contributions
SSL-0.119
fox-0.118
SPONSORED-0.116
 ‎-0.107
 �-0.107
TokenAS
Token ID1921
Feature activation-1.91e-01

Pos logit contributions
UTERS+0.307
inent+0.287
 Detail+0.279
Interstitial+0.277
idences+0.275
Neg logit contributions
SSL-0.356
fox-0.348
SPONSORED-0.347
 �-0.314
 ‎-0.313
Token instrument
Token ID8875
Feature activation+3.94e-02

Pos logit contributions
SSL+0.421
fox+0.418
SPONSORED+0.413
 �+0.378
 ‎+0.377
Neg logit contributions
UTERS-0.352
inent-0.326
 Detail-0.314
Interstitial-0.314
idences-0.311
Token was
Token ID373
Feature activation+6.65e-02

Pos logit contributions
UTERS+0.083
inent+0.077
 Detail+0.076
Interstitial+0.075
iege+0.075
Neg logit contributions
SSL-0.077
fox-0.076
SPONSORED-0.075
 �-0.068
 ‎-0.068
Token a
Token ID257
Feature activation-1.87e-02

Pos logit contributions
UTERS+0.137
inent+0.127
 Detail+0.123
Interstitial+0.123
idences+0.123
Neg logit contributions
SSL-0.134
fox-0.133
SPONSORED-0.131
 ‎-0.119
 �-0.119
Token design
Token ID1486
Feature activation-2.24e-01

Pos logit contributions
SSL+0.041
fox+0.040
SPONSORED+0.039
 ‎+0.037
 �+0.036
Neg logit contributions
UTERS-0.036
inent-0.032
Interstitial-0.032
iege-0.031
 Detail-0.031
Token success
Token ID1943
Feature activation-5.45e-02

Pos logit contributions
fox+0.443
SSL+0.443
SPONSORED+0.437
 ‎+0.400
 �+0.396
Neg logit contributions
UTERS-0.457
inent-0.426
Interstitial-0.414
idences-0.413
iege-0.410
Token,
Token ID11
Feature activation+2.14e-02

Pos logit contributions
SSL+0.109
fox+0.109
SPONSORED+0.107
 �+0.097
 ‎+0.097
Neg logit contributions
UTERS-0.112
inent-0.103
 Detail-0.101
Interstitial-0.100
iege-0.099
Token but
Token ID475
Feature activation-6.02e-02

Pos logit contributions
UTERS+0.042
inent+0.039
 Detail+0.038
Interstitial+0.038
iege+0.038
Neg logit contributions
SSL-0.045
fox-0.045
SPONSORED-0.044
 �-0.040
 ‎-0.040
Token the
Token ID262
Feature activation-1.39e-02

Pos logit contributions
SSL+0.116
fox+0.115
SPONSORED+0.113
 ‎+0.103
 �+0.103
Neg logit contributions
UTERS-0.129
inent-0.120
Interstitial-0.115
iege-0.115
 Detail-0.115
Token ultraviolet
Token ID49961
Feature activation+9.89e-02

Pos logit contributions
SSL+0.031
fox+0.030
SPONSORED+0.030
 ‎+0.028
 �+0.028
Neg logit contributions
UTERS-0.026
inent-0.024
Interstitial-0.023
idences-0.023
 Detail-0.023
Tokenating
Token ID803
Feature activation+1.10e-04

Pos logit contributions
SSL+0.464
fox+0.462
SPONSORED+0.454
 �+0.418
 ‎+0.418
Neg logit contributions
UTERS-0.374
inent-0.343
 Detail-0.337
Interstitial-0.330
iege-0.328
Token the
Token ID262
Feature activation+2.98e-03

Pos logit contributions
UTERS+0.000
inent+0.000
 Detail+0.000
Interstitial+0.000
iege+0.000
Neg logit contributions
SSL-0.000
fox-0.000
SPONSORED-0.000
 �-0.000
 ‎-0.000
Token y
Token ID331
Feature activation-9.86e-02

Pos logit contributions
UTERS+0.006
inent+0.005
Interstitial+0.005
 Detail+0.005
iege+0.005
Neg logit contributions
SSL-0.006
fox-0.006
SPONSORED-0.006
 �-0.006
 ‎-0.006
Tokenaku
Token ID8719
Feature activation-1.02e-01

Pos logit contributions
fox+0.256
SSL+0.251
SPONSORED+0.245
 �+0.234
 ‎+0.231
Neg logit contributions
UTERS-0.149
 Detail-0.133
Interstitial-0.131
inent-0.128
 defic-0.127
Tokenza
Token ID4496
Feature activation-9.20e-02

Pos logit contributions
fox+0.172
SSL+0.169
SPONSORED+0.163
 �+0.149
 ‎+0.148
Neg logit contributions
UTERS-0.244
inent-0.224
Interstitial-0.224
 Detail-0.223
iege-0.219
Token as
Token ID355
Feature activation+1.19e-03

Pos logit contributions
SSL+0.181
fox+0.178
SPONSORED+0.176
 �+0.159
 ‎+0.158
Neg logit contributions
UTERS-0.193
inent-0.180
 Detail-0.176
Interstitial-0.174
iege-0.173
Token a
Token ID257
Feature activation-2.33e-02

Pos logit contributions
UTERS+0.003
inent+0.002
 Detail+0.002
Interstitial+0.002
iege+0.002
Neg logit contributions
SSL-0.002
fox-0.002
SPONSORED-0.002
 �-0.002
 ‎-0.002
Token
Token ID564
Feature activation+6.98e-02

Pos logit contributions
SSL+0.053
fox+0.052
SPONSORED+0.051
 ‎+0.048
 �+0.048
Neg logit contributions
UTERS-0.042
inent-0.038
 Detail-0.037
Interstitial-0.037
iege-0.037
Token
Token ID250
Feature activation-3.12e-02

Pos logit contributions
UTERS+0.073
inent+0.062
 Detail+0.060
idences+0.058
Interstitial+0.057
Neg logit contributions
SSL-0.212
fox-0.209
SPONSORED-0.208
 ‎-0.197
 �-0.197
Tokentrans
Token ID7645
Feature activation+4.53e-01

Pos logit contributions
SSL+0.066
fox+0.066
SPONSORED+0.065
 ‎+0.059
 �+0.059
Neg logit contributions
UTERS-0.061
inent-0.055
 Detail-0.055
idences-0.053
iege-0.053
Tokennational
Token ID14648
Feature activation-5.89e-02

Pos logit contributions
UTERS+0.925
inent+0.859
 Detail+0.842
Interstitial+0.828
iege+0.824
Neg logit contributions
SSL-0.917
fox-0.906
SPONSORED-0.893
 �-0.810
 ‎-0.806
Tokenrist
Token ID1585
Feature activation-2.78e-01

Pos logit contributions
SSL+0.137
fox+0.136
SPONSORED+0.134
 ‎+0.123
 �+0.122
Neg logit contributions
UTERS-0.122
inent-0.112
 Detail-0.110
Interstitial-0.110
iege-0.107
Tokenown
Token ID593
Feature activation-3.08e-01

Pos logit contributions
SSL+0.470
fox+0.464
SPONSORED+0.452
 �+0.405
 ‎+0.403
Neg logit contributions
UTERS-0.662
inent-0.620
 Detail-0.611
Interstitial-0.606
iege-0.598
Token,
Token ID11
Feature activation-6.49e-02

Pos logit contributions
SSL+0.643
fox+0.636
SPONSORED+0.629
 �+0.568
 ‎+0.562
Neg logit contributions
UTERS-0.610
inent-0.565
 Detail-0.554
Interstitial-0.543
iege-0.541
Token N
Token ID399
Feature activation-1.37e-01

Pos logit contributions
SSL+0.134
fox+0.132
SPONSORED+0.130
 �+0.118
 ‎+0.117
Neg logit contributions
UTERS-0.130
inent-0.121
 Detail-0.119
Interstitial-0.116
iege-0.116
Token.
Token ID13
Feature activation-2.83e-02

Pos logit contributions
SSL+0.275
fox+0.273
SPONSORED+0.268
 ‎+0.245
 �+0.243
Neg logit contributions
UTERS-0.281
inent-0.262
 Detail-0.258
Interstitial-0.255
iege-0.251
TokenJ
Token ID41
Feature activation-3.95e-02

Pos logit contributions
SSL+0.068
fox+0.067
SPONSORED+0.066
 �+0.061
cens+0.061
Neg logit contributions
UTERS-0.047
inent-0.042
 Detail-0.042
Interstitial-0.041
iege-0.040
Token.
Token ID13
Feature activation+1.27e-02

Pos logit contributions
SSL+0.094
fox+0.092
SPONSORED+0.092
 �+0.083
cens+0.083
Neg logit contributions
UTERS-0.067
inent-0.062
 Detail-0.060
idences-0.059
iege-0.059
Token Early
Token ID12556
Feature activation+1.25e-01

Pos logit contributions
UTERS+0.028
inent+0.026
 Detail+0.025
Interstitial+0.025
iege+0.025
Neg logit contributions
SSL-0.024
fox-0.024
SPONSORED-0.023
 �-0.021
 ‎-0.021
Token-
Token ID12
Feature activation-4.74e-02

Pos logit contributions
UTERS+0.254
inent+0.235
 Detail+0.230
iege+0.227
Interstitial+0.227
Neg logit contributions
SSL-0.252
fox-0.251
SPONSORED-0.246
 ‎-0.226
 �-0.225
Token19
Token ID1129
Feature activation-1.12e-02

Pos logit contributions
SSL+0.125
fox+0.125
SPONSORED+0.122
 ‎+0.114
 �+0.114
Neg logit contributions
UTERS-0.069
inent-0.061
 Detail-0.060
iege-0.058
Interstitial-0.058
Tokenth
Token ID400
Feature activation+2.38e-01

Pos logit contributions
SSL+0.020
fox+0.019
SPONSORED+0.019
 ‎+0.017
 �+0.017
Neg logit contributions
UTERS-0.026
inent-0.024
 Detail-0.024
Interstitial-0.024
iege-0.024
Token per
Token ID583
Feature activation+4.71e-02

Pos logit contributions
UTERS+0.195
inent+0.181
 Detail+0.177
Interstitial+0.174
iege+0.173
Neg logit contributions
SSL-0.213
fox-0.211
SPONSORED-0.208
 �-0.189
 ‎-0.188
Token animal
Token ID5044
Feature activation-9.96e-02

Pos logit contributions
UTERS+0.092
inent+0.085
 Detail+0.083
Interstitial+0.082
idences+0.082
Neg logit contributions
SSL-0.099
fox-0.098
SPONSORED-0.097
 �-0.089
 ‎-0.089
Token for
Token ID329
Feature activation+1.12e-02

Pos logit contributions
SSL+0.209
fox+0.207
SPONSORED+0.204
 �+0.186
 ‎+0.185
Neg logit contributions
UTERS-0.196
inent-0.181
 Detail-0.177
Interstitial-0.174
iege-0.173
Token the
Token ID262
Feature activation-1.01e-02

Pos logit contributions
UTERS+0.023
inent+0.021
 Detail+0.021
Interstitial+0.021
iege+0.020
Neg logit contributions
SSL-0.023
fox-0.022
SPONSORED-0.022
 �-0.020
 ‎-0.020
Token farmer
Token ID18739
Feature activation-1.65e-01

Pos logit contributions
SSL+0.020
fox+0.020
SPONSORED+0.019
 �+0.018
 ‎+0.018
Neg logit contributions
UTERS-0.021
inent-0.020
 Detail-0.019
Interstitial-0.019
iege-0.019
Token.
Token ID13
Feature activation-6.12e-03

Pos logit contributions
SSL+0.340
fox+0.336
SPONSORED+0.332
 �+0.302
 ‎+0.301
Neg logit contributions
UTERS-0.330
inent-0.306
 Detail-0.300
Interstitial-0.295
iege-0.293
Token
Token ID198
Feature activation-8.92e-03

Pos logit contributions
SSL+0.012
fox+0.012
SPONSORED+0.011
 ‎+0.010
 �+0.010
Neg logit contributions
UTERS-0.013
inent-0.013
idences-0.012
Interstitial-0.012
iege-0.012
Token
Token ID198
Feature activation-5.27e-03

Pos logit contributions
SSL+0.013
fox+0.013
SPONSORED+0.013
 ‎+0.011
 �+0.011
Neg logit contributions
UTERS-0.023
inent-0.022
 Detail-0.022
Interstitial-0.022
iege-0.021
TokenBut
Token ID1537
Feature activation+2.89e-03

Pos logit contributions
SSL+0.012
SPONSORED+0.012
fox+0.012
 ‎+0.010
cens+0.010
Neg logit contributions
UTERS-0.010
inent-0.009
 Detail-0.009
idences-0.009
iege-0.009
Token the
Token ID262
Feature activation+1.34e-02

Pos logit contributions
UTERS+0.006
inent+0.006
Interstitial+0.005
 Detail+0.005
iege+0.005
Neg logit contributions
SSL-0.006
fox-0.006
SPONSORED-0.006
 �-0.005
 ‎-0.005
Token people
Token ID661
Feature activation+2.59e-02

Pos logit contributions
UTERS+0.027
inent+0.025
Interstitial+0.024
 Detail+0.024
iege+0.024
Neg logit contributions
SSL-0.028
fox-0.028
SPONSORED-0.027
 �-0.025
 ‎-0.025
Token the
Token ID262
Feature activation-2.32e-02

Pos logit contributions
SSL+0.063
fox+0.062
SPONSORED+0.061
 �+0.056
 ‎+0.055
Neg logit contributions
UTERS-0.065
inent-0.060
 Detail-0.059
Interstitial-0.058
iege-0.058
Token National
Token ID2351
Feature activation+4.01e-02

Pos logit contributions
SSL+0.049
fox+0.049
SPONSORED+0.048
 �+0.044
 ‎+0.044
Neg logit contributions
UTERS-0.045
inent-0.042
 Detail-0.040
Interstitial-0.040
iege-0.040
Token Review
Token ID6602
Feature activation-1.11e-01

Pos logit contributions
UTERS+0.077
inent+0.071
Interstitial+0.069
idences+0.069
iege+0.068
Neg logit contributions
SSL-0.086
fox-0.085
SPONSORED-0.084
 ‎-0.078
 �-0.077
Token Institute
Token ID5136
Feature activation+2.52e-01

Pos logit contributions
SSL+0.245
fox+0.242
SPONSORED+0.239
 ‎+0.219
 �+0.219
Neg logit contributions
UTERS-0.208
inent-0.191
 Detail-0.186
Interstitial-0.184
iege-0.183
Token in
Token ID287
Feature activation-5.35e-02

Pos logit contributions
UTERS+0.528
inent+0.492
 Detail+0.481
Interstitial+0.477
iege+0.474
Neg logit contributions
SSL-0.493
fox-0.487
SPONSORED-0.480
 �-0.435
 ‎-0.435
Token Washington
Token ID2669
Feature activation-8.65e-02

Pos logit contributions
SSL+0.101
fox+0.100
SPONSORED+0.098
 ‎+0.090
 �+0.090
Neg logit contributions
UTERS-0.116
inent-0.108
Interstitial-0.106
iege-0.105
 Detail-0.104
Token on
Token ID319
Feature activation-4.30e-02

Pos logit contributions
SSL+0.171
fox+0.169
SPONSORED+0.167
 �+0.152
 ‎+0.151
Neg logit contributions
UTERS-0.179
inent-0.167
 Detail-0.163
Interstitial-0.163
iege-0.161
Token January
Token ID3269
Feature activation-2.21e-02

Pos logit contributions
SSL+0.074
fox+0.074
SPONSORED+0.073
 ‎+0.066
 �+0.066
Neg logit contributions
UTERS-0.100
inent-0.094
Interstitial-0.092
iege-0.091
 Detail-0.091
Token 20
Token ID1160
Feature activation-3.58e-02

Pos logit contributions
SSL+0.037
fox+0.037
SPONSORED+0.036
 ‎+0.033
 �+0.033
Neg logit contributions
UTERS-0.053
inent-0.050
Interstitial-0.049
idences-0.049
 Detail-0.049
Token,
Token ID11
Feature activation-4.88e-02

Pos logit contributions
fox+0.068
SSL+0.068
SPONSORED+0.067
 �+0.060
 ‎+0.060
Neg logit contributions
UTERS-0.077
inent-0.072
 Detail-0.071
Interstitial-0.070
iege-0.070
Token 2015
Token ID1853
Feature activation+1.21e-01

Pos logit contributions
SSL+0.123
fox+0.122
SPONSORED+0.121
 �+0.112
 ‎+0.112
Neg logit contributions
UTERS-0.075
inent-0.068
 Detail-0.066
Interstitial-0.065
iege-0.064
Token other
Token ID584
Feature activation-2.34e-02

Pos logit contributions
UTERS+0.106
inent+0.100
 Detail+0.098
Interstitial+0.096
iege+0.096
Neg logit contributions
SSL-0.085
fox-0.084
SPONSORED-0.082
 �-0.074
cens-0.073
Token in
Token ID287
Feature activation-4.61e-02

Pos logit contributions
SSL+0.047
fox+0.046
SPONSORED+0.045
 �+0.041
 ‎+0.041
Neg logit contributions
UTERS-0.048
inent-0.045
 Detail-0.044
Interstitial-0.043
iege-0.043
Token the
Token ID262
Feature activation-4.14e-02

Pos logit contributions
SSL+0.093
fox+0.092
SPONSORED+0.091
 �+0.083
 ‎+0.083
Neg logit contributions
UTERS-0.094
inent-0.087
Interstitial-0.085
 Detail-0.085
iege-0.084
Token Ham
Token ID4345
Feature activation-2.25e-02

Pos logit contributions
SSL+0.085
fox+0.084
SPONSORED+0.081
 �+0.076
 ‎+0.076
Neg logit contributions
UTERS-0.083
inent-0.077
Interstitial-0.075
 Detail-0.074
idences-0.074
Tokenpt
Token ID457
Feature activation-2.03e-01

Pos logit contributions
fox+0.039
SSL+0.039
SPONSORED+0.037
 ‎+0.034
 �+0.034
Neg logit contributions
UTERS-0.052
inent-0.049
 Detail-0.048
Interstitial-0.048
iege-0.048
Tokenons
Token ID684
Feature activation-3.77e-01

Pos logit contributions
SSL+0.188
fox+0.184
SPONSORED+0.176
 �+0.140
 ‎+0.139
Neg logit contributions
UTERS-0.636
inent-0.605
 Detail-0.598
Interstitial-0.592
iege-0.590
Token,
Token ID11
Feature activation-1.79e-02

Pos logit contributions
SSL+0.752
fox+0.743
SPONSORED+0.733
 �+0.663
 ‎+0.660
Neg logit contributions
UTERS-0.779
inent-0.724
 Detail-0.710
Interstitial-0.699
iege-0.695
Token and
Token ID290
Feature activation-5.44e-02

Pos logit contributions
SSL+0.034
fox+0.034
SPONSORED+0.033
 �+0.030
 ‎+0.030
Neg logit contributions
UTERS-0.039
inent-0.036
 Detail-0.035
Interstitial-0.035
iege-0.035
Token their
Token ID511
Feature activation-1.00e-01

Pos logit contributions
SSL+0.105
fox+0.104
SPONSORED+0.103
 ‎+0.093
 �+0.093
Neg logit contributions
UTERS-0.116
inent-0.108
 Detail-0.105
Interstitial-0.105
iege-0.104
Token children
Token ID1751
Feature activation-8.84e-03

Pos logit contributions
SSL+0.212
fox+0.210
SPONSORED+0.205
 ‎+0.191
 �+0.191
Neg logit contributions
UTERS-0.194
inent-0.179
 Detail-0.175
Interstitial-0.174
iege-0.172
Token attended
Token ID9141
Feature activation+6.07e-02

Pos logit contributions
SSL+0.018
fox+0.018
SPONSORED+0.017
 ‎+0.016
 �+0.016
Neg logit contributions
UTERS-0.018
inent-0.017
 Detail-0.016
Interstitial-0.016
iege-0.016
Token.
Token ID13
Feature activation+5.23e-02

Pos logit contributions
UTERS+0.101
inent+0.094
 Detail+0.092
Interstitial+0.091
iege+0.090
Neg logit contributions
SSL-0.102
fox-0.101
SPONSORED-0.100
 �-0.091
 ‎-0.090
Token Coord
Token ID22819
Feature activation+3.51e-01

Pos logit contributions
UTERS+0.111
inent+0.104
 Detail+0.100
Interstitial+0.100
iege+0.100
Neg logit contributions
SSL-0.101
fox-0.100
SPONSORED-0.099
 �-0.090
 ‎-0.090
Tokenination
Token ID1883
Feature activation+2.16e-01

Pos logit contributions
UTERS+0.485
inent+0.435
 Detail+0.420
Interstitial+0.409
iege+0.407
Neg logit contributions
SSL-0.940
fox-0.931
SPONSORED-0.922
 �-0.858
 ‎-0.854
Token on
Token ID319
Feature activation+7.36e-02

Pos logit contributions
UTERS+0.469
inent+0.438
 Detail+0.429
Interstitial+0.423
iege+0.421
Neg logit contributions
SSL-0.408
fox-0.404
SPONSORED-0.397
 �-0.358
 ‎-0.357
Token this
Token ID428
Feature activation+8.04e-02

Pos logit contributions
UTERS+0.152
inent+0.141
 Detail+0.137
Interstitial+0.136
iege+0.136
Neg logit contributions
SSL-0.147
fox-0.146
SPONSORED-0.144
 �-0.131
 ‎-0.131
Token front
Token ID2166
Feature activation-3.68e-01

Pos logit contributions
UTERS+0.169
inent+0.158
 Detail+0.153
idences+0.152
iege+0.151
Neg logit contributions
SSL-0.157
fox-0.156
SPONSORED-0.155
 ‎-0.141
 �-0.140
Token is
Token ID318
Feature activation-3.19e-02

Pos logit contributions
fox+0.653
SSL+0.649
SPONSORED+0.633
 ‎+0.575
 �+0.574
Neg logit contributions
UTERS-0.842
inent-0.782
 Detail-0.770
Interstitial-0.768
iege-0.758
Token not
Token ID407
Feature activation-2.05e-02

Pos logit contributions
SSL+0.065
fox+0.065
SPONSORED+0.064
 ‎+0.059
 �+0.059
Neg logit contributions
UTERS-0.064
inent-0.060
idences-0.058
iege-0.058
 Detail-0.058
Token a
Token ID257
Feature activation-2.33e-02

Pos logit contributions
SSL+0.040
fox+0.039
SPONSORED+0.039
 ‎+0.036
 �+0.035
Neg logit contributions
UTERS-0.043
inent-0.041
iege-0.039
 Detail-0.039
idences-0.039
Token small
Token ID1402
Feature activation+1.05e-01

Pos logit contributions
SSL+0.051
fox+0.050
SPONSORED+0.049
 ‎+0.046
 �+0.045
Neg logit contributions
UTERS-0.044
inent-0.041
Interstitial-0.040
iege-0.040
 Detail-0.039
Token thing
Token ID1517
Feature activation-3.83e-02

Pos logit contributions
UTERS+0.216
inent+0.199
Interstitial+0.193
idences+0.192
 Detail+0.192
Neg logit contributions
SSL-0.213
fox-0.211
SPONSORED-0.207
 ‎-0.191
 �-0.190
Token be
Token ID307
Feature activation-5.81e-02

Pos logit contributions
UTERS+0.228
inent+0.211
 Detail+0.206
Interstitial+0.203
iege+0.201
Neg logit contributions
SSL-0.253
fox-0.250
SPONSORED-0.247
 �-0.226
 ‎-0.225
Token taken
Token ID2077
Feature activation+1.00e-02

Pos logit contributions
SSL+0.110
fox+0.109
SPONSORED+0.107
 �+0.097
 ‎+0.097
Neg logit contributions
UTERS-0.127
inent-0.118
 Detail-0.115
iege-0.114
idences-0.114
Token seriously
Token ID6411
Feature activation-3.49e-02

Pos logit contributions
UTERS+0.022
inent+0.021
 Detail+0.020
Interstitial+0.020
iege+0.020
Neg logit contributions
SSL-0.019
fox-0.018
SPONSORED-0.018
 �-0.016
 ‎-0.016
Token by
Token ID416
Feature activation-9.12e-02

Pos logit contributions
SSL+0.074
fox+0.073
SPONSORED+0.072
 �+0.065
 ‎+0.065
Neg logit contributions
UTERS-0.068
inent-0.063
 Detail-0.062
Interstitial-0.061
iege-0.060
Token audi
Token ID40504
Feature activation+2.06e-01

Pos logit contributions
SSL+0.187
fox+0.184
SPONSORED+0.182
 ‎+0.168
 �+0.167
Neg logit contributions
UTERS-0.185
inent-0.170
 Detail-0.166
Interstitial-0.164
iege-0.164
Tokenoph
Token ID2522
Feature activation-3.68e-01

Pos logit contributions
UTERS+0.595
inent+0.566
 Detail+0.558
Interstitial+0.552
iege+0.550
Neg logit contributions
SSL-0.241
fox-0.237
SPONSORED-0.231
 �-0.193
 ‎-0.191
Tokeniles
Token ID2915
Feature activation-7.65e-02

Pos logit contributions
SSL+0.751
fox+0.749
SPONSORED+0.729
 ‎+0.675
 �+0.669
Neg logit contributions
UTERS-0.742
Interstitial-0.676
 Detail-0.676
inent-0.675
iege-0.654
Token?
Token ID30
Feature activation-1.64e-01

Pos logit contributions
SSL+0.160
fox+0.158
SPONSORED+0.156
 �+0.142
 ‎+0.141
Neg logit contributions
UTERS-0.150
inent-0.139
 Detail-0.136
Interstitial-0.134
iege-0.134
Token For
Token ID1114
Feature activation-6.31e-02

Pos logit contributions
SSL+0.345
fox+0.342
SPONSORED+0.337
 �+0.311
 ‎+0.310
Neg logit contributions
UTERS-0.323
inent-0.300
Interstitial-0.288
 Detail-0.288
iege-0.287
Token their
Token ID511
Feature activation-1.37e-01

Pos logit contributions
SSL+0.127
fox+0.125
SPONSORED+0.123
 ‎+0.113
 �+0.113
Neg logit contributions
UTERS-0.131
inent-0.121
 Detail-0.117
Interstitial-0.117
iege-0.116
Token imaging
Token ID19560
Feature activation-1.58e-01

Pos logit contributions
SSL+0.290
fox+0.286
SPONSORED+0.284
 �+0.261
 ‎+0.261
Neg logit contributions
UTERS-0.265
inent-0.243
 Detail-0.238
iege-0.235
idences-0.234
Tokenm
Token ID76
Feature activation-7.42e-02

Pos logit contributions
SSL+0.061
fox+0.061
SPONSORED+0.059
 ‎+0.054
 �+0.054
Neg logit contributions
UTERS-0.068
inent-0.062
Interstitial-0.062
 Detail-0.061
idences-0.060
Tokenose
Token ID577
Feature activation+6.45e-02

Pos logit contributions
SSL+0.152
fox+0.151
SPONSORED+0.145
 ‎+0.135
 �+0.135
Neg logit contributions
UTERS-0.150
inent-0.137
Interstitial-0.136
 Detail-0.135
idences-0.132
Token,
Token ID11
Feature activation-1.32e-01

Pos logit contributions
UTERS+0.133
inent+0.123
 Detail+0.121
Interstitial+0.119
iege+0.118
Neg logit contributions
SSL-0.129
fox-0.128
SPONSORED-0.126
 �-0.114
 ‎-0.114
Token an
Token ID281
Feature activation-3.90e-02

Pos logit contributions
SSL+0.267
fox+0.264
SPONSORED+0.260
 �+0.238
 ‎+0.237
Neg logit contributions
UTERS-0.270
inent-0.252
 Detail-0.245
Interstitial-0.243
iege-0.241
Token Ike
Token ID34880
Feature activation+4.69e-02

Pos logit contributions
SSL+0.073
fox+0.072
SPONSORED+0.071
 �+0.064
 ‎+0.064
Neg logit contributions
UTERS-0.085
inent-0.080
 Detail-0.078
Interstitial-0.078
idences-0.077
Tokena
Token ID64
Feature activation-4.27e-01

Pos logit contributions
UTERS+0.120
inent+0.113
Interstitial+0.111
 Detail+0.111
idences+0.109
Neg logit contributions
fox-0.072
SSL-0.071
SPONSORED-0.068
 ‎-0.061
 �-0.060
Token manager
Token ID4706
Feature activation-1.21e-01

Pos logit contributions
SSL+0.538
fox+0.521
SPONSORED+0.507
 ‎+0.451
 �+0.444
Neg logit contributions
UTERS-1.200
inent-1.141
Interstitial-1.125
idences-1.110
 Detail-1.109
Token.
Token ID13
Feature activation-8.05e-02

Pos logit contributions
SSL+0.253
fox+0.251
SPONSORED+0.247
 �+0.225
 ‎+0.225
Neg logit contributions
UTERS-0.239
inent-0.221
 Detail-0.216
Interstitial-0.214
iege-0.212
Token "
Token ID366
Feature activation-5.43e-02

Pos logit contributions
SSL+0.169
fox+0.167
SPONSORED+0.165
 �+0.151
 ‎+0.150
Neg logit contributions
UTERS-0.158
inent-0.147
 Detail-0.143
Interstitial-0.141
iege-0.140
TokenThe
Token ID464
Feature activation+4.62e-02

Pos logit contributions
SSL+0.119
fox+0.117
SPONSORED+0.116
 ‎+0.106
 �+0.105
Neg logit contributions
UTERS-0.103
inent-0.098
 Detail-0.093
idences-0.093
iege-0.093
Token use
Token ID779
Feature activation-1.11e-01

Pos logit contributions
UTERS+0.092
inent+0.085
Interstitial+0.083
 Detail+0.083
iege+0.082
Neg logit contributions
SSL-0.096
fox-0.095
SPONSORED-0.093
 ‎-0.086
 �-0.086
Token have
Token ID423
Feature activation-2.88e-02

Pos logit contributions
UTERS+0.130
inent+0.120
 Detail+0.117
Interstitial+0.116
idences+0.114
Neg logit contributions
SSL-0.128
fox-0.127
SPONSORED-0.124
 ‎-0.115
 �-0.114
Token done
Token ID1760
Feature activation+4.28e-03

Pos logit contributions
SSL+0.052
fox+0.052
SPONSORED+0.051
 �+0.046
 ‎+0.045
Neg logit contributions
UTERS-0.065
inent-0.060
 Detail-0.059
Interstitial-0.058
iege-0.058
Token a
Token ID257
Feature activation-1.87e-02

Pos logit contributions
UTERS+0.009
inent+0.008
 Detail+0.008
Interstitial+0.008
iege+0.008
Neg logit contributions
SSL-0.008
fox-0.008
SPONSORED-0.008
 �-0.007
 ‎-0.007
Token bit
Token ID1643
Feature activation-1.31e-01

Pos logit contributions
SSL+0.044
fox+0.044
SPONSORED+0.043
 �+0.040
 ‎+0.040
Neg logit contributions
UTERS-0.031
inent-0.029
 Detail-0.028
Interstitial-0.028
iege-0.027
Token more
Token ID517
Feature activation+1.18e-03

Pos logit contributions
SSL+0.238
fox+0.236
SPONSORED+0.231
 �+0.209
 ‎+0.208
Neg logit contributions
UTERS-0.292
inent-0.274
 Detail-0.268
Interstitial-0.265
idences-0.264
Token clearly
Token ID4084
Feature activation-3.59e-01

Pos logit contributions
UTERS+0.003
inent+0.002
 Detail+0.002
Interstitial+0.002
idences+0.002
Neg logit contributions
SSL-0.002
fox-0.002
SPONSORED-0.002
 �-0.002
 ‎-0.002
Token.
Token ID13
Feature activation+6.48e-02

Pos logit contributions
SSL+0.699
fox+0.696
SPONSORED+0.682
 ‎+0.621
 �+0.620
Neg logit contributions
UTERS-0.753
inent-0.701
 Detail-0.688
Interstitial-0.680
idences-0.674
Token
Token ID198
Feature activation-3.88e-03

Pos logit contributions
UTERS+0.146
inent+0.136
 Detail+0.134
Interstitial+0.132
iege+0.131
Neg logit contributions
SSL-0.118
fox-0.116
SPONSORED-0.114
 �-0.102
 ‎-0.102
Token
Token ID198
Feature activation-2.70e-02

Pos logit contributions
SSL+0.006
fox+0.006
SPONSORED+0.005
 ‎+0.005
 �+0.005
Neg logit contributions
UTERS-0.010
inent-0.010
 Detail-0.009
Interstitial-0.009
iege-0.009
TokenIt
Token ID1026
Feature activation+4.69e-02

Pos logit contributions
SSL+0.060
fox+0.059
SPONSORED+0.058
 ‎+0.053
 �+0.053
Neg logit contributions
UTERS-0.050
inent-0.047
 Detail-0.046
idences-0.045
iege-0.045
Token's
Token ID338
Feature activation+7.09e-02

Pos logit contributions
UTERS+0.106
inent+0.099
 Detail+0.097
Interstitial+0.096
iege+0.096
Neg logit contributions
SSL-0.084
fox-0.083
SPONSORED-0.082
 �-0.073
 ‎-0.073