TOP ACTIVATIONS
MAX = 4.743

ported License . <|endoftext|> Image copyright AP Image caption Peace talks
million years . <|endoftext|> Image copyright AFP The Bank
. <|endoftext|> Image copyright Deadline Police have
. <|endoftext|> Image copyright publicity Image caption The Greeks
Serve hot ! <|endoftext|> Image copyright ESA Image caption Go ce
media reported . <|endoftext|> Image caption Some talked of " b
ren owned perf umer Fr é d é ric Mal le
mentioned . No word if the Str and Craft
a bunch of paint and spread it out . The cardboard
! Ichigo th umped his abdomen a few times
only his trousers , and spread them near the sunk en
t weet / <|endoftext|> Story highlights Secretary of Defense Chuck Hag
_ full v ) { // Time component const float TA
the Nexus 6 . No word on if there will be
Louisiana State University . How common is a Ph . D
Last week , he comm ended Trump for conducting military strikes
{ let prev : Board = self . prev _ state
room Come along , my dear , come
born Farmer on " Fr ances Farmer Will Have Her Revenge
or c ra ppy .

MIN ACTIVATIONS
MIN = -4.327

than some candidates give them credit for , says Mor ley
not clear what long - term good the Trump peace initiative
, so I give him credit for that . It 's
R . E . M .' s lead singer Michael St
t even remember when til ap ia came out .
with a new short - term disability plan .
with the same short - term disability proposal the Conservatives made
. <|endoftext|> One day after the PM appeared to
, it is fair to assume that there is some degree
it after ." ' Common threat '
work for the long - term movement , said
're changing all of that .' That 's up ending 10
using only 5 total portal plac ements ( 29 )
claiming at least short - term results ; the street -
taken out a long - term lease . Gl ü ck
cross fire . Advertisement Advertisement
not right there ," Ms Ag ost ino said .
the world is being held hostage by 3 DES .
let the future be held hostage by the failures of the
politics has become that one assumes that a politician who defends

INTERVAL 2.476 - 4.743
CONTAINS 0.189%

Credit Reporting Act ( FC RA ), 15 U . S
Hurricane Matthew in Kingston , Jamaica . Credit : AP Cuban
etry Arts in Atlanta , Georgia .[ 7 ]
ap . add _ argument (" - i ", " --
Officials said May ra Martinez was brought to the

INTERVAL 0.208 - 2.476
CONTAINS 36.127%

population are Catholic , while Muslims form a large minority in
keep the basic software engineering from being the limiting factor .
IL ED Israel s third policy is
the amb ience and wildlife typically found in the associated area
are driving . Proceed at your own risk . I would

INTERVAL -2.059 - 0.208
CONTAINS 63.212%

P ORTS B 6 HAS BE EN NOT IFIED . B
. They did not . Instead , Republicans spent
can install server less framework with , n pm
easy because the camera has an exposure z ebra with adjustable
"... is that ?" Legend finished the question .

INTERVAL -4.327 - -2.059
CONTAINS 0.473%

' ag ression de t out cit oy en Imp é
doors of a dr ab brick building in D ae je
.' s crude oil storage tanks at their tank farm in
the glove box . Make sure the passenger seat is moved
up ended by a re class ification of assets from firms
Tokenported
Token ID9213
Feature activation-9.94e-01

Pos logit contributions
resa+0.275
lot+0.259
iesta+0.252
yrinth+0.251
lace+0.249
Neg logit contributions
 indu-0.524
 ruining-0.471
 popping-0.464
 scient-0.458
 intellig-0.437
Token License
Token ID13789
Feature activation-3.41e-01

Pos logit contributions
resa+0.986
lot+0.953
iesta+0.939
yrinth+0.935
lace+0.932
Neg logit contributions
 indu-0.615
 ruining-0.509
 popping-0.496
 scient-0.482
 intellig-0.440
Token.
Token ID13
Feature activation-4.97e-01

Pos logit contributions
resa+0.223
lot+0.212
iesta+0.209
yrinth+0.207
lace+0.206
Neg logit contributions
 indu-0.325
 ruining-0.289
 popping-0.285
 scient-0.280
 intellig-0.265
Token<|endoftext|>
Token ID50256
Feature activation-3.77e-01

Pos logit contributions
resa+0.370
lot+0.354
iesta+0.347
yrinth+0.347
lace+0.345
Neg logit contributions
 indu-0.429
 ruining-0.377
 popping-0.371
 scient-0.364
 intellig-0.342
TokenImage
Token ID5159
Feature activation-2.86e-01

Pos logit contributions
resa+0.249
lot+0.237
iesta+0.232
yrinth+0.231
lace+0.229
Neg logit contributions
 indu-0.357
 ruining-0.318
 popping-0.313
 scient-0.308
 intellig-0.292
Token copyright
Token ID6634
Feature activation+4.74e+00

Pos logit contributions
resa+0.203
lot+0.194
iesta+0.190
yrinth+0.189
lace+0.188
Neg logit contributions
 indu-0.257
 ruining-0.227
 popping-0.223
 scient-0.219
 intellig-0.207
Token AP
Token ID3486
Feature activation+1.60e+00

Pos logit contributions
 indu+3.626
 ruining+3.134
 popping+3.090
 scient+3.079
 intellig+2.857
Neg logit contributions
resa-3.858
lot-3.752
yrinth-3.728
iesta-3.680
lace-3.636
Token Image
Token ID7412
Feature activation-1.02e+00

Pos logit contributions
 indu+1.494
 ruining+1.330
 popping+1.306
 scient+1.291
 intellig+1.218
Neg logit contributions
resa-1.070
lot-1.017
iesta-1.000
yrinth-0.999
lace-0.989
Token caption
Token ID8305
Feature activation+3.66e+00

Pos logit contributions
resa+0.689
lot+0.657
iesta+0.642
yrinth+0.641
lace+0.636
Neg logit contributions
 indu-0.947
 ruining-0.840
 popping-0.827
 scient-0.812
 intellig-0.769
Token Peace
Token ID12689
Feature activation+7.42e-01

Pos logit contributions
 indu+2.848
 ruining+2.499
 popping+2.443
 scient+2.426
 Fold+2.276
Neg logit contributions
resa-2.904
lot-2.823
yrinth-2.810
iesta-2.757
lace-2.742
Token talks
Token ID6130
Feature activation+1.12e-01

Pos logit contributions
 indu+0.678
 ruining+0.600
 popping+0.592
 scient+0.579
 intellig+0.549
Neg logit contributions
resa-0.513
lot-0.491
iesta-0.480
yrinth-0.480
lace-0.474
Token million
Token ID1510
Feature activation-7.34e-01

Pos logit contributions
resa+0.478
lot+0.457
iesta+0.448
yrinth+0.445
lace+0.442
Neg logit contributions
 indu-0.588
 ruining-0.517
 popping-0.508
 scient-0.499
 intellig-0.471
Token years
Token ID812
Feature activation-8.85e-01

Pos logit contributions
resa+0.498
lot+0.474
yrinth+0.464
iesta+0.463
lace+0.460
Neg logit contributions
 indu-0.682
 ruining-0.605
 popping-0.598
 scient-0.587
 intellig-0.556
Token.
Token ID13
Feature activation-4.31e-01

Pos logit contributions
resa+0.581
lot+0.552
iesta+0.540
yrinth+0.539
lace+0.535
Neg logit contributions
 indu-0.842
 ruining-0.750
 popping-0.739
 scient-0.726
 intellig-0.688
Token<|endoftext|>
Token ID50256
Feature activation-1.76e-01

Pos logit contributions
resa+0.315
lot+0.301
iesta+0.295
yrinth+0.294
lace+0.293
Neg logit contributions
 indu-0.378
 ruining-0.332
 popping-0.327
 scient-0.321
 intellig-0.303
TokenImage
Token ID5159
Feature activation-3.43e-01

Pos logit contributions
resa+0.116
lot+0.110
iesta+0.108
yrinth+0.108
lace+0.107
Neg logit contributions
 indu-0.166
 ruining-0.148
 popping-0.145
 scient-0.143
 intellig-0.135
Token copyright
Token ID6634
Feature activation+4.65e+00

Pos logit contributions
resa+0.244
lot+0.232
iesta+0.228
yrinth+0.227
lace+0.225
Neg logit contributions
 indu-0.307
 ruining-0.271
 popping-0.266
 scient-0.262
 intellig-0.247
Token AFP
Token ID8916
Feature activation+1.05e+00

Pos logit contributions
 indu+3.548
 ruining+3.066
 popping+3.023
 scient+3.013
 intellig+2.794
Neg logit contributions
resa-3.792
lot-3.688
yrinth-3.668
iesta-3.620
lace-3.575
Token
Token ID198
Feature activation+4.53e-01

Pos logit contributions
 indu+1.002
 ruining+0.892
 popping+0.877
 scient+0.864
 intellig+0.817
Neg logit contributions
resa-0.689
lot-0.654
iesta-0.641
yrinth-0.641
lace-0.635
Token
Token ID198
Feature activation+5.35e-01

Pos logit contributions
 indu+0.419
 ruining+0.378
 popping+0.372
 scient+0.366
 intellig+0.350
Neg logit contributions
resa-0.300
yrinth-0.287
lot-0.281
iesta-0.278
lace-0.273
TokenThe
Token ID464
Feature activation-2.03e-01

Pos logit contributions
 indu+0.502
 ruining+0.449
 popping+0.441
 scient+0.433
 intellig+0.411
Neg logit contributions
resa-0.349
yrinth-0.330
lot-0.330
iesta-0.327
lace-0.322
Token Bank
Token ID5018
Feature activation-1.33e+00

Pos logit contributions
resa+0.163
lot+0.156
iesta+0.153
yrinth+0.153
lace+0.152
Neg logit contributions
 indu-0.164
 ruining-0.142
 popping-0.140
 scient-0.137
 intellig-0.128
Token.
Token ID13
Feature activation+6.40e-02

Pos logit contributions
 indu+0.023
 ruining+0.021
 popping+0.020
 scient+0.020
 intellig+0.019
Neg logit contributions
resa-0.018
lot-0.018
iesta-0.017
yrinth-0.017
lace-0.017
Token
Token ID447
Feature activation+2.63e-01

Pos logit contributions
 indu+0.057
 ruining+0.050
 popping+0.050
 scient+0.049
 intellig+0.046
Neg logit contributions
resa-0.046
lot-0.044
iesta-0.043
yrinth-0.043
lace-0.042
Token
Token ID251
Feature activation-1.78e-01

Pos logit contributions
 indu+0.224
 ruining+0.197
 popping+0.194
 scient+0.189
 intellig+0.179
Neg logit contributions
resa-0.198
lot-0.190
iesta-0.186
yrinth-0.186
lace-0.184
Token<|endoftext|>
Token ID50256
Feature activation-3.38e-01

Pos logit contributions
resa+0.128
lot+0.123
iesta+0.120
lace+0.119
yrinth+0.119
Neg logit contributions
 indu-0.158
 ruining-0.139
 popping-0.137
 scient-0.135
 intellig-0.127
TokenImage
Token ID5159
Feature activation-3.94e-01

Pos logit contributions
resa+0.223
lot+0.212
iesta+0.207
yrinth+0.207
lace+0.205
Neg logit contributions
 indu-0.320
 ruining-0.285
 popping-0.281
 scient-0.276
 intellig-0.261
Token copyright
Token ID6634
Feature activation+4.64e+00

Pos logit contributions
resa+0.280
lot+0.267
iesta+0.261
yrinth+0.260
lace+0.258
Neg logit contributions
 indu-0.354
 ruining-0.313
 popping-0.307
 scient-0.302
 intellig-0.285
Token Deadline
Token ID35954
Feature activation+5.09e-01

Pos logit contributions
 indu+3.558
 ruining+3.077
 popping+3.032
 scient+3.019
 intellig+2.802
Neg logit contributions
resa-3.768
lot-3.658
yrinth-3.635
iesta-3.592
lace-3.549
Token
Token ID198
Feature activation+1.16e-01

Pos logit contributions
 indu+0.479
 ruining+0.425
 popping+0.419
 scient+0.412
 intellig+0.390
Neg logit contributions
resa-0.340
lot-0.323
iesta-0.316
yrinth-0.315
lace-0.313
Token
Token ID198
Feature activation+2.35e-01

Pos logit contributions
 indu+0.109
 ruining+0.098
 popping+0.097
 scient+0.095
 intellig+0.091
Neg logit contributions
resa-0.075
yrinth-0.071
lot-0.070
iesta-0.070
lace-0.068
TokenPolice
Token ID9039
Feature activation-2.29e-01

Pos logit contributions
 indu+0.225
 ruining+0.201
 popping+0.198
 scient+0.195
 intellig+0.185
Neg logit contributions
resa-0.149
lot-0.141
yrinth-0.140
iesta-0.139
lace-0.137
Token have
Token ID423
Feature activation+2.38e-01

Pos logit contributions
resa+0.170
lot+0.161
iesta+0.157
yrinth+0.157
lace+0.156
Neg logit contributions
 indu-0.199
 ruining-0.174
 popping-0.171
 scient-0.168
 intellig-0.159
Token.
Token ID13
Feature activation-7.49e-01

Pos logit contributions
resa+0.466
lot+0.445
iesta+0.433
yrinth+0.432
lace+0.430
Neg logit contributions
 indu-0.666
 ruining-0.591
 popping-0.582
 scient-0.573
 intellig-0.541
Token
Token ID447
Feature activation+1.93e-01

Pos logit contributions
resa+0.478
lot+0.455
iesta+0.443
yrinth+0.441
lace+0.439
Neg logit contributions
 indu-0.728
 ruining-0.649
 popping-0.639
 scient-0.628
 intellig-0.596
Token
Token ID251
Feature activation-1.77e-01

Pos logit contributions
 indu+0.158
 ruining+0.139
 popping+0.137
 scient+0.134
 intellig+0.126
Neg logit contributions
resa-0.150
lot-0.143
yrinth-0.141
iesta-0.141
lace-0.140
Token<|endoftext|>
Token ID50256
Feature activation-5.66e-01

Pos logit contributions
resa+0.116
lot+0.110
iesta+0.108
yrinth+0.107
lace+0.107
Neg logit contributions
 indu-0.168
 ruining-0.150
 popping-0.147
 scient-0.145
 intellig-0.137
TokenImage
Token ID5159
Feature activation-3.72e-01

Pos logit contributions
resa+0.373
lot+0.355
iesta+0.347
yrinth+0.346
lace+0.344
Neg logit contributions
 indu-0.537
 ruining-0.478
 popping-0.470
 scient-0.462
 intellig-0.438
Token copyright
Token ID6634
Feature activation+4.62e+00

Pos logit contributions
resa+0.265
lot+0.252
iesta+0.247
yrinth+0.246
lace+0.244
Neg logit contributions
 indu-0.333
 ruining-0.295
 popping-0.290
 scient-0.285
 intellig-0.269
Token publicity
Token ID19403
Feature activation-7.13e-01

Pos logit contributions
 indu+3.530
 ruining+3.051
 popping+3.007
 scient+2.996
 intellig+2.780
Neg logit contributions
resa-3.760
lot-3.655
yrinth-3.635
iesta-3.589
lace-3.545
Token Image
Token ID7412
Feature activation-1.36e+00

Pos logit contributions
resa+0.474
lot+0.452
iesta+0.439
yrinth+0.438
lace+0.436
Neg logit contributions
 indu-0.672
 ruining-0.598
 popping-0.589
 scient-0.578
 intellig-0.549
Token caption
Token ID8305
Feature activation+3.44e+00

Pos logit contributions
resa+0.920
lot+0.876
iesta+0.856
yrinth+0.853
lace+0.848
Neg logit contributions
 indu-1.276
 ruining-1.131
 popping-1.114
 scient-1.095
 intellig-1.036
Token The
Token ID383
Feature activation+5.76e-02

Pos logit contributions
 indu+2.761
 ruining+2.428
 popping+2.381
 scient+2.357
 Fold+2.197
Neg logit contributions
resa-2.681
lot-2.594
yrinth-2.579
iesta-2.544
lace-2.522
Token Greeks
Token ID25059
Feature activation+4.89e-01

Pos logit contributions
 indu+0.046
 ruining+0.040
 popping+0.039
 scient+0.038
 intellig+0.036
Neg logit contributions
resa-0.047
lot-0.045
iesta-0.044
yrinth-0.044
lace-0.044
Token Serve
Token ID35557
Feature activation+1.03e+00

Pos logit contributions
 indu+0.043
 ruining+0.037
 popping+0.036
 scient+0.035
 intellig+0.033
Neg logit contributions
resa-0.050
lot-0.048
yrinth-0.047
iesta-0.047
lace-0.047
Token hot
Token ID3024
Feature activation-1.02e-01

Pos logit contributions
 indu+0.638
 ruining+0.533
 popping+0.529
 scient+0.501
 intellig+0.466
Neg logit contributions
resa-1.016
yrinth-0.986
lot-0.981
iesta-0.971
lace-0.964
Token!
Token ID0
Feature activation+2.83e-01

Pos logit contributions
resa+0.069
lot+0.066
yrinth+0.065
iesta+0.064
lace+0.064
Neg logit contributions
 indu-0.094
 ruining-0.084
 popping-0.083
 scient-0.081
 intellig-0.077
Token<|endoftext|>
Token ID50256
Feature activation-3.07e-02

Pos logit contributions
 indu+0.267
 ruining+0.237
 popping+0.234
 scient+0.230
 intellig+0.218
Neg logit contributions
resa-0.187
lot-0.178
iesta-0.174
yrinth-0.174
lace-0.173
TokenImage
Token ID5159
Feature activation-3.31e-01

Pos logit contributions
resa+0.020
lot+0.019
iesta+0.019
yrinth+0.019
lace+0.019
Neg logit contributions
 indu-0.029
 ruining-0.026
 popping-0.025
 scient-0.025
 intellig-0.024
Token copyright
Token ID6634
Feature activation+4.56e+00

Pos logit contributions
resa+0.236
lot+0.225
iesta+0.220
yrinth+0.219
lace+0.218
Neg logit contributions
 indu-0.296
 ruining-0.261
 popping-0.257
 scient-0.252
 intellig-0.238
Token ESA
Token ID42212
Feature activation+1.07e-01

Pos logit contributions
 indu+3.482
 ruining+3.009
 popping+2.967
 scient+2.954
 intellig+2.739
Neg logit contributions
resa-3.720
lot-3.615
yrinth-3.593
iesta-3.548
lace-3.504
Token Image
Token ID7412
Feature activation-1.27e+00

Pos logit contributions
 indu+0.103
 ruining+0.092
 popping+0.091
 scient+0.089
 intellig+0.085
Neg logit contributions
resa-0.069
lot-0.066
iesta-0.064
yrinth-0.064
lace-0.063
Token caption
Token ID8305
Feature activation+3.41e+00

Pos logit contributions
resa+0.849
lot+0.807
iesta+0.790
yrinth+0.784
lace+0.781
Neg logit contributions
 indu-1.195
 ruining-1.060
 popping-1.043
 scient-1.026
 intellig-0.971
Token Go
Token ID1514
Feature activation+4.36e-01

Pos logit contributions
 indu+2.555
 ruining+2.238
 popping+2.184
 scient+2.177
 Fold+2.036
Neg logit contributions
resa-2.821
lot-2.726
yrinth-2.709
iesta-2.674
lace-2.653
Tokence
Token ID344
Feature activation+1.74e+00

Pos logit contributions
 indu+0.402
 ruining+0.355
 popping+0.348
 scient+0.343
 intellig+0.323
Neg logit contributions
resa-0.303
lot-0.288
iesta-0.282
yrinth-0.280
lace-0.277
Token media
Token ID2056
Feature activation+9.44e-02

Pos logit contributions
 indu+0.145
 ruining+0.126
 popping+0.123
 scient+0.121
 disse+0.113
Neg logit contributions
resa-0.135
lot-0.128
iesta-0.126
yrinth-0.126
lace-0.125
Token reported
Token ID2098
Feature activation+3.70e-01

Pos logit contributions
 indu+0.073
 ruining+0.063
 popping+0.062
 scient+0.060
 intellig+0.056
Neg logit contributions
resa-0.078
lot-0.075
iesta-0.074
yrinth-0.073
lace-0.073
Token.
Token ID13
Feature activation+2.65e-01

Pos logit contributions
 indu+0.361
 ruining+0.323
 popping+0.318
 scient+0.313
 intellig+0.297
Neg logit contributions
resa-0.234
lot-0.222
iesta-0.217
yrinth-0.217
lace-0.215
Token<|endoftext|>
Token ID50256
Feature activation+3.41e-01

Pos logit contributions
 indu+0.234
 ruining+0.206
 popping+0.202
 scient+0.199
 intellig+0.187
Neg logit contributions
resa-0.193
lot-0.184
iesta-0.180
yrinth-0.179
lace-0.179
TokenImage
Token ID5159
Feature activation-2.47e-01

Pos logit contributions
 indu+0.322
 ruining+0.287
 popping+0.282
 scient+0.277
 intellig+0.263
Neg logit contributions
resa-0.224
lot-0.212
yrinth-0.208
iesta-0.208
lace-0.206
Token caption
Token ID8305
Feature activation+4.41e+00

Pos logit contributions
resa+0.176
lot+0.167
iesta+0.164
yrinth+0.163
lace+0.162
Neg logit contributions
 indu-0.221
 ruining-0.195
 popping-0.192
 scient-0.188
 intellig-0.178
Token Some
Token ID2773
Feature activation+1.03e+00

Pos logit contributions
 indu+3.498
 ruining+3.082
 popping+3.013
 scient+2.998
 Fold+2.814
Neg logit contributions
resa-3.411
lot-3.318
yrinth-3.306
iesta-3.250
lace-3.222
Token talked
Token ID6619
Feature activation+5.86e-01

Pos logit contributions
 indu+0.859
 ruining+0.750
 popping+0.737
 scient+0.723
 intellig+0.679
Neg logit contributions
resa-0.803
lot-0.770
iesta-0.755
yrinth-0.753
lace-0.749
Token of
Token ID286
Feature activation-6.05e-01

Pos logit contributions
 indu+0.521
 ruining+0.458
 popping+0.449
 scient+0.441
 intellig+0.415
Neg logit contributions
resa-0.422
lot-0.404
iesta-0.394
yrinth-0.392
lace-0.391
Token "
Token ID366
Feature activation+4.60e-01

Pos logit contributions
resa+0.531
lot+0.509
iesta+0.499
yrinth+0.496
lace+0.496
Neg logit contributions
 indu-0.443
 ruining-0.371
 popping-0.364
 scient-0.358
 obser-0.336
Tokenb
Token ID65
Feature activation+4.10e-01

Pos logit contributions
 indu+0.418
 ruining+0.370
 popping+0.364
 scient+0.357
 intellig+0.338
Neg logit contributions
resa-0.321
lot-0.306
iesta-0.300
yrinth-0.299
lace-0.297
Tokenren
Token ID918
Feature activation-2.89e-01

Pos logit contributions
 indu+0.189
 ruining+0.169
 popping+0.167
 scient+0.163
 intellig+0.155
Neg logit contributions
resa-0.125
lot-0.118
iesta-0.117
yrinth-0.116
lace-0.114
Tokenowned
Token ID11990
Feature activation+1.27e+00

Pos logit contributions
resa+0.195
lot+0.186
iesta+0.182
yrinth+0.182
lace+0.180
Neg logit contributions
 indu-0.270
 ruining-0.239
 popping-0.235
 scient-0.231
 intellig-0.219
Token perf
Token ID23035
Feature activation+1.64e-01

Pos logit contributions
 indu+0.932
 ruining+0.798
 popping+0.783
 scient+0.765
 intellig+0.711
Neg logit contributions
resa-1.105
lot-1.065
yrinth-1.046
iesta-1.046
lace-1.038
Tokenumer
Token ID6975
Feature activation+8.31e-01

Pos logit contributions
 indu+0.168
 ruining+0.150
 popping+0.149
 scient+0.146
 intellig+0.139
Neg logit contributions
resa-0.095
lot-0.090
yrinth-0.088
iesta-0.088
lace-0.087
Token Fr
Token ID1305
Feature activation-9.64e-01

Pos logit contributions
 indu+0.715
 ruining+0.628
 popping+0.620
 scient+0.607
 intellig+0.573
Neg logit contributions
resa-0.617
lot-0.591
yrinth-0.582
iesta-0.582
lace-0.576
Tokené
Token ID2634
Feature activation+4.31e+00

Pos logit contributions
resa+0.623
lot+0.595
iesta+0.574
yrinth+0.569
lace+0.564
Neg logit contributions
 indu-0.941
 ruining-0.833
 popping-0.820
 scient-0.803
 intellig-0.766
Tokend
Token ID67
Feature activation+3.72e-01

Pos logit contributions
 indu+3.416
 ruining+2.982
 popping+2.909
 scient+2.858
 intellig+2.662
Neg logit contributions
resa-3.436
yrinth-3.250
lot-3.242
iesta-3.232
lace-3.192
Tokené
Token ID2634
Feature activation+2.95e+00

Pos logit contributions
 indu+0.382
 ruining+0.342
 popping+0.338
 scient+0.332
 intellig+0.316
Neg logit contributions
resa-0.218
lot-0.206
iesta-0.201
yrinth-0.200
lace-0.199
Tokenric
Token ID1173
Feature activation+4.46e-01

Pos logit contributions
 indu+3.343
 ruining+3.046
 popping+3.019
 scient+2.968
 intellig+2.837
Neg logit contributions
resa-1.362
yrinth-1.242
lot-1.232
iesta-1.231
lace-1.189
Token Mal
Token ID4434
Feature activation-1.46e-01

Pos logit contributions
 indu+0.372
 ruining+0.326
 popping+0.320
 scient+0.314
 intellig+0.295
Neg logit contributions
resa-0.344
lot-0.328
yrinth-0.324
iesta-0.323
lace-0.320
Tokenle
Token ID293
Feature activation+9.61e-02

Pos logit contributions
resa+0.096
lot+0.091
iesta+0.089
yrinth+0.089
lace+0.088
Neg logit contributions
 indu-0.139
 ruining-0.123
 popping-0.122
 scient-0.119
 intellig-0.113
Token mentioned
Token ID4750
Feature activation+2.08e+00

Pos logit contributions
resa+0.883
lot+0.842
iesta+0.815
yrinth+0.813
lace+0.807
Neg logit contributions
 indu-1.051
 ruining-0.928
 popping-0.907
 scient-0.899
 proble-0.839
Token.
Token ID13
Feature activation+2.08e-02

Pos logit contributions
 indu+1.852
 ruining+1.640
 popping+1.619
 scient+1.575
 intellig+1.494
Neg logit contributions
resa-1.489
lot-1.413
yrinth-1.396
iesta-1.393
lace-1.382
Token
Token ID198
Feature activation-4.49e-01

Pos logit contributions
 indu+0.018
 ruining+0.016
 popping+0.016
 scient+0.015
 intellig+0.014
Neg logit contributions
resa-0.015
lot-0.015
iesta-0.015
lace-0.014
yrinth-0.014
Token
Token ID198
Feature activation-1.74e-01

Pos logit contributions
resa+0.279
lot+0.264
yrinth+0.258
iesta+0.258
lace+0.255
Neg logit contributions
 indu-0.442
 ruining-0.395
 popping-0.390
 scient-0.383
 intellig-0.364
TokenNo
Token ID2949
Feature activation-4.43e-01

Pos logit contributions
resa+0.120
lot+0.115
iesta+0.112
yrinth+0.111
lace+0.111
Neg logit contributions
 indu-0.160
 ruining-0.142
 popping-0.140
 scient-0.137
 intellig-0.130
Token word
Token ID1573
Feature activation+4.22e+00

Pos logit contributions
resa+0.368
lot+0.353
iesta+0.345
yrinth+0.344
lace+0.342
Neg logit contributions
 indu-0.347
 ruining-0.299
 popping-0.293
 scient-0.288
 intellig-0.268
Token if
Token ID611
Feature activation-1.19e-01

Pos logit contributions
 indu+3.056
 popping+2.656
 ruining+2.651
 scient+2.514
 intellig+2.366
Neg logit contributions
resa-3.644
yrinth-3.499
lot-3.490
iesta-3.475
lace-3.462
Token the
Token ID262
Feature activation-2.91e-02

Pos logit contributions
resa+0.102
lot+0.098
iesta+0.096
yrinth+0.096
lace+0.095
Neg logit contributions
 indu-0.090
 ruining-0.077
 popping-0.075
 scient-0.074
 intellig-0.069
Token Str
Token ID4285
Feature activation+1.98e-02

Pos logit contributions
resa+0.026
lot+0.024
iesta+0.024
yrinth+0.024
lace+0.024
Neg logit contributions
 indu-0.021
 ruining-0.018
 popping-0.018
 scient-0.018
 intellig-0.016
Tokenand
Token ID392
Feature activation-3.10e-01

Pos logit contributions
 indu+0.018
 ruining+0.016
 popping+0.016
 scient+0.016
 intellig+0.015
Neg logit contributions
resa-0.013
lot-0.013
yrinth-0.013
iesta-0.013
lace-0.012
Token Craft
Token ID15745
Feature activation+2.64e-01

Pos logit contributions
resa+0.241
lot+0.231
iesta+0.226
yrinth+0.226
lace+0.225
Neg logit contributions
 indu-0.256
 ruining-0.224
 popping-0.220
 scient-0.216
 intellig-0.202
Token a
Token ID257
Feature activation+5.25e-03

Pos logit contributions
 indu+0.387
 ruining+0.331
 popping+0.325
 scient+0.317
 intellig+0.295
Neg logit contributions
resa-0.454
lot-0.437
iesta-0.430
yrinth-0.429
lace-0.427
Token bunch
Token ID7684
Feature activation+4.20e-01

Pos logit contributions
 indu+0.004
 ruining+0.003
 popping+0.003
 scient+0.003
 intellig+0.003
Neg logit contributions
resa-0.004
lot-0.004
iesta-0.004
lace-0.004
yrinth-0.004
Token of
Token ID286
Feature activation-2.67e-01

Pos logit contributions
 indu+0.350
 ruining+0.305
 popping+0.300
 scient+0.294
 intellig+0.276
Neg logit contributions
resa-0.327
lot-0.313
iesta-0.307
yrinth-0.307
lace-0.304
Token paint
Token ID7521
Feature activation-1.26e-01

Pos logit contributions
resa+0.235
lot+0.227
iesta+0.222
lace+0.222
yrinth+0.222
Neg logit contributions
 indu-0.194
 ruining-0.165
 popping-0.161
 scient-0.158
 intellig-0.147
Token and
Token ID290
Feature activation+2.47e-01

Pos logit contributions
resa+0.094
lot+0.091
lace+0.088
iesta+0.088
yrinth+0.087
Neg logit contributions
 indu-0.108
 ruining-0.094
 popping-0.093
 scient-0.092
 obser-0.086
Token spread
Token ID4104
Feature activation+4.20e+00

Pos logit contributions
 indu+0.193
 ruining+0.166
 popping+0.162
 scient+0.161
 intellig+0.149
Neg logit contributions
resa-0.203
lot-0.195
iesta-0.190
yrinth-0.190
lace-0.190
Token it
Token ID340
Feature activation+3.65e-01

Pos logit contributions
 indu+3.015
 ruining+2.601
 popping+2.581
 scient+2.464
 intellig+2.328
Neg logit contributions
resa-3.706
lot-3.557
yrinth-3.542
iesta-3.512
lace-3.475
Token out
Token ID503
Feature activation-5.42e-01

Pos logit contributions
 indu+0.289
 ruining+0.249
 popping+0.243
 scient+0.240
 obser+0.223
Neg logit contributions
resa-0.298
lot-0.287
iesta-0.281
lace-0.279
yrinth-0.279
Token.
Token ID13
Feature activation+4.68e-01

Pos logit contributions
resa+0.410
lot+0.397
iesta+0.383
lace+0.382
yrinth+0.379
Neg logit contributions
 indu-0.459
 ruining-0.397
 popping-0.388
 scient-0.387
 obser-0.363
Token The
Token ID383
Feature activation+8.11e-02

Pos logit contributions
 indu+0.392
 ruining+0.341
 popping+0.335
 scient+0.329
 intellig+0.309
Neg logit contributions
resa-0.362
lot-0.349
iesta-0.341
lace-0.339
yrinth-0.339
Token cardboard
Token ID26819
Feature activation+1.27e-01

Pos logit contributions
 indu+0.061
 ruining+0.052
 popping+0.051
 scient+0.050
 intellig+0.046
Neg logit contributions
resa-0.070
lot-0.067
iesta-0.065
lace-0.065
yrinth-0.065
Token!
Token ID0
Feature activation+1.42e+00

Pos logit contributions
 indu+0.705
 ruining+0.629
 popping+0.620
 scient+0.607
 intellig+0.576
Neg logit contributions
resa-0.490
lot-0.465
iesta-0.455
yrinth-0.455
lace-0.451
Token
Token ID447
Feature activation+6.47e-01

Pos logit contributions
 indu+1.176
 ruining+1.032
 popping+1.014
 scient+0.991
 intellig+0.929
Neg logit contributions
resa-1.103
lot-1.053
yrinth-1.040
iesta-1.033
lace-1.026
Token
Token ID251
Feature activation+4.26e-01

Pos logit contributions
 indu+0.549
 ruining+0.484
 popping+0.479
 scient+0.465
 intellig+0.442
Neg logit contributions
resa-0.487
lot-0.465
yrinth-0.458
iesta-0.456
lace-0.450
Token Ichigo
Token ID44547
Feature activation+3.08e-01

Pos logit contributions
 indu+0.356
 ruining+0.311
 popping+0.305
 scient+0.300
 intellig+0.281
Neg logit contributions
resa-0.330
lot-0.317
iesta-0.310
yrinth-0.309
lace-0.308
Token th
Token ID294
Feature activation+5.17e-01

Pos logit contributions
 indu+0.255
 ruining+0.222
 popping+0.218
 scient+0.214
 intellig+0.200
Neg logit contributions
resa-0.241
lot-0.231
iesta-0.226
yrinth-0.226
lace-0.225
Tokenumped
Token ID27073
Feature activation+4.19e+00

Pos logit contributions
 indu+0.484
 ruining+0.429
 popping+0.422
 scient+0.415
 intellig+0.394
Neg logit contributions
resa-0.346
lot-0.330
iesta-0.322
yrinth-0.322
lace-0.320
Token his
Token ID465
Feature activation+7.52e-01

Pos logit contributions
 indu+3.450
 ruining+3.033
 popping+3.001
 scient+2.916
 intellig+2.744
Neg logit contributions
resa-3.266
lot-3.095
yrinth-3.064
iesta-3.060
lace-3.026
Token abdomen
Token ID32956
Feature activation+2.74e-01

Pos logit contributions
 indu+0.527
 ruining+0.449
 popping+0.436
 scient+0.428
 intellig+0.396
Neg logit contributions
resa-0.681
lot-0.658
iesta-0.645
yrinth-0.642
lace-0.641
Token a
Token ID257
Feature activation+2.11e-01

Pos logit contributions
 indu+0.228
 ruining+0.199
 popping+0.195
 scient+0.192
 intellig+0.180
Neg logit contributions
resa-0.212
lot-0.204
iesta-0.199
yrinth-0.198
lace-0.198
Token few
Token ID1178
Feature activation-4.63e-01

Pos logit contributions
 indu+0.174
 ruining+0.152
 popping+0.150
 scient+0.147
 intellig+0.138
Neg logit contributions
resa-0.164
lot-0.157
iesta-0.155
yrinth-0.154
lace-0.153
Token times
Token ID1661
Feature activation+1.15e+00

Pos logit contributions
resa+0.304
lot+0.291
iesta+0.283
yrinth+0.281
lace+0.281
Neg logit contributions
 indu-0.439
 ruining-0.390
 popping-0.383
 scient-0.378
 intellig-0.357
Token only
Token ID691
Feature activation+8.53e-01

Pos logit contributions
 indu+1.328
 ruining+1.136
 popping+1.114
 scient+1.086
 intellig+1.008
Neg logit contributions
resa-1.615
lot-1.557
iesta-1.530
yrinth-1.529
lace-1.519
Token his
Token ID465
Feature activation-7.71e-02

Pos logit contributions
 indu+0.585
 ruining+0.494
 popping+0.482
 scient+0.470
 intellig+0.435
Neg logit contributions
resa-0.787
lot-0.759
iesta-0.747
lace-0.743
yrinth-0.743
Token trousers
Token ID37191
Feature activation-4.91e-02

Pos logit contributions
resa+0.071
lot+0.068
iesta+0.067
lace+0.067
yrinth+0.066
Neg logit contributions
 indu-0.053
 ruining-0.045
 popping-0.043
 scient-0.042
 intellig-0.039
Token,
Token ID11
Feature activation-3.79e-02

Pos logit contributions
resa+0.033
lot+0.032
iesta+0.031
lace+0.031
yrinth+0.031
Neg logit contributions
 indu-0.046
 ruining-0.040
 popping-0.040
 scient-0.039
 intellig-0.037
Token and
Token ID290
Feature activation-3.15e-01

Pos logit contributions
resa+0.033
lot+0.032
iesta+0.031
lace+0.031
yrinth+0.031
Neg logit contributions
 indu-0.028
 ruining-0.023
 popping-0.023
 scient-0.023
 intellig-0.021
Token spread
Token ID4104
Feature activation+4.17e+00

Pos logit contributions
resa+0.260
lot+0.249
lace+0.245
iesta+0.245
yrinth+0.242
Neg logit contributions
 indu-0.245
 ruining-0.210
 popping-0.204
 scient-0.203
 proble-0.189
Token them
Token ID606
Feature activation+4.17e-01

Pos logit contributions
 indu+3.014
 ruining+2.594
 popping+2.572
 scient+2.469
 intellig+2.316
Neg logit contributions
resa-3.654
lot-3.522
yrinth-3.480
iesta-3.455
lace-3.426
Token near
Token ID1474
Feature activation-2.72e-01

Pos logit contributions
 indu+0.336
 ruining+0.290
 popping+0.284
 scient+0.281
 obser+0.261
Neg logit contributions
resa-0.335
lot-0.323
iesta-0.315
lace-0.314
yrinth-0.312
Token the
Token ID262
Feature activation-5.02e-02

Pos logit contributions
resa+0.244
lot+0.235
iesta+0.232
lace+0.230
yrinth+0.230
Neg logit contributions
 indu-0.193
 ruining-0.163
 popping-0.159
 scient-0.157
 intellig-0.145
Token sunk
Token ID24790
Feature activation+6.44e-01

Pos logit contributions
resa+0.042
lot+0.040
iesta+0.039
yrinth+0.039
lace+0.039
Neg logit contributions
 indu-0.039
 ruining-0.034
 popping-0.033
 scient-0.032
 intellig-0.030
Tokenen
Token ID268
Feature activation-1.90e-01

Pos logit contributions
 indu+0.467
 ruining+0.399
 popping+0.391
 scient+0.382
 intellig+0.354
Neg logit contributions
resa-0.570
lot-0.549
iesta-0.540
yrinth-0.538
lace-0.536
Tokent
Token ID83
Feature activation-1.27e-01

Pos logit contributions
resa+0.410
lot+0.391
iesta+0.382
yrinth+0.381
lace+0.379
Neg logit contributions
 indu-0.549
 ruining-0.486
 popping-0.479
 scient-0.470
 intellig-0.445
Tokenweet
Token ID7277
Feature activation+5.55e-01

Pos logit contributions
resa+0.083
lot+0.079
yrinth+0.077
iesta+0.077
lace+0.077
Neg logit contributions
 indu-0.121
 ruining-0.107
 popping-0.106
 scient-0.104
 intellig-0.099
Token/
Token ID14
Feature activation-1.75e+00

Pos logit contributions
 indu+0.508
 ruining+0.450
 popping+0.443
 scient+0.434
 intellig+0.411
Neg logit contributions
resa-0.383
lot-0.366
iesta-0.358
yrinth-0.358
lace-0.354
Token<|endoftext|>
Token ID50256
Feature activation-4.89e-02

Pos logit contributions
resa+1.154
lot+1.103
iesta+1.072
lace+1.068
yrinth+1.065
Neg logit contributions
 indu-1.666
 ruining-1.480
 popping-1.456
 scient-1.437
 intellig-1.360
TokenStory
Token ID11605
Feature activation+1.08e+00

Pos logit contributions
resa+0.032
lot+0.031
iesta+0.030
yrinth+0.030
lace+0.030
Neg logit contributions
 indu-0.046
 ruining-0.041
 popping-0.041
 scient-0.040
 intellig-0.038
Token highlights
Token ID11330
Feature activation+4.14e+00

Pos logit contributions
 indu+0.860
 ruining+0.746
 popping+0.730
 scient+0.717
 intellig+0.671
Neg logit contributions
resa-0.871
lot-0.837
iesta-0.821
yrinth-0.820
lace-0.814
Token Secretary
Token ID4986
Feature activation-1.19e+00

Pos logit contributions
 indu+3.333
 ruining+2.943
 popping+2.879
 scient+2.859
 Fold+2.684
Neg logit contributions
resa-3.182
yrinth-3.071
lot-3.071
iesta-3.014
lace-2.979
Token of
Token ID286
Feature activation+3.28e-01

Pos logit contributions
resa+0.893
lot+0.853
iesta+0.833
lace+0.828
yrinth+0.827
Neg logit contributions
 indu-1.016
 ruining-0.890
 popping-0.875
 scient-0.855
 intellig-0.805
Token Defense
Token ID5947
Feature activation+1.73e-01

Pos logit contributions
 indu+0.223
 ruining+0.187
 popping+0.184
 scient+0.178
 intellig+0.164
Neg logit contributions
resa-0.306
lot-0.295
iesta-0.290
yrinth-0.289
lace-0.288
Token Chuck
Token ID14663
Feature activation-1.23e-01

Pos logit contributions
 indu+0.148
 ruining+0.128
 popping+0.126
 scient+0.124
 obser+0.116
Neg logit contributions
resa-0.131
lot-0.126
iesta-0.123
lace-0.122
yrinth-0.121
Token Hag
Token ID21375
Feature activation-3.75e-01

Pos logit contributions
resa+0.073
lot+0.069
iesta+0.067
yrinth+0.066
lace+0.066
Neg logit contributions
 indu-0.125
 ruining-0.112
 popping-0.110
 scient-0.109
 disse-0.103
Token _
Token ID4808
Feature activation+3.09e-01

Pos logit contributions
resa+0.052
lot+0.051
iesta+0.050
yrinth+0.050
lace+0.049
Neg logit contributions
 indu-0.039
 ruining-0.033
 popping-0.032
 scient-0.031
 intellig-0.029
Token full
Token ID1336
Feature activation+1.83e-01

Pos logit contributions
 indu+0.281
 ruining+0.247
 popping+0.242
 scient+0.239
 disse+0.225
Neg logit contributions
resa-0.215
lot-0.206
iesta-0.202
yrinth-0.201
lace-0.200
Token v
Token ID410
Feature activation+6.57e-02

Pos logit contributions
 indu+0.145
 ruining+0.126
 popping+0.123
 scient+0.121
 obser+0.113
Neg logit contributions
resa-0.148
lot-0.143
iesta-0.140
lace-0.139
yrinth-0.139
Token )
Token ID1267
Feature activation+4.04e-01

Pos logit contributions
 indu+0.076
 ruining+0.069
 popping+0.069
 scient+0.068
 intellig+0.065
Neg logit contributions
resa-0.029
lot-0.027
iesta-0.026
yrinth-0.026
lace-0.026
Token {
Token ID1391
Feature activation+1.77e+00

Pos logit contributions
 indu+0.359
 ruining+0.318
 popping+0.313
 scient+0.307
 intellig+0.292
Neg logit contributions
resa-0.289
lot-0.274
yrinth-0.271
iesta-0.269
lace-0.264
Token //
Token ID3373
Feature activation+3.92e+00

Pos logit contributions
 indu+1.512
 ruining+1.325
 popping+1.304
 scient+1.272
 intellig+1.207
Neg logit contributions
resa-1.342
lot-1.277
iesta-1.256
yrinth-1.249
lace-1.238
Token Time
Token ID3862
Feature activation+1.37e+00

Pos logit contributions
 indu+3.427
 ruining+3.048
 popping+3.004
 scient+2.915
 Fold+2.802
Neg logit contributions
resa-2.798
lot-2.653
yrinth-2.628
iesta-2.595
lace-2.532
Token component
Token ID7515
Feature activation-2.56e-01

Pos logit contributions
 indu+0.862
 ruining+0.716
 popping+0.707
 scient+0.687
 intellig+0.628
Neg logit contributions
resa-1.342
lot-1.297
iesta-1.288
yrinth-1.287
lace-1.269
Token const
Token ID1500
Feature activation-3.08e-01

Pos logit contributions
resa+0.186
lot+0.177
yrinth+0.174
iesta+0.174
lace+0.172
Neg logit contributions
 indu-0.227
 ruining-0.200
 popping-0.197
 scient-0.193
 intellig-0.183
Token float
Token ID12178
Feature activation+9.59e-01

Pos logit contributions
resa+0.266
lot+0.257
iesta+0.252
lace+0.251
yrinth+0.251
Neg logit contributions
 indu-0.229
 ruining-0.197
 popping-0.192
 scient-0.189
 intellig-0.174
Token TA
Token ID21664
Feature activation-9.10e-03

Pos logit contributions
 indu+0.660
 ruining+0.560
 popping+0.548
 scient+0.532
 intellig+0.493
Neg logit contributions
resa-0.882
lot-0.852
yrinth-0.839
iesta-0.836
lace-0.832
Token the
Token ID262
Feature activation-8.56e-02

Pos logit contributions
 indu+0.713
 ruining+0.612
 popping+0.599
 scient+0.587
 disse+0.547
Neg logit contributions
resa-0.771
lot-0.742
iesta-0.726
yrinth-0.726
lace-0.721
Token Nexus
Token ID16756
Feature activation+5.98e-01

Pos logit contributions
resa+0.069
lot+0.066
yrinth+0.065
iesta+0.064
lace+0.064
Neg logit contributions
 indu-0.069
 ruining-0.060
 popping-0.058
 scient-0.057
 disse-0.053
Token 6
Token ID718
Feature activation+1.90e+00

Pos logit contributions
 indu+0.556
 ruining+0.492
 popping+0.484
 scient+0.477
 intellig+0.450
Neg logit contributions
resa-0.407
lot-0.388
iesta-0.379
yrinth-0.378
lace-0.376
Token.
Token ID13
Feature activation+5.55e-01

Pos logit contributions
 indu+1.739
 ruining+1.541
 popping+1.519
 scient+1.488
 intellig+1.412
Neg logit contributions
resa-1.320
lot-1.258
iesta-1.233
yrinth-1.229
lace-1.222
Token No
Token ID1400
Feature activation-2.59e-01

Pos logit contributions
 indu+0.464
 ruining+0.404
 popping+0.396
 scient+0.389
 intellig+0.365
Neg logit contributions
resa-0.430
lot-0.413
iesta-0.404
yrinth-0.403
lace-0.402
Token word
Token ID1573
Feature activation+3.89e+00

Pos logit contributions
resa+0.218
lot+0.210
iesta+0.204
yrinth+0.204
lace+0.203
Neg logit contributions
 indu-0.200
 ruining-0.171
 popping-0.167
 scient-0.165
 intellig-0.154
Token on
Token ID319
Feature activation-2.27e-01

Pos logit contributions
 indu+2.903
 ruining+2.526
 popping+2.523
 scient+2.403
 intellig+2.253
Neg logit contributions
resa-3.303
yrinth-3.136
lot-3.131
iesta-3.121
lace-3.102
Token if
Token ID611
Feature activation-7.31e-01

Pos logit contributions
resa+0.184
lot+0.177
iesta+0.173
yrinth+0.172
lace+0.172
Neg logit contributions
 indu-0.182
 ruining-0.156
 popping-0.153
 scient-0.151
 disse-0.141
Token there
Token ID612
Feature activation+1.89e-01

Pos logit contributions
resa+0.614
lot+0.590
iesta+0.575
yrinth+0.574
lace+0.573
Neg logit contributions
 indu-0.564
 ruining-0.482
 popping-0.471
 scient-0.463
 disse-0.433
Token will
Token ID481
Feature activation+8.35e-01

Pos logit contributions
 indu+0.175
 ruining+0.155
 popping+0.153
 scient+0.150
 intellig+0.142
Neg logit contributions
resa-0.129
lot-0.123
iesta-0.120
yrinth-0.120
lace-0.119
Token be
Token ID307
Feature activation-3.05e-02

Pos logit contributions
 indu+0.623
 ruining+0.535
 popping+0.523
 scient+0.512
 intellig+0.476
Neg logit contributions
resa-0.720
lot-0.694
iesta-0.681
yrinth-0.680
lace-0.676
Token Louisiana
Token ID13340
Feature activation-3.68e-02

Pos logit contributions
resa+0.212
lot+0.203
iesta+0.200
lace+0.198
yrinth+0.198
Neg logit contributions
 indu-0.224
 ruining-0.195
 popping-0.191
 scient-0.187
 obser-0.175
Token State
Token ID1812
Feature activation+9.94e-01

Pos logit contributions
resa+0.035
lot+0.033
iesta+0.033
yrinth+0.033
lace+0.033
Neg logit contributions
 indu-0.025
 ruining-0.021
 popping-0.020
 scient-0.020
 intellig-0.018
Token University
Token ID2059
Feature activation+6.97e-01

Pos logit contributions
 indu+0.865
 ruining+0.767
 popping+0.754
 scient+0.737
 intellig+0.701
Neg logit contributions
resa-0.731
lot-0.697
yrinth-0.688
iesta-0.679
lace-0.671
Token.
Token ID13
Feature activation-5.75e-01

Pos logit contributions
 indu+0.661
 ruining+0.589
 popping+0.580
 scient+0.569
 intellig+0.540
Neg logit contributions
resa-0.459
lot-0.437
iesta-0.427
yrinth-0.426
lace-0.423
Token How
Token ID1374
Feature activation-2.09e-01

Pos logit contributions
resa+0.479
lot+0.463
iesta+0.452
lace+0.449
yrinth+0.448
Neg logit contributions
 indu-0.450
 ruining-0.388
 popping-0.380
 scient-0.368
 obser-0.348
Token common
Token ID2219
Feature activation+3.84e+00

Pos logit contributions
resa+0.142
lot+0.136
iesta+0.132
yrinth+0.132
lace+0.130
Neg logit contributions
 indu-0.193
 ruining-0.171
 popping-0.168
 scient-0.164
 obser-0.156
Token is
Token ID318
Feature activation+1.93e-01

Pos logit contributions
 indu+3.555
 ruining+3.152
 popping+3.124
 scient+3.080
 intellig+2.899
Neg logit contributions
resa-2.601
lot-2.461
iesta-2.436
yrinth-2.430
lace-2.415
Token a
Token ID257
Feature activation-6.62e-02

Pos logit contributions
 indu+0.146
 ruining+0.125
 popping+0.123
 scient+0.120
 intellig+0.112
Neg logit contributions
resa-0.164
lot-0.158
iesta-0.155
yrinth-0.154
lace-0.153
Token Ph
Token ID1380
Feature activation+6.70e-02

Pos logit contributions
resa+0.054
lot+0.052
iesta+0.051
lace+0.050
yrinth+0.050
Neg logit contributions
 indu-0.053
 ruining-0.045
 popping-0.044
 scient-0.043
 intellig-0.041
Token.
Token ID13
Feature activation+4.35e-01

Pos logit contributions
 indu+0.065
 ruining+0.058
 popping+0.058
 scient+0.056
 intellig+0.054
Neg logit contributions
resa-0.042
yrinth-0.040
lot-0.039
iesta-0.039
lace-0.039
TokenD
Token ID35
Feature activation-2.11e-01

Pos logit contributions
 indu+0.446
 ruining+0.401
 popping+0.397
 scient+0.390
 intellig+0.372
Neg logit contributions
resa-0.251
lot-0.236
yrinth-0.234
iesta-0.231
lace-0.228
Token Last
Token ID4586
Feature activation-5.13e-01

Pos logit contributions
 indu+0.093
 ruining+0.083
 popping+0.081
 scient+0.080
 intellig+0.076
Neg logit contributions
resa-0.067
lot-0.064
iesta-0.063
lace-0.062
yrinth-0.062
Token week
Token ID1285
Feature activation+3.27e-01

Pos logit contributions
resa+0.293
lot+0.276
iesta+0.269
yrinth+0.267
lace+0.266
Neg logit contributions
 indu-0.532
 ruining-0.478
 popping-0.470
 scient-0.464
 intellig-0.441
Token,
Token ID11
Feature activation-4.26e-01

Pos logit contributions
 indu+0.284
 ruining+0.249
 popping+0.245
 scient+0.240
 intellig+0.226
Neg logit contributions
resa-0.243
lot-0.233
iesta-0.227
yrinth-0.226
lace-0.226
Token he
Token ID339
Feature activation-1.90e-01

Pos logit contributions
resa+0.375
lot+0.360
iesta+0.354
lace+0.352
yrinth+0.351
Neg logit contributions
 indu-0.311
 ruining-0.264
 popping-0.258
 scient-0.251
 disse-0.234
Token comm
Token ID725
Feature activation-1.76e+00

Pos logit contributions
resa+0.137
lot+0.131
iesta+0.128
yrinth+0.127
lace+0.127
Neg logit contributions
 indu-0.168
 ruining-0.148
 popping-0.146
 scient-0.143
 intellig-0.135
Tokenended
Token ID1631
Feature activation+3.79e+00

Pos logit contributions
resa+0.869
lot+0.810
iesta+0.779
yrinth+0.773
lace+0.769
Neg logit contributions
 indu-1.978
 ruining-1.787
 popping-1.764
 scient-1.739
 intellig-1.662
Token Trump
Token ID1301
Feature activation+1.24e+00

Pos logit contributions
 indu+2.827
 ruining+2.466
 popping+2.420
 scient+2.376
 intellig+2.216
Neg logit contributions
resa-3.179
lot-3.084
yrinth-3.037
iesta-3.012
lace-3.005
Token for
Token ID329
Feature activation+1.26e-01

Pos logit contributions
 indu+1.116
 ruining+0.990
 popping+0.974
 scient+0.956
 intellig+0.906
Neg logit contributions
resa-0.866
lot-0.826
yrinth-0.811
iesta-0.808
lace-0.804
Token conducting
Token ID14523
Feature activation+1.59e-01

Pos logit contributions
 indu+0.085
 ruining+0.071
 popping+0.070
 scient+0.068
 intellig+0.063
Neg logit contributions
resa-0.118
lot-0.113
iesta-0.112
yrinth-0.111
lace-0.111
Token military
Token ID2422
Feature activation+3.61e-02

Pos logit contributions
 indu+0.121
 ruining+0.104
 popping+0.102
 scient+0.099
 intellig+0.092
Neg logit contributions
resa-0.135
lot-0.130
iesta-0.128
yrinth-0.127
lace-0.127
Token strikes
Token ID8956
Feature activation-1.27e+00

Pos logit contributions
 indu+0.030
 ruining+0.026
 popping+0.026
 scient+0.025
 intellig+0.024
Neg logit contributions
resa-0.028
lot-0.027
iesta-0.026
yrinth-0.026
lace-0.026
Token {
Token ID1391
Feature activation+1.83e+00

Pos logit contributions
 indu+0.668
 ruining+0.592
 popping+0.584
 scient+0.572
 intellig+0.542
Neg logit contributions
resa-0.524
lot-0.498
yrinth-0.490
iesta-0.489
lace-0.482
Token let
Token ID1309
Feature activation+5.85e-01

Pos logit contributions
 indu+1.257
 ruining+1.063
 popping+1.039
 scient+1.016
 intellig+0.936
Neg logit contributions
resa-1.682
lot-1.624
iesta-1.597
yrinth-1.594
lace-1.587
Token prev
Token ID8654
Feature activation-5.31e-02

Pos logit contributions
 indu+0.417
 ruining+0.356
 popping+0.348
 scient+0.345
 intellig+0.317
Neg logit contributions
resa-0.521
lot-0.497
yrinth-0.493
iesta-0.490
lace-0.488
Token :
Token ID1058
Feature activation+2.81e+00

Pos logit contributions
resa+0.024
lot+0.022
yrinth+0.022
iesta+0.021
lace+0.021
Neg logit contributions
 indu-0.061
 ruining-0.056
 popping-0.055
 scient-0.054
 intellig-0.052
Token Board
Token ID5926
Feature activation+2.13e+00

Pos logit contributions
 indu+2.682
 ruining+2.386
 popping+2.351
 scient+2.309
 intellig+2.191
Neg logit contributions
resa-1.830
lot-1.740
iesta-1.700
yrinth-1.695
lace-1.683
Token =
Token ID796
Feature activation+3.76e+00

Pos logit contributions
 indu+1.962
 ruining+1.737
 popping+1.716
 scient+1.673
 intellig+1.592
Neg logit contributions
resa-1.458
lot-1.381
iesta-1.358
yrinth-1.351
lace-1.339
Token self
Token ID2116
Feature activation+7.76e-01

Pos logit contributions
 indu+2.765
 ruining+2.367
 popping+2.327
 scient+2.258
 intellig+2.108
Neg logit contributions
resa-3.289
lot-3.177
iesta-3.118
yrinth-3.105
lace-3.095
Token.
Token ID764
Feature activation+2.10e+00

Pos logit contributions
 indu+0.803
 ruining+0.721
 popping+0.712
 scient+0.699
 intellig+0.668
Neg logit contributions
resa-0.447
lot-0.421
iesta-0.411
yrinth-0.408
lace-0.403
Tokenprev
Token ID47050
Feature activation+1.97e-01

Pos logit contributions
 indu+1.849
 ruining+1.627
 popping+1.605
 scient+1.565
 intellig+1.480
Neg logit contributions
resa-1.515
lot-1.444
iesta-1.422
yrinth-1.413
lace-1.404
Token_
Token ID62
Feature activation+1.56e-01

Pos logit contributions
 indu+0.225
 ruining+0.204
 popping+0.201
 scient+0.198
 intellig+0.190
Neg logit contributions
resa-0.092
lot-0.086
iesta-0.083
yrinth-0.082
lace-0.081
Tokenstate
Token ID5219
Feature activation+5.27e-02

Pos logit contributions
 indu+0.108
 ruining+0.091
 popping+0.089
 scient+0.087
 intellig+0.081
Neg logit contributions
resa-0.144
lot-0.139
iesta-0.136
yrinth-0.136
lace-0.136
Token room
Token ID2119
Feature activation-8.17e-01

Pos logit contributions
resa+0.948
lot+0.915
iesta+0.893
lace+0.889
yrinth+0.882
Neg logit contributions
 indu-0.684
 ruining-0.582
 popping-0.560
 scient-0.543
 proble-0.504
Token
Token ID198
Feature activation-2.06e-01

Pos logit contributions
resa+0.582
lot+0.558
iesta+0.543
yrinth+0.541
lace+0.540
Neg logit contributions
 indu-0.732
 ruining-0.645
 popping-0.633
 scient-0.624
 intellig-0.587
Token
Token ID198
Feature activation+1.84e-02

Pos logit contributions
resa+0.133
yrinth+0.125
lot+0.125
iesta+0.123
lace+0.121
Neg logit contributions
 indu-0.196
 ruining-0.176
 popping-0.174
 scient-0.170
 intellig-0.163
Token
Token ID1906
Feature activation-1.50e-02

Pos logit contributions
 indu+0.019
 ruining+0.017
 popping+0.017
 scient+0.017
 intellig+0.016
Neg logit contributions
resa-0.010
lot-0.010
iesta-0.009
yrinth-0.009
lace-0.009
Token Come
Token ID7911
Feature activation+1.52e+00

Pos logit contributions
resa+0.012
lot+0.012
iesta+0.012
yrinth+0.011
lace+0.011
Neg logit contributions
 indu-0.012
 ruining-0.010
 popping-0.010
 scient-0.010
 intellig-0.009
Token along
Token ID1863
Feature activation+3.76e+00

Pos logit contributions
 indu+1.262
 ruining+1.103
 popping+1.085
 scient+1.062
 intellig+0.998
Neg logit contributions
resa-1.174
lot-1.125
yrinth-1.104
iesta-1.103
lace-1.096
Token,
Token ID11
Feature activation+9.99e-01

Pos logit contributions
 indu+3.255
 ruining+2.895
 popping+2.856
 scient+2.796
 intellig+2.641
Neg logit contributions
resa-2.720
lot-2.603
yrinth-2.576
lace-2.567
iesta-2.566
Token my
Token ID616
Feature activation-1.08e-01

Pos logit contributions
 indu+0.797
 ruining+0.692
 popping+0.679
 scient+0.665
 intellig+0.622
Neg logit contributions
resa-0.809
lot-0.777
iesta-0.763
yrinth-0.761
lace-0.757
Token dear
Token ID13674
Feature activation-5.69e-01

Pos logit contributions
resa+0.085
lot+0.081
iesta+0.080
yrinth+0.079
lace+0.079
Neg logit contributions
 indu-0.089
 ruining-0.077
 popping-0.076
 scient-0.074
 intellig-0.070
Token,
Token ID11
Feature activation+1.68e-01

Pos logit contributions
resa+0.415
lot+0.397
iesta+0.388
yrinth+0.387
lace+0.385
Neg logit contributions
 indu-0.500
 ruining-0.440
 popping-0.433
 scient-0.424
 intellig-0.400
Token come
Token ID1282
Feature activation+3.96e-01

Pos logit contributions
 indu+0.138
 ruining+0.120
 popping+0.118
 scient+0.116
 intellig+0.109
Neg logit contributions
resa-0.132
lot-0.127
iesta-0.124
yrinth-0.124
lace-0.123
Tokenborn
Token ID6286
Feature activation+1.05e+00

Pos logit contributions
 indu+0.230
 ruining+0.202
 popping+0.199
 scient+0.195
 intellig+0.184
Neg logit contributions
resa-0.199
lot-0.189
iesta-0.187
yrinth-0.186
lace-0.184
Token Farmer
Token ID37755
Feature activation-5.75e-01

Pos logit contributions
 indu+0.880
 ruining+0.769
 popping+0.755
 scient+0.740
 intellig+0.695
Neg logit contributions
resa-0.810
lot-0.776
iesta-0.761
yrinth-0.759
lace-0.755
Token on
Token ID319
Feature activation+3.14e-01

Pos logit contributions
resa+0.443
lot+0.425
iesta+0.416
yrinth+0.413
lace+0.412
Neg logit contributions
 indu-0.483
 ruining-0.422
 popping-0.414
 scient-0.406
 intellig-0.381
Token "
Token ID366
Feature activation+6.86e-01

Pos logit contributions
 indu+0.237
 ruining+0.204
 popping+0.199
 scient+0.195
 intellig+0.182
Neg logit contributions
resa-0.267
lot-0.258
iesta-0.253
yrinth-0.252
lace-0.251
TokenFr
Token ID6732
Feature activation-1.44e-01

Pos logit contributions
 indu+0.665
 ruining+0.593
 popping+0.584
 scient+0.574
 intellig+0.545
Neg logit contributions
resa-0.437
lot-0.414
iesta-0.406
yrinth-0.405
lace-0.401
Tokenances
Token ID1817
Feature activation+3.75e+00

Pos logit contributions
resa+0.090
lot+0.085
iesta+0.083
yrinth+0.083
lace+0.082
Neg logit contributions
 indu-0.142
 ruining-0.126
 popping-0.124
 scient-0.122
 intellig-0.116
Token Farmer
Token ID37755
Feature activation+6.97e-01

Pos logit contributions
 indu+3.265
 ruining+2.901
 popping+2.851
 scient+2.776
 Fold+2.622
Neg logit contributions
resa-2.684
yrinth-2.567
lot-2.544
iesta-2.529
lace-2.503
Token Will
Token ID2561
Feature activation+2.28e-01

Pos logit contributions
 indu+0.595
 ruining+0.522
 popping+0.513
 scient+0.503
 intellig+0.473
Neg logit contributions
resa-0.526
lot-0.503
iesta-0.494
yrinth-0.493
lace-0.489
Token Have
Token ID8192
Feature activation-5.57e-03

Pos logit contributions
 indu+0.184
 ruining+0.159
 popping+0.156
 scient+0.153
 intellig+0.143
Neg logit contributions
resa-0.185
lot-0.178
iesta-0.174
lace-0.173
yrinth-0.173
Token Her
Token ID2332
Feature activation-8.59e-02

Pos logit contributions
resa+0.004
lot+0.004
iesta+0.004
lace+0.004
yrinth+0.004
Neg logit contributions
 indu-0.005
 ruining-0.004
 popping-0.004
 scient-0.004
 intellig-0.004
Token Revenge
Token ID24366
Feature activation-2.90e-01

Pos logit contributions
resa+0.069
lot+0.066
iesta+0.065
lace+0.065
yrinth+0.064
Neg logit contributions
 indu-0.070
 ruining-0.060
 popping-0.059
 scient-0.058
 intellig-0.054
Token
Token ID251
Feature activation-2.82e-01

Pos logit contributions
 indu+0.573
 ruining+0.497
 popping+0.488
 scient+0.476
 intellig+0.447
Neg logit contributions
resa-0.606
lot-0.584
iesta-0.572
yrinth-0.572
lace-0.568
Token or
Token ID393
Feature activation+4.37e-01

Pos logit contributions
resa+0.196
lot+0.188
iesta+0.184
yrinth+0.182
lace+0.182
Neg logit contributions
 indu-0.257
 ruining-0.227
 popping-0.223
 scient-0.220
 intellig-0.207
Token
Token ID564
Feature activation+3.38e-01

Pos logit contributions
 indu+0.373
 ruining+0.326
 popping+0.320
 scient+0.316
 intellig+0.296
Neg logit contributions
resa-0.329
lot-0.315
iesta-0.310
yrinth-0.308
lace-0.307
Token
Token ID250
Feature activation+2.66e-01

Pos logit contributions
 indu+0.255
 ruining+0.219
 popping+0.215
 scient+0.210
 intellig+0.195
Neg logit contributions
resa-0.289
lot-0.278
iesta-0.273
yrinth-0.273
lace-0.272
Tokenc
Token ID66
Feature activation-8.02e-02

Pos logit contributions
 indu+0.237
 ruining+0.209
 popping+0.206
 scient+0.202
 intellig+0.191
Neg logit contributions
resa-0.190
lot-0.182
iesta-0.178
yrinth-0.177
lace-0.177
Tokenra
Token ID430
Feature activation+3.74e+00

Pos logit contributions
resa+0.062
lot+0.059
iesta+0.058
yrinth+0.058
lace+0.057
Neg logit contributions
 indu-0.068
 ruining-0.059
 popping-0.058
 scient-0.057
 intellig-0.054
Tokenppy
Token ID14097
Feature activation+5.76e-01

Pos logit contributions
 indu+3.432
 ruining+3.050
 popping+2.997
 scient+2.926
 intellig+2.793
Neg logit contributions
resa-2.537
lot-2.446
yrinth-2.386
lace-2.380
iesta-2.371
Token.
Token ID13
Feature activation+2.30e-01

Pos logit contributions
 indu+0.617
 ruining+0.557
 popping+0.550
 scient+0.541
 intellig+0.517
Neg logit contributions
resa-0.309
lot-0.291
iesta-0.282
yrinth-0.282
lace-0.279
Token
Token ID447
Feature activation+3.16e-01

Pos logit contributions
 indu+0.211
 ruining+0.186
 popping+0.183
 scient+0.180
 intellig+0.170
Neg logit contributions
resa-0.160
lot-0.153
iesta-0.150
lace-0.149
yrinth-0.148
Token
Token ID251
Feature activation-1.78e-01

Pos logit contributions
 indu+0.311
 ruining+0.278
 popping+0.274
 scient+0.269
 intellig+0.256
Neg logit contributions
resa-0.196
lot-0.186
iesta-0.182
yrinth-0.181
lace-0.180
Token
Token ID198
Feature activation-5.42e-01

Pos logit contributions
resa+0.129
lot+0.124
iesta+0.121
lace+0.120
yrinth+0.120
Neg logit contributions
 indu-0.158
 ruining-0.139
 popping-0.137
 scient-0.134
 intellig-0.126
Token than
Token ID621
Feature activation+1.78e-01

Pos logit contributions
 indu+0.299
 ruining+0.262
 popping+0.258
 scient+0.252
 intellig+0.238
Neg logit contributions
resa-0.277
lot-0.264
iesta-0.260
yrinth-0.259
lace-0.258
Token some
Token ID617
Feature activation+1.30e-01

Pos logit contributions
 indu+0.144
 ruining+0.125
 popping+0.123
 scient+0.121
 intellig+0.113
Neg logit contributions
resa-0.142
lot-0.136
iesta-0.133
yrinth-0.133
lace-0.132
Token candidates
Token ID5871
Feature activation+2.16e-01

Pos logit contributions
 indu+0.112
 ruining+0.098
 popping+0.096
 scient+0.094
 intellig+0.089
Neg logit contributions
resa-0.098
lot-0.094
iesta-0.092
yrinth-0.092
lace-0.091
Token give
Token ID1577
Feature activation+2.31e-01

Pos logit contributions
 indu+0.193
 ruining+0.169
 popping+0.166
 scient+0.164
 intellig+0.154
Neg logit contributions
resa-0.155
lot-0.148
iesta-0.145
lace-0.144
yrinth-0.143
Token them
Token ID606
Feature activation-3.67e-02

Pos logit contributions
 indu+0.203
 ruining+0.179
 popping+0.176
 scient+0.173
 intellig+0.163
Neg logit contributions
resa-0.168
lot-0.160
iesta-0.157
yrinth-0.157
lace-0.156
Token credit
Token ID3884
Feature activation-4.33e+00

Pos logit contributions
resa+0.023
lot+0.022
iesta+0.021
yrinth+0.021
lace+0.021
Neg logit contributions
 indu-0.036
 ruining-0.032
 popping-0.032
 scient-0.031
 intellig-0.029
Token for
Token ID329
Feature activation-3.29e-01

Pos logit contributions
resa+2.753
lot+2.675
iesta+2.587
lace+2.534
yrinth+2.522
Neg logit contributions
 indu-4.104
 ruining-3.607
 popping-3.562
 scient-3.537
 obser-3.350
Token,
Token ID11
Feature activation-3.14e-01

Pos logit contributions
resa+0.203
lot+0.193
iesta+0.188
yrinth+0.186
lace+0.186
Neg logit contributions
 indu-0.325
 ruining-0.289
 popping-0.285
 scient-0.282
 intellig-0.266
Token says
Token ID1139
Feature activation+1.07e-01

Pos logit contributions
resa+0.232
lot+0.222
iesta+0.217
lace+0.217
yrinth+0.216
Neg logit contributions
 indu-0.272
 ruining-0.236
 popping-0.232
 scient-0.229
 obser-0.216
Token Mor
Token ID3461
Feature activation-2.65e-01

Pos logit contributions
 indu+0.090
 ruining+0.079
 popping+0.078
 scient+0.076
 intellig+0.072
Neg logit contributions
resa-0.082
lot-0.078
iesta-0.077
yrinth-0.077
lace-0.076
Tokenley
Token ID1636
Feature activation-2.78e-01

Pos logit contributions
resa+0.157
lot+0.149
iesta+0.145
yrinth+0.145
lace+0.144
Neg logit contributions
 indu-0.269
 ruining-0.241
 popping-0.237
 scient-0.234
 intellig-0.222
Token not
Token ID407
Feature activation-1.17e+00

Pos logit contributions
resa+0.289
lot+0.277
iesta+0.271
yrinth+0.271
lace+0.270
Neg logit contributions
 indu-0.271
 ruining-0.232
 popping-0.227
 scient-0.223
 intellig-0.208
Token clear
Token ID1598
Feature activation+7.38e-02

Pos logit contributions
resa+1.035
lot+0.995
iesta+0.974
yrinth+0.972
lace+0.964
Neg logit contributions
 indu-0.854
 ruining-0.719
 popping-0.703
 scient-0.692
 obser-0.645
Token what
Token ID644
Feature activation-2.38e-01

Pos logit contributions
 indu+0.056
 ruining+0.048
 popping+0.047
 scient+0.046
 intellig+0.043
Neg logit contributions
resa-0.063
lot-0.060
iesta-0.059
yrinth-0.059
lace-0.059
Token long
Token ID890
Feature activation-2.95e-01

Pos logit contributions
resa+0.191
lot+0.182
iesta+0.179
lace+0.178
yrinth+0.177
Neg logit contributions
 indu-0.191
 ruining-0.166
 popping-0.162
 scient-0.159
 intellig-0.149
Token-
Token ID12
Feature activation-1.42e+00

Pos logit contributions
resa+0.203
lot+0.194
iesta+0.189
yrinth+0.188
lace+0.187
Neg logit contributions
 indu-0.271
 ruining-0.239
 popping-0.235
 scient-0.232
 intellig-0.220
Tokenterm
Token ID4354
Feature activation-4.32e+00

Pos logit contributions
resa+0.398
lot+0.353
iesta+0.331
yrinth+0.330
lace+0.324
Neg logit contributions
 indu-1.884
 ruining-1.734
 popping-1.716
 scient-1.696
 intellig-1.636
Token good
Token ID922
Feature activation-3.44e-01

Pos logit contributions
resa+3.264
lot+3.117
lace+3.009
iesta+2.988
yrinth+2.961
Neg logit contributions
 indu-3.564
 ruining-3.073
 popping-3.023
 scient-2.977
 obser-2.800
Token the
Token ID262
Feature activation-6.06e-01

Pos logit contributions
resa+0.251
lot+0.239
iesta+0.234
lace+0.232
yrinth+0.232
Neg logit contributions
 indu-0.303
 ruining-0.265
 popping-0.261
 scient-0.257
 intellig-0.243
Token Trump
Token ID1301
Feature activation+1.50e+00

Pos logit contributions
resa+0.493
lot+0.469
iesta+0.459
lace+0.457
yrinth+0.456
Neg logit contributions
 indu-0.486
 ruining-0.419
 popping-0.410
 scient-0.403
 intellig-0.377
Token peace
Token ID4167
Feature activation-2.52e-01

Pos logit contributions
 indu+1.236
 ruining+1.079
 popping+1.060
 scient+1.038
 intellig+0.975
Neg logit contributions
resa-1.172
lot-1.123
iesta-1.102
yrinth-1.100
lace-1.093
Token initiative
Token ID10219
Feature activation-1.00e+00

Pos logit contributions
resa+0.188
lot+0.179
iesta+0.175
yrinth+0.175
lace+0.174
Neg logit contributions
 indu-0.218
 ruining-0.191
 popping-0.188
 scient-0.185
 intellig-0.174
Token,
Token ID11
Feature activation-1.79e-01

Pos logit contributions
 indu+0.584
 ruining+0.514
 popping+0.506
 scient+0.494
 intellig+0.467
Neg logit contributions
resa-0.499
lot-0.475
iesta-0.469
yrinth-0.468
lace-0.465
Token so
Token ID523
Feature activation-4.20e-01

Pos logit contributions
resa+0.142
lot+0.137
iesta+0.133
yrinth+0.133
lace+0.133
Neg logit contributions
 indu-0.145
 ruining-0.126
 popping-0.123
 scient-0.121
 intellig-0.113
Token I
Token ID314
Feature activation-1.11e-02

Pos logit contributions
resa+0.332
lot+0.319
iesta+0.311
yrinth+0.310
lace+0.310
Neg logit contributions
 indu-0.344
 ruining-0.297
 popping-0.290
 scient-0.286
 intellig-0.267
Token give
Token ID1577
Feature activation+2.36e-01

Pos logit contributions
resa+0.008
lot+0.008
yrinth+0.008
iesta+0.008
lace+0.008
Neg logit contributions
 indu-0.010
 ruining-0.008
 popping-0.008
 scient-0.008
 intellig-0.008
Token him
Token ID683
Feature activation+4.79e-01

Pos logit contributions
 indu+0.180
 ruining+0.155
 popping+0.152
 scient+0.149
 intellig+0.139
Neg logit contributions
resa-0.200
lot-0.192
iesta-0.189
yrinth-0.189
lace-0.188
Token credit
Token ID3884
Feature activation-4.25e+00

Pos logit contributions
 indu+0.371
 ruining+0.320
 popping+0.314
 scient+0.307
 intellig+0.287
Neg logit contributions
resa-0.399
lot-0.384
iesta-0.377
yrinth-0.376
lace-0.374
Token for
Token ID329
Feature activation-2.45e-02

Pos logit contributions
resa+2.721
lot+2.705
iesta+2.566
lace+2.535
yrinth+2.504
Neg logit contributions
 indu-3.987
 ruining-3.472
 popping-3.412
 scient-3.395
 obser-3.267
Token that
Token ID326
Feature activation-1.13e+00

Pos logit contributions
resa+0.022
lot+0.021
iesta+0.021
yrinth+0.021
lace+0.021
Neg logit contributions
 indu-0.017
 ruining-0.014
 popping-0.014
 scient-0.014
 obser-0.013
Token.
Token ID13
Feature activation-6.97e-01

Pos logit contributions
resa+0.735
lot+0.702
iesta+0.681
yrinth+0.678
lace+0.675
Neg logit contributions
 indu-1.079
 ruining-0.956
 popping-0.939
 scient-0.928
 intellig-0.875
Token It
Token ID632
Feature activation-1.06e-01

Pos logit contributions
resa+0.571
lot+0.551
iesta+0.537
lace+0.535
yrinth+0.533
Neg logit contributions
 indu-0.556
 ruining-0.478
 popping-0.469
 scient-0.458
 obser-0.430
Token's
Token ID338
Feature activation-5.49e-01

Pos logit contributions
resa+0.070
lot+0.067
iesta+0.065
yrinth+0.065
lace+0.065
Neg logit contributions
 indu-0.100
 ruining-0.088
 popping-0.087
 scient-0.086
 intellig-0.081
Token R
Token ID371
Feature activation+5.09e-01

Pos logit contributions
resa+0.351
lot+0.335
iesta+0.328
yrinth+0.326
lace+0.326
Neg logit contributions
 indu-0.389
 ruining-0.339
 popping-0.333
 scient-0.326
 intellig-0.307
Token.
Token ID13
Feature activation+2.82e-01

Pos logit contributions
 indu+0.479
 ruining+0.427
 popping+0.421
 scient+0.414
 intellig+0.392
Neg logit contributions
resa-0.336
lot-0.320
yrinth-0.313
iesta-0.313
lace-0.311
TokenE
Token ID36
Feature activation-4.95e-02

Pos logit contributions
 indu+0.269
 ruining+0.239
 popping+0.236
 scient+0.232
 intellig+0.220
Neg logit contributions
resa-0.185
lot-0.175
yrinth-0.172
iesta-0.172
lace-0.170
Token.
Token ID13
Feature activation-7.88e-01

Pos logit contributions
resa+0.030
lot+0.029
iesta+0.028
yrinth+0.028
lace+0.028
Neg logit contributions
 indu-0.049
 ruining-0.044
 popping-0.043
 scient-0.043
 intellig-0.041
TokenM
Token ID44
Feature activation-1.14e+00

Pos logit contributions
resa+0.566
lot+0.541
iesta+0.530
yrinth+0.528
lace+0.525
Neg logit contributions
 indu-0.702
 ruining-0.618
 popping-0.608
 scient-0.597
 intellig-0.563
Token.'
Token ID2637
Feature activation-4.14e+00

Pos logit contributions
resa+0.768
lot+0.733
iesta+0.715
yrinth+0.713
lace+0.708
Neg logit contributions
 indu-1.059
 ruining-0.937
 popping-0.922
 scient-0.906
 intellig-0.859
Tokens
Token ID82
Feature activation-1.11e+00

Pos logit contributions
resa+2.015
lot+1.922
iesta+1.850
lace+1.814
yrinth+1.720
Neg logit contributions
 indu-4.676
 ruining-4.206
 popping-4.131
 scient-4.085
 obser-4.005
Token lead
Token ID1085
Feature activation-5.47e-03

Pos logit contributions
resa+0.859
lot+0.819
iesta+0.801
yrinth+0.795
lace+0.793
Neg logit contributions
 indu-0.932
 ruining-0.812
 popping-0.797
 scient-0.780
 intellig-0.734
Token singer
Token ID14015
Feature activation-4.86e-01

Pos logit contributions
resa+0.004
lot+0.004
iesta+0.004
yrinth+0.004
lace+0.004
Neg logit contributions
 indu-0.004
 ruining-0.004
 popping-0.004
 scient-0.004
 intellig-0.004
Token Michael
Token ID3899
Feature activation-2.68e-01

Pos logit contributions
resa+0.358
lot+0.342
iesta+0.335
yrinth+0.333
lace+0.332
Neg logit contributions
 indu-0.424
 ruining-0.372
 popping-0.366
 scient-0.359
 intellig-0.339
Token St
Token ID520
Feature activation-1.51e+00

Pos logit contributions
resa+0.212
lot+0.204
iesta+0.199
yrinth+0.198
lace+0.197
Neg logit contributions
 indu-0.220
 ruining-0.191
 popping-0.188
 scient-0.184
 intellig-0.173
Token
Token ID247
Feature activation+6.47e-01

Pos logit contributions
 indu+0.608
 ruining+0.542
 popping+0.535
 scient+0.525
 intellig+0.499
Neg logit contributions
resa-0.426
lot-0.404
yrinth-0.398
iesta-0.396
lace-0.391
Tokent
Token ID83
Feature activation-1.99e-01

Pos logit contributions
 indu+0.638
 ruining+0.569
 popping+0.561
 scient+0.552
 intellig+0.524
Neg logit contributions
resa-0.403
lot-0.382
iesta-0.373
yrinth-0.372
lace-0.369
Token even
Token ID772
Feature activation+6.56e-01

Pos logit contributions
resa+0.158
lot+0.152
iesta+0.149
yrinth+0.147
lace+0.147
Neg logit contributions
 indu-0.161
 ruining-0.140
 popping-0.137
 scient-0.135
 intellig-0.126
Token remember
Token ID3505
Feature activation-7.58e-02

Pos logit contributions
 indu+0.533
 ruining+0.464
 popping+0.455
 scient+0.446
 intellig+0.418
Neg logit contributions
resa-0.522
lot-0.501
iesta-0.491
yrinth-0.488
lace-0.487
Token when
Token ID618
Feature activation+1.55e-01

Pos logit contributions
resa+0.065
lot+0.063
iesta+0.062
lace+0.062
yrinth+0.061
Neg logit contributions
 indu-0.056
 ruining-0.048
 popping-0.046
 scient-0.046
 intellig-0.043
Token til
Token ID21502
Feature activation-4.05e+00

Pos logit contributions
 indu+0.122
 ruining+0.106
 popping+0.104
 scient+0.102
 intellig+0.095
Neg logit contributions
resa-0.127
lot-0.122
iesta-0.120
yrinth-0.119
lace-0.119
Tokenap
Token ID499
Feature activation-3.68e-02

Pos logit contributions
resa+2.134
lot+2.015
iesta+1.965
lace+1.903
yrinth+1.853
Neg logit contributions
 indu-4.368
 ruining-3.921
 popping-3.832
 scient-3.807
 obser-3.676
Tokenia
Token ID544
Feature activation+7.18e-01

Pos logit contributions
resa+0.020
lot+0.019
iesta+0.018
yrinth+0.018
lace+0.018
Neg logit contributions
 indu-0.039
 ruining-0.035
 popping-0.035
 scient-0.034
 intellig-0.033
Token came
Token ID1625
Feature activation-2.65e-01

Pos logit contributions
 indu+0.662
 ruining+0.587
 popping+0.578
 scient+0.567
 intellig+0.536
Neg logit contributions
resa-0.492
lot-0.469
iesta-0.459
yrinth-0.459
lace-0.455
Token out
Token ID503
Feature activation+1.19e+00

Pos logit contributions
resa+0.208
lot+0.199
iesta+0.196
yrinth+0.195
lace+0.194
Neg logit contributions
 indu-0.219
 ruining-0.190
 popping-0.186
 scient-0.184
 intellig-0.172
Token.
Token ID13
Feature activation+3.47e-02

Pos logit contributions
 indu+1.106
 ruining+0.982
 popping+0.969
 scient+0.948
 intellig+0.898
Neg logit contributions
resa-0.802
lot-0.761
yrinth-0.747
iesta-0.746
lace-0.739
Token with
Token ID351
Feature activation-5.01e-01

Pos logit contributions
 indu+0.973
 ruining+0.855
 popping+0.840
 scient+0.823
 intellig+0.773
Neg logit contributions
resa-0.889
lot-0.851
iesta-0.837
yrinth-0.837
lace-0.832
Token a
Token ID257
Feature activation-5.05e-01

Pos logit contributions
resa+0.415
lot+0.399
iesta+0.390
yrinth+0.389
lace+0.387
Neg logit contributions
 indu-0.392
 ruining-0.338
 popping-0.331
 scient-0.323
 disse-0.302
Token new
Token ID649
Feature activation-7.87e-01

Pos logit contributions
resa+0.417
lot+0.401
iesta+0.391
yrinth+0.390
lace+0.389
Neg logit contributions
 indu-0.396
 ruining-0.342
 popping-0.334
 scient-0.326
 intellig-0.306
Token short
Token ID1790
Feature activation+2.76e-01

Pos logit contributions
resa+0.669
lot+0.643
iesta+0.629
yrinth+0.625
lace+0.624
Neg logit contributions
 indu-0.599
 ruining-0.516
 popping-0.505
 scient-0.492
 disse-0.460
Token-
Token ID12
Feature activation-1.66e+00

Pos logit contributions
 indu+0.250
 ruining+0.220
 popping+0.217
 scient+0.213
 intellig+0.201
Neg logit contributions
resa-0.194
lot-0.185
iesta-0.181
yrinth-0.180
lace-0.179
Tokenterm
Token ID4354
Feature activation-3.93e+00

Pos logit contributions
resa+0.384
lot+0.333
iesta+0.307
yrinth+0.301
lace+0.298
Neg logit contributions
 indu-2.284
 ruining-2.108
 popping-2.087
 scient-2.065
 intellig-1.992
Token disability
Token ID14013
Feature activation+7.62e-01

Pos logit contributions
resa+3.014
lot+2.883
iesta+2.823
lace+2.739
yrinth+2.723
Neg logit contributions
 indu-3.249
 ruining-2.837
 popping-2.773
 scient-2.725
 disse-2.563
Token plan
Token ID1410
Feature activation+3.74e-02

Pos logit contributions
 indu+0.682
 ruining+0.601
 popping+0.592
 scient+0.581
 intellig+0.549
Neg logit contributions
resa-0.544
lot-0.521
yrinth-0.510
iesta-0.510
lace-0.506
Token.
Token ID13
Feature activation+2.40e-02

Pos logit contributions
 indu+0.034
 ruining+0.030
 popping+0.030
 scient+0.029
 intellig+0.028
Neg logit contributions
resa-0.026
lot-0.025
iesta-0.024
yrinth-0.024
lace-0.024
Token
Token ID198
Feature activation+4.10e-02

Pos logit contributions
 indu+0.023
 ruining+0.020
 popping+0.020
 scient+0.019
 intellig+0.018
Neg logit contributions
resa-0.016
lot-0.015
iesta-0.015
yrinth-0.015
lace-0.015
Token
Token ID198
Feature activation+3.46e-01

Pos logit contributions
 indu+0.039
 ruining+0.035
 popping+0.035
 scient+0.034
 intellig+0.033
Neg logit contributions
resa-0.026
lot-0.025
yrinth-0.025
iesta-0.024
lace-0.024
Token with
Token ID351
Feature activation+1.12e+00

Pos logit contributions
 indu+0.374
 ruining+0.323
 popping+0.317
 scient+0.310
 intellig+0.290
Neg logit contributions
resa-0.393
lot-0.378
iesta-0.371
yrinth-0.370
lace-0.369
Token the
Token ID262
Feature activation-1.94e-01

Pos logit contributions
 indu+0.805
 ruining+0.689
 popping+0.675
 scient+0.659
 intellig+0.610
Neg logit contributions
resa-0.997
lot-0.962
iesta-0.946
yrinth-0.946
lace-0.939
Token same
Token ID976
Feature activation+5.34e-01

Pos logit contributions
resa+0.156
lot+0.149
iesta+0.146
yrinth+0.146
lace+0.145
Neg logit contributions
 indu-0.157
 ruining-0.136
 popping-0.133
 scient-0.131
 intellig-0.122
Token short
Token ID1790
Feature activation-6.92e-03

Pos logit contributions
 indu+0.420
 ruining+0.365
 popping+0.358
 scient+0.350
 intellig+0.328
Neg logit contributions
resa-0.438
lot-0.421
iesta-0.414
yrinth-0.414
lace-0.411
Token-
Token ID12
Feature activation-1.43e+00

Pos logit contributions
resa+0.005
lot+0.005
iesta+0.005
yrinth+0.005
lace+0.005
Neg logit contributions
 indu-0.006
 ruining-0.006
 popping-0.005
 scient-0.005
 intellig-0.005
Tokenterm
Token ID4354
Feature activation-3.92e+00

Pos logit contributions
resa+0.302
lot+0.255
iesta+0.237
yrinth+0.236
lace+0.227
Neg logit contributions
 indu-1.988
 ruining-1.838
 popping-1.821
 scient-1.799
 intellig-1.740
Token disability
Token ID14013
Feature activation+8.67e-01

Pos logit contributions
resa+2.894
lot+2.748
iesta+2.682
lace+2.653
yrinth+2.635
Neg logit contributions
 indu-3.353
 ruining-2.936
 popping-2.903
 scient-2.842
 obser-2.671
Token proposal
Token ID6961
Feature activation-1.23e+00

Pos logit contributions
 indu+0.808
 ruining+0.717
 popping+0.706
 scient+0.693
 intellig+0.657
Neg logit contributions
resa-0.586
lot-0.560
yrinth-0.550
iesta-0.549
lace-0.543
Token the
Token ID262
Feature activation+3.46e-01

Pos logit contributions
resa+0.840
lot+0.798
iesta+0.778
yrinth+0.775
lace+0.773
Neg logit contributions
 indu-1.146
 ruining-1.012
 popping-0.996
 scient-0.983
 intellig-0.928
Token Conservatives
Token ID17897
Feature activation+8.73e-01

Pos logit contributions
 indu+0.280
 ruining+0.243
 popping+0.239
 scient+0.234
 intellig+0.219
Neg logit contributions
resa-0.279
lot-0.266
iesta-0.261
yrinth-0.259
lace-0.259
Token made
Token ID925
Feature activation-4.61e-01

Pos logit contributions
 indu+0.746
 ruining+0.653
 popping+0.642
 scient+0.629
 intellig+0.593
Neg logit contributions
resa-0.658
lot-0.631
iesta-0.618
yrinth-0.618
lace-0.613
Token.
Token ID13
Feature activation+1.14e-01

Pos logit contributions
 indu+0.090
 ruining+0.079
 popping+0.078
 scient+0.077
 intellig+0.072
Neg logit contributions
resa-0.069
lot-0.066
iesta-0.065
yrinth-0.065
lace-0.064
Token
Token ID447
Feature activation-3.84e-01

Pos logit contributions
 indu+0.104
 ruining+0.092
 popping+0.091
 scient+0.089
 intellig+0.084
Neg logit contributions
resa-0.079
lot-0.075
iesta-0.074
yrinth-0.073
lace-0.073
Token
Token ID251
Feature activation-2.79e-01

Pos logit contributions
resa+0.315
lot+0.302
iesta+0.297
yrinth+0.297
lace+0.295
Neg logit contributions
 indu-0.303
 ruining-0.262
 popping-0.258
 scient-0.252
 intellig-0.236
Token<|endoftext|>
Token ID50256
Feature activation-3.58e-01

Pos logit contributions
resa+0.191
lot+0.184
iesta+0.179
lace+0.178
yrinth+0.177
Neg logit contributions
 indu-0.258
 ruining-0.227
 popping-0.224
 scient-0.219
 intellig-0.208
TokenOne
Token ID3198
Feature activation+5.70e-01

Pos logit contributions
resa+0.236
lot+0.225
iesta+0.220
yrinth+0.220
lace+0.218
Neg logit contributions
 indu-0.339
 ruining-0.302
 popping-0.297
 scient-0.292
 intellig-0.277
Token day
Token ID1110
Feature activation-3.91e+00

Pos logit contributions
 indu+0.473
 ruining+0.413
 popping+0.406
 scient+0.398
 intellig+0.373
Neg logit contributions
resa-0.444
lot-0.425
iesta-0.417
yrinth-0.416
lace-0.414
Token after
Token ID706
Feature activation-7.23e-01

Pos logit contributions
resa+2.948
lot+2.826
iesta+2.743
lace+2.728
yrinth+2.690
Neg logit contributions
 indu-3.300
 ruining-2.834
 popping-2.767
 scient-2.747
 obser-2.628
Token the
Token ID262
Feature activation-1.46e+00

Pos logit contributions
resa+0.613
lot+0.587
iesta+0.577
yrinth+0.573
lace+0.572
Neg logit contributions
 indu-0.552
 ruining-0.469
 popping-0.458
 scient-0.453
 intellig-0.422
Token PM
Token ID3122
Feature activation-2.03e-01

Pos logit contributions
resa+1.182
lot+1.114
iesta+1.093
yrinth+1.090
lace+1.086
Neg logit contributions
 indu-1.186
 ruining-1.020
 popping-0.997
 scient-0.979
 obser-0.921
Token appeared
Token ID4120
Feature activation+3.33e-02

Pos logit contributions
resa+0.141
lot+0.135
iesta+0.132
yrinth+0.132
lace+0.131
Neg logit contributions
 indu-0.185
 ruining-0.164
 popping-0.162
 scient-0.159
 intellig-0.150
Token to
Token ID284
Feature activation+4.33e-01

Pos logit contributions
 indu+0.027
 ruining+0.023
 popping+0.023
 scient+0.022
 intellig+0.021
Neg logit contributions
resa-0.027
lot-0.026
iesta-0.025
yrinth-0.025
lace-0.025
Token,
Token ID11
Feature activation+2.75e-01

Pos logit contributions
resa+0.313
lot+0.299
iesta+0.293
yrinth+0.292
lace+0.291
Neg logit contributions
 indu-0.370
 ruining-0.325
 popping-0.319
 scient-0.314
 intellig-0.296
Token it
Token ID340
Feature activation+3.13e-01

Pos logit contributions
 indu+0.203
 ruining+0.173
 popping+0.170
 scient+0.166
 intellig+0.154
Neg logit contributions
resa-0.239
lot-0.230
iesta-0.226
yrinth-0.226
lace-0.225
Token is
Token ID318
Feature activation-2.87e-01

Pos logit contributions
 indu+0.297
 ruining+0.263
 popping+0.259
 scient+0.255
 intellig+0.241
Neg logit contributions
resa-0.208
lot-0.198
iesta-0.193
yrinth-0.192
lace-0.191
Token fair
Token ID3148
Feature activation+8.14e-01

Pos logit contributions
resa+0.214
lot+0.206
iesta+0.200
yrinth+0.199
lace+0.199
Neg logit contributions
 indu-0.247
 ruining-0.215
 popping-0.211
 scient-0.207
 obser-0.196
Token to
Token ID284
Feature activation-5.28e-01

Pos logit contributions
 indu+0.623
 ruining+0.537
 popping+0.527
 scient+0.516
 intellig+0.481
Neg logit contributions
resa-0.686
lot-0.660
iesta-0.648
yrinth-0.648
lace-0.644
Token assume
Token ID7048
Feature activation-3.87e+00

Pos logit contributions
resa+0.385
lot+0.368
lace+0.355
iesta+0.355
yrinth+0.352
Neg logit contributions
 indu-0.461
 ruining-0.406
 popping-0.395
 scient-0.387
 disse-0.366
Token that
Token ID326
Feature activation-1.07e-01

Pos logit contributions
resa+2.897
lot+2.767
iesta+2.688
lace+2.680
yrinth+2.677
Neg logit contributions
 indu-3.285
 ruining-2.810
 popping-2.774
 scient-2.711
 obser-2.606
Token there
Token ID612
Feature activation+7.97e-02

Pos logit contributions
resa+0.088
lot+0.085
iesta+0.083
yrinth+0.083
lace+0.083
Neg logit contributions
 indu-0.084
 ruining-0.072
 popping-0.070
 scient-0.069
 intellig-0.065
Token is
Token ID318
Feature activation+5.66e-01

Pos logit contributions
 indu+0.073
 ruining+0.065
 popping+0.064
 scient+0.063
 intellig+0.059
Neg logit contributions
resa-0.055
lot-0.052
iesta-0.051
yrinth-0.051
lace-0.051
Token some
Token ID617
Feature activation+6.67e-01

Pos logit contributions
 indu+0.489
 ruining+0.429
 popping+0.421
 scient+0.413
 intellig+0.389
Neg logit contributions
resa-0.422
lot-0.404
iesta-0.395
yrinth-0.394
lace-0.392
Token degree
Token ID4922
Feature activation-5.43e-01

Pos logit contributions
 indu+0.512
 ruining+0.442
 popping+0.433
 scient+0.423
 intellig+0.395
Neg logit contributions
resa-0.561
lot-0.540
iesta-0.530
yrinth-0.528
lace-0.526
Token it
Token ID340
Feature activation-1.69e-01

Pos logit contributions
resa+0.454
lot+0.436
iesta+0.427
yrinth+0.425
lace+0.425
Neg logit contributions
 indu-0.449
 ruining-0.387
 popping-0.381
 scient-0.373
 obser-0.348
Token after
Token ID706
Feature activation-1.02e+00

Pos logit contributions
resa+0.118
lot+0.113
iesta+0.110
yrinth+0.110
lace+0.109
Neg logit contributions
 indu-0.154
 ruining-0.136
 popping-0.134
 scient-0.131
 intellig-0.125
Token."
Token ID526
Feature activation+4.23e-01

Pos logit contributions
resa+0.862
lot+0.829
iesta+0.814
yrinth+0.813
lace+0.808
Neg logit contributions
 indu-0.783
 ruining-0.671
 popping-0.659
 scient-0.647
 intellig-0.602
Token
Token ID198
Feature activation-2.61e-01

Pos logit contributions
 indu+0.403
 ruining+0.359
 popping+0.353
 scient+0.347
 intellig+0.329
Neg logit contributions
resa-0.278
lot-0.264
iesta-0.258
yrinth-0.258
lace-0.256
Token
Token ID198
Feature activation-1.95e-02

Pos logit contributions
resa+0.167
lot+0.157
yrinth+0.157
iesta+0.155
lace+0.152
Neg logit contributions
 indu-0.251
 ruining-0.225
 popping-0.222
 scient-0.218
 intellig-0.208
Token'
Token ID6
Feature activation-3.87e+00

Pos logit contributions
resa+0.013
lot+0.012
yrinth+0.012
iesta+0.012
lace+0.012
Neg logit contributions
 indu-0.018
 ruining-0.016
 popping-0.016
 scient-0.016
 intellig-0.015
TokenCommon
Token ID17227
Feature activation+2.77e+00

Pos logit contributions
resa+2.421
lot+2.355
lace+2.253
iesta+2.251
yrinth+2.205
Neg logit contributions
 indu-3.808
 ruining-3.353
 popping-3.345
 scient-3.283
 obser-3.150
Token threat
Token ID2372
Feature activation+9.57e-01

Pos logit contributions
 indu+1.970
 ruining+1.682
 popping+1.647
 scient+1.605
 intellig+1.505
Neg logit contributions
resa-2.474
lot-2.383
yrinth-2.343
iesta-2.340
lace-2.321
Token'
Token ID6
Feature activation-1.90e+00

Pos logit contributions
 indu+0.830
 ruining+0.730
 popping+0.718
 scient+0.703
 intellig+0.664
Neg logit contributions
resa-0.710
lot-0.679
yrinth-0.667
iesta-0.665
lace-0.660
Token
Token ID198
Feature activation+3.84e-01

Pos logit contributions
resa+1.183
lot+1.121
iesta+1.093
yrinth+1.087
lace+1.083
Neg logit contributions
 indu-1.875
 ruining-1.671
 popping-1.648
 scient-1.622
 intellig-1.541
Token
Token ID198
Feature activation+3.34e-01

Pos logit contributions
 indu+0.356
 ruining+0.321
 popping+0.316
 scient+0.310
 intellig+0.297
Neg logit contributions
resa-0.255
yrinth-0.243
lot-0.238
iesta-0.236
lace-0.232
Token work
Token ID670
Feature activation+7.83e-01

Pos logit contributions
resa+0.040
lot+0.038
iesta+0.038
yrinth+0.037
lace+0.037
Neg logit contributions
 indu-0.038
 ruining-0.033
 popping-0.032
 scient-0.032
 obser-0.029
Token for
Token ID329
Feature activation-3.00e-01

Pos logit contributions
 indu+0.611
 ruining+0.529
 popping+0.520
 scient+0.509
 intellig+0.478
Neg logit contributions
resa-0.647
lot-0.621
iesta-0.612
yrinth-0.610
lace-0.606
Token the
Token ID262
Feature activation+6.30e-02

Pos logit contributions
resa+0.254
lot+0.244
iesta+0.239
yrinth+0.239
lace+0.238
Neg logit contributions
 indu-0.228
 ruining-0.196
 popping-0.192
 scient-0.188
 intellig-0.175
Token long
Token ID890
Feature activation-8.23e-01

Pos logit contributions
 indu+0.052
 ruining+0.045
 popping+0.044
 scient+0.043
 intellig+0.041
Neg logit contributions
resa-0.050
lot-0.048
iesta-0.047
yrinth-0.047
lace-0.046
Token-
Token ID12
Feature activation-1.17e+00

Pos logit contributions
resa+0.625
lot+0.600
iesta+0.587
yrinth+0.585
lace+0.582
Neg logit contributions
 indu-0.698
 ruining-0.611
 popping-0.600
 scient-0.590
 intellig-0.554
Tokenterm
Token ID4354
Feature activation-3.87e+00

Pos logit contributions
resa+0.268
lot+0.228
iesta+0.216
yrinth+0.212
lace+0.206
Neg logit contributions
 indu-1.615
 ruining-1.493
 popping-1.479
 scient-1.459
 intellig-1.410
Token movement
Token ID3356
Feature activation-2.01e+00

Pos logit contributions
resa+2.876
lot+2.754
iesta+2.703
lace+2.665
yrinth+2.665
Neg logit contributions
 indu-3.312
 ruining-2.889
 popping-2.851
 scient-2.807
 disse-2.620
Token,
Token ID11
Feature activation-1.96e-01

Pos logit contributions
resa+1.521
lot+1.459
iesta+1.423
yrinth+1.415
lace+1.414
Neg logit contributions
 indu-1.711
 ruining-1.495
 popping-1.470
 scient-1.445
 disse-1.355
Token
Token ID447
Feature activation-2.60e-01

Pos logit contributions
resa+0.150
lot+0.144
iesta+0.141
yrinth+0.140
lace+0.140
Neg logit contributions
 indu-0.165
 ruining-0.144
 popping-0.142
 scient-0.139
 intellig-0.130
Token
Token ID251
Feature activation-5.63e-01

Pos logit contributions
resa+0.195
lot+0.187
iesta+0.183
yrinth+0.183
lace+0.182
Neg logit contributions
 indu-0.222
 ruining-0.195
 popping-0.192
 scient-0.188
 intellig-0.177
Token said
Token ID531
Feature activation+5.45e-01

Pos logit contributions
resa+0.396
lot+0.379
iesta+0.369
yrinth+0.368
lace+0.366
Neg logit contributions
 indu-0.509
 ruining-0.448
 popping-0.442
 scient-0.435
 disse-0.409
Token're
Token ID821
Feature activation-1.17e+00

Pos logit contributions
resa+0.295
lot+0.280
iesta+0.273
yrinth+0.271
lace+0.271
Neg logit contributions
 indu-0.401
 ruining-0.354
 popping-0.348
 scient-0.344
 obser-0.323
Token changing
Token ID5609
Feature activation-3.67e-01

Pos logit contributions
resa+0.973
lot+0.935
iesta+0.914
yrinth+0.907
lace+0.903
Neg logit contributions
 indu-0.903
 ruining-0.759
 scient-0.748
 popping-0.746
 obser-0.702
Token all
Token ID477
Feature activation-4.79e-01

Pos logit contributions
resa+0.306
lot+0.294
iesta+0.290
lace+0.287
yrinth+0.287
Neg logit contributions
 indu-0.283
 ruining-0.243
 popping-0.239
 scient-0.234
 intellig-0.219
Token of
Token ID286
Feature activation-1.28e+00

Pos logit contributions
resa+0.387
lot+0.372
iesta+0.364
yrinth+0.363
lace+0.362
Neg logit contributions
 indu-0.383
 ruining-0.332
 popping-0.325
 scient-0.318
 intellig-0.298
Token that
Token ID326
Feature activation-1.47e+00

Pos logit contributions
resa+1.035
lot+0.996
iesta+0.974
yrinth+0.971
lace+0.970
Neg logit contributions
 indu-1.020
 ruining-0.880
 popping-0.863
 scient-0.843
 intellig-0.792
Token.'
Token ID2637
Feature activation-3.83e+00

Pos logit contributions
resa+1.057
lot+1.012
iesta+0.987
lace+0.977
yrinth+0.976
Neg logit contributions
 indu-1.299
 ruining-1.136
 popping-1.118
 scient-1.102
 disse-1.040
Token That
Token ID1320
Feature activation-1.50e+00

Pos logit contributions
resa+3.053
lot+2.962
iesta+2.868
lace+2.850
yrinth+2.818
Neg logit contributions
 indu-3.111
 ruining-2.656
 popping-2.606
 scient-2.563
 obser-2.459
Token's
Token ID338
Feature activation-1.23e-01

Pos logit contributions
resa+0.985
lot+0.933
iesta+0.904
lace+0.896
yrinth+0.894
Neg logit contributions
 indu-1.418
 ruining-1.250
 popping-1.228
 scient-1.219
 intellig-1.152
Token up
Token ID510
Feature activation-1.13e+00

Pos logit contributions
resa+0.103
lot+0.099
iesta+0.097
lace+0.096
yrinth+0.096
Neg logit contributions
 indu-0.095
 ruining-0.080
 popping-0.079
 scient-0.077
 obser-0.073
Tokenending
Token ID1571
Feature activation+1.29e+00

Pos logit contributions
resa+0.888
lot+0.856
iesta+0.834
yrinth+0.831
lace+0.824
Neg logit contributions
 indu-0.922
 ruining-0.798
 popping-0.777
 scient-0.772
 obser-0.718
Token 10
Token ID838
Feature activation+2.24e-01

Pos logit contributions
 indu+0.946
 ruining+0.816
 popping+0.801
 scient+0.781
 intellig+0.727
Neg logit contributions
resa-1.129
lot-1.088
yrinth-1.076
iesta-1.069
lace-1.065
Token using
Token ID1262
Feature activation+2.44e-01

Pos logit contributions
 indu+0.468
 ruining+0.410
 popping+0.403
 scient+0.394
 intellig+0.372
Neg logit contributions
resa-0.417
lot-0.398
iesta-0.390
yrinth-0.389
lace-0.387
Token only
Token ID691
Feature activation+2.00e-01

Pos logit contributions
 indu+0.188
 ruining+0.163
 popping+0.159
 scient+0.156
 intellig+0.146
Neg logit contributions
resa-0.204
lot-0.196
iesta-0.192
yrinth-0.192
lace-0.191
Token 5
Token ID642
Feature activation-4.71e-01

Pos logit contributions
 indu+0.156
 ruining+0.135
 popping+0.132
 scient+0.129
 intellig+0.121
Neg logit contributions
resa-0.166
lot-0.160
iesta-0.157
yrinth-0.156
lace-0.156
Token total
Token ID2472
Feature activation-7.48e-01

Pos logit contributions
resa+0.381
lot+0.367
iesta+0.359
yrinth+0.358
lace+0.357
Neg logit contributions
 indu-0.375
 ruining-0.326
 popping-0.319
 scient-0.313
 intellig-0.292
Token portal
Token ID17898
Feature activation-1.81e-01

Pos logit contributions
resa+0.611
lot+0.587
iesta+0.575
yrinth+0.573
lace+0.572
Neg logit contributions
 indu-0.590
 ruining-0.511
 popping-0.500
 scient-0.491
 intellig-0.456
Token plac
Token ID21957
Feature activation-3.80e+00

Pos logit contributions
resa+0.153
lot+0.148
iesta+0.145
yrinth+0.144
lace+0.144
Neg logit contributions
 indu-0.138
 ruining-0.119
 popping-0.116
 scient-0.114
 intellig-0.106
Tokenements
Token ID3196
Feature activation-2.03e+00

Pos logit contributions
resa+2.016
lot+1.915
yrinth+1.818
iesta+1.809
lace+1.796
Neg logit contributions
 indu-4.050
 ruining-3.679
 popping-3.613
 scient-3.588
 proble-3.426
Token (
Token ID357
Feature activation-2.99e-01

Pos logit contributions
resa+1.456
lot+1.409
iesta+1.358
yrinth+1.354
lace+1.353
Neg logit contributions
 indu-1.787
 ruining-1.566
 popping-1.537
 scient-1.527
 disse-1.427
Token29
Token ID1959
Feature activation-4.78e-01

Pos logit contributions
resa+0.223
lot+0.214
iesta+0.209
yrinth+0.209
lace+0.208
Neg logit contributions
 indu-0.258
 ruining-0.227
 popping-0.223
 scient-0.219
 intellig-0.206
Token)
Token ID8
Feature activation+2.81e-01

Pos logit contributions
resa+0.280
lot+0.265
iesta+0.258
yrinth+0.258
lace+0.255
Neg logit contributions
 indu-0.489
 ruining-0.438
 popping-0.432
 scient-0.425
 intellig-0.405
Token
Token ID198
Feature activation-6.95e-01

Pos logit contributions
 indu+0.273
 ruining+0.243
 popping+0.239
 scient+0.236
 intellig+0.224
Neg logit contributions
resa-0.180
lot-0.170
iesta-0.166
yrinth-0.165
lace-0.164
Token claiming
Token ID8512
Feature activation-6.31e-01

Pos logit contributions
resa+0.045
lot+0.044
yrinth+0.043
iesta+0.043
lace+0.042
Neg logit contributions
 indu-0.039
 ruining-0.034
 popping-0.033
 scient-0.032
 disse-0.030
Token at
Token ID379
Feature activation+2.78e-01

Pos logit contributions
resa+0.478
lot+0.457
iesta+0.450
yrinth+0.447
lace+0.445
Neg logit contributions
 indu-0.537
 ruining-0.470
 popping-0.463
 scient-0.454
 intellig-0.427
Token least
Token ID1551
Feature activation-5.25e-01

Pos logit contributions
 indu+0.238
 ruining+0.209
 popping+0.205
 scient+0.201
 intellig+0.190
Neg logit contributions
resa-0.209
lot-0.200
iesta-0.196
yrinth-0.195
lace-0.194
Token short
Token ID1790
Feature activation+1.09e+00

Pos logit contributions
resa+0.371
lot+0.356
iesta+0.347
yrinth+0.346
lace+0.343
Neg logit contributions
 indu-0.472
 ruining-0.415
 popping-0.408
 scient-0.401
 intellig-0.378
Token-
Token ID12
Feature activation-1.42e+00

Pos logit contributions
 indu+0.978
 ruining+0.862
 popping+0.849
 scient+0.833
 intellig+0.787
Neg logit contributions
resa-0.776
lot-0.739
iesta-0.725
yrinth-0.724
lace-0.718
Tokenterm
Token ID4354
Feature activation-3.79e+00

Pos logit contributions
resa+0.297
lot+0.251
iesta+0.230
yrinth+0.228
lace+0.222
Neg logit contributions
 indu-1.992
 ruining-1.842
 popping-1.824
 scient-1.804
 intellig-1.743
Token results
Token ID2482
Feature activation+7.12e-01

Pos logit contributions
resa+2.992
lot+2.859
iesta+2.789
lace+2.740
yrinth+2.726
Neg logit contributions
 indu-3.032
 ruining-2.637
 popping-2.568
 scient-2.565
 proble-2.385
Token;
Token ID26
Feature activation-7.89e-03

Pos logit contributions
 indu+0.636
 ruining+0.562
 popping+0.553
 scient+0.542
 intellig+0.512
Neg logit contributions
resa-0.509
lot-0.486
iesta-0.476
yrinth-0.475
lace-0.472
Token the
Token ID262
Feature activation-2.77e-01

Pos logit contributions
resa+0.006
lot+0.006
iesta+0.006
yrinth+0.006
lace+0.006
Neg logit contributions
 indu-0.006
 ruining-0.005
 popping-0.005
 scient-0.005
 intellig-0.005
Token street
Token ID4675
Feature activation-3.29e-01

Pos logit contributions
resa+0.224
lot+0.211
iesta+0.207
yrinth+0.206
lace+0.205
Neg logit contributions
 indu-0.226
 ruining-0.197
 popping-0.192
 scient-0.189
 disse-0.177
Token-
Token ID12
Feature activation+5.24e-01

Pos logit contributions
resa+0.262
lot+0.251
iesta+0.246
yrinth+0.244
lace+0.244
Neg logit contributions
 indu-0.268
 ruining-0.233
 popping-0.228
 scient-0.226
 intellig-0.210
Token taken
Token ID2077
Feature activation-6.89e-01

Pos logit contributions
resa+0.095
lot+0.091
iesta+0.089
yrinth+0.089
lace+0.088
Neg logit contributions
 indu-0.099
 ruining-0.087
 popping-0.085
 scient-0.083
 intellig-0.078
Token out
Token ID503
Feature activation+1.21e-01

Pos logit contributions
resa+0.567
lot+0.547
iesta+0.537
yrinth+0.532
lace+0.531
Neg logit contributions
 indu-0.538
 ruining-0.462
 popping-0.452
 scient-0.443
 intellig-0.414
Token a
Token ID257
Feature activation-1.79e-01

Pos logit contributions
 indu+0.092
 ruining+0.079
 popping+0.078
 scient+0.076
 intellig+0.071
Neg logit contributions
resa-0.102
lot-0.099
iesta-0.097
yrinth-0.096
lace-0.096
Token long
Token ID890
Feature activation-3.40e-01

Pos logit contributions
resa+0.146
lot+0.140
iesta+0.137
yrinth+0.137
lace+0.136
Neg logit contributions
 indu-0.143
 ruining-0.123
 popping-0.121
 scient-0.119
 intellig-0.111
Token-
Token ID12
Feature activation-1.12e+00

Pos logit contributions
resa+0.261
lot+0.252
iesta+0.247
lace+0.244
yrinth+0.244
Neg logit contributions
 indu-0.284
 ruining-0.248
 popping-0.244
 scient-0.240
 intellig-0.225
Tokenterm
Token ID4354
Feature activation-3.78e+00

Pos logit contributions
resa+0.597
lot+0.558
iesta+0.545
yrinth+0.544
lace+0.536
Neg logit contributions
 indu-1.207
 ruining-1.091
 popping-1.076
 scient-1.058
 intellig-1.011
Token lease
Token ID15278
Feature activation-7.96e-01

Pos logit contributions
resa+2.703
lot+2.612
iesta+2.543
lace+2.485
yrinth+2.460
Neg logit contributions
 indu-3.287
 ruining-2.868
 popping-2.843
 scient-2.794
 obser-2.637
Token.
Token ID13
Feature activation-2.49e-01

Pos logit contributions
resa+0.593
lot+0.567
iesta+0.556
yrinth+0.554
lace+0.551
Neg logit contributions
 indu-0.687
 ruining-0.603
 popping-0.593
 scient-0.582
 intellig-0.548
Token Gl
Token ID2671
Feature activation+7.79e-01

Pos logit contributions
resa+0.189
lot+0.182
iesta+0.178
lace+0.176
yrinth+0.176
Neg logit contributions
 indu-0.213
 ruining-0.186
 popping-0.183
 scient-0.179
 intellig-0.168
Tokenü
Token ID9116
Feature activation+2.15e+00

Pos logit contributions
 indu+0.716
 ruining+0.635
 popping+0.626
 scient+0.616
 intellig+0.582
Neg logit contributions
resa-0.530
lot-0.504
yrinth-0.494
iesta-0.494
lace-0.492
Tokenck
Token ID694
Feature activation-5.91e-02

Pos logit contributions
 indu+2.036
 ruining+1.814
 popping+1.791
 scient+1.765
 intellig+1.667
Neg logit contributions
resa-1.398
lot-1.319
yrinth-1.292
iesta-1.286
lace-1.281
Token cross
Token ID3272
Feature activation+2.57e-01

Pos logit contributions
resa+0.796
lot+0.765
iesta+0.750
yrinth+0.748
lace+0.748
Neg logit contributions
 indu-0.831
 ruining-0.720
 popping-0.707
 scient-0.696
 intellig-0.650
Tokenfire
Token ID6495
Feature activation+8.98e-01

Pos logit contributions
 indu+0.292
 ruining+0.264
 popping+0.261
 scient+0.258
 intellig+0.247
Neg logit contributions
resa-0.122
lot-0.115
yrinth-0.110
iesta-0.109
lace-0.109
Token.
Token ID13
Feature activation+2.57e-01

Pos logit contributions
 indu+0.861
 ruining+0.772
 popping+0.760
 scient+0.742
 intellig+0.708
Neg logit contributions
resa-0.584
lot-0.551
yrinth-0.543
iesta-0.542
lace-0.536
Token
Token ID198
Feature activation+2.12e-01

Pos logit contributions
 indu+0.236
 ruining+0.208
 popping+0.205
 scient+0.201
 intellig+0.191
Neg logit contributions
resa-0.178
lot-0.170
iesta-0.166
lace-0.165
yrinth-0.164
Token
Token ID198
Feature activation+4.51e-01

Pos logit contributions
 indu+0.199
 ruining+0.179
 popping+0.177
 scient+0.173
 intellig+0.166
Neg logit contributions
resa-0.138
yrinth-0.131
lot-0.129
iesta-0.128
lace-0.126
TokenAdvertisement
Token ID4723
Feature activation-3.78e+00

Pos logit contributions
 indu+0.407
 ruining+0.360
 popping+0.355
 scient+0.348
 intellig+0.329
Neg logit contributions
resa-0.316
lot-0.301
iesta-0.295
yrinth-0.295
lace-0.292
Token
Token ID198
Feature activation+7.38e-01

Pos logit contributions
resa+2.329
lot+2.199
lace+2.151
iesta+2.150
yrinth+2.082
Neg logit contributions
 indu-3.738
 ruining-3.313
 popping-3.258
 scient-3.232
 obser-3.069
Token
Token ID198
Feature activation+6.43e-01

Pos logit contributions
 indu+0.694
 ruining+0.625
 popping+0.616
 scient+0.605
 intellig+0.578
Neg logit contributions
resa-0.480
yrinth-0.456
lot-0.451
iesta-0.446
lace-0.439
TokenAdvertisement
Token ID4723
Feature activation-2.90e+00

Pos logit contributions
 indu+0.587
 ruining+0.521
 popping+0.512
 scient+0.503
 intellig+0.476
Neg logit contributions
resa-0.444
lot-0.420
yrinth-0.416
iesta-0.414
lace-0.408
Token
Token ID198
Feature activation+6.01e-01

Pos logit contributions
resa+1.693
lot+1.616
iesta+1.556
lace+1.554
yrinth+1.501
Neg logit contributions
 indu-3.009
 ruining-2.677
 popping-2.635
 scient-2.598
 obser-2.519
Token
Token ID198
Feature activation+4.54e-01

Pos logit contributions
 indu+0.562
 ruining+0.505
 popping+0.499
 scient+0.489
 intellig+0.468
Neg logit contributions
resa-0.393
yrinth-0.374
lot-0.369
iesta-0.365
lace-0.359
Token not
Token ID407
Feature activation-1.88e-01

Pos logit contributions
 indu+0.557
 ruining+0.482
 popping+0.473
 scient+0.462
 intellig+0.432
Neg logit contributions
resa-0.586
lot-0.564
iesta-0.553
yrinth-0.552
lace-0.549
Token right
Token ID826
Feature activation-4.06e-01

Pos logit contributions
resa+0.162
lot+0.156
iesta+0.153
yrinth+0.153
lace+0.152
Neg logit contributions
 indu-0.140
 ruining-0.119
 popping-0.115
 scient-0.115
 disse-0.106
Token there
Token ID612
Feature activation+6.78e-01

Pos logit contributions
resa+0.296
lot+0.282
iesta+0.277
yrinth+0.276
lace+0.274
Neg logit contributions
 indu-0.359
 ruining-0.316
 popping-0.311
 scient-0.305
 intellig-0.288
Token,"
Token ID553
Feature activation+9.07e-01

Pos logit contributions
 indu+0.607
 ruining+0.539
 popping+0.531
 scient+0.517
 intellig+0.491
Neg logit contributions
resa-0.484
lot-0.461
yrinth-0.453
iesta-0.453
lace-0.450
Token Ms
Token ID6997
Feature activation-3.12e+00

Pos logit contributions
 indu+0.797
 ruining+0.701
 popping+0.691
 scient+0.679
 intellig+0.642
Neg logit contributions
resa-0.658
lot-0.631
yrinth-0.620
iesta-0.619
lace-0.614
Token Ag
Token ID2449
Feature activation-3.76e+00

Pos logit contributions
resa+2.154
lot+2.051
iesta+1.996
lace+1.984
yrinth+1.981
Neg logit contributions
 indu-2.858
 ruining-2.530
 popping-2.487
 scient-2.427
 obser-2.292
Tokenost
Token ID455
Feature activation-9.78e-01

Pos logit contributions
resa+3.100
lot+3.000
iesta+2.944
lace+2.911
yrinth+2.889
Neg logit contributions
 indu-3.019
 ruining-2.584
 popping-2.538
 scient-2.473
 obser-2.373
Tokenino
Token ID2879
Feature activation-1.30e+00

Pos logit contributions
resa+0.615
lot+0.584
iesta+0.570
yrinth+0.567
lace+0.564
Neg logit contributions
 indu-0.961
 ruining-0.857
 popping-0.844
 scient-0.830
 intellig-0.788
Token said
Token ID531
Feature activation+2.54e-01

Pos logit contributions
resa+0.754
lot+0.712
iesta+0.692
yrinth+0.689
lace+0.685
Neg logit contributions
 indu-1.341
 ruining-1.204
 popping-1.187
 scient-1.169
 intellig-1.112
Token.
Token ID13
Feature activation-1.35e-01

Pos logit contributions
 indu+0.254
 ruining+0.227
 popping+0.224
 scient+0.221
 intellig+0.210
Neg logit contributions
resa-0.154
lot-0.146
iesta-0.142
yrinth-0.141
lace-0.140
Token
Token ID198
Feature activation+2.67e-01

Pos logit contributions
resa+0.090
lot+0.086
iesta+0.084
yrinth+0.084
lace+0.083
Neg logit contributions
 indu-0.127
 ruining-0.113
 popping-0.111
 scient-0.109
 intellig-0.103
Token the
Token ID262
Feature activation-7.67e-02

Pos logit contributions
resa+0.046
lot+0.044
iesta+0.043
yrinth+0.043
lace+0.043
Neg logit contributions
 indu-0.038
 ruining-0.032
 popping-0.031
 scient-0.030
 obser-0.028
Token world
Token ID995
Feature activation-4.90e-01

Pos logit contributions
resa+0.065
lot+0.062
iesta+0.061
yrinth+0.061
lace+0.060
Neg logit contributions
 indu-0.059
 ruining-0.051
 popping-0.050
 scient-0.048
 disse-0.045
Token is
Token ID318
Feature activation+7.09e-02

Pos logit contributions
resa+0.363
lot+0.347
iesta+0.340
yrinth+0.338
lace+0.337
Neg logit contributions
 indu-0.426
 ruining-0.374
 popping-0.367
 scient-0.361
 intellig-0.339
Token being
Token ID852
Feature activation-1.21e+00

Pos logit contributions
 indu+0.055
 ruining+0.048
 popping+0.047
 scient+0.046
 intellig+0.043
Neg logit contributions
resa-0.058
lot-0.056
iesta-0.055
yrinth-0.055
lace-0.055
Token held
Token ID2714
Feature activation-4.06e-01

Pos logit contributions
resa+0.992
lot+0.953
yrinth+0.934
iesta+0.927
lace+0.924
Neg logit contributions
 indu-0.940
 ruining-0.815
 popping-0.799
 scient-0.782
 obser-0.725
Token hostage
Token ID23229
Feature activation-3.75e+00

Pos logit contributions
resa+0.303
lot+0.290
iesta+0.284
yrinth+0.284
lace+0.282
Neg logit contributions
 indu-0.349
 ruining-0.306
 popping-0.301
 scient-0.296
 intellig-0.278
Token by
Token ID416
Feature activation-1.06e-01

Pos logit contributions
resa+3.054
lot+2.963
iesta+2.889
lace+2.888
yrinth+2.846
Neg logit contributions
 indu-2.927
 ruining-2.484
 popping-2.434
 scient-2.407
 obser-2.275
Token 3
Token ID513
Feature activation+4.84e-02

Pos logit contributions
resa+0.092
lot+0.088
iesta+0.087
yrinth+0.086
lace+0.086
Neg logit contributions
 indu-0.078
 ruining-0.067
 popping-0.065
 scient-0.063
 obser-0.059
TokenDES
Token ID30910
Feature activation-4.31e-01

Pos logit contributions
 indu+0.048
 ruining+0.042
 popping+0.042
 scient+0.041
 intellig+0.039
Neg logit contributions
resa-0.030
lot-0.029
iesta-0.028
yrinth-0.028
lace-0.028
Token.
Token ID13
Feature activation-5.49e-02

Pos logit contributions
resa+0.298
lot+0.285
iesta+0.278
yrinth+0.277
lace+0.275
Neg logit contributions
 indu-0.395
 ruining-0.348
 popping-0.342
 scient-0.338
 intellig-0.318
Token
Token ID198
Feature activation-3.03e-01

Pos logit contributions
resa+0.042
lot+0.041
iesta+0.040
lace+0.040
yrinth+0.040
Neg logit contributions
 indu-0.046
 ruining-0.040
 popping-0.039
 scient-0.039
 obser-0.036
Token let
Token ID1309
Feature activation+2.78e-01

Pos logit contributions
resa+0.834
lot+0.800
iesta+0.789
yrinth+0.780
lace+0.778
Neg logit contributions
 indu-0.731
 ruining-0.631
 popping-0.621
 scient-0.605
 obser-0.558
Token the
Token ID262
Feature activation+9.80e-03

Pos logit contributions
 indu+0.208
 ruining+0.178
 popping+0.175
 scient+0.171
 intellig+0.159
Neg logit contributions
resa-0.239
lot-0.230
iesta-0.226
yrinth-0.226
lace-0.225
Token future
Token ID2003
Feature activation-7.39e-01

Pos logit contributions
 indu+0.007
 ruining+0.006
 popping+0.006
 scient+0.006
 obser+0.005
Neg logit contributions
resa-0.009
lot-0.008
iesta-0.008
yrinth-0.008
lace-0.008
Token be
Token ID307
Feature activation-2.96e-01

Pos logit contributions
resa+0.620
lot+0.596
iesta+0.583
yrinth+0.583
lace+0.583
Neg logit contributions
 indu-0.567
 ruining-0.486
 popping-0.478
 scient-0.469
 intellig-0.435
Token held
Token ID2714
Feature activation-4.39e-01

Pos logit contributions
resa+0.241
lot+0.232
yrinth+0.226
iesta+0.226
lace+0.225
Neg logit contributions
 indu-0.234
 ruining-0.202
 popping-0.199
 scient-0.194
 intellig-0.181
Token hostage
Token ID23229
Feature activation-3.75e+00

Pos logit contributions
resa+0.327
lot+0.313
iesta+0.306
yrinth+0.305
lace+0.304
Neg logit contributions
 indu-0.378
 ruining-0.332
 popping-0.326
 scient-0.320
 intellig-0.301
Token by
Token ID416
Feature activation-2.84e-01

Pos logit contributions
resa+2.928
lot+2.811
iesta+2.755
lace+2.746
yrinth+2.699
Neg logit contributions
 indu-3.058
 ruining-2.587
 popping-2.568
 scient-2.535
 obser-2.395
Token the
Token ID262
Feature activation-6.07e-01

Pos logit contributions
resa+0.247
lot+0.238
iesta+0.234
yrinth+0.233
lace+0.232
Neg logit contributions
 indu-0.208
 ruining-0.175
 popping-0.172
 scient-0.167
 obser-0.157
Token failures
Token ID15536
Feature activation-1.06e+00

Pos logit contributions
resa+0.525
lot+0.502
iesta+0.492
yrinth+0.492
lace+0.490
Neg logit contributions
 indu-0.453
 ruining-0.385
 popping-0.378
 scient-0.369
 obser-0.344
Token of
Token ID286
Feature activation+3.58e-01

Pos logit contributions
resa+0.793
lot+0.759
iesta+0.743
yrinth+0.742
lace+0.739
Neg logit contributions
 indu-0.905
 ruining-0.791
 popping-0.778
 scient-0.764
 intellig-0.719
Token the
Token ID262
Feature activation+1.77e-01

Pos logit contributions
 indu+0.254
 ruining+0.214
 popping+0.210
 scient+0.204
 obser+0.189
Neg logit contributions
resa-0.322
lot-0.309
iesta-0.305
yrinth-0.304
lace-0.303
Token politics
Token ID4819
Feature activation+6.31e-01

Pos logit contributions
 indu+0.706
 ruining+0.602
 popping+0.589
 scient+0.575
 intellig+0.532
Neg logit contributions
resa-0.881
lot-0.849
iesta-0.835
yrinth-0.833
lace-0.829
Token has
Token ID468
Feature activation+8.17e-01

Pos logit contributions
 indu+0.557
 ruining+0.491
 popping+0.483
 scient+0.474
 intellig+0.447
Neg logit contributions
resa-0.458
lot-0.438
iesta-0.429
yrinth-0.428
lace-0.425
Token become
Token ID1716
Feature activation+2.68e-01

Pos logit contributions
 indu+0.710
 ruining+0.625
 popping+0.615
 scient+0.603
 intellig+0.569
Neg logit contributions
resa-0.603
lot-0.576
iesta-0.567
yrinth-0.565
lace-0.562
Token that
Token ID326
Feature activation-2.06e-02

Pos logit contributions
 indu+0.247
 ruining+0.219
 popping+0.215
 scient+0.211
 intellig+0.200
Neg logit contributions
resa-0.184
lot-0.175
iesta-0.171
yrinth-0.171
lace-0.170
Token one
Token ID530
Feature activation+3.13e-01

Pos logit contributions
resa+0.017
lot+0.016
iesta+0.016
yrinth+0.016
lace+0.016
Neg logit contributions
 indu-0.016
 ruining-0.014
 popping-0.014
 scient-0.013
 obser-0.013
Token assumes
Token ID18533
Feature activation-3.74e+00

Pos logit contributions
 indu+0.256
 ruining+0.223
 popping+0.218
 scient+0.214
 intellig+0.200
Neg logit contributions
resa-0.247
lot-0.237
iesta-0.232
yrinth-0.231
lace-0.230
Token that
Token ID326
Feature activation-5.56e-01

Pos logit contributions
resa+2.803
lot+2.661
iesta+2.604
lace+2.596
yrinth+2.571
Neg logit contributions
 indu-3.131
 ruining-2.691
 popping-2.655
 scient-2.581
 obser-2.507
Token a
Token ID257
Feature activation-3.25e-01

Pos logit contributions
resa+0.457
lot+0.437
iesta+0.428
lace+0.425
yrinth+0.425
Neg logit contributions
 indu-0.436
 ruining-0.372
 popping-0.365
 scient-0.357
 obser-0.337
Token politician
Token ID14971
Feature activation-9.28e-01

Pos logit contributions
resa+0.267
lot+0.257
iesta+0.250
lace+0.249
yrinth+0.249
Neg logit contributions
 indu-0.255
 ruining-0.220
 popping-0.216
 scient-0.211
 obser-0.197
Token who
Token ID508
Feature activation-9.86e-01

Pos logit contributions
resa+0.663
lot+0.635
iesta+0.614
lace+0.612
yrinth+0.610
Neg logit contributions
 indu-0.827
 ruining-0.721
 popping-0.709
 scient-0.700
 obser-0.661
Token defends
Token ID33446
Feature activation+6.06e-02

Pos logit contributions
resa+0.750
lot+0.718
iesta+0.697
lace+0.696
yrinth+0.693
Neg logit contributions
 indu-0.830
 ruining-0.723
 popping-0.709
 scient-0.696
 obser-0.655
Token Credit
Token ID10504
Feature activation-2.11e+00

Pos logit contributions
 indu+0.852
 ruining+0.754
 popping+0.744
 scient+0.731
 intellig+0.690
Neg logit contributions
resa-0.673
lot-0.639
yrinth-0.632
iesta-0.631
lace-0.621
Token Reporting
Token ID29595
Feature activation+3.07e-01

Pos logit contributions
resa+1.598
lot+1.534
iesta+1.495
lace+1.490
yrinth+1.486
Neg logit contributions
 indu-1.791
 ruining-1.563
 popping-1.534
 scient-1.508
 intellig-1.420
Token Act
Token ID2191
Feature activation-8.35e-02

Pos logit contributions
 indu+0.272
 ruining+0.239
 popping+0.235
 scient+0.231
 intellig+0.217
Neg logit contributions
resa-0.223
lot-0.213
iesta-0.208
yrinth-0.207
lace-0.207
Token (
Token ID357
Feature activation-3.06e-01

Pos logit contributions
resa+0.063
lot+0.060
iesta+0.059
yrinth+0.059
lace+0.058
Neg logit contributions
 indu-0.072
 ruining-0.063
 popping-0.062
 scient-0.061
 intellig-0.057
TokenFC
Token ID4851
Feature activation-1.05e+00

Pos logit contributions
resa+0.143
lot+0.133
iesta+0.129
yrinth+0.128
lace+0.127
Neg logit contributions
 indu-0.348
 ruining-0.316
 popping-0.312
 scient-0.308
 intellig-0.294
TokenRA
Token ID3861
Feature activation+2.49e+00

Pos logit contributions
resa+0.446
lot+0.414
iesta+0.399
yrinth+0.399
lace+0.393
Neg logit contributions
 indu-1.233
 ruining-1.123
 popping-1.111
 scient-1.097
 intellig-1.050
Token),
Token ID828
Feature activation-6.26e-01

Pos logit contributions
 indu+2.403
 ruining+2.140
 popping+2.107
 scient+2.077
 intellig+1.982
Neg logit contributions
resa-1.564
lot-1.506
iesta-1.480
yrinth-1.474
lace-1.455
Token 15
Token ID1315
Feature activation-4.37e-01

Pos logit contributions
resa+0.479
lot+0.458
iesta+0.449
yrinth+0.449
lace+0.446
Neg logit contributions
 indu-0.528
 ruining-0.460
 popping-0.452
 scient-0.444
 intellig-0.416
Token U
Token ID471
Feature activation+1.08e+00

Pos logit contributions
resa+0.330
lot+0.316
iesta+0.310
yrinth+0.309
lace+0.307
Neg logit contributions
 indu-0.372
 ruining-0.326
 popping-0.321
 scient-0.315
 intellig-0.296
Token.
Token ID13
Feature activation-5.63e-01

Pos logit contributions
 indu+1.014
 ruining+0.914
 popping+0.906
 scient+0.892
 intellig+0.849
Neg logit contributions
resa-0.701
yrinth-0.664
lot-0.657
iesta-0.646
lace-0.637
TokenS
Token ID50
Feature activation-8.62e-01

Pos logit contributions
resa+0.334
lot+0.315
yrinth+0.310
iesta+0.308
lace+0.303
Neg logit contributions
 indu-0.570
 ruining-0.511
 popping-0.505
 scient-0.497
 intellig-0.474
Token Hurricane
Token ID16004
Feature activation+1.69e+00

Pos logit contributions
 indu+0.041
 ruining+0.035
 popping+0.035
 scient+0.034
 intellig+0.032
Neg logit contributions
resa-0.043
lot-0.041
iesta-0.040
yrinth-0.040
lace-0.040
Token Matthew
Token ID9308
Feature activation+8.45e-01

Pos logit contributions
 indu+1.701
 ruining+1.533
 popping+1.507
 scient+1.486
 intellig+1.412
Neg logit contributions
resa-0.984
lot-0.944
yrinth-0.933
iesta-0.932
lace-0.915
Token in
Token ID287
Feature activation+3.89e-01

Pos logit contributions
 indu+0.761
 ruining+0.673
 popping+0.662
 scient+0.649
 intellig+0.613
Neg logit contributions
resa-0.598
lot-0.571
iesta-0.560
yrinth-0.560
lace-0.555
Token Kingston
Token ID34612
Feature activation+3.06e-01

Pos logit contributions
 indu+0.317
 ruining+0.276
 popping+0.271
 scient+0.265
 intellig+0.249
Neg logit contributions
resa-0.310
lot-0.297
iesta-0.292
yrinth-0.291
lace-0.289
Token,
Token ID11
Feature activation+5.96e-01

Pos logit contributions
 indu+0.271
 ruining+0.238
 popping+0.235
 scient+0.230
 intellig+0.217
Neg logit contributions
resa-0.221
lot-0.211
iesta-0.207
yrinth-0.206
lace-0.205
Token Jamaica
Token ID31620
Feature activation+2.71e+00

Pos logit contributions
 indu+0.496
 ruining+0.433
 popping+0.425
 scient+0.417
 intellig+0.391
Neg logit contributions
resa-0.464
lot-0.444
iesta-0.436
yrinth-0.435
lace-0.432
Token.
Token ID13
Feature activation+3.85e-01

Pos logit contributions
 indu+2.405
 ruining+2.124
 popping+2.099
 scient+2.054
 intellig+1.942
Neg logit contributions
resa-1.916
lot-1.829
iesta-1.813
yrinth-1.796
lace-1.789
Token Credit
Token ID10504
Feature activation-1.41e+00

Pos logit contributions
 indu+0.331
 ruining+0.290
 popping+0.286
 scient+0.280
 intellig+0.264
Neg logit contributions
resa-0.288
lot-0.276
iesta-0.270
yrinth-0.270
lace-0.268
Token:
Token ID25
Feature activation+6.07e-01

Pos logit contributions
resa+0.730
lot+0.684
yrinth+0.666
iesta+0.665
lace+0.656
Neg logit contributions
 indu-1.535
 ruining-1.388
 popping-1.370
 scient-1.350
 intellig-1.291
TokenAP
Token ID2969
Feature activation+9.24e-01

Pos logit contributions
 indu+0.548
 ruining+0.484
 popping+0.476
 scient+0.468
 intellig+0.442
Neg logit contributions
resa-0.427
lot-0.408
yrinth-0.399
iesta-0.399
lace-0.396
Token Cuban
Token ID18147
Feature activation+2.47e-01

Pos logit contributions
 indu+0.798
 ruining+0.701
 popping+0.689
 scient+0.677
 intellig+0.636
Neg logit contributions
resa-0.687
lot-0.657
yrinth-0.645
iesta-0.644
lace-0.640
Tokenetry
Token ID11973
Feature activation-1.01e+00

Pos logit contributions
resa+0.843
lot+0.798
iesta+0.774
yrinth+0.769
lace+0.767
Neg logit contributions
 indu-1.543
 ruining-1.385
 popping-1.366
 scient-1.345
 intellig-1.280
Token Arts
Token ID11536
Feature activation-2.26e-01

Pos logit contributions
resa+0.743
lot+0.715
iesta+0.693
yrinth+0.692
lace+0.690
Neg logit contributions
 indu-0.879
 ruining-0.771
 popping-0.754
 scient-0.741
 intellig-0.701
Token in
Token ID287
Feature activation+1.44e-01

Pos logit contributions
resa+0.167
lot+0.162
iesta+0.157
yrinth+0.157
lace+0.157
Neg logit contributions
 indu-0.195
 ruining-0.170
 popping-0.166
 scient-0.164
 intellig-0.155
Token Atlanta
Token ID9371
Feature activation+5.11e-02

Pos logit contributions
 indu+0.116
 ruining+0.101
 popping+0.099
 scient+0.096
 obser+0.090
Neg logit contributions
resa-0.115
lot-0.111
iesta-0.109
yrinth-0.108
lace-0.108
Token,
Token ID11
Feature activation+2.40e-01

Pos logit contributions
 indu+0.047
 ruining+0.042
 popping+0.041
 scient+0.040
 intellig+0.038
Neg logit contributions
resa-0.035
lot-0.034
iesta-0.033
yrinth-0.033
lace-0.032
Token Georgia
Token ID7859
Feature activation+2.67e+00

Pos logit contributions
 indu+0.225
 ruining+0.199
 popping+0.195
 scient+0.193
 intellig+0.182
Neg logit contributions
resa-0.160
lot-0.153
iesta-0.149
yrinth-0.149
lace-0.148
Token.[
Token ID3693
Feature activation+6.01e-01

Pos logit contributions
 indu+2.420
 ruining+2.165
 popping+2.142
 scient+2.084
 intellig+1.974
Neg logit contributions
resa-1.872
lot-1.758
iesta-1.747
yrinth-1.736
lace-1.716
Token7
Token ID22
Feature activation+1.02e+00

Pos logit contributions
 indu+0.524
 ruining+0.460
 popping+0.452
 scient+0.443
 intellig+0.418
Neg logit contributions
resa-0.443
lot-0.423
iesta-0.416
yrinth-0.415
lace-0.411
Token]
Token ID60
Feature activation-3.06e-01

Pos logit contributions
 indu+0.603
 ruining+0.495
 popping+0.482
 scient+0.468
 intellig+0.424
Neg logit contributions
resa-1.038
lot-1.005
iesta-0.991
yrinth-0.990
lace-0.985
Token
Token ID198
Feature activation-1.45e-01

Pos logit contributions
resa+0.228
lot+0.219
iesta+0.214
yrinth+0.213
lace+0.213
Neg logit contributions
 indu-0.264
 ruining-0.232
 popping-0.228
 scient-0.223
 intellig-0.210
Token
Token ID198
Feature activation-8.49e-02

Pos logit contributions
resa+0.094
yrinth+0.088
lot+0.088
iesta+0.087
lace+0.085
Neg logit contributions
 indu-0.138
 ruining-0.124
 popping-0.123
 scient-0.120
 intellig-0.115
Token ap
Token ID2471
Feature activation-6.57e-01

Pos logit contributions
resa+0.638
lot+0.616
iesta+0.605
lace+0.602
yrinth+0.601
Neg logit contributions
 indu-0.393
 ruining-0.324
 popping-0.311
 scient-0.304
 obser-0.277
Token.
Token ID13
Feature activation+9.43e-01

Pos logit contributions
resa+0.398
lot+0.376
yrinth+0.369
iesta+0.367
lace+0.363
Neg logit contributions
 indu-0.657
 ruining-0.589
 popping-0.581
 scient-0.571
 intellig-0.544
Tokenadd
Token ID2860
Feature activation+3.30e-01

Pos logit contributions
 indu+0.756
 ruining+0.657
 popping+0.652
 scient+0.631
 intellig+0.600
Neg logit contributions
resa-0.750
lot-0.714
iesta-0.711
yrinth-0.709
lace-0.698
Token_
Token ID62
Feature activation-3.00e-01

Pos logit contributions
 indu+0.367
 ruining+0.337
 popping+0.335
 scient+0.327
 intellig+0.317
Neg logit contributions
resa-0.155
yrinth-0.146
lot-0.143
iesta-0.141
lace-0.137
Tokenargument
Token ID49140
Feature activation-9.56e-01

Pos logit contributions
resa+0.229
lot+0.218
yrinth+0.216
iesta+0.215
lace+0.213
Neg logit contributions
 indu-0.252
 ruining-0.221
 popping-0.219
 scient-0.213
 intellig-0.202
Token("
Token ID7203
Feature activation+3.52e+00

Pos logit contributions
resa+0.764
lot+0.734
iesta+0.716
lace+0.714
yrinth+0.712
Neg logit contributions
 indu-0.780
 ruining-0.677
 popping-0.662
 scient-0.651
 obser-0.609
Token-
Token ID12
Feature activation-4.21e-02

Pos logit contributions
 indu+2.821
 ruining+2.494
 popping+2.492
 scient+2.404
 intellig+2.303
Neg logit contributions
resa-2.707
yrinth-2.585
iesta-2.565
lot-2.550
lace-2.491
Tokeni
Token ID72
Feature activation-1.23e+00

Pos logit contributions
resa+0.033
lot+0.031
iesta+0.031
yrinth+0.031
lace+0.030
Neg logit contributions
 indu-0.035
 ruining-0.030
 popping-0.030
 scient-0.029
 intellig-0.028
Token",
Token ID1600
Feature activation-1.35e+00

Pos logit contributions
resa+0.924
lot+0.885
iesta+0.866
yrinth+0.862
lace+0.859
Neg logit contributions
 indu-1.058
 ruining-0.926
 popping-0.910
 scient-0.894
 intellig-0.840
Token "
Token ID366
Feature activation+8.53e-01

Pos logit contributions
resa+1.125
lot+1.083
lace+1.060
iesta+1.058
yrinth+1.053
Neg logit contributions
 indu-1.046
 ruining-0.898
 popping-0.876
 scient-0.858
 obser-0.809
Token--
Token ID438
Feature activation+7.55e-01

Pos logit contributions
 indu+0.860
 ruining+0.778
 popping+0.769
 scient+0.755
 intellig+0.726
Neg logit contributions
resa-0.497
iesta-0.461
lot-0.461
yrinth-0.460
lace-0.444
Token
Token ID198
Feature activation+5.95e-02

Pos logit contributions
resa+0.011
lot+0.011
iesta+0.010
yrinth+0.010
lace+0.010
Neg logit contributions
 indu-0.017
 ruining-0.015
 popping-0.015
 scient-0.014
 intellig-0.014
Token
Token ID198
Feature activation+2.45e-01

Pos logit contributions
 indu+0.057
 ruining+0.051
 popping+0.050
 scient+0.049
 intellig+0.047
Neg logit contributions
resa-0.038
lot-0.036
yrinth-0.036
iesta-0.035
lace-0.035
TokenOfficials
Token ID25883
Feature activation-6.70e-01

Pos logit contributions
 indu+0.227
 ruining+0.202
 popping+0.198
 scient+0.195
 intellig+0.185
Neg logit contributions
resa-0.164
lot-0.155
yrinth-0.154
iesta-0.153
lace-0.151
Token said
Token ID531
Feature activation-5.86e-01

Pos logit contributions
resa+0.459
lot+0.439
iesta+0.425
yrinth+0.423
lace+0.422
Neg logit contributions
 indu-0.619
 ruining-0.546
 popping-0.536
 scient-0.528
 intellig-0.500
Token May
Token ID1737
Feature activation+2.93e-02

Pos logit contributions
resa+0.507
lot+0.488
iesta+0.479
yrinth+0.477
lace+0.475
Neg logit contributions
 indu-0.437
 ruining-0.374
 popping-0.366
 scient-0.358
 intellig-0.332
Tokenra
Token ID430
Feature activation+2.97e+00

Pos logit contributions
 indu+0.027
 ruining+0.024
 popping+0.024
 scient+0.023
 intellig+0.022
Neg logit contributions
resa-0.020
lot-0.019
iesta-0.018
yrinth-0.018
lace-0.018
Token Martinez
Token ID20741
Feature activation-9.72e-02

Pos logit contributions
 indu+2.465
 ruining+2.171
 popping+2.127
 scient+2.099
 intellig+1.971
Neg logit contributions
resa-2.250
lot-2.165
iesta-2.135
yrinth-2.133
lace-2.105
Token was
Token ID373
Feature activation-1.01e-01

Pos logit contributions
resa+0.070
lot+0.067
iesta+0.065
yrinth+0.065
lace+0.065
Neg logit contributions
 indu-0.087
 ruining-0.076
 popping-0.075
 scient-0.074
 intellig-0.069
Token brought
Token ID3181
Feature activation+2.48e-01

Pos logit contributions
resa+0.087
lot+0.084
iesta+0.081
lace+0.081
yrinth+0.081
Neg logit contributions
 indu-0.076
 ruining-0.064
 popping-0.063
 scient-0.062
 intellig-0.058
Token to
Token ID284
Feature activation+8.16e-02

Pos logit contributions
 indu+0.189
 ruining+0.162
 popping+0.158
 scient+0.156
 intellig+0.144
Neg logit contributions
resa-0.210
lot-0.202
iesta-0.198
lace-0.197
yrinth-0.197
Token the
Token ID262
Feature activation+4.57e-02

Pos logit contributions
 indu+0.059
 ruining+0.050
 popping+0.049
 scient+0.048
 intellig+0.045
Neg logit contributions
resa-0.072
lot-0.070
iesta-0.069
yrinth-0.068
lace-0.068
Token population
Token ID3265
Feature activation+2.62e-01

Pos logit contributions
resa+0.186
lot+0.178
iesta+0.174
yrinth+0.174
lace+0.173
Neg logit contributions
 indu-0.212
 ruining-0.186
 popping-0.183
 scient-0.179
 intellig-0.168
Token are
Token ID389
Feature activation-4.47e-02

Pos logit contributions
 indu+0.236
 ruining+0.209
 popping+0.205
 scient+0.202
 intellig+0.190
Neg logit contributions
resa-0.185
lot-0.177
iesta-0.173
yrinth-0.173
lace-0.172
Token Catholic
Token ID7835
Feature activation+1.44e+00

Pos logit contributions
resa+0.035
lot+0.034
iesta+0.033
yrinth+0.033
lace+0.033
Neg logit contributions
 indu-0.036
 ruining-0.032
 popping-0.031
 scient-0.030
 obser-0.028
Token,
Token ID11
Feature activation+1.53e-01

Pos logit contributions
 indu+1.320
 ruining+1.171
 popping+1.156
 scient+1.134
 intellig+1.078
Neg logit contributions
resa-0.987
lot-0.942
iesta-0.926
yrinth-0.923
lace-0.918
Token while
Token ID981
Feature activation+3.48e-01

Pos logit contributions
 indu+0.130
 ruining+0.113
 popping+0.111
 scient+0.109
 intellig+0.103
Neg logit contributions
resa-0.117
lot-0.112
iesta-0.110
yrinth-0.110
lace-0.109
Token Muslims
Token ID7045
Feature activation+1.11e+00

Pos logit contributions
 indu+0.298
 ruining+0.261
 popping+0.256
 scient+0.252
 intellig+0.237
Neg logit contributions
resa-0.262
lot-0.250
iesta-0.246
yrinth-0.245
lace-0.243
Token form
Token ID1296
Feature activation+1.38e+00

Pos logit contributions
 indu+0.843
 ruining+0.725
 popping+0.712
 scient+0.695
 intellig+0.649
Neg logit contributions
resa-0.943
lot-0.907
yrinth-0.891
iesta-0.891
lace-0.885
Token a
Token ID257
Feature activation-2.27e-01

Pos logit contributions
 indu+1.181
 ruining+1.034
 popping+1.015
 scient+0.997
 intellig+0.936
Neg logit contributions
resa-1.045
lot-1.000
iesta-0.980
yrinth-0.977
lace-0.971
Token large
Token ID1588
Feature activation-3.79e-01

Pos logit contributions
resa+0.186
lot+0.180
iesta+0.175
yrinth+0.174
lace+0.174
Neg logit contributions
 indu-0.179
 ruining-0.154
 popping-0.150
 scient-0.147
 obser-0.138
Token minority
Token ID9137
Feature activation-1.53e+00

Pos logit contributions
resa+0.310
lot+0.300
iesta+0.293
yrinth+0.289
lace+0.289
Neg logit contributions
 indu-0.297
 ruining-0.258
 popping-0.251
 scient-0.246
 obser-0.230
Token in
Token ID287
Feature activation-2.16e-01

Pos logit contributions
resa+1.109
lot+1.069
iesta+1.043
lace+1.034
yrinth+1.029
Neg logit contributions
 indu-1.338
 ruining-1.175
 popping-1.152
 scient-1.133
 disse-1.069
Token keep
Token ID1394
Feature activation+1.07e+00

Pos logit contributions
 indu+0.328
 ruining+0.279
 popping+0.273
 scient+0.267
 obser+0.245
Neg logit contributions
resa-0.411
lot-0.396
iesta-0.390
yrinth-0.390
lace-0.388
Token the
Token ID262
Feature activation+1.38e-01

Pos logit contributions
 indu+0.810
 ruining+0.697
 popping+0.682
 scient+0.668
 intellig+0.621
Neg logit contributions
resa-0.911
lot-0.878
iesta-0.861
yrinth-0.860
lace-0.856
Token basic
Token ID4096
Feature activation-2.46e-01

Pos logit contributions
 indu+0.108
 ruining+0.093
 popping+0.091
 scient+0.089
 intellig+0.083
Neg logit contributions
resa-0.113
lot-0.109
iesta-0.107
yrinth-0.106
lace-0.106
Token software
Token ID3788
Feature activation-6.18e-01

Pos logit contributions
resa+0.202
lot+0.195
iesta+0.191
yrinth+0.191
lace+0.190
Neg logit contributions
 indu-0.192
 ruining-0.167
 popping-0.163
 scient-0.159
 intellig-0.148
Token engineering
Token ID8705
Feature activation-1.44e+00

Pos logit contributions
resa+0.485
lot+0.467
iesta+0.458
yrinth+0.455
lace+0.454
Neg logit contributions
 indu-0.505
 ruining-0.439
 popping-0.428
 scient-0.421
 disse-0.393
Token from
Token ID422
Feature activation+5.54e-01

Pos logit contributions
resa+1.140
lot+1.099
iesta+1.077
yrinth+1.073
lace+1.072
Neg logit contributions
 indu-1.147
 ruining-0.997
 popping-0.974
 scient-0.948
 obser-0.885
Token being
Token ID852
Feature activation-1.09e+00

Pos logit contributions
 indu+0.360
 ruining+0.295
 popping+0.288
 scient+0.284
 intellig+0.261
Neg logit contributions
resa-0.528
lot-0.511
yrinth-0.503
iesta-0.503
lace-0.499
Token the
Token ID262
Feature activation-2.66e-01

Pos logit contributions
resa+0.943
lot+0.909
yrinth+0.895
iesta+0.886
lace+0.883
Neg logit contributions
 indu-0.790
 ruining-0.669
 popping-0.657
 scient-0.645
 obser-0.600
Token limiting
Token ID15637
Feature activation+1.12e+00

Pos logit contributions
resa+0.235
lot+0.226
iesta+0.222
lace+0.220
yrinth+0.220
Neg logit contributions
 indu-0.191
 ruining-0.163
 popping-0.160
 scient-0.156
 intellig-0.145
Token factor
Token ID5766
Feature activation+1.78e+00

Pos logit contributions
 indu+0.743
 ruining+0.625
 popping+0.611
 scient+0.594
 intellig+0.547
Neg logit contributions
resa-1.064
lot-1.029
iesta-1.012
yrinth-1.010
lace-1.006
Token.
Token ID13
Feature activation-5.20e-02

Pos logit contributions
 indu+1.585
 ruining+1.403
 popping+1.379
 scient+1.349
 intellig+1.277
Neg logit contributions
resa-1.280
lot-1.216
yrinth-1.196
iesta-1.193
lace-1.186
TokenIL
Token ID4146
Feature activation+1.12e-01

Pos logit contributions
resa+0.315
lot+0.300
yrinth+0.295
iesta+0.293
lace+0.292
Neg logit contributions
 indu-0.395
 ruining-0.350
 popping-0.344
 scient-0.337
 intellig-0.319
TokenED
Token ID1961
Feature activation-1.29e+00

Pos logit contributions
 indu+0.088
 ruining+0.077
 popping+0.075
 scient+0.074
 intellig+0.069
Neg logit contributions
resa-0.091
lot-0.088
yrinth-0.086
iesta-0.086
lace-0.085
Token
Token ID198
Feature activation+1.64e-01

Pos logit contributions
resa+0.795
lot+0.755
iesta+0.736
yrinth+0.733
lace+0.728
Neg logit contributions
 indu-1.277
 ruining-1.141
 popping-1.125
 scient-1.106
 intellig-1.052
Token
Token ID198
Feature activation+2.86e-01

Pos logit contributions
 indu+0.154
 ruining+0.139
 popping+0.137
 scient+0.134
 intellig+0.128
Neg logit contributions
resa-0.107
yrinth-0.101
lot-0.100
iesta-0.099
lace-0.098
TokenIsrael
Token ID14040
Feature activation-5.30e-01

Pos logit contributions
 indu+0.265
 ruining+0.235
 popping+0.231
 scient+0.227
 intellig+0.215
Neg logit contributions
resa-0.194
lot-0.184
yrinth-0.181
iesta-0.181
lace-0.179
Token
Token ID447
Feature activation+5.21e-01

Pos logit contributions
resa+0.384
lot+0.366
iesta+0.358
yrinth+0.357
lace+0.355
Neg logit contributions
 indu-0.470
 ruining-0.413
 popping-0.407
 scient-0.399
 intellig-0.375
Token
Token ID247
Feature activation+4.73e-01

Pos logit contributions
 indu+0.559
 ruining+0.509
 popping+0.504
 scient+0.494
 intellig+0.478
Neg logit contributions
resa-0.270
lot-0.253
yrinth-0.249
iesta-0.244
lace-0.242
Tokens
Token ID82
Feature activation-1.21e-02

Pos logit contributions
 indu+0.503
 ruining+0.453
 popping+0.447
 scient+0.440
 intellig+0.421
Neg logit contributions
resa-0.258
lot-0.242
iesta-0.236
yrinth-0.236
lace-0.233
Token third
Token ID2368
Feature activation+1.06e-01

Pos logit contributions
resa+0.010
lot+0.010
iesta+0.010
yrinth+0.010
lace+0.010
Neg logit contributions
 indu-0.009
 ruining-0.008
 popping-0.008
 scient-0.008
 intellig-0.007
Token policy
Token ID2450
Feature activation+5.95e-01

Pos logit contributions
 indu+0.088
 ruining+0.076
 popping+0.075
 scient+0.074
 intellig+0.069
Neg logit contributions
resa-0.083
lot-0.079
iesta-0.078
yrinth-0.078
lace-0.077
Token is
Token ID318
Feature activation+3.01e-01

Pos logit contributions
 indu+0.480
 ruining+0.417
 popping+0.410
 scient+0.402
 intellig+0.376
Neg logit contributions
resa-0.476
lot-0.457
iesta-0.448
yrinth-0.447
lace-0.445
Token the
Token ID262
Feature activation+3.87e-02

Pos logit contributions
resa+0.223
lot+0.215
iesta+0.212
yrinth+0.211
lace+0.210
Neg logit contributions
 indu-0.191
 ruining-0.163
 popping-0.160
 scient-0.157
 intellig-0.145
Token amb
Token ID4915
Feature activation-4.16e-02

Pos logit contributions
 indu+0.029
 ruining+0.025
 popping+0.025
 scient+0.024
 intellig+0.023
Neg logit contributions
resa-0.033
lot-0.032
iesta-0.031
yrinth-0.031
lace-0.031
Tokenience
Token ID1240
Feature activation+1.22e+00

Pos logit contributions
resa+0.020
lot+0.019
iesta+0.018
yrinth+0.018
lace+0.018
Neg logit contributions
 indu-0.046
 ruining-0.042
 popping-0.041
 scient-0.041
 intellig-0.039
Token and
Token ID290
Feature activation+1.10e-01

Pos logit contributions
 indu+1.071
 ruining+0.942
 popping+0.928
 scient+0.909
 intellig+0.858
Neg logit contributions
resa-0.896
lot-0.855
iesta-0.839
yrinth-0.837
lace-0.832
Token wildlife
Token ID15599
Feature activation-7.30e-01

Pos logit contributions
 indu+0.082
 ruining+0.070
 popping+0.068
 scient+0.067
 intellig+0.062
Neg logit contributions
resa-0.094
lot-0.091
iesta-0.089
yrinth-0.089
lace-0.088
Token typically
Token ID6032
Feature activation+9.26e-01

Pos logit contributions
resa+0.558
lot+0.539
iesta+0.525
yrinth+0.521
lace+0.519
Neg logit contributions
 indu-0.611
 ruining-0.532
 popping-0.520
 scient-0.515
 disse-0.481
Token found
Token ID1043
Feature activation+1.65e-01

Pos logit contributions
 indu+0.668
 ruining+0.569
 popping+0.556
 scient+0.547
 intellig+0.505
Neg logit contributions
resa-0.821
lot-0.791
iesta-0.777
yrinth-0.774
lace-0.772
Token in
Token ID287
Feature activation+6.51e-01

Pos logit contributions
 indu+0.128
 ruining+0.111
 popping+0.108
 scient+0.106
 intellig+0.099
Neg logit contributions
resa-0.136
lot-0.131
iesta-0.129
yrinth-0.129
lace-0.128
Token the
Token ID262
Feature activation+4.57e-01

Pos logit contributions
 indu+0.494
 ruining+0.425
 popping+0.416
 scient+0.408
 intellig+0.379
Neg logit contributions
resa-0.554
lot-0.533
iesta-0.524
yrinth-0.522
lace-0.520
Token associated
Token ID3917
Feature activation-6.37e-01

Pos logit contributions
 indu+0.349
 ruining+0.301
 popping+0.294
 scient+0.289
 intellig+0.268
Neg logit contributions
resa-0.385
lot-0.370
iesta-0.364
yrinth-0.362
lace-0.360
Token area
Token ID1989
Feature activation-1.59e-01

Pos logit contributions
resa+0.536
lot+0.517
iesta+0.507
yrinth+0.505
lace+0.503
Neg logit contributions
 indu-0.484
 ruining-0.419
 popping-0.407
 scient-0.400
 intellig-0.371
Token are
Token ID389
Feature activation-1.02e+00

Pos logit contributions
resa+0.132
lot+0.126
iesta+0.121
lace+0.121
yrinth+0.120
Neg logit contributions
 indu-0.179
 ruining-0.159
 popping-0.155
 scient-0.154
 obser-0.145
Token driving
Token ID5059
Feature activation-1.15e+00

Pos logit contributions
resa+0.938
lot+0.913
iesta+0.885
yrinth+0.882
lace+0.881
Neg logit contributions
 indu-0.697
 ruining-0.578
 popping-0.564
 scient-0.563
 obser-0.518
Token.
Token ID13
Feature activation+1.09e-02

Pos logit contributions
resa+0.795
lot+0.765
iesta+0.741
yrinth+0.737
lace+0.734
Neg logit contributions
 indu-1.057
 ruining-0.930
 popping-0.917
 scient-0.904
 disse-0.852
Token Proceed
Token ID24889
Feature activation+3.32e-01

Pos logit contributions
 indu+0.009
 ruining+0.008
 popping+0.008
 scient+0.008
 intellig+0.007
Neg logit contributions
resa-0.009
lot-0.008
iesta-0.008
lace-0.008
yrinth-0.008
Token at
Token ID379
Feature activation+1.19e+00

Pos logit contributions
 indu+0.267
 ruining+0.232
 popping+0.227
 scient+0.223
 intellig+0.209
Neg logit contributions
resa-0.267
lot-0.256
iesta-0.251
yrinth-0.251
lace-0.250
Token your
Token ID534
Feature activation+2.85e-01

Pos logit contributions
 indu+0.884
 ruining+0.759
 popping+0.744
 scient+0.727
 intellig+0.678
Neg logit contributions
resa-1.026
lot-0.987
iesta-0.970
yrinth-0.969
lace-0.962
Token own
Token ID898
Feature activation+1.83e+00

Pos logit contributions
 indu+0.213
 ruining+0.182
 popping+0.179
 scient+0.175
 intellig+0.163
Neg logit contributions
resa-0.245
lot-0.236
iesta-0.232
yrinth-0.231
lace-0.230
Token risk
Token ID2526
Feature activation+1.64e+00

Pos logit contributions
 indu+1.149
 ruining+0.958
 popping+0.935
 scient+0.905
 intellig+0.830
Neg logit contributions
resa-1.792
lot-1.730
yrinth-1.706
iesta-1.705
lace-1.697
Token.
Token ID13
Feature activation+3.48e-02

Pos logit contributions
 indu+1.533
 ruining+1.364
 popping+1.342
 scient+1.316
 intellig+1.248
Neg logit contributions
resa-1.100
lot-1.045
iesta-1.024
yrinth-1.023
lace-1.014
Token I
Token ID314
Feature activation+2.31e-01

Pos logit contributions
 indu+0.030
 ruining+0.027
 popping+0.026
 scient+0.026
 intellig+0.024
Neg logit contributions
resa-0.026
lot-0.025
iesta-0.024
lace-0.024
yrinth-0.024
Token would
Token ID561
Feature activation+8.82e-01

Pos logit contributions
 indu+0.205
 ruining+0.181
 popping+0.178
 scient+0.175
 intellig+0.165
Neg logit contributions
resa-0.166
lot-0.158
iesta-0.154
yrinth-0.154
lace-0.153
TokenP
Token ID47
Feature activation+2.60e-01

Pos logit contributions
resa+0.020
lot+0.019
yrinth+0.018
iesta+0.018
lace+0.018
Neg logit contributions
 indu-0.033
 ruining-0.030
 popping-0.029
 scient-0.029
 intellig-0.027
TokenORTS
Token ID33002
Feature activation+1.16e+00

Pos logit contributions
 indu+0.170
 ruining+0.142
 popping+0.140
 scient+0.136
 intellig+0.126
Neg logit contributions
resa-0.246
lot-0.239
yrinth-0.236
iesta-0.235
lace-0.233
Token B
Token ID347
Feature activation+1.17e-02

Pos logit contributions
 indu+0.871
 ruining+0.749
 popping+0.734
 scient+0.718
 intellig+0.668
Neg logit contributions
resa-1.000
lot-0.962
yrinth-0.946
iesta-0.946
lace-0.940
Token6
Token ID21
Feature activation-3.04e-01

Pos logit contributions
 indu+0.011
 ruining+0.010
 popping+0.010
 scient+0.010
 intellig+0.009
Neg logit contributions
resa-0.008
lot-0.007
iesta-0.007
yrinth-0.007
lace-0.007
Token HAS
Token ID33930
Feature activation-3.62e-01

Pos logit contributions
resa+0.218
lot+0.208
iesta+0.204
yrinth+0.203
lace+0.202
Neg logit contributions
 indu-0.271
 ruining-0.239
 popping-0.235
 scient-0.230
 intellig-0.217
Token BE
Token ID9348
Feature activation-7.09e-01

Pos logit contributions
resa+0.309
lot+0.298
iesta+0.292
yrinth+0.291
lace+0.290
Neg logit contributions
 indu-0.274
 ruining-0.235
 popping-0.231
 scient-0.225
 intellig-0.210
TokenEN
Token ID1677
Feature activation-6.79e-01

Pos logit contributions
resa+0.513
lot+0.490
iesta+0.478
yrinth+0.475
lace+0.474
Neg logit contributions
 indu-0.629
 ruining-0.552
 popping-0.545
 scient-0.535
 intellig-0.502
Token NOT
Token ID5626
Feature activation-1.37e-01

Pos logit contributions
resa+0.587
lot+0.568
iesta+0.555
lace+0.552
yrinth+0.550
Neg logit contributions
 indu-0.504
 ruining-0.429
 popping-0.421
 scient-0.411
 intellig-0.383
TokenIFIED
Token ID28343
Feature activation+1.70e+00

Pos logit contributions
resa+0.124
lot+0.120
iesta+0.118
yrinth+0.117
lace+0.117
Neg logit contributions
 indu-0.096
 ruining-0.081
 popping-0.079
 scient-0.077
 intellig-0.071
Token.
Token ID13
Feature activation-4.62e-01

Pos logit contributions
 indu+1.315
 ruining+1.137
 popping+1.116
 scient+1.095
 intellig+1.021
Neg logit contributions
resa-1.421
lot-1.367
yrinth-1.347
iesta-1.343
lace-1.333
Token B
Token ID347
Feature activation-4.83e-01

Pos logit contributions
resa+0.376
lot+0.362
iesta+0.354
lace+0.352
yrinth+0.352
Neg logit contributions
 indu-0.368
 ruining-0.318
 popping-0.313
 scient-0.306
 intellig-0.286
Token.
Token ID13
Feature activation-5.66e-01

Pos logit contributions
resa+0.196
lot+0.187
iesta+0.182
yrinth+0.182
lace+0.181
Neg logit contributions
 indu-0.283
 ruining-0.252
 popping-0.248
 scient-0.244
 intellig-0.231
Token They
Token ID1119
Feature activation-5.21e-01

Pos logit contributions
resa+0.433
lot+0.415
iesta+0.406
lace+0.404
yrinth+0.402
Neg logit contributions
 indu-0.483
 ruining-0.420
 popping-0.414
 scient-0.405
 obser-0.382
Token did
Token ID750
Feature activation-4.25e-01

Pos logit contributions
resa+0.368
lot+0.352
iesta+0.342
lace+0.340
yrinth+0.340
Neg logit contributions
 indu-0.470
 ruining-0.415
 popping-0.407
 scient-0.402
 obser-0.377
Token not
Token ID407
Feature activation-4.45e-01

Pos logit contributions
resa+0.347
lot+0.333
iesta+0.327
yrinth+0.326
lace+0.325
Neg logit contributions
 indu-0.337
 ruining-0.292
 popping-0.286
 scient-0.281
 intellig-0.262
Token.
Token ID13
Feature activation-3.99e-01

Pos logit contributions
resa+0.294
lot+0.279
iesta+0.273
yrinth+0.270
lace+0.270
Neg logit contributions
 indu-0.422
 ruining-0.375
 popping-0.369
 scient-0.363
 intellig-0.343
Token
Token ID198
Feature activation-6.96e-01

Pos logit contributions
resa+0.301
lot+0.288
iesta+0.282
lace+0.281
yrinth+0.279
Neg logit contributions
 indu-0.345
 ruining-0.300
 popping-0.296
 scient-0.289
 obser-0.273
Token
Token ID198
Feature activation-5.35e-01

Pos logit contributions
resa+0.440
lot+0.415
yrinth+0.411
iesta+0.407
lace+0.402
Neg logit contributions
 indu-0.676
 ruining-0.605
 popping-0.597
 scient-0.587
 intellig-0.559
TokenInstead
Token ID13193
Feature activation-1.64e+00

Pos logit contributions
resa+0.367
lot+0.350
iesta+0.341
lace+0.339
yrinth+0.339
Neg logit contributions
 indu-0.497
 ruining-0.439
 popping-0.433
 scient-0.425
 intellig-0.402
Token,
Token ID11
Feature activation-7.14e-01

Pos logit contributions
resa+1.184
lot+1.119
lace+1.100
iesta+1.099
yrinth+1.096
Neg logit contributions
 indu-1.456
 ruining-1.283
 popping-1.256
 scient-1.238
 disse-1.166
Token Republicans
Token ID4734
Feature activation+1.52e-02

Pos logit contributions
resa+0.569
lot+0.539
iesta+0.530
lace+0.529
yrinth+0.529
Neg logit contributions
 indu-0.583
 ruining-0.504
 popping-0.493
 scient-0.487
 obser-0.455
Token spent
Token ID3377
Feature activation-6.20e-01

Pos logit contributions
 indu+0.013
 ruining+0.012
 popping+0.011
 scient+0.011
 obser+0.010
Neg logit contributions
resa-0.011
lot-0.011
iesta-0.011
lace-0.010
yrinth-0.010
Token can
Token ID460
Feature activation-1.47e-01

Pos logit contributions
resa+0.458
lot+0.439
iesta+0.427
yrinth+0.427
lace+0.425
Neg logit contributions
 indu-0.518
 ruining-0.455
 popping-0.444
 scient-0.439
 intellig-0.410
Token install
Token ID2721
Feature activation+2.49e-01

Pos logit contributions
resa+0.123
lot+0.118
iesta+0.116
yrinth+0.116
lace+0.115
Neg logit contributions
 indu-0.112
 ruining-0.097
 popping-0.094
 scient-0.093
 obser-0.086
Token server
Token ID4382
Feature activation-8.30e-01

Pos logit contributions
 indu+0.183
 ruining+0.157
 popping+0.153
 scient+0.150
 intellig+0.139
Neg logit contributions
resa-0.218
lot-0.210
iesta-0.206
yrinth-0.206
lace-0.205
Tokenless
Token ID1203
Feature activation-6.98e-01

Pos logit contributions
resa+0.561
lot+0.533
iesta+0.522
yrinth+0.521
lace+0.517
Neg logit contributions
 indu-0.774
 ruining-0.686
 popping-0.677
 scient-0.664
 intellig-0.630
Token framework
Token ID9355
Feature activation-7.72e-01

Pos logit contributions
resa+0.554
lot+0.532
iesta+0.522
yrinth+0.520
lace+0.518
Neg logit contributions
 indu-0.568
 ruining-0.494
 popping-0.484
 scient-0.475
 intellig-0.444
Token with
Token ID351
Feature activation-5.52e-01

Pos logit contributions
resa+0.657
lot+0.633
iesta+0.621
yrinth+0.619
lace+0.618
Neg logit contributions
 indu-0.585
 ruining-0.502
 popping-0.490
 scient-0.481
 intellig-0.446
Token,
Token ID11
Feature activation-4.18e-01

Pos logit contributions
resa+0.422
lot+0.405
iesta+0.397
yrinth+0.396
lace+0.394
Neg logit contributions
 indu-0.465
 ruining-0.407
 popping-0.400
 scient-0.392
 intellig-0.369
Token
Token ID198
Feature activation-6.72e-01

Pos logit contributions
resa+0.316
lot+0.303
iesta+0.297
yrinth+0.296
lace+0.295
Neg logit contributions
 indu-0.356
 ruining-0.312
 popping-0.307
 scient-0.301
 intellig-0.283
Token
Token ID198
Feature activation-3.09e-01

Pos logit contributions
resa+0.427
lot+0.402
yrinth+0.397
iesta+0.394
lace+0.389
Neg logit contributions
 indu-0.652
 ruining-0.584
 popping-0.576
 scient-0.566
 intellig-0.539
Tokenn
Token ID77
Feature activation-8.84e-01

Pos logit contributions
resa+0.218
lot+0.207
iesta+0.204
yrinth+0.203
lace+0.201
Neg logit contributions
 indu-0.280
 ruining-0.247
 popping-0.243
 scient-0.239
 intellig-0.225
Tokenpm
Token ID4426
Feature activation-4.53e-01

Pos logit contributions
resa+0.326
lot+0.298
iesta+0.285
yrinth+0.284
lace+0.280
Neg logit contributions
 indu-1.096
 ruining-1.003
 popping-0.992
 scient-0.979
 intellig-0.942
Token easy
Token ID2562
Feature activation-5.85e-01

Pos logit contributions
 indu+0.169
 ruining+0.146
 popping+0.143
 scient+0.141
 disse+0.131
Neg logit contributions
resa-0.172
lot-0.166
iesta-0.163
yrinth-0.161
lace-0.161
Token because
Token ID780
Feature activation-6.63e-01

Pos logit contributions
resa+0.438
lot+0.422
iesta+0.412
yrinth+0.410
lace+0.409
Neg logit contributions
 indu-0.502
 ruining-0.440
 popping-0.432
 scient-0.425
 intellig-0.398
Token the
Token ID262
Feature activation-7.74e-01

Pos logit contributions
resa+0.535
lot+0.516
iesta+0.504
yrinth+0.502
lace+0.502
Neg logit contributions
 indu-0.528
 ruining-0.457
 popping-0.446
 scient-0.440
 disse-0.411
Token camera
Token ID4676
Feature activation-6.09e-01

Pos logit contributions
resa+0.662
lot+0.635
iesta+0.621
yrinth+0.618
lace+0.616
Neg logit contributions
 indu-0.580
 ruining-0.500
 popping-0.486
 scient-0.479
 intellig-0.444
Token has
Token ID468
Feature activation+8.03e-02

Pos logit contributions
resa+0.449
lot+0.432
iesta+0.420
yrinth+0.419
lace+0.417
Neg logit contributions
 indu-0.530
 ruining-0.466
 popping-0.457
 scient-0.450
 intellig-0.421
Token an
Token ID281
Feature activation-6.24e-01

Pos logit contributions
 indu+0.064
 ruining+0.056
 popping+0.055
 scient+0.053
 intellig+0.050
Neg logit contributions
resa-0.065
lot-0.063
iesta-0.061
yrinth-0.061
lace-0.061
Token exposure
Token ID7111
Feature activation-1.81e-01

Pos logit contributions
resa+0.520
lot+0.500
iesta+0.490
yrinth+0.489
lace+0.485
Neg logit contributions
 indu-0.481
 ruining-0.417
 popping-0.408
 scient-0.400
 disse-0.371
Token z
Token ID1976
Feature activation-4.23e-01

Pos logit contributions
resa+0.153
lot+0.148
iesta+0.145
yrinth+0.144
lace+0.144
Neg logit contributions
 indu-0.138
 ruining-0.119
 popping-0.116
 scient-0.114
 intellig-0.106
Tokenebra
Token ID37052
Feature activation-2.59e-01

Pos logit contributions
resa+0.314
lot+0.300
iesta+0.294
yrinth+0.294
lace+0.292
Neg logit contributions
 indu-0.367
 ruining-0.322
 popping-0.317
 scient-0.311
 intellig-0.293
Token with
Token ID351
Feature activation-4.10e-01

Pos logit contributions
resa+0.222
lot+0.214
iesta+0.210
yrinth+0.209
lace+0.209
Neg logit contributions
 indu-0.195
 ruining-0.168
 popping-0.164
 scient-0.161
 intellig-0.150
Token adjustable
Token ID28138
Feature activation-5.45e-01

Pos logit contributions
resa+0.338
lot+0.325
iesta+0.319
yrinth+0.318
lace+0.317
Neg logit contributions
 indu-0.322
 ruining-0.278
 popping-0.273
 scient-0.267
 intellig-0.249
Token
Token ID198
Feature activation+3.71e-01

Pos logit contributions
 indu+0.285
 ruining+0.256
 popping+0.253
 scient+0.248
 intellig+0.237
Neg logit contributions
resa-0.196
yrinth-0.186
lot-0.184
iesta-0.182
lace-0.179
Token"...
Token ID26214
Feature activation+2.02e+00

Pos logit contributions
 indu+0.337
 ruining+0.298
 popping+0.294
 scient+0.288
 intellig+0.273
Neg logit contributions
resa-0.259
lot-0.247
iesta-0.242
yrinth-0.241
lace-0.239
Tokenis
Token ID271
Feature activation+1.64e+00

Pos logit contributions
 indu+1.805
 ruining+1.594
 popping+1.566
 scient+1.537
 intellig+1.450
Neg logit contributions
resa-1.440
lot-1.371
iesta-1.350
yrinth-1.345
lace-1.335
Token that
Token ID326
Feature activation+1.91e-01

Pos logit contributions
 indu+1.292
 ruining+1.127
 popping+1.102
 scient+1.079
 intellig+1.011
Neg logit contributions
resa-1.334
lot-1.281
iesta-1.260
yrinth-1.258
lace-1.249
Token?"
Token ID1701
Feature activation+1.33e+00

Pos logit contributions
 indu+0.142
 ruining+0.121
 popping+0.119
 scient+0.116
 obser+0.108
Neg logit contributions
resa-0.166
lot-0.159
iesta-0.156
yrinth-0.155
lace-0.155
Token Legend
Token ID9883
Feature activation-1.01e+00

Pos logit contributions
 indu+1.172
 ruining+1.034
 popping+1.019
 scient+1.000
 intellig+0.943
Neg logit contributions
resa-0.959
lot-0.916
iesta-0.898
yrinth-0.897
lace-0.890
Token finished
Token ID5201
Feature activation+5.01e-01

Pos logit contributions
resa+0.698
lot+0.666
yrinth+0.648
iesta+0.647
lace+0.643
Neg logit contributions
 indu-0.928
 ruining-0.823
 popping-0.809
 scient-0.796
 intellig-0.752
Token the
Token ID262
Feature activation-3.84e-02

Pos logit contributions
 indu+0.440
 ruining+0.385
 popping+0.378
 scient+0.374
 intellig+0.350
Neg logit contributions
resa-0.364
lot-0.350
iesta-0.341
yrinth-0.340
lace-0.340
Token question
Token ID1808
Feature activation+1.08e+00

Pos logit contributions
resa+0.032
lot+0.031
iesta+0.030
yrinth+0.030
lace+0.030
Neg logit contributions
 indu-0.030
 ruining-0.026
 popping-0.025
 scient-0.024
 intellig-0.023
Token.
Token ID13
Feature activation+4.00e-01

Pos logit contributions
 indu+0.990
 ruining+0.877
 popping+0.863
 scient+0.847
 intellig+0.803
Neg logit contributions
resa-0.742
lot-0.707
iesta-0.693
yrinth-0.690
lace-0.685
Token
Token ID198
Feature activation+2.24e-01

Pos logit contributions
 indu+0.359
 ruining+0.317
 popping+0.312
 scient+0.307
 intellig+0.289
Neg logit contributions
resa-0.284
lot-0.270
iesta-0.265
yrinth-0.265
lace-0.262
Token'
Token ID6
Feature activation-1.66e-01

Pos logit contributions
resa+0.020
lot+0.019
iesta+0.018
yrinth+0.018
lace+0.018
Neg logit contributions
 indu-0.024
 ruining-0.021
 popping-0.020
 scient-0.020
 intellig-0.019
Tokenag
Token ID363
Feature activation-1.10e+00

Pos logit contributions
resa+0.110
lot+0.105
iesta+0.102
yrinth+0.102
lace+0.101
Neg logit contributions
 indu-0.157
 ruining-0.139
 popping-0.137
 scient-0.135
 intellig-0.128
Tokenression
Token ID2234
Feature activation-1.67e-01

Pos logit contributions
resa+0.767
lot+0.732
iesta+0.715
yrinth+0.711
lace+0.709
Neg logit contributions
 indu-1.004
 ruining-0.891
 popping-0.877
 scient-0.857
 intellig-0.811
Token de
Token ID390
Feature activation+9.86e-01

Pos logit contributions
resa+0.148
lot+0.142
iesta+0.140
yrinth+0.139
lace+0.139
Neg logit contributions
 indu-0.120
 ruining-0.103
 popping-0.101
 scient-0.098
 intellig-0.091
Token t
Token ID256
Feature activation+9.68e-01

Pos logit contributions
 indu+0.752
 ruining+0.648
 popping+0.635
 scient+0.622
 intellig+0.580
Neg logit contributions
resa-0.835
lot-0.804
iesta-0.790
yrinth-0.788
lace-0.784
Tokenout
Token ID448
Feature activation-2.32e+00

Pos logit contributions
 indu+1.035
 ruining+0.932
 popping+0.920
 scient+0.906
 intellig+0.865
Neg logit contributions
resa-0.523
lot-0.492
iesta-0.478
yrinth-0.476
lace-0.472
Token cit
Token ID15433
Feature activation+5.98e-01

Pos logit contributions
resa+1.973
lot+1.899
iesta+1.862
yrinth+1.857
lace+1.851
Neg logit contributions
 indu-1.724
 ruining-1.490
 popping-1.462
 scient-1.410
 Fold-1.313
Tokenoy
Token ID726
Feature activation+1.50e-01

Pos logit contributions
 indu+0.560
 ruining+0.497
 popping+0.490
 scient+0.480
 intellig+0.455
Neg logit contributions
resa-0.403
lot-0.384
iesta-0.375
yrinth-0.374
lace-0.371
Tokenen
Token ID268
Feature activation+6.14e-02

Pos logit contributions
 indu+0.119
 ruining+0.103
 popping+0.101
 scient+0.099
 intellig+0.093
Neg logit contributions
resa-0.122
lot-0.117
iesta-0.115
yrinth-0.115
lace-0.114
Token Imp
Token ID9855
Feature activation-5.26e-01

Pos logit contributions
 indu+0.047
 ruining+0.040
 popping+0.039
 scient+0.038
 intellig+0.036
Neg logit contributions
resa-0.052
lot-0.050
iesta-0.049
yrinth-0.049
lace-0.049
Tokené
Token ID2634
Feature activation+2.91e+00

Pos logit contributions
resa+0.313
lot+0.295
iesta+0.288
yrinth+0.287
lace+0.285
Neg logit contributions
 indu-0.535
 ruining-0.479
 popping-0.473
 scient-0.465
 intellig-0.442
Token doors
Token ID8215
Feature activation+2.55e-01

Pos logit contributions
 indu+0.573
 ruining+0.498
 popping+0.489
 scient+0.479
 intellig+0.449
Neg logit contributions
resa-0.564
lot-0.541
iesta-0.531
yrinth-0.530
lace-0.527
Token of
Token ID286
Feature activation-1.07e-02

Pos logit contributions
 indu+0.212
 ruining+0.185
 popping+0.182
 scient+0.179
 intellig+0.168
Neg logit contributions
resa-0.198
lot-0.189
iesta-0.186
yrinth-0.185
lace-0.184
Token a
Token ID257
Feature activation-4.25e-02

Pos logit contributions
resa+0.009
lot+0.009
iesta+0.009
yrinth+0.009
lace+0.009
Neg logit contributions
 indu-0.008
 ruining-0.007
 popping-0.007
 scient-0.007
 intellig-0.006
Token dr
Token ID1553
Feature activation-2.74e-01

Pos logit contributions
resa+0.036
lot+0.034
iesta+0.034
yrinth+0.034
lace+0.034
Neg logit contributions
 indu-0.033
 ruining-0.028
 popping-0.028
 scient-0.027
 intellig-0.025
Tokenab
Token ID397
Feature activation+4.89e-01

Pos logit contributions
resa+0.115
lot+0.106
iesta+0.102
yrinth+0.102
lace+0.101
Neg logit contributions
 indu-0.325
 ruining-0.297
 popping-0.294
 scient-0.290
 intellig-0.277
Token brick
Token ID17214
Feature activation-2.11e+00

Pos logit contributions
 indu+0.375
 ruining+0.323
 popping+0.317
 scient+0.310
 intellig+0.289
Neg logit contributions
resa-0.412
lot-0.397
iesta-0.390
yrinth-0.389
lace-0.387
Token building
Token ID2615
Feature activation-2.78e-01

Pos logit contributions
resa+1.957
lot+1.901
iesta+1.853
lace+1.851
yrinth+1.840
Neg logit contributions
 indu-1.424
 ruining-1.201
 popping-1.172
 scient-1.143
 intellig-1.051
Token in
Token ID287
Feature activation+1.39e-01

Pos logit contributions
resa+0.222
lot+0.213
iesta+0.209
yrinth+0.208
lace+0.207
Neg logit contributions
 indu-0.225
 ruining-0.196
 popping-0.193
 scient-0.188
 intellig-0.177
Token D
Token ID360
Feature activation+2.15e-02

Pos logit contributions
 indu+0.112
 ruining+0.097
 popping+0.095
 scient+0.093
 intellig+0.087
Neg logit contributions
resa-0.111
lot-0.107
iesta-0.105
yrinth-0.104
lace-0.104
Tokenae
Token ID3609
Feature activation+1.17e+00

Pos logit contributions
 indu+0.018
 ruining+0.016
 popping+0.016
 scient+0.016
 intellig+0.015
Neg logit contributions
resa-0.016
lot-0.016
iesta-0.015
yrinth-0.015
lace-0.015
Tokenje
Token ID18015
Feature activation+1.20e+00

Pos logit contributions
 indu+0.879
 ruining+0.756
 popping+0.740
 scient+0.723
 intellig+0.672
Neg logit contributions
resa-1.007
lot-0.970
yrinth-0.948
iesta-0.947
lace-0.942
Token.'
Token ID2637
Feature activation-3.03e+00

Pos logit contributions
 indu+0.352
 ruining+0.310
 popping+0.305
 scient+0.301
 intellig+0.285
Neg logit contributions
resa-0.274
lot-0.262
iesta-0.254
yrinth-0.253
lace-0.252
Tokens
Token ID82
Feature activation-3.15e-01

Pos logit contributions
resa+1.520
lot+1.441
iesta+1.383
lace+1.366
yrinth+1.333
Neg logit contributions
 indu-3.370
 ruining-3.041
 popping-2.987
 scient-2.958
 obser-2.867
Token crude
Token ID14897
Feature activation-8.64e-01

Pos logit contributions
resa+0.250
lot+0.241
iesta+0.233
yrinth+0.233
lace+0.230
Neg logit contributions
 indu-0.257
 ruining-0.223
 popping-0.217
 scient-0.216
 intellig-0.202
Token oil
Token ID3056
Feature activation-3.86e-01

Pos logit contributions
resa+0.667
lot+0.641
yrinth+0.617
iesta+0.616
lace+0.616
Neg logit contributions
 indu-0.716
 ruining-0.623
 scient-0.611
 popping-0.611
 obser-0.575
Token storage
Token ID6143
Feature activation-9.40e-01

Pos logit contributions
resa+0.342
lot+0.331
yrinth+0.320
lace+0.320
iesta+0.319
Neg logit contributions
 indu-0.276
 ruining-0.235
 popping-0.229
 scient-0.228
 obser-0.212
Token tanks
Token ID11657
Feature activation-2.52e+00

Pos logit contributions
resa+0.845
lot+0.827
yrinth+0.796
lace+0.794
iesta+0.793
Neg logit contributions
 indu-0.657
 ruining-0.558
 popping-0.542
 scient-0.538
 obser-0.498
Token at
Token ID379
Feature activation+3.37e-01

Pos logit contributions
resa+1.900
lot+1.837
lace+1.775
yrinth+1.761
iesta+1.761
Neg logit contributions
 indu-2.122
 ruining-1.839
 scient-1.803
 popping-1.784
 obser-1.712
Token their
Token ID511
Feature activation+6.76e-01

Pos logit contributions
 indu+0.266
 ruining+0.230
 popping+0.225
 scient+0.221
 intellig+0.207
Neg logit contributions
resa-0.277
lot-0.267
iesta-0.260
yrinth-0.260
lace-0.258
Token tank
Token ID6873
Feature activation-2.39e+00

Pos logit contributions
 indu+0.534
 ruining+0.462
 popping+0.451
 scient+0.444
 intellig+0.417
Neg logit contributions
resa-0.555
lot-0.535
iesta-0.519
yrinth-0.519
lace-0.515
Token farm
Token ID5318
Feature activation-6.02e-02

Pos logit contributions
resa+1.906
lot+1.839
yrinth+1.782
lace+1.775
iesta+1.760
Neg logit contributions
 indu-1.914
 ruining-1.655
 scient-1.625
 popping-1.603
 obser-1.518
Token in
Token ID287
Feature activation+2.07e-01

Pos logit contributions
resa+0.048
lot+0.047
iesta+0.045
yrinth+0.045
lace+0.045
Neg logit contributions
 indu-0.049
 ruining-0.042
 popping-0.041
 scient-0.041
 intellig-0.038
Token the
Token ID262
Feature activation+3.76e-01

Pos logit contributions
 indu+0.243
 ruining+0.207
 popping+0.202
 scient+0.198
 intellig+0.183
Neg logit contributions
resa-0.314
lot-0.303
iesta-0.298
yrinth-0.297
lace-0.296
Token glove
Token ID29144
Feature activation-2.18e-02

Pos logit contributions
 indu+0.281
 ruining+0.241
 popping+0.237
 scient+0.231
 intellig+0.215
Neg logit contributions
resa-0.324
lot-0.312
iesta-0.307
yrinth-0.306
lace-0.304
Tokenbox
Token ID3524
Feature activation-8.40e-01

Pos logit contributions
resa+0.020
lot+0.020
iesta+0.019
yrinth+0.019
lace+0.019
Neg logit contributions
 indu-0.015
 ruining-0.012
 popping-0.012
 scient-0.012
 intellig-0.011
Token.
Token ID13
Feature activation+2.99e-01

Pos logit contributions
resa+0.608
lot+0.582
iesta+0.567
yrinth+0.567
lace+0.565
Neg logit contributions
 indu-0.742
 ruining-0.653
 popping-0.641
 scient-0.631
 intellig-0.595
Token Make
Token ID6889
Feature activation+1.20e-01

Pos logit contributions
 indu+0.248
 ruining+0.216
 popping+0.211
 scient+0.208
 intellig+0.196
Neg logit contributions
resa-0.234
lot-0.225
lace-0.220
iesta-0.219
yrinth-0.219
Token sure
Token ID1654
Feature activation-2.27e+00

Pos logit contributions
 indu+0.090
 ruining+0.077
 popping+0.076
 scient+0.074
 intellig+0.069
Neg logit contributions
resa-0.103
lot-0.099
iesta-0.098
yrinth-0.097
lace-0.097
Token the
Token ID262
Feature activation-1.70e-01

Pos logit contributions
resa+1.779
lot+1.703
lace+1.666
yrinth+1.662
iesta+1.659
Neg logit contributions
 indu-1.870
 ruining-1.618
 popping-1.582
 scient-1.563
 intellig-1.473
Token passenger
Token ID11849
Feature activation-1.01e+00

Pos logit contributions
resa+0.150
lot+0.144
iesta+0.142
yrinth+0.142
lace+0.141
Neg logit contributions
 indu-0.124
 ruining-0.106
 popping-0.104
 scient-0.101
 intellig-0.094
Token seat
Token ID5852
Feature activation-2.78e-01

Pos logit contributions
resa+0.886
lot+0.853
iesta+0.837
yrinth+0.835
lace+0.833
Neg logit contributions
 indu-0.743
 ruining-0.637
 popping-0.623
 scient-0.609
 intellig-0.566
Token is
Token ID318
Feature activation+1.58e-01

Pos logit contributions
resa+0.208
lot+0.199
iesta+0.195
yrinth+0.194
lace+0.193
Neg logit contributions
 indu-0.239
 ruining-0.209
 popping-0.206
 scient-0.202
 intellig-0.190
Token moved
Token ID3888
Feature activation-7.86e-01

Pos logit contributions
 indu+0.120
 ruining+0.103
 popping+0.100
 scient+0.099
 intellig+0.092
Neg logit contributions
resa-0.134
lot-0.129
iesta-0.126
yrinth-0.126
lace-0.126
Token up
Token ID510
Feature activation-6.01e-01

Pos logit contributions
resa+0.311
lot+0.298
iesta+0.292
yrinth+0.291
lace+0.289
Neg logit contributions
 indu-0.314
 ruining-0.272
 popping-0.267
 scient-0.262
 intellig-0.245
Tokenended
Token ID1631
Feature activation+1.56e+00

Pos logit contributions
resa+0.452
lot+0.435
iesta+0.425
yrinth+0.424
lace+0.420
Neg logit contributions
 indu-0.516
 ruining-0.451
 popping-0.443
 scient-0.435
 intellig-0.409
Token by
Token ID416
Feature activation-3.19e-01

Pos logit contributions
 indu+1.174
 ruining+1.013
 popping+0.994
 scient+0.970
 intellig+0.906
Neg logit contributions
resa-1.340
lot-1.285
yrinth-1.266
iesta-1.265
lace-1.257
Token a
Token ID257
Feature activation-5.04e-01

Pos logit contributions
resa+0.269
lot+0.258
iesta+0.253
yrinth+0.252
lace+0.250
Neg logit contributions
 indu-0.245
 ruining-0.210
 popping-0.206
 scient-0.202
 intellig-0.188
Token re
Token ID302
Feature activation-1.70e+00

Pos logit contributions
resa+0.423
lot+0.406
iesta+0.396
yrinth+0.395
lace+0.394
Neg logit contributions
 indu-0.390
 ruining-0.335
 popping-0.328
 scient-0.322
 intellig-0.301
Tokenclass
Token ID4871
Feature activation-2.61e+00

Pos logit contributions
resa+1.173
lot+1.118
iesta+1.093
yrinth+1.091
lace+1.083
Neg logit contributions
 indu-1.566
 ruining-1.385
 popping-1.363
 scient-1.339
 intellig-1.268
Tokenification
Token ID2649
Feature activation+4.34e-01

Pos logit contributions
resa+2.239
lot+2.155
lace+2.114
yrinth+2.113
iesta+2.108
Neg logit contributions
 indu-1.956
 ruining-1.682
 popping-1.632
 scient-1.611
 disse-1.507
Token of
Token ID286
Feature activation-4.81e-01

Pos logit contributions
 indu+0.353
 ruining+0.307
 popping+0.301
 scient+0.295
 intellig+0.277
Neg logit contributions
resa-0.346
lot-0.332
iesta-0.326
yrinth-0.325
lace-0.323
Token assets
Token ID6798
Feature activation-1.49e+00

Pos logit contributions
resa+0.393
lot+0.377
iesta+0.370
yrinth+0.368
lace+0.366
Neg logit contributions
 indu-0.381
 ruining-0.330
 popping-0.324
 scient-0.317
 intellig-0.296
Token from
Token ID422
Feature activation-1.78e-01

Pos logit contributions
resa+1.169
lot+1.124
iesta+1.093
lace+1.078
yrinth+1.076
Neg logit contributions
 indu-1.226
 ruining-1.062
 popping-1.037
 scient-1.025
 intellig-0.958
Token firms
Token ID9611
Feature activation-7.74e-01

Pos logit contributions
resa+0.144
lot+0.139
iesta+0.136
yrinth+0.135
lace+0.135
Neg logit contributions
 indu-0.142
 ruining-0.123
 popping-0.121
 scient-0.118
 intellig-0.111