TOP ACTIVATIONS
MAX = 2.566

the ill - con ceived hostage rescue mission that ended with
during six seasons with the Winnipeg Jets / Atlanta Th ras
t 2 o M Winnipeg Jets (@ N HL J
.[ 16 ] <|endoftext|> D inosaur Jr .: " I 'll
opened on political grounds after Wikileaks published material embarrassing to the
Now prosecutors have filed motion to reconsider , believing P
the world is being held hostage by 3 DES .
as a trans national criminal organization .
ral Process ion Pir acy Charm vs Talent of
iff Tra x Reviewer : V the Happy L
Temple Address : Jam n agar , Dw ark
we think about a trans national network of operatives who want
conditions added at his arra ignment in December 2016 .
your character , but I wish it had been addressed between
Embassy coincided with the Edward Snowden leaks . Although Assange and
unpredictable , the fixture against Taj ik istan is unlikely to
- and - s oul defence man Josh G org es
hers , helped the new Winnipeg franchise make its first appearance
Times recently , edible tet rah yd roc ann ib in
to weaken the trans national political , economic , and

MIN ACTIVATIONS
MIN = -2.584

- as it 's not unheard of that collectors have paid
is " bas ically an isolation ist ," according to former
- fired electricity more than quadru ples . Solar and wind
an alternative to The Ad vertis er , a different voice
s has some miscar riages in the past ,
To break the isolation and bolster the teenagers
philosophy , is basically an isolation ist ," Cheney told ABC
is that Rails has g hett os , and Zed made
so I have to pencil this thing , and then
focusing problem . Tri angular segregation Act
s okay to just postpone a situation even if I
it so you don 't ejac ulate soon . So you
respectively . Er rict R hett eventually broke Smith
had perhaps a marginally lower blur when running at 144 Hz
people have set out to draw our memorial into the current
mism atched heroes , Jack Aub rey , a British naval
grape fruit and under g ird ed by che wy caramel
4 ms G 2 G AU Opt ronics AH VA (
he may have led a double life , where he twice
issue ; where do we draw the line ? So they

INTERVAL 1.279 - 2.566
CONTAINS 0.319%

19 04 ). Joyce 's Chicago - based he i ress
.[ 16 ] <|endoftext|> D inosaur Jr .: " I 'll
worked in his individual capacity whole living in London for years
Frank iv sk . <|endoftext|> [ Ex clusive ] Best Buy
life stories of whales and dolphins . It also scares me

INTERVAL -0.009 - 1.279
CONTAINS 49.968%

himself to use or how to call another person out .
over , things that were im min ently know able were
him for you . <|endoftext|> Tan aka 's artwork is ,
I smile . " Now , I need to
she can t take a public stance on any

INTERVAL -1.296 - -0.009
CONTAINS 49.474%

begin the gallery ) You can also check out
This is the nightmare for the Syrian regime , to have
This yields {{ 1 , 6 } < ->
could only draw lines the width of pixels but you get
acquired Pocket , a service that lets you save websites and

INTERVAL -2.584 - -1.296
CONTAINS 0.238%

suggestions on how terror in Israel could be deter red .
guy with the stage win record at the Tour Down Under
the bridge would allow the Park Board to take fuller advantage
gan s solo record . He has
distribution between the front and rear wheels , combines the best
Token the
Token ID262
Feature activation+9.98e-02

Pos logit contributions
cles+0.750
 unrelated+0.742
minist+0.702
interstitial+0.693
 Beir+0.646
Neg logit contributions
ertodd-0.722
isconsin-0.696
alsa-0.677
framework-0.651
urdue-0.649
Token ill
Token ID2801
Feature activation+6.31e-01

Pos logit contributions
ertodd+0.191
isconsin+0.185
alsa+0.181
 Taj+0.175
framework+0.175
Neg logit contributions
cles-0.179
 unrelated-0.175
minist-0.166
interstitial-0.164
 Beir-0.151
Token-
Token ID12
Feature activation+4.58e-01

Pos logit contributions
ertodd+1.181
isconsin+1.142
alsa+1.110
 Taj+1.091
framework+1.088
Neg logit contributions
cles-1.146
 unrelated-1.110
minist-1.053
interstitial-1.045
leans-0.971
Tokencon
Token ID1102
Feature activation+3.05e-01

Pos logit contributions
ertodd+0.930
isconsin+0.907
alsa+0.891
framework+0.883
cipled+0.859
Neg logit contributions
cles-0.746
 unrelated-0.739
interstitial-0.677
minist-0.676
 Beir-0.631
Tokenceived
Token ID6471
Feature activation-1.77e-01

Pos logit contributions
ertodd+0.721
isconsin+0.698
alsa+0.685
urdue+0.667
cipled+0.666
Neg logit contributions
cles-0.409
 unrelated-0.407
minist-0.370
interstitial-0.367
 Beir-0.330
Token hostage
Token ID23229
Feature activation+2.57e+00

Pos logit contributions
cles+0.322
 unrelated+0.317
minist+0.300
interstitial+0.297
 Beir+0.274
Neg logit contributions
ertodd-0.332
isconsin-0.321
alsa-0.313
framework-0.303
 Taj-0.303
Token rescue
Token ID9992
Feature activation+9.08e-01

Pos logit contributions
ertodd+4.143
isconsin+4.104
framework+3.993
alsa+3.987
 Taj+3.948
Neg logit contributions
cles-4.943
 unrelated-4.736
interstitial-4.724
minist-4.703
 Beir-4.457
Token mission
Token ID4365
Feature activation-1.08e-01

Pos logit contributions
ertodd+1.448
isconsin+1.401
alsa+1.376
framework+1.331
 Taj+1.328
Neg logit contributions
cles-1.865
 unrelated-1.817
interstitial-1.766
minist-1.766
 Beir-1.642
Token that
Token ID326
Feature activation-1.70e-01

Pos logit contributions
cles+0.193
 unrelated+0.191
minist+0.181
interstitial+0.178
 Beir+0.165
Neg logit contributions
ertodd-0.205
isconsin-0.198
alsa-0.193
urdue-0.186
framework-0.186
Token ended
Token ID4444
Feature activation+2.59e-01

Pos logit contributions
cles+0.308
 unrelated+0.305
minist+0.288
interstitial+0.283
 Beir+0.263
Neg logit contributions
ertodd-0.323
isconsin-0.312
alsa-0.303
framework-0.292
urdue-0.292
Token with
Token ID351
Feature activation+4.71e-01

Pos logit contributions
ertodd+0.520
isconsin+0.505
alsa+0.493
framework+0.476
urdue+0.476
Neg logit contributions
cles-0.437
 unrelated-0.430
minist-0.406
interstitial-0.399
 Beir-0.366
Token during
Token ID1141
Feature activation+4.89e-02

Pos logit contributions
ertodd+0.005
isconsin+0.005
alsa+0.005
urdue+0.005
framework+0.005
Neg logit contributions
cles-0.004
 unrelated-0.004
minist-0.004
interstitial-0.004
 Beir-0.004
Token six
Token ID2237
Feature activation+3.00e-01

Pos logit contributions
ertodd+0.097
isconsin+0.094
alsa+0.092
urdue+0.089
framework+0.088
Neg logit contributions
cles-0.084
 unrelated-0.082
minist-0.078
interstitial-0.077
 Beir-0.071
Token seasons
Token ID7028
Feature activation-2.61e-01

Pos logit contributions
ertodd+0.425
isconsin+0.413
alsa+0.396
urdue+0.376
 Taj+0.375
Neg logit contributions
cles-0.679
 unrelated-0.670
minist-0.645
interstitial-0.643
 Beir-0.604
Token with
Token ID351
Feature activation+3.40e-01

Pos logit contributions
cles+0.446
 unrelated+0.441
minist+0.415
interstitial+0.409
 Beir+0.378
Neg logit contributions
ertodd-0.523
isconsin-0.507
alsa-0.492
urdue-0.475
framework-0.475
Token the
Token ID262
Feature activation+4.11e-02

Pos logit contributions
ertodd+0.570
isconsin+0.554
alsa+0.535
 Taj+0.517
urdue+0.516
Neg logit contributions
cles-0.688
 unrelated-0.675
minist-0.645
interstitial-0.638
cle-0.592
Token Winnipeg
Token ID23434
Feature activation+2.26e+00

Pos logit contributions
ertodd+0.063
isconsin+0.060
alsa+0.058
urdue+0.056
framework+0.055
Neg logit contributions
cles-0.089
 unrelated-0.088
minist-0.084
interstitial-0.084
 Beir-0.078
Token Jets
Token ID14728
Feature activation+1.13e+00

Pos logit contributions
isconsin+2.808
ertodd+2.783
alsa+2.704
 Taj+2.682
urdue+2.633
Neg logit contributions
cles-5.412
 unrelated-5.212
minist-5.088
interstitial-4.961
 Beir-4.667
Token/
Token ID14
Feature activation-2.52e-01

Pos logit contributions
ertodd+2.044
isconsin+2.012
alsa+1.927
urdue+1.881
 Taj+1.871
Neg logit contributions
cles-2.112
 unrelated-2.065
minist-1.980
interstitial-1.938
 Beir-1.803
TokenAtlanta
Token ID43482
Feature activation+2.96e-02

Pos logit contributions
cles+0.469
 unrelated+0.466
minist+0.438
interstitial+0.432
 Beir+0.404
Neg logit contributions
ertodd-0.464
isconsin-0.451
alsa-0.438
framework-0.422
urdue-0.421
Token Th
Token ID536
Feature activation-4.64e-01

Pos logit contributions
ertodd+0.054
isconsin+0.053
alsa+0.052
 Taj+0.050
urdue+0.050
Neg logit contributions
cles-0.055
 unrelated-0.054
minist-0.051
interstitial-0.051
 Beir-0.047
Tokenras
Token ID8847
Feature activation+8.59e-01

Pos logit contributions
cles+1.055
 unrelated+1.050
minist+1.002
interstitial+0.991
 Beir+0.935
Neg logit contributions
ertodd-0.663
isconsin-0.635
alsa-0.615
framework-0.582
urdue-0.581
Tokent
Token ID83
Feature activation+2.65e-01

Pos logit contributions
ertodd+0.590
isconsin+0.573
alsa+0.562
framework+0.542
urdue+0.540
Neg logit contributions
 unrelated-0.476
cles-0.474
minist-0.442
interstitial-0.436
 Beir-0.406
Token2
Token ID17
Feature activation-1.66e-02

Pos logit contributions
ertodd+0.566
isconsin+0.551
alsa+0.542
framework+0.522
urdue+0.522
Neg logit contributions
 unrelated-0.412
cles-0.410
minist-0.380
interstitial-0.376
 Beir-0.346
Tokeno
Token ID78
Feature activation+6.52e-02

Pos logit contributions
cles+0.028
 unrelated+0.028
minist+0.026
interstitial+0.026
 Beir+0.024
Neg logit contributions
ertodd-0.034
isconsin-0.032
alsa-0.032
framework-0.031
urdue-0.031
TokenM
Token ID44
Feature activation-3.17e-01

Pos logit contributions
ertodd+0.142
isconsin+0.138
alsa+0.136
urdue+0.131
framework+0.131
Neg logit contributions
cles-0.099
 unrelated-0.099
minist-0.092
interstitial-0.090
 Beir-0.083
Token
Token ID851
Feature activation+2.88e-01

Pos logit contributions
cles+0.602
 unrelated+0.598
minist+0.563
interstitial+0.556
 Beir+0.519
Neg logit contributions
ertodd-0.574
isconsin-0.552
alsa-0.536
framework-0.515
urdue-0.514
Token Winnipeg
Token ID23434
Feature activation+2.26e+00

Pos logit contributions
ertodd+0.476
isconsin+0.457
alsa+0.443
framework+0.424
urdue+0.423
Neg logit contributions
cles-0.595
 unrelated-0.590
minist-0.560
interstitial-0.554
 Beir-0.518
Token Jets
Token ID14728
Feature activation+1.36e+00

Pos logit contributions
isconsin+2.607
ertodd+2.598
alsa+2.461
 Taj+2.442
urdue+2.319
Neg logit contributions
cles-5.498
 unrelated-5.418
minist-5.192
interstitial-5.190
 Beir-4.868
Token (@
Token ID4275
Feature activation-3.10e-01

Pos logit contributions
ertodd+2.647
isconsin+2.568
alsa+2.519
 Taj+2.429
framework+2.420
Neg logit contributions
cles-2.356
 unrelated-2.319
minist-2.167
interstitial-2.157
 Beir-1.998
TokenN
Token ID45
Feature activation-3.12e-02

Pos logit contributions
cles+0.567
 unrelated+0.564
minist+0.529
interstitial+0.523
 Beir+0.487
Neg logit contributions
ertodd-0.583
isconsin-0.563
alsa-0.547
framework-0.527
urdue-0.526
TokenHL
Token ID6581
Feature activation+1.00e+00

Pos logit contributions
cles+0.041
 unrelated+0.040
minist+0.037
interstitial+0.036
 Beir+0.033
Neg logit contributions
ertodd-0.075
isconsin-0.073
alsa-0.072
framework-0.069
urdue-0.069
TokenJ
Token ID41
Feature activation+5.71e-01

Pos logit contributions
ertodd+1.844
isconsin+1.818
alsa+1.750
framework+1.704
urdue+1.690
Neg logit contributions
cles-1.845
 unrelated-1.839
interstitial-1.705
minist-1.692
 Beir-1.618
Token.[
Token ID3693
Feature activation+3.22e-03

Pos logit contributions
ertodd+0.710
isconsin+0.687
alsa+0.675
 Taj+0.649
framework+0.647
Neg logit contributions
cles-0.628
 unrelated-0.607
minist-0.587
interstitial-0.579
 Beir-0.533
Token16
Token ID1433
Feature activation+5.82e-02

Pos logit contributions
ertodd+0.007
isconsin+0.006
alsa+0.006
framework+0.006
urdue+0.006
Neg logit contributions
cles-0.005
 unrelated-0.005
minist-0.005
interstitial-0.005
 Beir-0.005
Token]
Token ID60
Feature activation-3.49e-01

Pos logit contributions
ertodd+0.095
isconsin+0.091
alsa+0.089
framework+0.085
urdue+0.085
Neg logit contributions
cles-0.121
 unrelated-0.120
minist-0.114
interstitial-0.112
 Beir-0.105
Token<|endoftext|>
Token ID50256
Feature activation-6.95e-01

Pos logit contributions
cles+0.685
 unrelated+0.679
minist+0.642
interstitial+0.635
 Beir+0.589
Neg logit contributions
ertodd-0.612
isconsin-0.588
alsa-0.571
framework-0.550
 Taj-0.548
TokenD
Token ID35
Feature activation-3.26e-02

Pos logit contributions
cles+1.236
 unrelated+1.229
minist+1.151
interstitial+1.134
 Beir+1.057
Neg logit contributions
ertodd-1.343
isconsin-1.296
alsa-1.264
framework-1.218
urdue-1.214
Tokeninosaur
Token ID21317
Feature activation+2.19e+00

Pos logit contributions
cles+0.059
 unrelated+0.059
minist+0.055
interstitial+0.054
 Beir+0.051
Neg logit contributions
ertodd-0.062
isconsin-0.060
alsa-0.059
urdue-0.056
framework-0.056
Token Jr
Token ID7504
Feature activation+2.40e-01

Pos logit contributions
ertodd+3.944
alsa+3.744
isconsin+3.709
 Taj+3.611
urdue+3.557
Neg logit contributions
 unrelated-3.939
cles-3.929
interstitial-3.747
minist-3.708
leans-3.446
Token.:
Token ID11207
Feature activation-4.29e-01

Pos logit contributions
ertodd+0.441
isconsin+0.424
alsa+0.416
urdue+0.398
 Taj+0.397
Neg logit contributions
cles-0.446
 unrelated-0.442
minist-0.418
interstitial-0.416
 Beir-0.382
Token "
Token ID366
Feature activation+2.64e-01

Pos logit contributions
cles+0.826
 unrelated+0.821
minist+0.773
interstitial+0.763
 Beir+0.714
Neg logit contributions
ertodd-0.767
isconsin-0.737
alsa-0.716
framework-0.687
urdue-0.687
TokenI
Token ID40
Feature activation+2.01e-01

Pos logit contributions
ertodd+0.509
isconsin+0.494
alsa+0.483
framework+0.469
urdue+0.462
Neg logit contributions
cles-0.464
 unrelated-0.463
minist-0.431
interstitial-0.426
 Beir-0.398
Token'll
Token ID1183
Feature activation+5.19e-01

Pos logit contributions
ertodd+0.363
isconsin+0.349
alsa+0.341
framework+0.326
 Taj+0.326
Neg logit contributions
cles-0.378
 unrelated-0.377
minist-0.356
interstitial-0.354
 Beir-0.326
Tokenopened
Token ID26350
Feature activation+7.08e-01

Pos logit contributions
ertodd+0.896
isconsin+0.875
alsa+0.863
framework+0.844
urdue+0.826
Neg logit contributions
cles-0.511
 unrelated-0.510
minist-0.463
interstitial-0.456
 Beir-0.425
Token on
Token ID319
Feature activation+7.20e-03

Pos logit contributions
ertodd+1.373
isconsin+1.351
alsa+1.303
 Taj+1.273
urdue+1.264
Neg logit contributions
cles-1.215
 unrelated-1.172
interstitial-1.143
minist-1.138
leans-1.033
Token political
Token ID1964
Feature activation+5.65e-01

Pos logit contributions
ertodd+0.013
isconsin+0.012
alsa+0.012
framework+0.012
urdue+0.012
Neg logit contributions
cles-0.014
 unrelated-0.014
minist-0.013
interstitial-0.013
 Beir-0.012
Token grounds
Token ID9384
Feature activation+6.42e-01

Pos logit contributions
ertodd+0.741
isconsin+0.737
alsa+0.697
framework+0.680
 Taj+0.677
Neg logit contributions
cles-1.312
 unrelated-1.269
minist-1.252
interstitial-1.241
 Beir-1.172
Token after
Token ID706
Feature activation-3.10e-01

Pos logit contributions
ertodd+1.177
isconsin+1.150
alsa+1.107
urdue+1.077
framework+1.074
Neg logit contributions
cles-1.177
 unrelated-1.136
interstitial-1.116
minist-1.104
 Beir-1.009
Token Wikileaks
Token ID35828
Feature activation+2.16e+00

Pos logit contributions
cles+0.581
 unrelated+0.577
minist+0.543
interstitial+0.535
 Beir+0.499
Neg logit contributions
ertodd-0.572
isconsin-0.550
alsa-0.535
framework-0.514
urdue-0.513
Token published
Token ID3199
Feature activation+1.85e-01

Pos logit contributions
ertodd+3.898
isconsin+3.793
 Taj+3.669
alsa+3.665
framework+3.596
Neg logit contributions
cles-3.892
interstitial-3.749
 unrelated-3.744
minist-3.703
 Beir-3.353
Token material
Token ID2587
Feature activation+1.22e+00

Pos logit contributions
ertodd+0.323
isconsin+0.311
alsa+0.302
framework+0.290
 Taj+0.290
Neg logit contributions
cles-0.363
 unrelated-0.357
minist-0.340
interstitial-0.337
 Beir-0.315
Token embarrassing
Token ID18997
Feature activation+2.63e-01

Pos logit contributions
ertodd+2.327
isconsin+2.253
 Taj+2.201
alsa+2.194
framework+2.135
Neg logit contributions
cles-2.091
interstitial-1.969
minist-1.960
 unrelated-1.959
leans-1.770
Token to
Token ID284
Feature activation+1.85e-01

Pos logit contributions
ertodd+0.462
isconsin+0.446
alsa+0.434
 Taj+0.417
framework+0.416
Neg logit contributions
cles-0.509
 unrelated-0.501
minist-0.476
interstitial-0.473
 Beir-0.441
Token the
Token ID262
Feature activation+7.12e-02

Pos logit contributions
ertodd+0.310
isconsin+0.298
alsa+0.290
framework+0.277
urdue+0.277
Neg logit contributions
cles-0.375
 unrelated-0.372
minist-0.353
interstitial-0.349
 Beir-0.327
Token
Token ID198
Feature activation-2.17e-01

Pos logit contributions
cles+0.415
 unrelated+0.414
minist+0.384
interstitial+0.365
cle+0.360
Neg logit contributions
ertodd-0.454
isconsin-0.434
alsa-0.423
cipled-0.408
urdue-0.406
TokenNow
Token ID3844
Feature activation-4.78e-01

Pos logit contributions
cles+0.380
 unrelated+0.378
minist+0.353
interstitial+0.349
 Beir+0.325
Neg logit contributions
ertodd-0.426
isconsin-0.412
alsa-0.403
framework-0.389
urdue-0.387
Token prosecutors
Token ID11947
Feature activation-5.92e-01

Pos logit contributions
cles+0.892
 unrelated+0.888
minist+0.832
interstitial+0.822
 Beir+0.767
Neg logit contributions
ertodd-0.884
isconsin-0.850
alsa-0.827
framework-0.797
urdue-0.793
Token have
Token ID423
Feature activation-1.48e-01

Pos logit contributions
cles+1.083
 unrelated+1.076
minist+1.010
interstitial+0.995
 Beir+0.927
Neg logit contributions
ertodd-1.115
isconsin-1.073
alsa-1.045
framework-1.005
urdue-1.003
Token filed
Token ID5717
Feature activation+6.13e-02

Pos logit contributions
cles+0.259
 unrelated+0.258
minist+0.241
interstitial+0.237
 Beir+0.220
Neg logit contributions
ertodd-0.292
isconsin-0.281
alsa-0.274
framework-0.264
urdue-0.263
Token motion
Token ID6268
Feature activation+2.13e+00

Pos logit contributions
ertodd+0.110
isconsin+0.106
alsa+0.103
urdue+0.099
framework+0.099
Neg logit contributions
cles-0.117
 unrelated-0.115
minist-0.110
interstitial-0.108
 Beir-0.101
Token to
Token ID284
Feature activation-7.16e-02

Pos logit contributions
ertodd+3.731
isconsin+3.567
alsa+3.503
 Taj+3.377
urdue+3.351
Neg logit contributions
cles-3.926
 unrelated-3.836
interstitial-3.811
minist-3.796
leans-3.534
Token reconsider
Token ID26540
Feature activation+2.77e-02

Pos logit contributions
cles+0.130
 unrelated+0.127
minist+0.121
interstitial+0.121
 Beir+0.111
Neg logit contributions
ertodd-0.135
isconsin-0.131
alsa-0.128
framework-0.123
 Taj-0.123
Token,
Token ID11
Feature activation-8.07e-02

Pos logit contributions
ertodd+0.049
isconsin+0.048
alsa+0.046
urdue+0.045
 Taj+0.045
Neg logit contributions
cles-0.053
 unrelated-0.052
minist-0.050
interstitial-0.049
 Beir-0.046
Token believing
Token ID14773
Feature activation-4.02e-02

Pos logit contributions
cles+0.132
 unrelated+0.129
minist+0.122
interstitial+0.120
 Beir+0.110
Neg logit contributions
ertodd-0.167
isconsin-0.163
alsa-0.159
urdue-0.154
framework-0.153
Token P
Token ID350
Feature activation-2.45e-02

Pos logit contributions
cles+0.081
 unrelated+0.079
minist+0.076
interstitial+0.075
cle+0.070
Neg logit contributions
ertodd-0.068
isconsin-0.066
alsa-0.064
urdue-0.062
 Taj-0.061
Token the
Token ID262
Feature activation+1.49e-01

Pos logit contributions
cles+0.059
 unrelated+0.059
minist+0.056
interstitial+0.055
 Beir+0.051
Neg logit contributions
ertodd-0.053
isconsin-0.051
alsa-0.049
framework-0.047
urdue-0.047
Token world
Token ID995
Feature activation+1.20e-02

Pos logit contributions
ertodd+0.270
isconsin+0.260
alsa+0.254
framework+0.244
urdue+0.243
Neg logit contributions
cles-0.283
 unrelated-0.279
minist-0.264
interstitial-0.262
 Beir-0.243
Token is
Token ID318
Feature activation+8.07e-02

Pos logit contributions
ertodd+0.024
isconsin+0.023
alsa+0.022
framework+0.021
urdue+0.021
Neg logit contributions
cles-0.021
 unrelated-0.021
minist-0.019
interstitial-0.019
 Beir-0.018
Token being
Token ID852
Feature activation+4.19e-02

Pos logit contributions
ertodd+0.161
isconsin+0.155
alsa+0.152
framework+0.147
 Taj+0.146
Neg logit contributions
cles-0.138
 unrelated-0.135
minist-0.128
interstitial-0.127
 Beir-0.117
Token held
Token ID2714
Feature activation+3.86e-01

Pos logit contributions
ertodd+0.080
isconsin+0.077
alsa+0.075
framework+0.072
urdue+0.072
Neg logit contributions
cles-0.076
 unrelated-0.075
minist-0.071
interstitial-0.069
 Beir-0.065
Token hostage
Token ID23229
Feature activation+2.10e+00

Pos logit contributions
ertodd+0.718
isconsin+0.691
alsa+0.673
framework+0.650
urdue+0.648
Neg logit contributions
cles-0.712
 unrelated-0.699
interstitial-0.664
minist-0.662
 Beir-0.610
Token by
Token ID416
Feature activation-1.44e-01

Pos logit contributions
ertodd+4.025
isconsin+3.895
alsa+3.811
urdue+3.700
framework+3.659
Neg logit contributions
cles-3.617
 unrelated-3.468
interstitial-3.457
minist-3.267
 Beir-3.116
Token 3
Token ID513
Feature activation-6.44e-01

Pos logit contributions
cles+0.268
 unrelated+0.266
minist+0.250
interstitial+0.247
 Beir+0.230
Neg logit contributions
ertodd-0.265
isconsin-0.255
alsa-0.248
framework-0.238
urdue-0.238
TokenDES
Token ID30910
Feature activation+2.64e-01

Pos logit contributions
cles+1.137
 unrelated+1.135
minist+1.060
interstitial+1.040
 Beir+0.967
Neg logit contributions
ertodd-1.256
isconsin-1.209
alsa-1.177
framework-1.136
urdue-1.134
Token.
Token ID13
Feature activation-1.47e-01

Pos logit contributions
ertodd+0.494
isconsin+0.476
alsa+0.469
framework+0.448
urdue+0.447
Neg logit contributions
cles-0.481
 unrelated-0.476
interstitial-0.452
minist-0.446
 Beir-0.418
Token
Token ID198
Feature activation+4.05e-02

Pos logit contributions
cles+0.286
 unrelated+0.284
minist+0.268
interstitial+0.265
 Beir+0.248
Neg logit contributions
ertodd-0.261
isconsin-0.250
alsa-0.243
framework-0.233
urdue-0.233
Token as
Token ID355
Feature activation-2.17e-01

Pos logit contributions
ertodd+0.383
isconsin+0.370
alsa+0.360
framework+0.346
urdue+0.346
Neg logit contributions
cles-0.391
 unrelated-0.386
minist-0.364
interstitial-0.362
 Beir-0.336
Token a
Token ID257
Feature activation+1.44e-01

Pos logit contributions
cles+0.434
 unrelated+0.426
minist+0.405
interstitial+0.402
 Beir+0.373
Neg logit contributions
ertodd-0.372
isconsin-0.359
alsa-0.349
 Taj-0.334
framework-0.333
Token
Token ID564
Feature activation+6.22e-03

Pos logit contributions
ertodd+0.277
isconsin+0.269
alsa+0.264
 Taj+0.255
framework+0.254
Neg logit contributions
cles-0.255
 unrelated-0.249
minist-0.236
interstitial-0.235
leans-0.216
Token
Token ID250
Feature activation+1.35e-01

Pos logit contributions
ertodd+0.012
isconsin+0.011
alsa+0.011
urdue+0.010
framework+0.010
Neg logit contributions
cles-0.012
 unrelated-0.012
minist-0.011
interstitial-0.011
 Beir-0.010
Tokentrans
Token ID7645
Feature activation-1.04e-01

Pos logit contributions
ertodd+0.241
alsa+0.237
isconsin+0.235
framework+0.228
 Taj+0.220
Neg logit contributions
cles-0.250
 unrelated-0.246
interstitial-0.229
minist-0.229
 Beir-0.220
Tokennational
Token ID14648
Feature activation+2.10e+00

Pos logit contributions
cles+0.197
 unrelated+0.195
minist+0.184
interstitial+0.182
 Beir+0.170
Neg logit contributions
ertodd-0.188
isconsin-0.182
alsa-0.177
framework-0.170
 Taj-0.169
Token criminal
Token ID4301
Feature activation+1.75e-01

Pos logit contributions
ertodd+3.130
isconsin+3.115
alsa+3.063
 Taj+3.026
framework+2.951
Neg logit contributions
cles-4.389
 unrelated-4.163
minist-4.132
interstitial-4.114
leans-3.904
Token organization
Token ID4009
Feature activation+4.92e-01

Pos logit contributions
ertodd+0.135
isconsin+0.126
alsa+0.118
framework+0.107
 Taj+0.106
Neg logit contributions
cles-0.513
 unrelated-0.505
minist-0.490
interstitial-0.488
leans-0.465
Token.
Token ID13
Feature activation+2.03e-01

Pos logit contributions
ertodd+0.925
isconsin+0.900
alsa+0.874
framework+0.847
 Taj+0.841
Neg logit contributions
cles-0.895
 unrelated-0.865
minist-0.840
interstitial-0.834
leans-0.761
Token
Token ID447
Feature activation-1.35e-02

Pos logit contributions
ertodd+0.359
isconsin+0.347
alsa+0.335
framework+0.325
 Taj+0.325
Neg logit contributions
cles-0.395
 unrelated-0.391
minist-0.370
interstitial-0.368
leans-0.339
Token
Token ID251
Feature activation+1.57e-02

Pos logit contributions
cles+0.026
 unrelated+0.026
minist+0.024
interstitial+0.024
 Beir+0.022
Neg logit contributions
ertodd-0.024
isconsin-0.023
alsa-0.023
framework-0.022
urdue-0.022
Tokenral
Token ID1373
Feature activation+4.64e-01

Pos logit contributions
ertodd+0.451
isconsin+0.437
alsa+0.432
framework+0.417
urdue+0.416
Neg logit contributions
 unrelated-0.186
cles-0.185
minist-0.166
interstitial-0.164
 Beir-0.145
Token Process
Token ID10854
Feature activation+5.45e-01

Pos logit contributions
ertodd+0.831
isconsin+0.805
alsa+0.783
framework+0.759
 Taj+0.756
Neg logit contributions
cles-0.878
 unrelated-0.878
minist-0.825
interstitial-0.814
 Beir-0.751
Tokenion
Token ID295
Feature activation+4.33e-01

Pos logit contributions
ertodd+1.000
isconsin+0.953
alsa+0.944
framework+0.909
 Taj+0.906
Neg logit contributions
cles-1.003
 unrelated-1.003
interstitial-0.949
minist-0.944
 Beir-0.866
Token
Token ID198
Feature activation+2.04e-01

Pos logit contributions
ertodd+0.763
isconsin+0.730
alsa+0.711
framework+0.681
urdue+0.679
Neg logit contributions
cles-0.843
 unrelated-0.840
minist-0.792
interstitial-0.786
 Beir-0.730
Token
Token ID198
Feature activation+1.40e-01

Pos logit contributions
ertodd+0.385
isconsin+0.368
alsa+0.358
urdue+0.344
cipled+0.344
Neg logit contributions
cles-0.376
 unrelated-0.375
minist-0.350
interstitial-0.339
cle-0.325
TokenPir
Token ID46772
Feature activation+2.06e+00

Pos logit contributions
ertodd+0.274
isconsin+0.265
alsa+0.260
framework+0.252
urdue+0.248
Neg logit contributions
cles-0.245
 unrelated-0.244
minist-0.227
interstitial-0.225
 Beir-0.211
Tokenacy
Token ID1590
Feature activation+9.55e-01

Pos logit contributions
ertodd+3.986
alsa+3.871
isconsin+3.866
framework+3.651
cipled+3.626
Neg logit contributions
 unrelated-3.529
cles-3.409
minist-3.271
interstitial-3.262
 Beir-3.134
Token Charm
Token ID30225
Feature activation+7.23e-02

Pos logit contributions
ertodd+1.692
isconsin+1.625
alsa+1.584
 Taj+1.535
framework+1.518
Neg logit contributions
 unrelated-1.823
cles-1.818
interstitial-1.712
minist-1.710
 Beir-1.583
Token vs
Token ID3691
Feature activation+1.01e+00

Pos logit contributions
ertodd+0.119
isconsin+0.114
alsa+0.111
framework+0.106
urdue+0.106
Neg logit contributions
cles-0.149
 unrelated-0.148
minist-0.140
interstitial-0.139
 Beir-0.130
Token Talent
Token ID29505
Feature activation+5.55e-01

Pos logit contributions
ertodd+1.791
isconsin+1.723
alsa+1.692
 Taj+1.666
framework+1.633
Neg logit contributions
cles-1.911
 unrelated-1.885
minist-1.791
interstitial-1.789
leans-1.625
Token of
Token ID286
Feature activation+4.83e-01

Pos logit contributions
ertodd+1.012
isconsin+0.972
alsa+0.955
framework+0.916
urdue+0.914
Neg logit contributions
cles-1.031
 unrelated-1.031
minist-0.969
interstitial-0.961
 Beir-0.892
Tokeniff
Token ID733
Feature activation+3.81e-01

Pos logit contributions
cles+0.546
 unrelated+0.540
minist+0.503
interstitial+0.492
cle+0.463
Neg logit contributions
ertodd-0.729
isconsin-0.697
alsa-0.680
 Taj-0.654
cipled-0.653
TokenTra
Token ID15721
Feature activation-7.05e-01

Pos logit contributions
ertodd+0.785
isconsin+0.759
alsa+0.740
framework+0.714
urdue+0.714
Neg logit contributions
cles-0.631
 unrelated-0.626
minist-0.584
interstitial-0.575
 Beir-0.530
Tokenx
Token ID87
Feature activation-1.36e-01

Pos logit contributions
cles+1.254
 unrelated+1.213
minist+1.132
cle+1.077
interstitial+1.077
Neg logit contributions
ertodd-1.397
isconsin-1.333
alsa-1.296
 Taj-1.267
cipled-1.262
Token
Token ID198
Feature activation-9.95e-02

Pos logit contributions
cles+0.265
 unrelated+0.262
minist+0.248
interstitial+0.245
 Beir+0.229
Neg logit contributions
ertodd-0.241
isconsin-0.232
alsa-0.226
framework-0.216
urdue-0.216
Token
Token ID198
Feature activation-1.49e-01

Pos logit contributions
cles+0.179
 unrelated+0.178
minist+0.166
interstitial+0.159
cle+0.155
Neg logit contributions
ertodd-0.193
isconsin-0.185
alsa-0.179
urdue-0.173
cipled-0.173
TokenReviewer
Token ID35407
Feature activation+2.05e+00

Pos logit contributions
 unrelated+0.301
cles+0.300
minist+0.283
interstitial+0.279
 Beir+0.266
Neg logit contributions
ertodd-0.250
isconsin-0.242
alsa-0.238
framework-0.227
urdue-0.224
Token:
Token ID25
Feature activation-3.33e-01

Pos logit contributions
ertodd+3.280
isconsin+3.135
alsa+3.048
framework+2.948
 Taj+2.894
Neg logit contributions
cles-4.244
 unrelated-4.185
interstitial-4.097
minist-4.011
 Beir-3.808
Token V
Token ID569
Feature activation+4.75e-01

Pos logit contributions
cles+0.657
 unrelated+0.653
minist+0.616
interstitial+0.608
 Beir+0.569
Neg logit contributions
ertodd-0.580
isconsin-0.557
alsa-0.541
framework-0.518
urdue-0.518
Tokenthe
Token ID1169
Feature activation+4.79e-02

Pos logit contributions
ertodd+0.928
isconsin+0.896
alsa+0.877
framework+0.842
urdue+0.840
Neg logit contributions
cles-0.832
 unrelated-0.830
minist-0.774
interstitial-0.767
 Beir-0.711
TokenHappy
Token ID25082
Feature activation-9.94e-02

Pos logit contributions
ertodd+0.093
isconsin+0.090
alsa+0.088
framework+0.085
urdue+0.084
Neg logit contributions
 unrelated-0.084
cles-0.084
minist-0.078
interstitial-0.078
 Beir-0.072
TokenL
Token ID43
Feature activation-1.87e-01

Pos logit contributions
cles+0.180
 unrelated+0.179
minist+0.167
interstitial+0.167
 Beir+0.154
Neg logit contributions
ertodd-0.189
isconsin-0.182
alsa-0.178
framework-0.171
urdue-0.170
Token Temple
Token ID10857
Feature activation+4.87e-01

Pos logit contributions
ertodd+0.084
isconsin+0.080
alsa+0.078
framework+0.074
urdue+0.074
Neg logit contributions
cles-0.114
 unrelated-0.113
minist-0.108
interstitial-0.106
 Beir-0.100
Token
Token ID198
Feature activation-1.31e-01

Pos logit contributions
ertodd+0.836
isconsin+0.791
alsa+0.780
 Taj+0.756
framework+0.749
Neg logit contributions
cles-0.967
 unrelated-0.963
interstitial-0.909
minist-0.908
leans-0.838
Token
Token ID198
Feature activation-1.19e-01

Pos logit contributions
cles+0.235
 unrelated+0.234
minist+0.217
interstitial+0.207
cle+0.203
Neg logit contributions
ertodd-0.255
isconsin-0.244
alsa-0.238
cipled-0.230
urdue-0.228
TokenAddress
Token ID20231
Feature activation-6.07e-01

Pos logit contributions
cles+0.217
 unrelated+0.217
minist+0.203
interstitial+0.200
 Beir+0.188
Neg logit contributions
ertodd-0.225
isconsin-0.216
alsa-0.212
framework-0.204
urdue-0.203
Token:
Token ID25
Feature activation-2.82e-02

Pos logit contributions
cles+1.073
 unrelated+1.063
minist+0.982
interstitial+0.931
cle+0.921
Neg logit contributions
ertodd-1.202
isconsin-1.156
alsa-1.122
cipled-1.089
urdue-1.076
Token Jam
Token ID9986
Feature activation+2.05e+00

Pos logit contributions
cles+0.055
 unrelated+0.055
minist+0.052
interstitial+0.051
 Beir+0.048
Neg logit contributions
ertodd-0.049
isconsin-0.047
alsa-0.046
 Taj-0.044
framework-0.044
Tokenn
Token ID77
Feature activation+5.37e-02

Pos logit contributions
ertodd+3.951
alsa+3.947
isconsin+3.928
 Taj+3.741
framework+3.711
Neg logit contributions
 unrelated-3.415
cles-3.301
interstitial-3.129
minist-3.101
leans-2.897
Tokenagar
Token ID32452
Feature activation+1.21e-01

Pos logit contributions
ertodd+0.111
isconsin+0.108
alsa+0.106
framework+0.102
urdue+0.102
Neg logit contributions
cles-0.087
 unrelated-0.087
minist-0.082
interstitial-0.080
 Beir-0.073
Token,
Token ID11
Feature activation-3.26e-01

Pos logit contributions
ertodd+0.220
isconsin+0.213
alsa+0.209
framework+0.201
 Taj+0.201
Neg logit contributions
cles-0.226
 unrelated-0.226
minist-0.213
interstitial-0.211
 Beir-0.194
Token Dw
Token ID19113
Feature activation+1.06e+00

Pos logit contributions
cles+0.681
 unrelated+0.677
minist+0.641
interstitial+0.634
 Beir+0.595
Neg logit contributions
ertodd-0.529
isconsin-0.507
alsa-0.491
framework-0.469
urdue-0.468
Tokenark
Token ID668
Feature activation+2.98e-01

Pos logit contributions
isconsin+1.923
ertodd+1.922
alsa+1.877
urdue+1.778
framework+1.771
Neg logit contributions
 unrelated-1.956
cles-1.930
interstitial-1.810
minist-1.802
 Beir-1.675
Token we
Token ID356
Feature activation+3.01e-01

Pos logit contributions
cles+0.333
 unrelated+0.329
minist+0.310
interstitial+0.307
 Beir+0.282
Neg logit contributions
ertodd-0.390
isconsin-0.378
alsa-0.368
framework-0.355
urdue-0.354
Token think
Token ID892
Feature activation+1.28e+00

Pos logit contributions
ertodd+0.552
isconsin+0.530
alsa+0.515
framework+0.498
 Taj+0.496
Neg logit contributions
cles-0.560
 unrelated-0.551
interstitial-0.528
minist-0.526
 Beir-0.487
Token about
Token ID546
Feature activation-2.37e-02

Pos logit contributions
ertodd+2.447
isconsin+2.350
alsa+2.281
 Taj+2.279
framework+2.235
Neg logit contributions
cles-2.186
 unrelated-2.116
interstitial-2.095
minist-2.027
 Beir-1.873
Token a
Token ID257
Feature activation+2.41e-01

Pos logit contributions
cles+0.045
 unrelated+0.044
minist+0.042
interstitial+0.042
leans+0.038
Neg logit contributions
ertodd-0.043
isconsin-0.041
alsa-0.040
 Taj-0.039
framework-0.039
Token trans
Token ID1007
Feature activation+2.96e-01

Pos logit contributions
ertodd+0.452
isconsin+0.436
alsa+0.425
framework+0.411
urdue+0.408
Neg logit contributions
cles-0.439
 unrelated-0.435
minist-0.410
interstitial-0.407
 Beir-0.376
Tokennational
Token ID14648
Feature activation+2.04e+00

Pos logit contributions
ertodd+0.531
isconsin+0.513
alsa+0.501
framework+0.482
 Taj+0.478
Neg logit contributions
cles-0.564
 unrelated-0.559
minist-0.525
interstitial-0.522
 Beir-0.487
Token network
Token ID3127
Feature activation+6.69e-01

Pos logit contributions
ertodd+3.355
isconsin+3.253
 Taj+3.193
alsa+3.156
framework+3.134
Neg logit contributions
cles-4.021
 unrelated-3.887
interstitial-3.885
minist-3.773
leans-3.540
Token of
Token ID286
Feature activation+8.78e-02

Pos logit contributions
ertodd+1.269
isconsin+1.218
alsa+1.188
 Taj+1.152
framework+1.149
Neg logit contributions
cles-1.199
 unrelated-1.172
interstitial-1.126
minist-1.123
leans-1.030
Token operatives
Token ID27269
Feature activation+5.93e-01

Pos logit contributions
ertodd+0.164
isconsin+0.158
alsa+0.154
framework+0.148
urdue+0.148
Neg logit contributions
cles-0.161
 unrelated-0.160
minist-0.151
interstitial-0.149
 Beir-0.138
Token who
Token ID508
Feature activation+6.75e-02

Pos logit contributions
ertodd+1.140
isconsin+1.105
alsa+1.078
 Taj+1.042
framework+1.036
Neg logit contributions
cles-1.038
 unrelated-1.012
minist-0.975
interstitial-0.975
 Beir-0.888
Token want
Token ID765
Feature activation+6.36e-01

Pos logit contributions
ertodd+0.122
isconsin+0.117
alsa+0.114
urdue+0.109
framework+0.109
Neg logit contributions
cles-0.128
 unrelated-0.127
minist-0.121
interstitial-0.120
 Beir-0.111
Token conditions
Token ID3403
Feature activation+7.12e-01

Pos logit contributions
ertodd+1.855
isconsin+1.826
alsa+1.780
framework+1.718
urdue+1.705
Neg logit contributions
cles-1.657
 unrelated-1.576
minist-1.535
interstitial-1.518
cle-1.376
Token added
Token ID2087
Feature activation-4.16e-01

Pos logit contributions
ertodd+1.322
isconsin+1.290
alsa+1.258
framework+1.210
 Taj+1.205
Neg logit contributions
cles-1.291
 unrelated-1.234
minist-1.204
interstitial-1.201
 Beir-1.087
Token at
Token ID379
Feature activation-3.52e-01

Pos logit contributions
cles+0.757
 unrelated+0.750
minist+0.706
interstitial+0.697
 Beir+0.647
Neg logit contributions
ertodd-0.789
isconsin-0.762
alsa-0.741
framework-0.713
urdue-0.712
Token his
Token ID465
Feature activation+1.20e-01

Pos logit contributions
cles+0.660
 unrelated+0.644
minist+0.610
interstitial+0.609
cle+0.562
Neg logit contributions
ertodd-0.646
isconsin-0.626
alsa-0.609
urdue-0.585
framework-0.582
Token arra
Token ID44723
Feature activation+1.04e+00

Pos logit contributions
ertodd+0.229
isconsin+0.223
alsa+0.219
urdue+0.210
 Taj+0.210
Neg logit contributions
cles-0.215
 unrelated-0.206
interstitial-0.199
minist-0.198
leans-0.181
Tokenignment
Token ID16747
Feature activation+2.04e+00

Pos logit contributions
ertodd+1.329
isconsin+1.254
alsa+1.234
urdue+1.166
framework+1.151
Neg logit contributions
cles-2.511
 unrelated-2.510
minist-2.392
interstitial-2.390
 Beir-2.257
Token in
Token ID287
Feature activation+1.49e-01

Pos logit contributions
ertodd+3.520
isconsin+3.341
alsa+3.266
framework+3.152
urdue+3.151
Neg logit contributions
cles-3.937
interstitial-3.783
 unrelated-3.758
minist-3.697
leans-3.427
Token December
Token ID3426
Feature activation+3.58e-01

Pos logit contributions
ertodd+0.248
isconsin+0.238
alsa+0.231
 Taj+0.224
urdue+0.222
Neg logit contributions
cles-0.304
 unrelated-0.298
minist-0.287
interstitial-0.284
leans-0.264
Token 2016
Token ID1584
Feature activation+5.89e-02

Pos logit contributions
ertodd+0.628
isconsin+0.609
alsa+0.590
framework+0.567
urdue+0.567
Neg logit contributions
cles-0.693
 unrelated-0.680
minist-0.652
interstitial-0.645
 Beir-0.597
Token.
Token ID13
Feature activation+2.58e-02

Pos logit contributions
ertodd+0.108
isconsin+0.104
alsa+0.101
urdue+0.098
framework+0.098
Neg logit contributions
cles-0.110
 unrelated-0.108
minist-0.103
interstitial-0.103
 Beir-0.095
Token
Token ID198
Feature activation-2.35e-01

Pos logit contributions
ertodd+0.045
isconsin+0.044
alsa+0.042
framework+0.041
urdue+0.041
Neg logit contributions
cles-0.050
 unrelated-0.050
minist-0.047
interstitial-0.047
 Beir-0.043
Token your
Token ID534
Feature activation+6.17e-02

Pos logit contributions
cles+1.031
 unrelated+1.027
minist+0.968
interstitial+0.953
 Beir+0.893
Neg logit contributions
ertodd-0.906
isconsin-0.869
alsa-0.842
urdue-0.807
framework-0.806
Token character
Token ID2095
Feature activation+5.49e-01

Pos logit contributions
ertodd+0.100
isconsin+0.096
alsa+0.093
framework+0.089
urdue+0.089
Neg logit contributions
cles-0.129
 unrelated-0.127
minist-0.121
interstitial-0.120
 Beir-0.112
Token,
Token ID11
Feature activation+1.96e-01

Pos logit contributions
ertodd+1.076
isconsin+1.038
alsa+1.013
framework+0.976
urdue+0.974
Neg logit contributions
cles-0.959
 unrelated-0.951
minist-0.892
interstitial-0.886
 Beir-0.816
Token but
Token ID475
Feature activation-1.09e-01

Pos logit contributions
ertodd+0.392
isconsin+0.379
alsa+0.371
framework+0.359
urdue+0.358
Neg logit contributions
cles-0.334
 unrelated-0.328
minist-0.311
interstitial-0.309
 Beir-0.282
Token I
Token ID314
Feature activation+1.78e-01

Pos logit contributions
cles+0.195
 unrelated+0.192
minist+0.182
interstitial+0.181
 Beir+0.167
Neg logit contributions
ertodd-0.207
isconsin-0.200
alsa-0.194
framework-0.188
urdue-0.188
Token wish
Token ID4601
Feature activation+2.04e+00

Pos logit contributions
ertodd+0.322
isconsin+0.307
alsa+0.301
framework+0.288
 Taj+0.287
Neg logit contributions
cles-0.338
 unrelated-0.334
interstitial-0.319
minist-0.318
 Beir-0.292
Token it
Token ID340
Feature activation+2.88e-02

Pos logit contributions
ertodd+3.389
isconsin+3.249
alsa+3.206
 Taj+3.203
framework+3.136
Neg logit contributions
cles-3.962
 unrelated-3.809
interstitial-3.741
minist-3.681
leans-3.405
Token had
Token ID550
Feature activation-2.14e-01

Pos logit contributions
ertodd+0.058
isconsin+0.056
alsa+0.054
framework+0.053
urdue+0.052
Neg logit contributions
cles-0.049
 unrelated-0.048
minist-0.046
interstitial-0.045
 Beir-0.041
Token been
Token ID587
Feature activation-6.17e-02

Pos logit contributions
cles+0.348
 unrelated+0.344
minist+0.322
interstitial+0.318
 Beir+0.292
Neg logit contributions
ertodd-0.447
isconsin-0.432
alsa-0.422
framework-0.408
urdue-0.407
Token addressed
Token ID9469
Feature activation-6.29e-01

Pos logit contributions
cles+0.108
 unrelated+0.107
minist+0.101
interstitial+0.101
 Beir+0.092
Neg logit contributions
ertodd-0.119
isconsin-0.116
alsa-0.113
framework-0.109
 Taj-0.109
Token between
Token ID1022
Feature activation-3.74e-01

Pos logit contributions
cles+1.117
 unrelated+1.116
minist+1.041
interstitial+1.009
cle+0.951
Neg logit contributions
ertodd-1.224
isconsin-1.177
alsa-1.151
urdue-1.102
framework-1.101
Token Embassy
Token ID23233
Feature activation+8.09e-01

Pos logit contributions
cles+0.130
 unrelated+0.128
minist+0.123
interstitial+0.121
 Beir+0.114
Neg logit contributions
ertodd-0.089
isconsin-0.085
alsa-0.082
framework-0.078
 Taj-0.078
Token coincided
Token ID41085
Feature activation+2.95e-01

Pos logit contributions
ertodd+1.550
isconsin+1.496
alsa+1.458
 Taj+1.422
framework+1.420
Neg logit contributions
cles-1.424
 unrelated-1.388
minist-1.337
interstitial-1.325
leans-1.201
Token with
Token ID351
Feature activation-1.95e-02

Pos logit contributions
ertodd+0.637
isconsin+0.621
alsa+0.601
urdue+0.585
framework+0.583
Neg logit contributions
cles-0.455
 unrelated-0.445
interstitial-0.422
minist-0.420
leans-0.375
Token the
Token ID262
Feature activation-1.16e-01

Pos logit contributions
cles+0.037
 unrelated+0.037
minist+0.035
interstitial+0.035
 Beir+0.032
Neg logit contributions
ertodd-0.035
isconsin-0.033
alsa-0.033
urdue-0.031
framework-0.031
Token Edward
Token ID10443
Feature activation+5.98e-01

Pos logit contributions
cles+0.218
 unrelated+0.216
minist+0.204
interstitial+0.201
 Beir+0.187
Neg logit contributions
ertodd-0.211
isconsin-0.204
alsa-0.198
framework-0.190
urdue-0.190
Token Snowden
Token ID15015
Feature activation+2.03e+00

Pos logit contributions
ertodd+0.629
isconsin+0.584
alsa+0.554
framework+0.515
urdue+0.511
Neg logit contributions
cles-1.596
 unrelated-1.594
minist-1.524
interstitial-1.508
 Beir-1.441
Token leaks
Token ID17316
Feature activation+1.10e+00

Pos logit contributions
ertodd+4.004
isconsin+3.893
alsa+3.816
 Taj+3.805
framework+3.729
Neg logit contributions
cles-3.388
 unrelated-3.206
interstitial-3.133
minist-3.113
 Beir-2.905
Token.
Token ID13
Feature activation+7.26e-02

Pos logit contributions
ertodd+1.977
isconsin+1.912
alsa+1.861
 Taj+1.811
framework+1.809
Neg logit contributions
cles-2.042
 unrelated-1.974
minist-1.907
interstitial-1.889
 Beir-1.753
Token Although
Token ID4900
Feature activation-4.14e-01

Pos logit contributions
ertodd+0.122
isconsin+0.118
alsa+0.114
framework+0.109
urdue+0.109
Neg logit contributions
cles-0.147
 unrelated-0.146
minist-0.138
interstitial-0.137
 Beir-0.128
Token Assange
Token ID21882
Feature activation+8.82e-01

Pos logit contributions
cles+0.869
 unrelated+0.862
minist+0.819
interstitial+0.809
 Beir+0.760
Neg logit contributions
ertodd-0.669
isconsin-0.640
alsa-0.620
framework-0.592
urdue-0.591
Token and
Token ID290
Feature activation+1.71e-01

Pos logit contributions
ertodd+1.716
isconsin+1.673
alsa+1.614
 Taj+1.591
urdue+1.579
Neg logit contributions
cles-1.510
 unrelated-1.479
interstitial-1.438
minist-1.429
 Beir-1.296
Token unpredictable
Token ID22900
Feature activation-2.62e-01

Pos logit contributions
ertodd+0.377
isconsin+0.371
alsa+0.359
 Taj+0.352
framework+0.348
Neg logit contributions
cles-0.292
 unrelated-0.283
interstitial-0.273
minist-0.272
 Beir-0.244
Token,
Token ID11
Feature activation-3.29e-02

Pos logit contributions
cles+0.475
 unrelated+0.470
minist+0.443
interstitial+0.440
 Beir+0.406
Neg logit contributions
ertodd-0.497
isconsin-0.481
alsa-0.467
framework-0.450
urdue-0.449
Token the
Token ID262
Feature activation-9.04e-02

Pos logit contributions
cles+0.061
 unrelated+0.060
minist+0.057
interstitial+0.056
 Beir+0.052
Neg logit contributions
ertodd-0.061
isconsin-0.059
alsa-0.058
 Taj-0.056
urdue-0.056
Token fixture
Token ID29220
Feature activation+3.39e-01

Pos logit contributions
cles+0.165
 unrelated+0.162
minist+0.153
interstitial+0.152
 Beir+0.140
Neg logit contributions
ertodd-0.171
isconsin-0.165
alsa-0.160
 Taj-0.155
framework-0.155
Token against
Token ID1028
Feature activation+3.46e-01

Pos logit contributions
ertodd+0.676
isconsin+0.660
alsa+0.637
 Taj+0.622
urdue+0.621
Neg logit contributions
cles-0.572
 unrelated-0.560
interstitial-0.533
minist-0.533
 Beir-0.482
Token Taj
Token ID32490
Feature activation+2.02e+00

Pos logit contributions
ertodd+0.580
isconsin+0.564
alsa+0.544
 Taj+0.537
urdue+0.527
Neg logit contributions
cles-0.695
 unrelated-0.682
minist-0.652
interstitial-0.652
leans-0.603
Tokenik
Token ID1134
Feature activation+9.22e-01

Pos logit contributions
ertodd+2.915
alsa+2.864
 Taj+2.856
isconsin+2.854
framework+2.760
Neg logit contributions
cles-4.352
 unrelated-4.282
interstitial-4.239
minist-4.171
 Beir-3.784
Tokenistan
Token ID4103
Feature activation-3.99e-03

Pos logit contributions
ertodd+1.468
isconsin+1.426
alsa+1.395
 Taj+1.380
urdue+1.335
Neg logit contributions
cles-1.899
 unrelated-1.885
minist-1.800
interstitial-1.799
 Beir-1.663
Token is
Token ID318
Feature activation-4.53e-02

Pos logit contributions
cles+0.007
 unrelated+0.007
minist+0.007
interstitial+0.006
 Beir+0.006
Neg logit contributions
ertodd-0.008
isconsin-0.008
alsa-0.007
urdue-0.007
framework-0.007
Token unlikely
Token ID7485
Feature activation-1.05e-01

Pos logit contributions
cles+0.077
 unrelated+0.075
minist+0.072
interstitial+0.072
 Beir+0.065
Neg logit contributions
ertodd-0.090
isconsin-0.088
alsa-0.085
 Taj-0.083
framework-0.083
Token to
Token ID284
Feature activation+2.27e-01

Pos logit contributions
cles+0.203
 unrelated+0.200
minist+0.190
interstitial+0.188
 Beir+0.175
Neg logit contributions
ertodd-0.189
isconsin-0.182
alsa-0.176
framework-0.170
urdue-0.169
Token-
Token ID12
Feature activation-4.41e-02

Pos logit contributions
cles+0.982
 unrelated+0.974
minist+0.916
interstitial+0.905
 Beir+0.834
Neg logit contributions
ertodd-1.166
isconsin-1.124
alsa-1.096
framework-1.060
 Taj-1.053
Tokenand
Token ID392
Feature activation+7.37e-01

Pos logit contributions
 unrelated+0.082
cles+0.082
minist+0.077
interstitial+0.076
 Beir+0.072
Neg logit contributions
ertodd-0.080
isconsin-0.077
alsa-0.076
framework-0.073
urdue-0.072
Token-
Token ID12
Feature activation+1.53e-02

Pos logit contributions
ertodd+1.527
isconsin+1.472
alsa+1.438
framework+1.394
urdue+1.385
Neg logit contributions
cles-1.198
 unrelated-1.185
minist-1.118
interstitial-1.106
 Beir-1.018
Tokens
Token ID82
Feature activation+1.25e-01

Pos logit contributions
ertodd+0.029
isconsin+0.028
alsa+0.027
framework+0.026
cipled+0.026
Neg logit contributions
 unrelated-0.028
cles-0.028
minist-0.026
interstitial-0.026
 Beir-0.024
Tokenoul
Token ID2852
Feature activation-1.92e-01

Pos logit contributions
ertodd+0.286
isconsin+0.280
alsa+0.277
urdue+0.265
framework+0.264
Neg logit contributions
 unrelated-0.175
cles-0.174
minist-0.161
interstitial-0.159
 Beir-0.145
Token defence
Token ID9366
Feature activation+2.02e+00

Pos logit contributions
cles+0.357
 unrelated+0.353
minist+0.333
interstitial+0.331
 Beir+0.307
Neg logit contributions
ertodd-0.353
isconsin-0.341
alsa-0.334
 Taj-0.321
urdue-0.319
Tokenman
Token ID805
Feature activation+6.50e-02

Pos logit contributions
ertodd+2.698
isconsin+2.604
alsa+2.602
 Taj+2.455
framework+2.373
Neg logit contributions
 unrelated-4.502
cles-4.501
interstitial-4.285
minist-4.259
 Beir-4.119
Token Josh
Token ID8518
Feature activation+2.41e-01

Pos logit contributions
ertodd+0.111
isconsin+0.106
alsa+0.103
framework+0.099
urdue+0.099
Neg logit contributions
cles-0.131
 unrelated-0.130
minist-0.123
interstitial-0.121
 Beir-0.113
Token G
Token ID402
Feature activation-3.29e-01

Pos logit contributions
ertodd+0.527
isconsin+0.513
alsa+0.501
framework+0.486
 Taj+0.485
Neg logit contributions
cles-0.365
 unrelated-0.362
minist-0.338
interstitial-0.333
 Beir-0.298
Tokenorg
Token ID2398
Feature activation-2.95e-01

Pos logit contributions
 unrelated+0.574
cles+0.574
minist+0.536
interstitial+0.528
 Beir+0.488
Neg logit contributions
ertodd-0.641
isconsin-0.626
alsa-0.615
urdue-0.588
framework-0.587
Tokenes
Token ID274
Feature activation-4.73e-01

Pos logit contributions
cles+0.358
 unrelated+0.355
minist+0.323
interstitial+0.317
 Beir+0.283
Neg logit contributions
ertodd-0.740
isconsin-0.719
alsa-0.704
framework-0.684
urdue-0.684
Tokenhers
Token ID7084
Feature activation-1.21e-02

Pos logit contributions
ertodd+1.973
isconsin+1.929
alsa+1.898
framework+1.850
urdue+1.846
Neg logit contributions
cles-0.741
 unrelated-0.739
minist-0.662
interstitial-0.656
 Beir-0.568
Token,
Token ID11
Feature activation+2.50e-03

Pos logit contributions
cles+0.023
 unrelated+0.022
minist+0.021
interstitial+0.021
 Beir+0.019
Neg logit contributions
ertodd-0.022
isconsin-0.021
alsa-0.021
framework-0.020
urdue-0.020
Token helped
Token ID4193
Feature activation+3.18e-01

Pos logit contributions
ertodd+0.005
isconsin+0.005
alsa+0.005
 Taj+0.004
urdue+0.004
Neg logit contributions
cles-0.004
 unrelated-0.004
minist-0.004
interstitial-0.004
 Beir-0.004
Token the
Token ID262
Feature activation-6.69e-02

Pos logit contributions
ertodd+0.511
isconsin+0.497
alsa+0.480
 Taj+0.460
urdue+0.459
Neg logit contributions
cles-0.663
 unrelated-0.656
minist-0.628
interstitial-0.620
 Beir-0.577
Token new
Token ID649
Feature activation-3.48e-01

Pos logit contributions
cles+0.144
 unrelated+0.143
minist+0.136
interstitial+0.134
 Beir+0.126
Neg logit contributions
ertodd-0.105
isconsin-0.100
alsa-0.097
framework-0.092
urdue-0.092
Token Winnipeg
Token ID23434
Feature activation+2.01e+00

Pos logit contributions
cles+0.778
 unrelated+0.774
minist+0.735
interstitial+0.727
 Beir+0.687
Neg logit contributions
ertodd-0.518
isconsin-0.491
alsa-0.475
framework-0.451
urdue-0.450
Token franchise
Token ID8663
Feature activation+3.80e-01

Pos logit contributions
isconsin+2.786
ertodd+2.764
alsa+2.665
 Taj+2.627
framework+2.560
Neg logit contributions
cles-4.414
 unrelated-4.346
minist-4.223
interstitial-4.167
 Beir-3.924
Token make
Token ID787
Feature activation-1.47e-01

Pos logit contributions
ertodd+0.639
isconsin+0.623
alsa+0.600
urdue+0.579
 Taj+0.578
Neg logit contributions
cles-0.759
 unrelated-0.752
minist-0.724
interstitial-0.713
 Beir-0.661
Token its
Token ID663
Feature activation-1.54e-02

Pos logit contributions
cles+0.284
 unrelated+0.279
minist+0.267
interstitial+0.263
 Beir+0.244
Neg logit contributions
ertodd-0.257
isconsin-0.251
alsa-0.242
 Taj-0.235
urdue-0.234
Token first
Token ID717
Feature activation-3.38e-02

Pos logit contributions
cles+0.030
 unrelated+0.030
minist+0.028
interstitial+0.028
 Beir+0.026
Neg logit contributions
ertodd-0.027
isconsin-0.026
alsa-0.025
urdue-0.024
framework-0.024
Token appearance
Token ID5585
Feature activation+2.04e-01

Pos logit contributions
cles+0.065
 unrelated+0.063
minist+0.061
interstitial+0.060
 Beir+0.056
Neg logit contributions
ertodd-0.060
isconsin-0.059
alsa-0.057
 Taj-0.055
framework-0.055
Token Times
Token ID3782
Feature activation+3.85e-01

Pos logit contributions
ertodd+0.667
isconsin+0.638
alsa+0.607
framework+0.583
 Taj+0.582
Neg logit contributions
cles-1.205
 unrelated-1.187
minist-1.138
interstitial-1.130
 Beir-1.069
Token recently
Token ID2904
Feature activation-5.12e-01

Pos logit contributions
ertodd+0.719
isconsin+0.695
alsa+0.676
framework+0.651
urdue+0.648
Neg logit contributions
cles-0.709
 unrelated-0.699
minist-0.659
interstitial-0.652
 Beir-0.605
Token,
Token ID11
Feature activation+2.37e-01

Pos logit contributions
cles+0.929
 unrelated+0.922
minist+0.866
interstitial+0.854
 Beir+0.794
Neg logit contributions
ertodd-0.973
isconsin-0.937
alsa-0.912
framework-0.878
urdue-0.877
Token edible
Token ID35988
Feature activation+3.96e-01

Pos logit contributions
ertodd+0.452
isconsin+0.439
alsa+0.427
urdue+0.412
 Taj+0.411
Neg logit contributions
cles-0.426
 unrelated-0.420
minist-0.396
interstitial-0.393
 Beir-0.362
Token tet
Token ID28408
Feature activation-7.84e-01

Pos logit contributions
ertodd+0.749
isconsin+0.727
alsa+0.711
framework+0.684
 Taj+0.683
Neg logit contributions
cles-0.709
 unrelated-0.702
interstitial-0.667
minist-0.662
 Beir-0.610
Tokenrah
Token ID11392
Feature activation+2.00e+00

Pos logit contributions
cles+1.338
 unrelated+1.313
minist+1.240
interstitial+1.203
cle+1.120
Neg logit contributions
ertodd-1.575
isconsin-1.527
alsa-1.476
framework-1.436
cipled-1.426
Tokenyd
Token ID5173
Feature activation-4.83e-01

Pos logit contributions
ertodd+3.026
isconsin+2.876
alsa+2.843
urdue+2.660
framework+2.649
Neg logit contributions
cles-4.315
 unrelated-4.312
interstitial-4.111
minist-4.029
 Beir-3.927
Tokenroc
Token ID12204
Feature activation+1.21e+00

Pos logit contributions
cles+0.817
 unrelated+0.806
minist+0.756
interstitial+0.739
cle+0.685
Neg logit contributions
ertodd-0.978
isconsin-0.945
alsa-0.918
framework-0.892
urdue-0.885
Tokenann
Token ID1236
Feature activation+1.20e-02

Pos logit contributions
ertodd+1.503
isconsin+1.485
alsa+1.424
urdue+1.340
framework+1.311
Neg logit contributions
cles-2.921
 unrelated-2.910
interstitial-2.794
minist-2.793
 Beir-2.658
Tokenib
Token ID571
Feature activation+7.61e-01

Pos logit contributions
ertodd+0.029
isconsin+0.028
alsa+0.027
framework+0.026
urdue+0.026
Neg logit contributions
cles-0.016
 unrelated-0.016
minist-0.014
interstitial-0.014
 Beir-0.013
Tokenin
Token ID259
Feature activation+8.94e-01

Pos logit contributions
ertodd+1.577
isconsin+1.535
alsa+1.519
urdue+1.462
framework+1.450
Neg logit contributions
 unrelated-1.225
cles-1.216
minist-1.139
interstitial-1.134
 Beir-1.068
Token
Token ID250
Feature activation+1.19e-01

Pos logit contributions
cles+0.290
 unrelated+0.288
minist+0.272
interstitial+0.269
 Beir+0.251
Neg logit contributions
ertodd-0.259
isconsin-0.249
alsa-0.242
framework-0.232
urdue-0.231
Tokento
Token ID1462
Feature activation+1.83e-02

Pos logit contributions
ertodd+0.218
isconsin+0.210
alsa+0.206
framework+0.199
urdue+0.196
Neg logit contributions
cles-0.222
 unrelated-0.222
minist-0.207
interstitial-0.205
 Beir-0.194
Token weaken
Token ID13813
Feature activation+6.97e-02

Pos logit contributions
ertodd+0.032
isconsin+0.030
alsa+0.029
framework+0.028
urdue+0.028
Neg logit contributions
cles-0.036
 unrelated-0.036
minist-0.034
interstitial-0.034
 Beir-0.032
Token the
Token ID262
Feature activation+1.22e-02

Pos logit contributions
ertodd+0.128
isconsin+0.123
alsa+0.120
framework+0.115
urdue+0.115
Neg logit contributions
cles-0.131
 unrelated-0.130
minist-0.122
interstitial-0.121
 Beir-0.112
Token trans
Token ID1007
Feature activation+1.66e-01

Pos logit contributions
ertodd+0.022
isconsin+0.021
alsa+0.021
framework+0.020
urdue+0.020
Neg logit contributions
cles-0.023
 unrelated-0.023
minist-0.022
interstitial-0.022
 Beir-0.020
Tokennational
Token ID14648
Feature activation+1.99e+00

Pos logit contributions
ertodd+0.308
isconsin+0.297
alsa+0.288
framework+0.277
urdue+0.277
Neg logit contributions
cles-0.307
 unrelated-0.305
minist-0.287
interstitial-0.283
 Beir-0.263
Token political
Token ID1964
Feature activation+3.55e-01

Pos logit contributions
ertodd+3.345
isconsin+3.253
alsa+3.192
 Taj+3.148
framework+3.101
Neg logit contributions
cles-3.878
 unrelated-3.806
interstitial-3.653
minist-3.618
 Beir-3.375
Token,
Token ID11
Feature activation-2.61e-01

Pos logit contributions
ertodd+0.598
isconsin+0.574
alsa+0.556
framework+0.533
urdue+0.532
Neg logit contributions
cles-0.720
 unrelated-0.715
minist-0.676
interstitial-0.668
 Beir-0.626
Token economic
Token ID3034
Feature activation-4.98e-01

Pos logit contributions
 unrelated+0.458
cles+0.458
minist+0.427
interstitial+0.420
 Beir+0.391
Neg logit contributions
ertodd-0.514
isconsin-0.495
alsa-0.480
urdue-0.466
framework-0.464
Token,
Token ID11
Feature activation-4.39e-01

Pos logit contributions
cles+0.871
 unrelated+0.864
minist+0.810
interstitial+0.791
 Beir+0.737
Neg logit contributions
ertodd-0.980
isconsin-0.944
alsa-0.918
urdue-0.890
framework-0.883
Token and
Token ID290
Feature activation-2.36e-01

Pos logit contributions
cles+0.680
 unrelated+0.679
minist+0.627
interstitial+0.615
 Beir+0.566
Neg logit contributions
ertodd-0.952
isconsin-0.919
alsa-0.894
urdue-0.869
framework-0.865
Token -
Token ID532
Feature activation+1.75e-01

Pos logit contributions
ertodd+0.757
isconsin+0.731
alsa+0.713
urdue+0.686
framework+0.684
Neg logit contributions
cles-0.779
 unrelated-0.770
minist-0.732
interstitial-0.727
 Beir-0.677
Token as
Token ID355
Feature activation+2.16e-03

Pos logit contributions
ertodd+0.332
isconsin+0.323
alsa+0.315
 Taj+0.304
urdue+0.303
Neg logit contributions
cles-0.314
 unrelated-0.307
minist-0.292
interstitial-0.289
 Beir-0.266
Token it
Token ID340
Feature activation-1.64e-01

Pos logit contributions
ertodd+0.004
isconsin+0.004
alsa+0.004
 Taj+0.004
framework+0.004
Neg logit contributions
cles-0.004
 unrelated-0.004
minist-0.004
interstitial-0.004
 Beir-0.003
Token's
Token ID338
Feature activation-6.66e-01

Pos logit contributions
cles+0.292
 unrelated+0.290
minist+0.274
interstitial+0.272
 Beir+0.251
Neg logit contributions
ertodd-0.314
isconsin-0.303
alsa-0.295
urdue-0.285
framework-0.285
Token not
Token ID407
Feature activation+3.68e-01

Pos logit contributions
cles+1.111
 unrelated+1.098
minist+1.029
interstitial+1.015
 Beir+0.933
Neg logit contributions
ertodd-1.361
isconsin-1.317
alsa-1.285
framework-1.240
urdue-1.239
Token unheard
Token ID36511
Feature activation-2.58e+00

Pos logit contributions
ertodd+0.732
isconsin+0.716
alsa+0.697
 Taj+0.684
framework+0.675
Neg logit contributions
cles-0.619
 unrelated-0.596
minist-0.575
interstitial-0.575
leans-0.520
Token of
Token ID286
Feature activation+2.72e-02

Pos logit contributions
 unrelated+3.846
cles+3.839
minist+3.547
interstitial+3.352
cle+3.173
Neg logit contributions
ertodd-5.644
isconsin-5.438
alsa-5.365
urdue-5.189
cipled-5.157
Token that
Token ID326
Feature activation-2.89e-01

Pos logit contributions
ertodd+0.051
isconsin+0.049
alsa+0.048
 Taj+0.046
urdue+0.046
Neg logit contributions
cles-0.050
 unrelated-0.049
minist-0.046
interstitial-0.046
 Beir-0.043
Token collectors
Token ID26668
Feature activation-6.57e-01

Pos logit contributions
cles+0.530
 unrelated+0.526
minist+0.494
interstitial+0.487
 Beir+0.454
Neg logit contributions
ertodd-0.546
isconsin-0.525
alsa-0.512
framework-0.492
urdue-0.491
Token have
Token ID423
Feature activation-2.41e-01

Pos logit contributions
cles+1.232
 unrelated+1.223
minist+1.153
interstitial+1.139
 Beir+1.060
Neg logit contributions
ertodd-1.206
isconsin-1.160
alsa-1.128
framework-1.084
urdue-1.083
Token paid
Token ID3432
Feature activation+4.80e-01

Pos logit contributions
cles+0.422
 unrelated+0.418
minist+0.393
interstitial+0.388
 Beir+0.359
Neg logit contributions
ertodd-0.473
isconsin-0.456
alsa-0.445
urdue-0.428
framework-0.428
Token is
Token ID318
Feature activation+1.31e-01

Pos logit contributions
cles+0.397
 unrelated+0.393
minist+0.371
interstitial+0.366
 Beir+0.339
Neg logit contributions
ertodd-0.398
isconsin-0.386
alsa-0.375
urdue-0.361
framework-0.361
Token "
Token ID366
Feature activation+1.90e-01

Pos logit contributions
ertodd+0.267
isconsin+0.261
alsa+0.254
framework+0.246
urdue+0.245
Neg logit contributions
cles-0.218
 unrelated-0.212
minist-0.202
interstitial-0.200
 Beir-0.182
Tokenbas
Token ID12093
Feature activation+2.26e-01

Pos logit contributions
ertodd+0.348
isconsin+0.337
alsa+0.332
framework+0.321
urdue+0.315
Neg logit contributions
cles-0.352
 unrelated-0.351
minist-0.326
interstitial-0.325
 Beir-0.307
Tokenically
Token ID1146
Feature activation-7.14e-02

Pos logit contributions
ertodd+0.529
isconsin+0.513
alsa+0.503
cipled+0.486
urdue+0.485
Neg logit contributions
 unrelated-0.309
cles-0.308
minist-0.283
interstitial-0.282
 Beir-0.256
Token an
Token ID281
Feature activation-2.39e-01

Pos logit contributions
cles+0.123
 unrelated+0.121
minist+0.114
interstitial+0.113
 Beir+0.104
Neg logit contributions
ertodd-0.142
isconsin-0.138
alsa-0.134
framework-0.129
urdue-0.129
Token isolation
Token ID15133
Feature activation-2.44e+00

Pos logit contributions
cles+0.435
 unrelated+0.428
minist+0.407
interstitial+0.399
 Beir+0.371
Neg logit contributions
ertodd-0.453
isconsin-0.437
alsa-0.427
framework-0.409
 Taj-0.408
Tokenist
Token ID396
Feature activation-3.28e-01

Pos logit contributions
 unrelated+4.347
cles+4.262
minist+4.120
interstitial+3.878
cle+3.730
Neg logit contributions
ertodd-4.625
isconsin-4.450
alsa-4.367
urdue-4.236
framework-4.126
Token,"
Token ID553
Feature activation+3.30e-01

Pos logit contributions
cles+0.582
 unrelated+0.575
minist+0.539
interstitial+0.534
 Beir+0.494
Neg logit contributions
ertodd-0.637
isconsin-0.616
alsa-0.599
framework-0.578
urdue-0.576
Token according
Token ID1864
Feature activation+5.73e-01

Pos logit contributions
ertodd+0.623
isconsin+0.606
alsa+0.586
 Taj+0.572
urdue+0.568
Neg logit contributions
cles-0.603
 unrelated-0.586
minist-0.557
interstitial-0.549
leans-0.505
Token to
Token ID284
Feature activation-3.75e-03

Pos logit contributions
ertodd+1.052
isconsin+1.011
alsa+0.984
framework+0.944
urdue+0.944
Neg logit contributions
cles-1.080
 unrelated-1.074
minist-1.009
interstitial-0.994
 Beir-0.929
Token former
Token ID1966
Feature activation+1.85e-01

Pos logit contributions
cles+0.007
 unrelated+0.007
minist+0.007
interstitial+0.007
 Beir+0.006
Neg logit contributions
ertodd-0.007
isconsin-0.006
alsa-0.006
urdue-0.006
 Taj-0.006
Token-
Token ID12
Feature activation+1.32e-01

Pos logit contributions
cles+1.083
 unrelated+1.073
minist+1.008
interstitial+0.995
 Beir+0.919
Neg logit contributions
ertodd-1.232
isconsin-1.190
alsa-1.159
urdue-1.118
framework-1.116
Tokenfired
Token ID26803
Feature activation-2.11e-01

Pos logit contributions
ertodd+0.238
isconsin+0.233
alsa+0.231
framework+0.221
urdue+0.220
Neg logit contributions
 unrelated-0.240
cles-0.240
minist-0.225
interstitial-0.225
 Beir-0.212
Token electricity
Token ID8744
Feature activation-4.44e-01

Pos logit contributions
cles+0.384
 unrelated+0.379
minist+0.362
interstitial+0.362
 Beir+0.332
Neg logit contributions
ertodd-0.392
isconsin-0.381
alsa-0.370
 Taj-0.358
urdue-0.357
Token more
Token ID517
Feature activation-1.27e-01

Pos logit contributions
cles+0.757
 unrelated+0.747
minist+0.706
interstitial+0.701
 Beir+0.641
Neg logit contributions
ertodd-0.884
isconsin-0.858
alsa-0.834
urdue-0.808
framework-0.804
Token than
Token ID621
Feature activation-7.12e-02

Pos logit contributions
cles+0.229
 unrelated+0.226
minist+0.214
interstitial+0.213
 Beir+0.196
Neg logit contributions
ertodd-0.240
isconsin-0.232
alsa-0.225
urdue-0.218
framework-0.216
Token quadru
Token ID40977
Feature activation-2.41e+00

Pos logit contributions
cles+0.123
 unrelated+0.122
minist+0.115
interstitial+0.114
 Beir+0.105
Neg logit contributions
ertodd-0.140
isconsin-0.136
alsa-0.132
urdue-0.128
 Taj-0.127
Tokenples
Token ID2374
Feature activation-5.46e-01

Pos logit contributions
cles+3.626
 unrelated+3.320
minist+3.112
interstitial+2.928
leans+2.892
Neg logit contributions
ertodd-5.432
isconsin-5.281
alsa-5.139
framework-5.106
 Taj-5.067
Token.
Token ID13
Feature activation+6.84e-02

Pos logit contributions
cles+0.999
 unrelated+0.992
minist+0.932
interstitial+0.918
 Beir+0.855
Neg logit contributions
ertodd-1.032
isconsin-0.993
alsa-0.967
framework-0.930
urdue-0.928
Token Solar
Token ID12347
Feature activation-7.48e-02

Pos logit contributions
ertodd+0.118
isconsin+0.114
alsa+0.110
urdue+0.106
framework+0.106
Neg logit contributions
cles-0.136
 unrelated-0.135
minist-0.128
interstitial-0.127
 Beir-0.117
Token and
Token ID290
Feature activation-1.83e-01

Pos logit contributions
 unrelated+0.133
cles+0.132
minist+0.126
interstitial+0.126
 Beir+0.115
Neg logit contributions
ertodd-0.142
isconsin-0.137
alsa-0.134
urdue-0.129
framework-0.129
Token wind
Token ID2344
Feature activation-9.41e-03

Pos logit contributions
cles+0.348
 unrelated+0.341
minist+0.327
interstitial+0.323
 Beir+0.299
Neg logit contributions
ertodd-0.330
isconsin-0.318
alsa-0.312
framework-0.300
urdue-0.299
Token an
Token ID281
Feature activation-1.15e-01

Pos logit contributions
ertodd+1.689
isconsin+1.629
alsa+1.578
 Taj+1.549
cipled+1.508
Neg logit contributions
cles-1.813
 unrelated-1.693
minist-1.679
interstitial-1.654
cle-1.539
Token alternative
Token ID5559
Feature activation-3.55e-02

Pos logit contributions
cles+0.170
 unrelated+0.157
minist+0.153
interstitial+0.151
 Beir+0.138
Neg logit contributions
ertodd-0.254
alsa-0.248
isconsin-0.247
framework-0.238
cipled-0.238
Token to
Token ID284
Feature activation+1.24e-01

Pos logit contributions
 unrelated+0.066
cles+0.065
minist+0.061
interstitial+0.060
 Beir+0.056
Neg logit contributions
ertodd-0.067
isconsin-0.064
alsa-0.063
urdue-0.060
framework-0.060
Token The
Token ID383
Feature activation-2.53e-01

Pos logit contributions
ertodd+0.218
isconsin+0.210
alsa+0.203
urdue+0.196
framework+0.195
Neg logit contributions
cles-0.245
 unrelated-0.245
minist-0.229
interstitial-0.223
cle-0.212
Token Ad
Token ID1215
Feature activation+3.38e-01

Pos logit contributions
cles+0.468
 unrelated+0.467
minist+0.437
interstitial+0.430
 Beir+0.402
Neg logit contributions
ertodd-0.474
isconsin-0.457
alsa-0.444
framework-0.427
urdue-0.426
Tokenvertis
Token ID3346
Feature activation-2.39e+00

Pos logit contributions
ertodd+0.805
isconsin+0.783
alsa+0.766
urdue+0.743
framework+0.742
Neg logit contributions
cles-0.451
 unrelated-0.449
minist-0.412
interstitial-0.402
 Beir-0.361
Tokener
Token ID263
Feature activation-6.79e-01

Pos logit contributions
 unrelated+2.510
cles+2.435
minist+2.258
cle+1.895
riad+1.794
Neg logit contributions
isconsin-6.214
ertodd-6.035
alsa-5.987
 Taj-5.906
cipled-5.898
Token,
Token ID11
Feature activation-3.30e-01

Pos logit contributions
 unrelated+1.052
cles+1.031
minist+0.963
interstitial+0.901
 Beir+0.859
Neg logit contributions
ertodd-1.458
isconsin-1.457
alsa-1.413
cipled-1.373
urdue-1.348
Token a
Token ID257
Feature activation-3.96e-01

Pos logit contributions
 unrelated+0.640
cles+0.630
minist+0.593
interstitial+0.568
cle+0.546
Neg logit contributions
ertodd-0.609
isconsin-0.578
alsa-0.561
urdue-0.541
cipled-0.529
Token different
Token ID1180
Feature activation+3.74e-01

Pos logit contributions
cles+0.714
 unrelated+0.697
interstitial+0.674
minist+0.668
 Beir+0.630
Neg logit contributions
ertodd-0.733
isconsin-0.719
alsa-0.700
framework-0.691
 Taj-0.680
Token voice
Token ID3809
Feature activation-1.47e-01

Pos logit contributions
ertodd+0.584
isconsin+0.558
alsa+0.539
framework+0.531
 Taj+0.523
Neg logit contributions
cles-0.797
 unrelated-0.786
minist-0.755
interstitial-0.752
 Beir-0.707
Token
Token ID447
Feature activation-1.26e-01

Pos logit contributions
cles+0.251
 unrelated+0.249
minist+0.234
interstitial+0.231
 Beir+0.214
Neg logit contributions
ertodd-0.270
isconsin-0.261
alsa-0.254
framework-0.244
urdue-0.244
Token
Token ID247
Feature activation-6.44e-02

Pos logit contributions
cles+0.253
 unrelated+0.252
minist+0.237
interstitial+0.236
cle+0.219
Neg logit contributions
ertodd-0.217
isconsin-0.208
alsa-0.201
urdue-0.193
framework-0.193
Tokens
Token ID82
Feature activation-2.01e-01

Pos logit contributions
cles+0.107
 unrelated+0.106
minist+0.099
interstitial+0.098
 Beir+0.091
Neg logit contributions
ertodd-0.132
isconsin-0.127
alsa-0.124
framework-0.120
urdue-0.120
Token has
Token ID468
Feature activation+1.23e-01

Pos logit contributions
cles+0.335
 unrelated+0.331
minist+0.310
interstitial+0.307
 Beir+0.282
Neg logit contributions
ertodd-0.410
isconsin-0.397
alsa-0.388
framework-0.375
urdue-0.374
Token some
Token ID617
Feature activation+1.78e-01

Pos logit contributions
ertodd+0.231
isconsin+0.223
alsa+0.217
framework+0.209
urdue+0.209
Neg logit contributions
cles-0.225
 unrelated-0.223
minist-0.211
interstitial-0.209
 Beir-0.194
Token miscar
Token ID35976
Feature activation-2.33e+00

Pos logit contributions
ertodd+0.330
isconsin+0.319
alsa+0.312
framework+0.301
 Taj+0.300
Neg logit contributions
cles-0.329
 unrelated-0.322
minist-0.308
interstitial-0.306
 Beir-0.283
Tokenriages
Token ID16451
Feature activation+3.39e-02

Pos logit contributions
cles+3.378
 unrelated+3.257
minist+3.031
interstitial+2.993
cle+2.744
Neg logit contributions
ertodd-5.319
isconsin-5.114
alsa-4.946
 Taj-4.874
urdue-4.854
Token in
Token ID287
Feature activation-5.93e-02

Pos logit contributions
ertodd+0.065
isconsin+0.063
alsa+0.061
framework+0.059
urdue+0.059
Neg logit contributions
cles-0.061
 unrelated-0.059
interstitial-0.057
minist-0.057
 Beir-0.052
Token the
Token ID262
Feature activation-1.97e-01

Pos logit contributions
cles+0.112
 unrelated+0.110
minist+0.105
interstitial+0.104
 Beir+0.096
Neg logit contributions
ertodd-0.108
isconsin-0.104
alsa-0.102
framework-0.097
urdue-0.097
Token past
Token ID1613
Feature activation-7.59e-01

Pos logit contributions
cles+0.255
 unrelated+0.254
minist+0.230
interstitial+0.225
 Beir+0.202
Neg logit contributions
ertodd-0.478
isconsin-0.463
alsa-0.454
framework-0.440
urdue-0.440
Token,
Token ID11
Feature activation-3.10e-01

Pos logit contributions
cles+1.356
 unrelated+1.349
minist+1.262
interstitial+1.241
 Beir+1.154
Neg logit contributions
ertodd-1.465
isconsin-1.412
alsa-1.376
framework-1.324
urdue-1.322
Token
Token ID198
Feature activation+1.11e-01

Pos logit contributions
cles+0.578
 unrelated+0.575
minist+0.542
interstitial+0.534
 Beir+0.501
Neg logit contributions
ertodd-0.517
isconsin-0.496
alsa-0.482
urdue-0.461
framework-0.461
Token
Token ID198
Feature activation+6.16e-02

Pos logit contributions
ertodd+0.212
isconsin+0.203
alsa+0.198
cipled+0.190
urdue+0.190
Neg logit contributions
cles-0.203
 unrelated-0.202
minist-0.188
interstitial-0.181
cle-0.175
TokenTo
Token ID2514
Feature activation+1.23e-01

Pos logit contributions
ertodd+0.119
isconsin+0.116
alsa+0.113
framework+0.110
urdue+0.108
Neg logit contributions
cles-0.108
 unrelated-0.108
minist-0.100
interstitial-0.100
 Beir-0.093
Token break
Token ID2270
Feature activation-1.89e-01

Pos logit contributions
ertodd+0.216
isconsin+0.209
alsa+0.202
urdue+0.195
framework+0.194
Neg logit contributions
cles-0.240
 unrelated-0.237
minist-0.227
interstitial-0.224
 Beir-0.207
Token the
Token ID262
Feature activation+5.41e-02

Pos logit contributions
cles+0.333
 unrelated+0.330
minist+0.309
interstitial+0.305
 Beir+0.283
Neg logit contributions
ertodd-0.371
isconsin-0.358
alsa-0.348
framework-0.336
urdue-0.335
Token isolation
Token ID15133
Feature activation-2.29e+00

Pos logit contributions
ertodd+0.105
isconsin+0.102
alsa+0.099
framework+0.096
 Taj+0.095
Neg logit contributions
cles-0.095
 unrelated-0.094
minist-0.089
interstitial-0.087
 Beir-0.081
Token and
Token ID290
Feature activation-3.23e-01

Pos logit contributions
 unrelated+3.822
cles+3.793
minist+3.510
interstitial+3.395
 Beir+3.238
Neg logit contributions
ertodd-4.695
isconsin-4.483
alsa-4.384
urdue-4.242
cipled-4.227
Token bolster
Token ID26091
Feature activation-1.33e-01

Pos logit contributions
cles+0.589
 unrelated+0.585
minist+0.550
interstitial+0.542
 Beir+0.504
Neg logit contributions
ertodd-0.611
isconsin-0.588
alsa-0.573
framework-0.551
urdue-0.550
Token the
Token ID262
Feature activation-6.38e-02

Pos logit contributions
cles+0.246
 unrelated+0.243
minist+0.230
interstitial+0.227
 Beir+0.211
Neg logit contributions
ertodd-0.248
isconsin-0.240
alsa-0.233
framework-0.224
urdue-0.224
Token teenagers
Token ID17366
Feature activation-7.74e-02

Pos logit contributions
cles+0.126
 unrelated+0.124
minist+0.118
interstitial+0.116
 Beir+0.109
Neg logit contributions
ertodd-0.111
isconsin-0.107
alsa-0.104
framework-0.100
urdue-0.100
Token
Token ID447
Feature activation+1.37e-01

Pos logit contributions
cles+0.142
 unrelated+0.141
minist+0.133
interstitial+0.131
 Beir+0.122
Neg logit contributions
ertodd-0.145
isconsin-0.140
alsa-0.136
framework-0.131
urdue-0.131
Token philosophy
Token ID8876
Feature activation+3.07e-01

Pos logit contributions
ertodd+0.588
isconsin+0.568
alsa+0.553
 Taj+0.534
framework+0.534
Neg logit contributions
cles-0.625
 unrelated-0.615
minist-0.587
interstitial-0.587
 Beir-0.540
Token,
Token ID11
Feature activation+9.11e-02

Pos logit contributions
ertodd+0.588
isconsin+0.566
alsa+0.552
framework+0.533
urdue+0.530
Neg logit contributions
cles-0.546
 unrelated-0.539
interstitial-0.513
minist-0.512
 Beir-0.468
Token is
Token ID318
Feature activation+4.22e-03

Pos logit contributions
ertodd+0.181
isconsin+0.175
alsa+0.170
framework+0.165
 Taj+0.164
Neg logit contributions
cles-0.157
 unrelated-0.154
minist-0.146
interstitial-0.145
 Beir-0.132
Token basically
Token ID6209
Feature activation+7.13e-02

Pos logit contributions
ertodd+0.008
isconsin+0.008
alsa+0.007
framework+0.007
 Taj+0.007
Neg logit contributions
cles-0.008
 unrelated-0.008
minist-0.007
interstitial-0.007
 Beir-0.007
Token an
Token ID281
Feature activation-1.62e-01

Pos logit contributions
ertodd+0.139
isconsin+0.133
alsa+0.131
framework+0.126
 Taj+0.125
Neg logit contributions
cles-0.126
 unrelated-0.124
minist-0.117
interstitial-0.115
 Beir-0.107
Token isolation
Token ID15133
Feature activation-2.28e+00

Pos logit contributions
cles+0.181
 unrelated+0.175
minist+0.162
interstitial+0.157
 Beir+0.138
Neg logit contributions
ertodd-0.422
isconsin-0.411
alsa-0.404
framework-0.393
 Taj-0.392
Tokenist
Token ID396
Feature activation-2.92e-01

Pos logit contributions
 unrelated+3.851
cles+3.748
minist+3.694
interstitial+3.322
cle+3.279
Neg logit contributions
ertodd-4.470
isconsin-4.338
alsa-4.278
urdue-4.130
apeake-4.045
Token,"
Token ID553
Feature activation+6.73e-01

Pos logit contributions
cles+0.547
 unrelated+0.542
minist+0.510
interstitial+0.504
 Beir+0.469
Neg logit contributions
ertodd-0.539
isconsin-0.519
alsa-0.505
framework-0.486
urdue-0.485
Token Cheney
Token ID31287
Feature activation+1.06e-01

Pos logit contributions
ertodd+1.242
isconsin+1.213
alsa+1.162
 Taj+1.141
urdue+1.134
Neg logit contributions
cles-1.242
 unrelated-1.218
minist-1.162
interstitial-1.149
leans-1.057
Token told
Token ID1297
Feature activation+1.34e-01

Pos logit contributions
ertodd+0.203
isconsin+0.197
alsa+0.191
 Taj+0.186
urdue+0.185
Neg logit contributions
cles-0.187
 unrelated-0.184
interstitial-0.175
minist-0.174
 Beir-0.158
Token ABC
Token ID9738
Feature activation-5.05e-02

Pos logit contributions
ertodd+0.250
isconsin+0.243
alsa+0.237
 Taj+0.228
urdue+0.228
Neg logit contributions
cles-0.247
 unrelated-0.242
minist-0.230
interstitial-0.227
 Beir-0.209
Token is
Token ID318
Feature activation+3.04e-01

Pos logit contributions
ertodd+0.469
isconsin+0.451
alsa+0.440
framework+0.428
 Taj+0.426
Neg logit contributions
cles-0.459
 unrelated-0.444
interstitial-0.430
minist-0.426
 Beir-0.391
Token that
Token ID326
Feature activation+1.35e-01

Pos logit contributions
ertodd+0.555
isconsin+0.528
alsa+0.520
framework+0.502
 Taj+0.501
Neg logit contributions
cles-0.571
 unrelated-0.557
minist-0.535
interstitial-0.532
 Beir-0.492
Token Rails
Token ID31493
Feature activation-2.17e-01

Pos logit contributions
ertodd+0.254
isconsin+0.243
alsa+0.239
framework+0.231
 Taj+0.229
Neg logit contributions
cles-0.245
 unrelated-0.240
minist-0.228
interstitial-0.227
 Beir-0.211
Token has
Token ID468
Feature activation-1.32e-01

Pos logit contributions
cles+0.389
 unrelated+0.386
minist+0.362
interstitial+0.358
 Beir+0.332
Neg logit contributions
ertodd-0.418
isconsin-0.403
alsa-0.393
framework-0.378
urdue-0.377
Token g
Token ID308
Feature activation-6.28e-01

Pos logit contributions
cles+0.238
 unrelated+0.235
minist+0.222
interstitial+0.219
 Beir+0.203
Neg logit contributions
ertodd-0.253
isconsin-0.244
alsa-0.238
framework-0.229
urdue-0.229
Tokenhett
Token ID17442
Feature activation-2.27e+00

Pos logit contributions
cles+1.211
 unrelated+1.203
minist+1.135
interstitial+1.118
 Beir+1.045
Neg logit contributions
ertodd-1.122
isconsin-1.078
alsa-1.046
framework-1.004
urdue-1.003
Tokenos
Token ID418
Feature activation+7.09e-02

Pos logit contributions
cles+3.851
 unrelated+3.832
minist+3.594
interstitial+3.385
cle+3.281
Neg logit contributions
ertodd-4.453
isconsin-4.396
alsa-4.122
framework-4.062
urdue-4.061
Token,
Token ID11
Feature activation-2.04e-01

Pos logit contributions
ertodd+0.135
isconsin+0.130
alsa+0.127
framework+0.123
 Taj+0.122
Neg logit contributions
cles-0.127
 unrelated-0.125
minist-0.119
interstitial-0.118
 Beir-0.109
Token and
Token ID290
Feature activation-6.54e-02

Pos logit contributions
cles+0.355
 unrelated+0.349
minist+0.330
interstitial+0.326
 Beir+0.301
Neg logit contributions
ertodd-0.402
isconsin-0.388
alsa-0.380
framework-0.366
urdue-0.365
Token Zed
Token ID46159
Feature activation+2.43e-01

Pos logit contributions
cles+0.121
 unrelated+0.120
minist+0.114
interstitial+0.113
 Beir+0.104
Neg logit contributions
ertodd-0.121
isconsin-0.116
alsa-0.114
framework-0.109
 Taj-0.109
Token made
Token ID925
Feature activation-1.62e-01

Pos logit contributions
ertodd+0.467
isconsin+0.451
alsa+0.440
 Taj+0.427
framework+0.426
Neg logit contributions
cles-0.430
 unrelated-0.424
minist-0.403
interstitial-0.401
 Beir-0.368
Token
Token ID851
Feature activation+4.41e-01

Pos logit contributions
ertodd+0.428
isconsin+0.414
alsa+0.404
framework+0.391
 Taj+0.390
Neg logit contributions
cles-0.372
 unrelated-0.368
minist-0.347
interstitial-0.343
 Beir-0.317
Token so
Token ID523
Feature activation-1.33e-01

Pos logit contributions
ertodd+0.849
isconsin+0.820
alsa+0.804
framework+0.775
 Taj+0.773
Neg logit contributions
cles-0.781
 unrelated-0.767
minist-0.729
interstitial-0.720
 Beir-0.664
Token I
Token ID314
Feature activation-1.41e-01

Pos logit contributions
cles+0.238
 unrelated+0.235
minist+0.222
interstitial+0.219
 Beir+0.203
Neg logit contributions
ertodd-0.255
isconsin-0.247
alsa-0.240
framework-0.232
urdue-0.231
Token have
Token ID423
Feature activation+7.79e-02

Pos logit contributions
cles+0.256
 unrelated+0.253
minist+0.238
interstitial+0.236
 Beir+0.219
Neg logit contributions
ertodd-0.269
isconsin-0.259
alsa-0.253
framework-0.243
urdue-0.243
Token to
Token ID284
Feature activation+1.01e-01

Pos logit contributions
ertodd+0.141
isconsin+0.136
alsa+0.133
framework+0.127
urdue+0.127
Neg logit contributions
cles-0.147
 unrelated-0.146
minist-0.138
interstitial-0.136
 Beir-0.127
Token pencil
Token ID21613
Feature activation-2.25e+00

Pos logit contributions
ertodd+0.172
isconsin+0.165
alsa+0.160
framework+0.154
urdue+0.154
Neg logit contributions
cles-0.203
 unrelated-0.201
minist-0.191
interstitial-0.189
 Beir-0.177
Token this
Token ID428
Feature activation+3.69e-01

Pos logit contributions
 unrelated+3.793
cles+3.791
minist+3.533
interstitial+3.427
cle+3.203
Neg logit contributions
ertodd-4.520
isconsin-4.329
alsa-4.201
framework-4.077
cipled-4.072
Token thing
Token ID1517
Feature activation-7.50e-01

Pos logit contributions
ertodd+0.733
isconsin+0.712
alsa+0.697
 Taj+0.672
framework+0.670
Neg logit contributions
cles-0.630
 unrelated-0.610
minist-0.581
interstitial-0.577
leans-0.530
Token,
Token ID11
Feature activation+2.50e-02

Pos logit contributions
cles+1.264
 unrelated+1.256
minist+1.171
interstitial+1.152
 Beir+1.066
Neg logit contributions
ertodd-1.525
isconsin-1.471
alsa-1.434
framework-1.385
urdue-1.383
Token and
Token ID290
Feature activation+1.09e-01

Pos logit contributions
ertodd+0.051
isconsin+0.050
alsa+0.048
framework+0.047
urdue+0.046
Neg logit contributions
cles-0.042
 unrelated-0.041
minist-0.039
interstitial-0.038
 Beir-0.035
Token then
Token ID788
Feature activation-4.82e-01

Pos logit contributions
ertodd+0.203
isconsin+0.197
alsa+0.192
framework+0.185
 Taj+0.185
Neg logit contributions
cles-0.198
 unrelated-0.195
minist-0.185
interstitial-0.184
 Beir-0.170
Token focusing
Token ID10759
Feature activation-9.38e-01

Pos logit contributions
ertodd+0.073
isconsin+0.070
alsa+0.069
framework+0.066
 Taj+0.066
Neg logit contributions
cles-0.074
 unrelated-0.073
minist-0.069
interstitial-0.069
 Beir-0.063
Token problem
Token ID1917
Feature activation-9.86e-01

Pos logit contributions
cles+1.585
 unrelated+1.578
minist+1.469
interstitial+1.443
 Beir+1.339
Neg logit contributions
ertodd-1.904
isconsin-1.838
alsa-1.789
urdue-1.726
framework-1.722
Token.
Token ID13
Feature activation-3.62e-02

Pos logit contributions
cles+1.777
 unrelated+1.765
minist+1.656
interstitial+1.633
 Beir+1.517
Neg logit contributions
ertodd-1.885
isconsin-1.816
alsa-1.768
framework-1.702
urdue-1.700
Token
Token ID198
Feature activation+8.83e-02

Pos logit contributions
cles+0.070
 unrelated+0.070
minist+0.066
interstitial+0.065
 Beir+0.061
Neg logit contributions
ertodd-0.064
isconsin-0.062
alsa-0.060
framework-0.057
urdue-0.057
Token
Token ID198
Feature activation+6.48e-02

Pos logit contributions
ertodd+0.167
isconsin+0.160
alsa+0.156
urdue+0.150
cipled+0.150
Neg logit contributions
cles-0.163
 unrelated-0.162
minist-0.151
interstitial-0.146
cle-0.140
TokenTri
Token ID14824
Feature activation-2.17e+00

Pos logit contributions
ertodd+0.123
isconsin+0.118
alsa+0.116
framework+0.112
urdue+0.110
Neg logit contributions
cles-0.117
 unrelated-0.117
minist-0.110
interstitial-0.108
 Beir-0.102
Tokenangular
Token ID21413
Feature activation-1.32e-01

Pos logit contributions
cles+3.527
 unrelated+3.453
minist+3.205
interstitial+3.137
leans+2.940
Neg logit contributions
ertodd-4.496
isconsin-4.361
alsa-4.186
urdue-4.104
framework-4.076
Token segregation
Token ID26718
Feature activation-1.05e+00

Pos logit contributions
cles+0.251
 unrelated+0.249
minist+0.236
interstitial+0.233
 Beir+0.216
Neg logit contributions
ertodd-0.240
isconsin-0.231
alsa-0.225
framework-0.217
urdue-0.215
Token
Token ID198
Feature activation+5.04e-02

Pos logit contributions
cles+1.949
 unrelated+1.935
minist+1.816
interstitial+1.786
 Beir+1.667
Neg logit contributions
ertodd-1.962
isconsin-1.891
alsa-1.835
urdue-1.766
framework-1.764
Token
Token ID198
Feature activation-6.06e-03

Pos logit contributions
ertodd+0.095
isconsin+0.091
alsa+0.089
urdue+0.085
cipled+0.085
Neg logit contributions
cles-0.093
 unrelated-0.093
minist-0.087
interstitial-0.084
cle-0.080
TokenAct
Token ID6398
Feature activation-5.03e-01

Pos logit contributions
cles+0.011
 unrelated+0.011
minist+0.010
interstitial+0.010
 Beir+0.009
Neg logit contributions
ertodd-0.011
isconsin-0.011
alsa-0.011
framework-0.011
urdue-0.010
Token
Token ID247
Feature activation-1.10e-01

Pos logit contributions
ertodd+0.085
isconsin+0.081
alsa+0.079
urdue+0.076
framework+0.076
Neg logit contributions
cles-0.096
 unrelated-0.096
minist-0.090
interstitial-0.089
cle-0.083
Tokens
Token ID82
Feature activation-2.13e-01

Pos logit contributions
cles+0.182
 unrelated+0.181
minist+0.169
interstitial+0.167
 Beir+0.155
Neg logit contributions
ertodd-0.227
isconsin-0.219
alsa-0.214
framework-0.207
urdue-0.205
Token okay
Token ID8788
Feature activation-1.39e-01

Pos logit contributions
cles+0.362
 unrelated+0.355
minist+0.336
interstitial+0.335
 Beir+0.306
Neg logit contributions
ertodd-0.427
isconsin-0.414
alsa-0.404
framework-0.391
 Taj-0.390
Token to
Token ID284
Feature activation+3.27e-02

Pos logit contributions
cles+0.263
 unrelated+0.260
minist+0.246
interstitial+0.244
 Beir+0.227
Neg logit contributions
ertodd-0.253
isconsin-0.243
alsa-0.237
framework-0.228
urdue-0.227
Token just
Token ID655
Feature activation-2.29e-01

Pos logit contributions
ertodd+0.057
isconsin+0.054
alsa+0.053
framework+0.051
urdue+0.051
Neg logit contributions
cles-0.064
 unrelated-0.064
minist-0.060
interstitial-0.060
 Beir-0.056
Token postpone
Token ID47328
Feature activation-2.14e+00

Pos logit contributions
cles+0.449
 unrelated+0.443
minist+0.421
interstitial+0.418
 Beir+0.389
Neg logit contributions
ertodd-0.403
isconsin-0.386
alsa-0.377
framework-0.361
urdue-0.361
Token a
Token ID257
Feature activation-2.72e-01

Pos logit contributions
 unrelated+3.701
cles+3.639
minist+3.419
interstitial+3.301
cle+3.099
Neg logit contributions
ertodd-4.273
isconsin-4.107
alsa-4.004
cipled-3.863
framework-3.859
Token situation
Token ID3074
Feature activation-5.40e-01

Pos logit contributions
cles+0.478
 unrelated+0.468
interstitial+0.445
minist+0.444
 Beir+0.406
Neg logit contributions
ertodd-0.527
isconsin-0.510
alsa-0.499
urdue-0.482
 Taj-0.481
Token even
Token ID772
Feature activation+6.91e-01

Pos logit contributions
cles+0.939
 unrelated+0.931
minist+0.873
interstitial+0.861
 Beir+0.797
Neg logit contributions
ertodd-1.066
isconsin-1.029
alsa-1.002
framework-0.966
urdue-0.965
Token if
Token ID611
Feature activation+1.56e-01

Pos logit contributions
ertodd+1.224
isconsin+1.192
alsa+1.156
 Taj+1.121
urdue+1.118
Neg logit contributions
cles-1.307
 unrelated-1.277
interstitial-1.233
minist-1.220
 Beir-1.129
Token I
Token ID314
Feature activation+1.62e-01

Pos logit contributions
ertodd+0.284
isconsin+0.273
alsa+0.266
 Taj+0.258
framework+0.258
Neg logit contributions
cles-0.293
 unrelated-0.284
interstitial-0.274
minist-0.273
 Beir-0.251
Token it
Token ID340
Feature activation-9.24e-02

Pos logit contributions
cles+0.118
 unrelated+0.116
minist+0.110
interstitial+0.109
 Beir+0.102
Neg logit contributions
ertodd-0.107
isconsin-0.102
alsa-0.100
urdue-0.096
framework-0.096
Token so
Token ID523
Feature activation-2.82e-01

Pos logit contributions
cles+0.153
 unrelated+0.151
minist+0.142
interstitial+0.140
 Beir+0.129
Neg logit contributions
ertodd-0.190
isconsin-0.184
alsa-0.179
urdue-0.173
framework-0.173
Token you
Token ID345
Feature activation-2.15e-01

Pos logit contributions
cles+0.509
 unrelated+0.503
minist+0.474
interstitial+0.469
 Beir+0.436
Neg logit contributions
ertodd-0.537
isconsin-0.518
alsa-0.505
framework-0.486
urdue-0.486
Token don
Token ID836
Feature activation-1.52e-01

Pos logit contributions
cles+0.389
 unrelated+0.385
minist+0.363
interstitial+0.361
 Beir+0.335
Neg logit contributions
ertodd-0.409
isconsin-0.393
alsa-0.384
urdue-0.369
framework-0.369
Token't
Token ID470
Feature activation+3.69e-01

Pos logit contributions
cles+0.199
 unrelated+0.197
minist+0.179
interstitial+0.171
cle+0.160
Neg logit contributions
ertodd-0.368
isconsin-0.356
alsa-0.350
urdue-0.339
cipled-0.339
Token ejac
Token ID39426
Feature activation-2.10e+00

Pos logit contributions
ertodd+0.690
isconsin+0.653
alsa+0.645
urdue+0.621
 Taj+0.619
Neg logit contributions
cles-0.676
 unrelated-0.665
interstitial-0.640
minist-0.629
 Beir-0.589
Tokenulate
Token ID5039
Feature activation+7.51e-02

Pos logit contributions
cles+3.682
 unrelated+3.653
minist+3.449
interstitial+3.323
cle+3.162
Neg logit contributions
ertodd-4.100
isconsin-3.940
alsa-3.840
framework-3.700
urdue-3.676
Token soon
Token ID2582
Feature activation+1.86e-01

Pos logit contributions
ertodd+0.146
isconsin+0.141
alsa+0.137
urdue+0.132
 Taj+0.132
Neg logit contributions
cles-0.132
 unrelated-0.130
minist-0.123
interstitial-0.123
 Beir-0.114
Token.
Token ID13
Feature activation+8.27e-02

Pos logit contributions
ertodd+0.360
isconsin+0.348
alsa+0.339
urdue+0.326
framework+0.326
Neg logit contributions
cles-0.326
 unrelated-0.324
minist-0.306
interstitial-0.305
 Beir-0.284
Token So
Token ID1406
Feature activation-3.75e-01

Pos logit contributions
ertodd+0.137
isconsin+0.131
alsa+0.127
framework+0.121
urdue+0.121
Neg logit contributions
cles-0.171
 unrelated-0.170
minist-0.160
interstitial-0.158
 Beir-0.149
Token you
Token ID345
Feature activation-1.71e-01

Pos logit contributions
cles+0.676
 unrelated+0.672
minist+0.630
interstitial+0.621
 Beir+0.577
Neg logit contributions
ertodd-0.717
isconsin-0.691
alsa-0.673
framework-0.648
urdue-0.647
Token respectively
Token ID8148
Feature activation+5.80e-01

Pos logit contributions
ertodd+0.290
isconsin+0.284
alsa+0.275
 Taj+0.268
urdue+0.267
Neg logit contributions
cles-0.264
 unrelated-0.258
minist-0.246
interstitial-0.243
 Beir-0.221
Token.
Token ID13
Feature activation+1.15e-01

Pos logit contributions
ertodd+1.027
isconsin+1.000
alsa+0.961
urdue+0.934
framework+0.922
Neg logit contributions
cles-1.114
 unrelated-1.096
minist-1.051
interstitial-1.035
 Beir-0.963
Token Er
Token ID5256
Feature activation+1.29e-01

Pos logit contributions
ertodd+0.202
isconsin+0.196
alsa+0.189
framework+0.183
urdue+0.183
Neg logit contributions
cles-0.226
 unrelated-0.224
minist-0.212
interstitial-0.210
 Beir-0.194
Tokenrict
Token ID2012
Feature activation+5.81e-02

Pos logit contributions
ertodd+0.247
isconsin+0.245
alsa+0.236
framework+0.227
urdue+0.227
Neg logit contributions
 unrelated-0.225
cles-0.223
minist-0.210
interstitial-0.209
 Beir-0.195
Token R
Token ID371
Feature activation-2.03e-01

Pos logit contributions
ertodd+0.107
isconsin+0.104
alsa+0.102
urdue+0.098
framework+0.097
Neg logit contributions
cles-0.107
 unrelated-0.106
minist-0.100
interstitial-0.098
 Beir-0.092
Tokenhett
Token ID17442
Feature activation-2.08e+00

Pos logit contributions
cles+0.372
 unrelated+0.371
minist+0.347
interstitial+0.343
 Beir+0.320
Neg logit contributions
ertodd-0.380
isconsin-0.368
alsa-0.358
urdue-0.344
framework-0.344
Token eventually
Token ID4191
Feature activation+3.63e-02

Pos logit contributions
 unrelated+3.679
cles+3.653
minist+3.388
interstitial+3.348
 Beir+3.181
Neg logit contributions
ertodd-4.052
isconsin-3.851
alsa-3.746
framework-3.634
cipled-3.601
Token broke
Token ID6265
Feature activation-8.52e-02

Pos logit contributions
ertodd+0.068
isconsin+0.066
alsa+0.064
urdue+0.061
framework+0.061
Neg logit contributions
cles-0.067
 unrelated-0.066
minist-0.063
interstitial-0.062
 Beir-0.057
Token Smith
Token ID4176
Feature activation-2.04e-01

Pos logit contributions
cles+0.162
 unrelated+0.160
minist+0.152
interstitial+0.150
 Beir+0.139
Neg logit contributions
ertodd-0.152
isconsin-0.149
alsa-0.144
 Taj-0.139
urdue-0.139
Token
Token ID447
Feature activation-3.73e-02

Pos logit contributions
cles+0.361
 unrelated+0.355
minist+0.336
interstitial+0.330
 Beir+0.308
Neg logit contributions
ertodd-0.394
isconsin-0.384
alsa-0.374
urdue-0.359
 Taj-0.358
Token
Token ID247
Feature activation+1.40e-02

Pos logit contributions
cles+0.074
 unrelated+0.074
minist+0.070
interstitial+0.069
cle+0.064
Neg logit contributions
ertodd-0.064
isconsin-0.062
alsa-0.060
framework-0.057
urdue-0.057
Token had
Token ID550
Feature activation-3.55e-01

Pos logit contributions
cles+1.555
 unrelated+1.541
minist+1.458
interstitial+1.440
 Beir+1.342
Neg logit contributions
ertodd-1.426
isconsin-1.369
alsa-1.337
framework-1.279
urdue-1.277
Token perhaps
Token ID3737
Feature activation-3.02e-01

Pos logit contributions
cles+0.680
 unrelated+0.675
minist+0.637
interstitial+0.629
 Beir+0.586
Neg logit contributions
ertodd-0.637
isconsin-0.612
alsa-0.596
framework-0.571
urdue-0.571
Token a
Token ID257
Feature activation+2.86e-01

Pos logit contributions
cles+0.585
 unrelated+0.578
minist+0.550
interstitial+0.543
 Beir+0.505
Neg logit contributions
ertodd-0.532
isconsin-0.511
alsa-0.497
urdue-0.478
framework-0.478
Token marginally
Token ID44108
Feature activation-1.03e-01

Pos logit contributions
ertodd+0.528
isconsin+0.509
alsa+0.498
framework+0.483
 Taj+0.481
Neg logit contributions
cles-0.526
 unrelated-0.517
minist-0.494
interstitial-0.489
 Beir-0.450
Token lower
Token ID2793
Feature activation-3.39e-02

Pos logit contributions
cles+0.191
 unrelated+0.187
minist+0.179
interstitial+0.176
 Beir+0.163
Neg logit contributions
ertodd-0.191
isconsin-0.184
alsa-0.179
framework-0.173
urdue-0.173
Token blur
Token ID23671
Feature activation-2.08e+00

Pos logit contributions
cles+0.065
 unrelated+0.064
minist+0.062
interstitial+0.061
leans+0.056
Neg logit contributions
ertodd-0.060
isconsin-0.058
alsa-0.056
framework-0.054
 Taj-0.054
Token when
Token ID618
Feature activation-1.17e-01

Pos logit contributions
 unrelated+3.733
cles+3.724
minist+3.480
interstitial+3.373
cle+3.208
Neg logit contributions
ertodd-3.977
isconsin-3.817
alsa-3.713
urdue-3.569
framework-3.540
Token running
Token ID2491
Feature activation-8.44e-01

Pos logit contributions
cles+0.200
 unrelated+0.197
minist+0.187
interstitial+0.185
 Beir+0.169
Neg logit contributions
ertodd-0.232
isconsin-0.224
alsa-0.219
urdue-0.212
framework-0.212
Token at
Token ID379
Feature activation-4.20e-01

Pos logit contributions
cles+1.483
 unrelated+1.469
minist+1.382
interstitial+1.364
 Beir+1.261
Neg logit contributions
ertodd-1.649
isconsin-1.591
alsa-1.554
framework-1.494
urdue-1.493
Token 144
Token ID20224
Feature activation-8.83e-01

Pos logit contributions
cles+0.745
 unrelated+0.737
minist+0.695
interstitial+0.685
 Beir+0.632
Neg logit contributions
ertodd-0.812
isconsin-0.783
alsa-0.766
framework-0.736
urdue-0.735
TokenHz
Token ID7399
Feature activation-7.07e-01

Pos logit contributions
cles+1.524
 unrelated+1.512
minist+1.412
interstitial+1.387
 Beir+1.285
Neg logit contributions
ertodd-1.760
isconsin-1.698
alsa-1.652
framework-1.593
urdue-1.591
Token people
Token ID661
Feature activation-6.07e-01

Pos logit contributions
cles+0.124
 unrelated+0.123
minist+0.116
interstitial+0.114
 Beir+0.105
Neg logit contributions
ertodd-0.136
isconsin-0.131
alsa-0.128
framework-0.123
urdue-0.123
Token have
Token ID423
Feature activation-8.62e-02

Pos logit contributions
 unrelated+1.121
cles+1.118
minist+1.041
interstitial+1.022
 Beir+0.963
Neg logit contributions
ertodd-1.137
isconsin-1.093
alsa-1.066
framework-1.026
urdue-1.023
Token set
Token ID900
Feature activation+2.30e-01

Pos logit contributions
cles+0.154
 unrelated+0.153
minist+0.143
interstitial+0.141
 Beir+0.131
Neg logit contributions
ertodd-0.166
isconsin-0.160
alsa-0.156
framework-0.151
urdue-0.150
Token out
Token ID503
Feature activation-2.49e-01

Pos logit contributions
ertodd+0.440
isconsin+0.429
alsa+0.414
 Taj+0.406
framework+0.402
Neg logit contributions
cles-0.409
 unrelated-0.399
interstitial-0.381
minist-0.380
leans-0.346
Token to
Token ID284
Feature activation-5.37e-02

Pos logit contributions
cles+0.466
 unrelated+0.462
minist+0.436
interstitial+0.431
 Beir+0.400
Neg logit contributions
ertodd-0.460
isconsin-0.443
alsa-0.431
framework-0.414
urdue-0.413
Token draw
Token ID3197
Feature activation-2.07e+00

Pos logit contributions
cles+0.107
 unrelated+0.105
minist+0.100
interstitial+0.100
 Beir+0.092
Neg logit contributions
ertodd-0.092
isconsin-0.089
alsa-0.086
urdue-0.083
framework-0.083
Token our
Token ID674
Feature activation-3.94e-01

Pos logit contributions
 unrelated+3.540
cles+3.472
minist+3.247
interstitial+3.107
 Beir+3.036
Neg logit contributions
ertodd-4.186
isconsin-3.974
alsa-3.933
urdue-3.783
framework-3.781
Token memorial
Token ID17357
Feature activation-3.87e-01

Pos logit contributions
cles+0.705
 unrelated+0.699
minist+0.657
interstitial+0.650
 Beir+0.600
Neg logit contributions
ertodd-0.759
isconsin-0.732
alsa-0.713
framework-0.687
urdue-0.685
Token into
Token ID656
Feature activation+3.20e-01

Pos logit contributions
cles+0.650
 unrelated+0.642
minist+0.602
interstitial+0.596
 Beir+0.547
Neg logit contributions
ertodd-0.786
isconsin-0.760
alsa-0.740
framework-0.715
urdue-0.712
Token the
Token ID262
Feature activation-8.37e-02

Pos logit contributions
ertodd+0.561
isconsin+0.542
alsa+0.524
 Taj+0.505
framework+0.502
Neg logit contributions
cles-0.621
 unrelated-0.609
minist-0.581
interstitial-0.580
leans-0.534
Token current
Token ID1459
Feature activation-3.58e-01

Pos logit contributions
cles+0.160
 unrelated+0.158
minist+0.150
interstitial+0.149
 Beir+0.137
Neg logit contributions
ertodd-0.150
isconsin-0.145
alsa-0.141
framework-0.135
urdue-0.135
Token mism
Token ID32691
Feature activation+4.59e-01

Pos logit contributions
ertodd+0.276
isconsin+0.269
alsa+0.262
 Taj+0.254
framework+0.252
Neg logit contributions
cles-0.271
 unrelated-0.264
minist-0.254
interstitial-0.252
 Beir-0.231
Tokenatched
Token ID14265
Feature activation+5.41e-01

Pos logit contributions
ertodd+0.553
isconsin+0.526
alsa+0.506
framework+0.478
cipled+0.469
Neg logit contributions
cles-1.143
 unrelated-1.135
minist-1.088
interstitial-1.086
 Beir-1.031
Token heroes
Token ID10281
Feature activation-4.79e-01

Pos logit contributions
ertodd+0.894
isconsin+0.874
alsa+0.852
 Taj+0.826
framework+0.819
Neg logit contributions
cles-1.082
 unrelated-1.054
interstitial-1.017
minist-1.017
 Beir-0.934
Token,
Token ID11
Feature activation+7.49e-02

Pos logit contributions
cles+0.839
 unrelated+0.833
minist+0.781
interstitial+0.769
 Beir+0.713
Neg logit contributions
ertodd-0.939
isconsin-0.906
alsa-0.882
framework-0.850
urdue-0.849
Token Jack
Token ID3619
Feature activation+9.64e-02

Pos logit contributions
ertodd+0.140
isconsin+0.136
alsa+0.133
 Taj+0.128
urdue+0.128
Neg logit contributions
cles-0.136
 unrelated-0.133
minist-0.127
interstitial-0.126
 Beir-0.116
Token Aub
Token ID19723
Feature activation-2.07e+00

Pos logit contributions
ertodd+0.184
isconsin+0.179
alsa+0.175
 Taj+0.168
framework+0.168
Neg logit contributions
cles-0.173
 unrelated-0.170
minist-0.162
interstitial-0.159
 Beir-0.146
Tokenrey
Token ID4364
Feature activation-3.94e-01

Pos logit contributions
cles+2.516
 unrelated+2.462
minist+2.261
interstitial+2.197
cle+1.996
Neg logit contributions
ertodd-5.154
isconsin-4.967
alsa-4.850
urdue-4.745
framework-4.738
Token,
Token ID11
Feature activation-2.05e-02

Pos logit contributions
cles+0.657
 unrelated+0.651
minist+0.611
interstitial+0.602
 Beir+0.553
Neg logit contributions
ertodd-0.804
isconsin-0.779
alsa-0.760
framework-0.733
urdue-0.732
Token a
Token ID257
Feature activation-5.28e-03

Pos logit contributions
cles+0.039
 unrelated+0.039
minist+0.037
interstitial+0.036
 Beir+0.034
Neg logit contributions
ertodd-0.037
isconsin-0.036
alsa-0.035
 Taj-0.033
framework-0.033
Token British
Token ID3517
Feature activation-5.39e-02

Pos logit contributions
cles+0.010
 unrelated+0.010
minist+0.009
interstitial+0.009
 Beir+0.009
Neg logit contributions
ertodd-0.010
isconsin-0.009
alsa-0.009
framework-0.009
urdue-0.009
Token naval
Token ID19014
Feature activation+2.73e-01

Pos logit contributions
cles+0.106
 unrelated+0.105
minist+0.099
interstitial+0.098
 Beir+0.092
Neg logit contributions
ertodd-0.094
isconsin-0.090
alsa-0.088
urdue-0.084
framework-0.084
Token grape
Token ID30777
Feature activation-8.87e-01

Pos logit contributions
ertodd+0.281
isconsin+0.270
alsa+0.263
framework+0.253
urdue+0.252
Neg logit contributions
cles-0.288
 unrelated-0.285
minist-0.269
interstitial-0.265
 Beir-0.247
Tokenfruit
Token ID34711
Feature activation-6.13e-01

Pos logit contributions
cles+1.093
 unrelated+1.082
minist+0.979
interstitial+0.957
cle+0.856
Neg logit contributions
ertodd-2.209
isconsin-2.139
alsa-2.092
urdue-2.036
framework-2.035
Token and
Token ID290
Feature activation+8.44e-02

Pos logit contributions
cles+1.102
 unrelated+1.097
minist+1.025
interstitial+1.008
 Beir+0.939
Neg logit contributions
ertodd-1.174
isconsin-1.131
alsa-1.097
urdue-1.060
framework-1.059
Token under
Token ID739
Feature activation+5.42e-01

Pos logit contributions
ertodd+0.159
isconsin+0.154
alsa+0.150
framework+0.144
 Taj+0.144
Neg logit contributions
cles-0.154
 unrelated-0.152
minist-0.144
interstitial-0.142
 Beir-0.131
Tokeng
Token ID70
Feature activation-1.95e-01

Pos logit contributions
ertodd+0.672
isconsin+0.635
alsa+0.610
framework+0.573
urdue+0.570
Neg logit contributions
cles-1.340
 unrelated-1.332
minist-1.274
interstitial-1.261
 Beir-1.198
Tokenird
Token ID1447
Feature activation-2.05e+00

Pos logit contributions
cles+0.267
 unrelated+0.266
minist+0.245
interstitial+0.242
 Beir+0.219
Neg logit contributions
ertodd-0.455
isconsin-0.442
alsa-0.435
urdue-0.420
framework-0.418
Tokened
Token ID276
Feature activation-2.49e-01

Pos logit contributions
 unrelated+3.665
cles+3.647
minist+3.388
interstitial+3.347
 Beir+3.125
Neg logit contributions
ertodd-3.864
isconsin-3.759
alsa-3.564
cipled-3.515
urdue-3.513
Token by
Token ID416
Feature activation+7.43e-02

Pos logit contributions
cles+0.380
 unrelated+0.377
minist+0.352
interstitial+0.350
 Beir+0.315
Neg logit contributions
ertodd-0.541
isconsin-0.524
alsa-0.514
framework-0.494
urdue-0.494
Token che
Token ID1125
Feature activation+9.96e-02

Pos logit contributions
ertodd+0.136
isconsin+0.130
alsa+0.127
framework+0.122
urdue+0.121
Neg logit contributions
cles-0.141
 unrelated-0.139
minist-0.132
interstitial-0.130
 Beir-0.121
Tokenwy
Token ID21768
Feature activation-1.84e-02

Pos logit contributions
ertodd+0.191
isconsin+0.184
alsa+0.179
framework+0.173
urdue+0.172
Neg logit contributions
cles-0.179
 unrelated-0.178
minist-0.168
interstitial-0.165
 Beir-0.154
Token caramel
Token ID32913
Feature activation-1.56e-01

Pos logit contributions
cles+0.034
 unrelated+0.034
minist+0.032
interstitial+0.032
 Beir+0.030
Neg logit contributions
ertodd-0.034
isconsin-0.033
alsa-0.032
framework-0.031
urdue-0.030
Token 4
Token ID604
Feature activation-5.20e-01

Pos logit contributions
ertodd+0.332
isconsin+0.319
alsa+0.314
framework+0.301
urdue+0.301
Neg logit contributions
cles-0.324
 unrelated-0.321
minist-0.304
interstitial-0.299
 Beir-0.276
Tokenms
Token ID907
Feature activation-2.00e-01

Pos logit contributions
cles+0.766
 unrelated+0.752
minist+0.693
interstitial+0.665
cle+0.622
Neg logit contributions
ertodd-1.184
isconsin-1.145
alsa-1.110
cipled-1.082
urdue-1.077
Token G
Token ID402
Feature activation-4.00e-01

Pos logit contributions
cles+0.338
 unrelated+0.335
minist+0.316
interstitial+0.311
 Beir+0.286
Neg logit contributions
ertodd-0.405
isconsin-0.391
alsa-0.383
urdue-0.369
framework-0.368
Token2
Token ID17
Feature activation-8.89e-01

Pos logit contributions
cles+0.423
 unrelated+0.418
minist+0.372
interstitial+0.359
cle+0.316
Neg logit contributions
ertodd-1.067
isconsin-1.041
alsa-1.014
urdue-0.989
framework-0.988
TokenG
Token ID38
Feature activation-4.02e-01

Pos logit contributions
cles+1.134
 unrelated+1.125
minist+1.005
interstitial+0.945
cle+0.918
Neg logit contributions
ertodd-2.204
isconsin-2.126
alsa-2.069
cipled-2.025
urdue-2.004
Token AU
Token ID27548
Feature activation-2.05e+00

Pos logit contributions
cles+0.657
 unrelated+0.650
minist+0.610
interstitial+0.600
 Beir+0.551
Neg logit contributions
ertodd-0.834
isconsin-0.806
alsa-0.790
framework-0.761
urdue-0.760
Token Opt
Token ID13123
Feature activation-6.35e-01

Pos logit contributions
cles+3.096
 unrelated+3.086
minist+2.827
interstitial+2.638
 Beir+2.582
Neg logit contributions
ertodd-4.447
isconsin-4.363
alsa-4.192
cipled-4.099
urdue-4.064
Tokenronics
Token ID20844
Feature activation-4.58e-01

Pos logit contributions
cles+1.298
 unrelated+1.264
minist+1.202
interstitial+1.134
cle+1.118
Neg logit contributions
ertodd-1.093
isconsin-1.036
alsa-1.007
 Taj-0.971
cipled-0.969
Token AH
Token ID28159
Feature activation-2.81e-01

Pos logit contributions
cles+0.757
 unrelated+0.750
minist+0.703
interstitial+0.691
 Beir+0.634
Neg logit contributions
ertodd-0.945
isconsin-0.912
alsa-0.893
framework-0.861
urdue-0.859
TokenVA
Token ID11731
Feature activation-7.11e-01

Pos logit contributions
cles+0.464
 unrelated+0.460
minist+0.430
interstitial+0.420
cle+0.390
Neg logit contributions
ertodd-0.580
isconsin-0.558
alsa-0.541
urdue-0.525
cipled-0.524
Token (
Token ID357
Feature activation-2.71e-01

Pos logit contributions
 unrelated+1.342
cles+1.334
minist+1.236
interstitial+1.199
cle+1.158
Neg logit contributions
ertodd-1.311
isconsin-1.257
alsa-1.219
cipled-1.166
urdue-1.164
Token he
Token ID339
Feature activation+1.51e-01

Pos logit contributions
ertodd+0.218
isconsin+0.210
alsa+0.205
 Taj+0.198
urdue+0.197
Neg logit contributions
cles-0.202
 unrelated-0.198
minist-0.189
interstitial-0.186
cle-0.171
Token may
Token ID743
Feature activation+5.14e-01

Pos logit contributions
ertodd+0.300
isconsin+0.290
alsa+0.282
urdue+0.272
framework+0.272
Neg logit contributions
cles-0.261
 unrelated-0.259
minist-0.244
interstitial-0.241
 Beir-0.221
Token have
Token ID423
Feature activation+8.34e-02

Pos logit contributions
ertodd+1.027
isconsin+0.988
alsa+0.970
framework+0.932
 Taj+0.929
Neg logit contributions
cles-0.877
 unrelated-0.860
minist-0.822
interstitial-0.820
 Beir-0.740
Token led
Token ID2957
Feature activation+3.77e-01

Pos logit contributions
ertodd+0.166
isconsin+0.161
alsa+0.156
framework+0.151
urdue+0.151
Neg logit contributions
cles-0.143
 unrelated-0.142
minist-0.133
interstitial-0.131
 Beir-0.121
Token a
Token ID257
Feature activation-7.90e-02

Pos logit contributions
ertodd+0.677
isconsin+0.653
alsa+0.636
urdue+0.609
 Taj+0.608
Neg logit contributions
cles-0.721
 unrelated-0.706
minist-0.673
interstitial-0.669
 Beir-0.617
Token double
Token ID4274
Feature activation-2.04e+00

Pos logit contributions
cles+0.148
 unrelated+0.147
minist+0.138
interstitial+0.136
 Beir+0.127
Neg logit contributions
ertodd-0.146
isconsin-0.140
alsa-0.136
framework-0.131
urdue-0.131
Token life
Token ID1204
Feature activation+8.52e-02

Pos logit contributions
 unrelated+4.092
cles+4.073
minist+3.826
interstitial+3.704
 Beir+3.539
Neg logit contributions
ertodd-3.468
isconsin-3.352
alsa-3.230
framework-3.116
urdue-3.109
Token,
Token ID11
Feature activation-1.45e-01

Pos logit contributions
ertodd+0.157
isconsin+0.151
alsa+0.146
urdue+0.141
 Taj+0.141
Neg logit contributions
cles-0.158
 unrelated-0.154
minist-0.149
interstitial-0.149
 Beir-0.137
Token where
Token ID810
Feature activation+4.92e-02

Pos logit contributions
cles+0.247
 unrelated+0.242
minist+0.230
interstitial+0.227
 Beir+0.207
Neg logit contributions
ertodd-0.292
isconsin-0.283
alsa-0.275
urdue-0.266
 Taj-0.265
Token he
Token ID339
Feature activation+4.50e-01

Pos logit contributions
ertodd+0.100
isconsin+0.096
alsa+0.094
 Taj+0.091
urdue+0.091
Neg logit contributions
cles-0.083
 unrelated-0.081
minist-0.077
interstitial-0.076
 Beir-0.069
Token twice
Token ID5403
Feature activation-5.10e-01

Pos logit contributions
ertodd+0.838
isconsin+0.810
alsa+0.782
urdue+0.758
 Taj+0.758
Neg logit contributions
cles-0.825
 unrelated-0.813
minist-0.779
interstitial-0.777
 Beir-0.709
Token issue
Token ID2071
Feature activation-8.90e-01

Pos logit contributions
ertodd+0.096
isconsin+0.092
alsa+0.090
framework+0.086
urdue+0.086
Neg logit contributions
cles-0.103
 unrelated-0.102
minist-0.097
interstitial-0.096
 Beir-0.089
Token;
Token ID26
Feature activation-7.52e-02

Pos logit contributions
cles+1.586
 unrelated+1.571
minist+1.478
interstitial+1.457
 Beir+1.350
Neg logit contributions
ertodd-1.720
isconsin-1.659
alsa-1.616
framework-1.556
urdue-1.555
Token where
Token ID810
Feature activation+6.32e-02

Pos logit contributions
cles+0.138
 unrelated+0.136
minist+0.129
interstitial+0.127
 Beir+0.117
Neg logit contributions
ertodd-0.142
isconsin-0.137
alsa-0.133
framework-0.128
urdue-0.128
Token do
Token ID466
Feature activation+2.71e-01

Pos logit contributions
ertodd+0.120
isconsin+0.116
alsa+0.113
urdue+0.109
framework+0.108
Neg logit contributions
cles-0.114
 unrelated-0.113
minist-0.107
interstitial-0.106
 Beir-0.097
Token we
Token ID356
Feature activation+4.46e-02

Pos logit contributions
ertodd+0.496
isconsin+0.481
alsa+0.466
 Taj+0.450
urdue+0.449
Neg logit contributions
cles-0.506
 unrelated-0.499
minist-0.474
interstitial-0.470
 Beir-0.433
Token draw
Token ID3197
Feature activation-2.03e+00

Pos logit contributions
ertodd+0.079
isconsin+0.076
alsa+0.074
framework+0.071
urdue+0.071
Neg logit contributions
cles-0.086
 unrelated-0.086
minist-0.081
interstitial-0.080
 Beir-0.075
Token the
Token ID262
Feature activation-1.72e-01

Pos logit contributions
 unrelated+3.618
cles+3.586
minist+3.367
interstitial+3.243
 Beir+3.085
Neg logit contributions
ertodd-3.905
isconsin-3.697
alsa-3.650
urdue-3.548
framework-3.520
Token line
Token ID1627
Feature activation-8.51e-01

Pos logit contributions
cles+0.317
 unrelated+0.311
minist+0.295
interstitial+0.294
 Beir+0.270
Neg logit contributions
ertodd-0.321
isconsin-0.312
alsa-0.303
framework-0.292
 Taj-0.291
Token?
Token ID30
Feature activation-1.22e-02

Pos logit contributions
cles+1.266
 unrelated+1.255
minist+1.162
interstitial+1.139
 Beir+1.042
Neg logit contributions
ertodd-1.895
isconsin-1.834
alsa-1.793
framework-1.736
urdue-1.735
Token So
Token ID1406
Feature activation-1.08e-01

Pos logit contributions
cles+0.024
 unrelated+0.024
minist+0.023
interstitial+0.023
 Beir+0.021
Neg logit contributions
ertodd-0.021
isconsin-0.020
alsa-0.019
framework-0.019
urdue-0.019
Token they
Token ID484
Feature activation-6.90e-02

Pos logit contributions
cles+0.197
 unrelated+0.195
minist+0.185
interstitial+0.182
 Beir+0.168
Neg logit contributions
ertodd-0.204
isconsin-0.197
alsa-0.192
urdue-0.185
framework-0.185
Token19
Token ID1129
Feature activation+4.53e-01

Pos logit contributions
ertodd+0.164
isconsin+0.161
alsa+0.157
framework+0.152
urdue+0.151
Neg logit contributions
cles-0.138
 unrelated-0.137
minist-0.128
interstitial-0.126
 Beir-0.118
Token04
Token ID3023
Feature activation-3.16e-01

Pos logit contributions
ertodd+0.971
isconsin+0.946
alsa+0.923
framework+0.898
urdue+0.892
Neg logit contributions
cles-0.707
 unrelated-0.697
minist-0.649
interstitial-0.643
 Beir-0.589
Token).
Token ID737
Feature activation+7.59e-02

Pos logit contributions
cles+0.524
 unrelated+0.519
minist+0.486
interstitial+0.479
 Beir+0.443
Neg logit contributions
ertodd-0.646
isconsin-0.626
alsa-0.610
urdue-0.591
framework-0.589
Token Joyce
Token ID25936
Feature activation+1.57e-01

Pos logit contributions
ertodd+0.135
isconsin+0.129
alsa+0.126
framework+0.122
urdue+0.122
Neg logit contributions
cles-0.146
 unrelated-0.145
minist-0.137
interstitial-0.137
leans-0.125
Token's
Token ID338
Feature activation-1.14e-01

Pos logit contributions
ertodd+0.298
isconsin+0.287
alsa+0.280
urdue+0.272
 Taj+0.272
Neg logit contributions
cles-0.278
 unrelated-0.275
minist-0.262
interstitial-0.261
 Beir-0.238
Token Chicago
Token ID4842
Feature activation+1.36e+00

Pos logit contributions
cles+0.208
 unrelated+0.204
minist+0.194
interstitial+0.193
 Beir+0.177
Neg logit contributions
ertodd-0.214
isconsin-0.206
alsa-0.202
 Taj-0.194
framework-0.194
Token-
Token ID12
Feature activation-6.94e-02

Pos logit contributions
ertodd+2.517
isconsin+2.443
alsa+2.396
 Taj+2.355
urdue+2.303
Neg logit contributions
cles-2.415
 unrelated-2.393
minist-2.282
interstitial-2.262
 Beir-2.102
Tokenbased
Token ID3106
Feature activation+8.94e-01

Pos logit contributions
cles+0.144
 unrelated+0.144
minist+0.136
interstitial+0.135
 Beir+0.127
Neg logit contributions
ertodd-0.111
isconsin-0.107
alsa-0.105
framework-0.100
urdue-0.100
Token he
Token ID339
Feature activation+6.25e-02

Pos logit contributions
ertodd+1.584
isconsin+1.531
alsa+1.509
 Taj+1.470
framework+1.448
Neg logit contributions
cles-1.679
 unrelated-1.642
interstitial-1.582
minist-1.575
leans-1.445
Tokeni
Token ID72
Feature activation+3.22e-01

Pos logit contributions
ertodd+0.139
isconsin+0.136
alsa+0.134
framework+0.129
urdue+0.129
Neg logit contributions
 unrelated-0.091
cles-0.090
interstitial-0.083
minist-0.082
 Beir-0.075
Tokenress
Token ID601
Feature activation-6.00e-01

Pos logit contributions
ertodd+0.839
isconsin+0.821
alsa+0.804
framework+0.786
urdue+0.783
Neg logit contributions
cles-0.347
 unrelated-0.343
minist-0.305
interstitial-0.303
 Beir-0.270
Token.[
Token ID3693
Feature activation+3.22e-03

Pos logit contributions
ertodd+0.710
isconsin+0.687
alsa+0.675
 Taj+0.649
framework+0.647
Neg logit contributions
cles-0.628
 unrelated-0.607
minist-0.587
interstitial-0.579
 Beir-0.533
Token16
Token ID1433
Feature activation+5.82e-02

Pos logit contributions
ertodd+0.007
isconsin+0.006
alsa+0.006
framework+0.006
urdue+0.006
Neg logit contributions
cles-0.005
 unrelated-0.005
minist-0.005
interstitial-0.005
 Beir-0.005
Token]
Token ID60
Feature activation-3.49e-01

Pos logit contributions
ertodd+0.095
isconsin+0.091
alsa+0.089
framework+0.085
urdue+0.085
Neg logit contributions
cles-0.121
 unrelated-0.120
minist-0.114
interstitial-0.112
 Beir-0.105
Token<|endoftext|>
Token ID50256
Feature activation-6.95e-01

Pos logit contributions
cles+0.685
 unrelated+0.679
minist+0.642
interstitial+0.635
 Beir+0.589
Neg logit contributions
ertodd-0.612
isconsin-0.588
alsa-0.571
framework-0.550
 Taj-0.548
TokenD
Token ID35
Feature activation-3.26e-02

Pos logit contributions
cles+1.236
 unrelated+1.229
minist+1.151
interstitial+1.134
 Beir+1.057
Neg logit contributions
ertodd-1.343
isconsin-1.296
alsa-1.264
framework-1.218
urdue-1.214
Tokeninosaur
Token ID21317
Feature activation+2.19e+00

Pos logit contributions
cles+0.059
 unrelated+0.059
minist+0.055
interstitial+0.054
 Beir+0.051
Neg logit contributions
ertodd-0.062
isconsin-0.060
alsa-0.059
urdue-0.056
framework-0.056
Token Jr
Token ID7504
Feature activation+2.40e-01

Pos logit contributions
ertodd+3.944
alsa+3.744
isconsin+3.709
 Taj+3.611
urdue+3.557
Neg logit contributions
 unrelated-3.939
cles-3.929
interstitial-3.747
minist-3.708
leans-3.446
Token.:
Token ID11207
Feature activation-4.29e-01

Pos logit contributions
ertodd+0.441
isconsin+0.424
alsa+0.416
urdue+0.398
 Taj+0.397
Neg logit contributions
cles-0.446
 unrelated-0.442
minist-0.418
interstitial-0.416
 Beir-0.382
Token "
Token ID366
Feature activation+2.64e-01

Pos logit contributions
cles+0.826
 unrelated+0.821
minist+0.773
interstitial+0.763
 Beir+0.714
Neg logit contributions
ertodd-0.767
isconsin-0.737
alsa-0.716
framework-0.687
urdue-0.687
TokenI
Token ID40
Feature activation+2.01e-01

Pos logit contributions
ertodd+0.509
isconsin+0.494
alsa+0.483
framework+0.469
urdue+0.462
Neg logit contributions
cles-0.464
 unrelated-0.463
minist-0.431
interstitial-0.426
 Beir-0.398
Token'll
Token ID1183
Feature activation+5.19e-01

Pos logit contributions
ertodd+0.363
isconsin+0.349
alsa+0.341
framework+0.326
 Taj+0.326
Neg logit contributions
cles-0.378
 unrelated-0.377
minist-0.356
interstitial-0.354
 Beir-0.326
Token worked
Token ID3111
Feature activation-4.83e-01

Pos logit contributions
cles+0.025
 unrelated+0.024
minist+0.023
interstitial+0.023
 Beir+0.021
Neg logit contributions
ertodd-0.028
isconsin-0.027
alsa-0.026
 Taj-0.026
urdue-0.025
Token in
Token ID287
Feature activation-7.49e-03

Pos logit contributions
cles+0.840
 unrelated+0.826
minist+0.781
interstitial+0.776
 Beir+0.712
Neg logit contributions
ertodd-0.953
isconsin-0.921
alsa-0.895
framework-0.865
urdue-0.864
Token his
Token ID465
Feature activation+4.09e-02

Pos logit contributions
cles+0.015
 unrelated+0.015
minist+0.014
interstitial+0.014
 Beir+0.013
Neg logit contributions
ertodd-0.013
isconsin-0.012
alsa-0.012
 Taj-0.012
urdue-0.011
Token individual
Token ID1981
Feature activation+1.09e+00

Pos logit contributions
ertodd+0.075
isconsin+0.073
alsa+0.071
 Taj+0.069
urdue+0.068
Neg logit contributions
cles-0.076
 unrelated-0.075
minist-0.071
interstitial-0.071
leans-0.065
Token capacity
Token ID5339
Feature activation-1.96e-01

Pos logit contributions
ertodd+2.019
isconsin+1.964
 Taj+1.921
alsa+1.921
urdue+1.844
Neg logit contributions
cles-1.963
 unrelated-1.906
interstitial-1.847
minist-1.827
leans-1.710
Token whole
Token ID2187
Feature activation+1.36e+00

Pos logit contributions
cles+0.342
 unrelated+0.337
minist+0.318
interstitial+0.315
 Beir+0.290
Neg logit contributions
ertodd-0.383
isconsin-0.370
alsa-0.360
framework-0.348
urdue-0.348
Token living
Token ID2877
Feature activation+5.69e-01

Pos logit contributions
ertodd+2.301
isconsin+2.184
alsa+2.143
urdue+2.083
 Taj+2.058
Neg logit contributions
cles-2.654
interstitial-2.572
 unrelated-2.567
minist-2.514
 Beir-2.331
Token in
Token ID287
Feature activation-6.53e-02

Pos logit contributions
ertodd+1.114
isconsin+1.084
alsa+1.050
 Taj+1.039
urdue+1.019
Neg logit contributions
cles-0.978
 unrelated-0.943
interstitial-0.915
minist-0.906
leans-0.838
Token London
Token ID3576
Feature activation+7.92e-02

Pos logit contributions
cles+0.135
 unrelated+0.133
minist+0.128
interstitial+0.127
leans+0.118
Neg logit contributions
ertodd-0.106
isconsin-0.102
alsa-0.099
 Taj-0.096
urdue-0.095
Token for
Token ID329
Feature activation-1.66e-01

Pos logit contributions
ertodd+0.152
isconsin+0.147
alsa+0.143
framework+0.138
urdue+0.138
Neg logit contributions
cles-0.142
 unrelated-0.139
minist-0.132
interstitial-0.131
 Beir-0.120
Token years
Token ID812
Feature activation+1.29e-01

Pos logit contributions
cles+0.301
 unrelated+0.295
minist+0.280
interstitial+0.278
 Beir+0.255
Neg logit contributions
ertodd-0.313
isconsin-0.302
alsa-0.295
 Taj-0.284
urdue-0.284
TokenFrank
Token ID17439
Feature activation+1.96e-01

Pos logit contributions
cles+0.326
 unrelated+0.322
minist+0.302
interstitial+0.302
 Beir+0.281
Neg logit contributions
ertodd-0.344
isconsin-0.332
alsa-0.326
framework-0.314
 Taj-0.313
Tokeniv
Token ID452
Feature activation+6.57e-01

Pos logit contributions
ertodd+0.346
isconsin+0.333
alsa+0.327
urdue+0.317
 Taj+0.314
Neg logit contributions
cles-0.377
 unrelated-0.369
minist-0.347
interstitial-0.346
 Beir-0.331
Tokensk
Token ID8135
Feature activation+5.09e-01

Pos logit contributions
ertodd+1.358
isconsin+1.323
alsa+1.283
framework+1.252
urdue+1.245
Neg logit contributions
cles-1.068
 unrelated-1.059
minist-0.992
interstitial-0.989
 Beir-0.895
Token.
Token ID13
Feature activation+1.96e-01

Pos logit contributions
ertodd+0.959
isconsin+0.933
alsa+0.900
urdue+0.880
framework+0.879
Neg logit contributions
cles-0.913
 unrelated-0.901
interstitial-0.851
minist-0.844
 Beir-0.777
Token<|endoftext|>
Token ID50256
Feature activation-6.14e-01

Pos logit contributions
ertodd+0.344
isconsin+0.331
alsa+0.320
 Taj+0.313
framework+0.312
Neg logit contributions
cles-0.384
 unrelated-0.379
interstitial-0.359
minist-0.358
leans-0.330
Token[
Token ID58
Feature activation+1.38e+00

Pos logit contributions
cles+1.093
 unrelated+1.087
minist+1.017
interstitial+1.002
 Beir+0.935
Neg logit contributions
ertodd-1.187
isconsin-1.146
alsa-1.119
framework-1.079
urdue-1.073
TokenEx
Token ID3109
Feature activation-7.94e-01

Pos logit contributions
ertodd+2.756
isconsin+2.679
alsa+2.661
framework+2.570
 Taj+2.523
Neg logit contributions
cles-2.297
 unrelated-2.279
minist-2.155
interstitial-2.069
 Beir-1.981
Tokenclusive
Token ID5731
Feature activation+1.13e+00

Pos logit contributions
cles+1.635
 unrelated+1.625
minist+1.539
interstitial+1.520
 Beir+1.426
Neg logit contributions
ertodd-1.317
isconsin-1.258
alsa-1.221
urdue-1.167
framework-1.167
Token]
Token ID60
Feature activation-6.20e-02

Pos logit contributions
ertodd+1.856
isconsin+1.792
alsa+1.773
 Taj+1.698
framework+1.674
Neg logit contributions
cles-2.300
 unrelated-2.249
minist-2.173
interstitial-2.129
 Beir-1.973
Token Best
Token ID6705
Feature activation+4.77e-01

Pos logit contributions
cles+0.120
 unrelated+0.119
minist+0.112
interstitial+0.111
 Beir+0.103
Neg logit contributions
ertodd-0.110
isconsin-0.106
alsa-0.103
framework-0.099
 Taj-0.099
Token Buy
Token ID11763
Feature activation-3.59e-01

Pos logit contributions
ertodd+0.855
isconsin+0.819
alsa+0.802
 Taj+0.770
framework+0.769
Neg logit contributions
cles-0.906
 unrelated-0.895
minist-0.854
interstitial-0.839
 Beir-0.782
Token life
Token ID1204
Feature activation+7.56e-01

Pos logit contributions
ertodd+0.097
isconsin+0.094
alsa+0.091
framework+0.088
urdue+0.087
Neg logit contributions
cles-0.097
 unrelated-0.095
minist-0.090
interstitial-0.090
 Beir-0.083
Token stories
Token ID3923
Feature activation-4.75e-01

Pos logit contributions
ertodd+1.419
isconsin+1.364
alsa+1.344
framework+1.294
 Taj+1.287
Neg logit contributions
cles-1.348
 unrelated-1.331
minist-1.286
interstitial-1.278
 Beir-1.183
Token of
Token ID286
Feature activation+3.16e-02

Pos logit contributions
cles+0.833
 unrelated+0.824
minist+0.779
interstitial+0.773
 Beir+0.711
Neg logit contributions
ertodd-0.920
isconsin-0.891
alsa-0.872
framework-0.839
 Taj-0.836
Token whales
Token ID24635
Feature activation+1.61e+00

Pos logit contributions
ertodd+0.056
isconsin+0.054
alsa+0.053
framework+0.051
 Taj+0.051
Neg logit contributions
cles-0.061
 unrelated-0.060
minist-0.057
interstitial-0.056
 Beir-0.052
Token and
Token ID290
Feature activation+5.39e-01

Pos logit contributions
ertodd+2.920
isconsin+2.825
alsa+2.806
 Taj+2.672
urdue+2.654
Neg logit contributions
cles-2.899
 unrelated-2.817
minist-2.758
interstitial-2.745
 Beir-2.533
Token dolphins
Token ID36798
Feature activation+1.49e+00

Pos logit contributions
ertodd+0.575
isconsin+0.538
alsa+0.513
framework+0.477
urdue+0.475
Neg logit contributions
cles-1.424
 unrelated-1.414
minist-1.359
interstitial-1.346
 Beir-1.282
Token.
Token ID13
Feature activation+1.74e-01

Pos logit contributions
ertodd+2.631
isconsin+2.543
alsa+2.519
urdue+2.396
 Taj+2.395
Neg logit contributions
cles-2.742
 unrelated-2.667
interstitial-2.619
minist-2.616
 Beir-2.413
Token It
Token ID632
Feature activation-1.49e-01

Pos logit contributions
ertodd+0.309
isconsin+0.297
alsa+0.288
framework+0.277
urdue+0.276
Neg logit contributions
cles-0.339
 unrelated-0.336
minist-0.318
interstitial-0.314
 Beir-0.293
Token also
Token ID635
Feature activation+1.36e-01

Pos logit contributions
cles+0.271
 unrelated+0.268
minist+0.254
interstitial+0.252
 Beir+0.232
Neg logit contributions
ertodd-0.279
isconsin-0.270
alsa-0.262
urdue-0.253
framework-0.252
Token scares
Token ID44462
Feature activation-8.48e-01

Pos logit contributions
ertodd+0.228
isconsin+0.220
alsa+0.213
urdue+0.205
framework+0.205
Neg logit contributions
cles-0.272
 unrelated-0.269
minist-0.257
interstitial-0.256
 Beir-0.238
Token me
Token ID502
Feature activation-5.21e-01

Pos logit contributions
 unrelated+1.589
cles+1.583
minist+1.490
interstitial+1.451
 Beir+1.372
Neg logit contributions
ertodd-1.561
isconsin-1.495
alsa-1.452
framework-1.403
urdue-1.399
Token himself
Token ID2241
Feature activation+1.48e-01

Pos logit contributions
ertodd+0.259
isconsin+0.250
alsa+0.243
framework+0.233
urdue+0.233
Neg logit contributions
cles-0.272
 unrelated-0.269
minist-0.254
interstitial-0.251
 Beir-0.234
Token to
Token ID284
Feature activation+4.20e-01

Pos logit contributions
ertodd+0.297
isconsin+0.287
alsa+0.280
 Taj+0.270
urdue+0.270
Neg logit contributions
cles-0.251
 unrelated-0.249
minist-0.234
interstitial-0.232
 Beir-0.213
Token use
Token ID779
Feature activation+1.28e-01

Pos logit contributions
ertodd+0.713
isconsin+0.676
alsa+0.667
framework+0.638
 Taj+0.638
Neg logit contributions
cles-0.845
 unrelated-0.831
minist-0.795
interstitial-0.794
 Beir-0.734
Token or
Token ID393
Feature activation-3.65e-01

Pos logit contributions
ertodd+0.244
isconsin+0.236
alsa+0.230
framework+0.221
urdue+0.221
Neg logit contributions
cles-0.230
 unrelated-0.227
minist-0.214
interstitial-0.212
 Beir-0.196
Token how
Token ID703
Feature activation-3.20e-01

Pos logit contributions
cles+0.718
 unrelated+0.712
minist+0.674
interstitial+0.667
 Beir+0.622
Neg logit contributions
ertodd-0.638
isconsin-0.613
alsa-0.596
framework-0.572
urdue-0.570
Token to
Token ID284
Feature activation+3.25e-01

Pos logit contributions
cles+0.608
 unrelated+0.603
minist+0.570
interstitial+0.563
 Beir+0.524
Neg logit contributions
ertodd-0.579
isconsin-0.557
alsa-0.542
framework-0.520
urdue-0.519
Token call
Token ID869
Feature activation-3.73e-01

Pos logit contributions
ertodd+0.579
isconsin+0.553
alsa+0.542
framework+0.521
urdue+0.519
Neg logit contributions
cles-0.627
 unrelated-0.617
minist-0.588
interstitial-0.586
 Beir-0.542
Token another
Token ID1194
Feature activation-3.28e-01

Pos logit contributions
cles+0.653
 unrelated+0.646
minist+0.607
interstitial+0.601
 Beir+0.555
Neg logit contributions
ertodd-0.731
isconsin-0.706
alsa-0.688
framework-0.663
urdue-0.662
Token person
Token ID1048
Feature activation-1.12e-01

Pos logit contributions
cles+0.609
 unrelated+0.604
minist+0.569
interstitial+0.561
 Beir+0.522
Neg logit contributions
ertodd-0.610
isconsin-0.587
alsa-0.571
framework-0.549
urdue-0.548
Token out
Token ID503
Feature activation-2.52e-01

Pos logit contributions
cles+0.196
 unrelated+0.194
minist+0.183
interstitial+0.182
 Beir+0.168
Neg logit contributions
ertodd-0.217
isconsin-0.210
alsa-0.205
framework-0.197
urdue-0.197
Token.
Token ID13
Feature activation+3.14e-02

Pos logit contributions
cles+0.436
 unrelated+0.433
minist+0.404
interstitial+0.397
 Beir+0.369
Neg logit contributions
ertodd-0.503
isconsin-0.485
alsa-0.472
urdue-0.455
framework-0.455
Token over
Token ID625
Feature activation+2.20e-01

Pos logit contributions
cles+0.035
 unrelated+0.034
minist+0.032
interstitial+0.032
 Beir+0.028
Neg logit contributions
ertodd-0.066
isconsin-0.065
alsa-0.063
urdue-0.061
 Taj-0.061
Token,
Token ID11
Feature activation+3.78e-02

Pos logit contributions
ertodd+0.412
isconsin+0.400
alsa+0.387
urdue+0.373
 Taj+0.373
Neg logit contributions
cles-0.404
 unrelated-0.397
minist-0.375
interstitial-0.372
 Beir-0.345
Token things
Token ID1243
Feature activation-6.33e-01

Pos logit contributions
ertodd+0.070
isconsin+0.067
alsa+0.065
 Taj+0.063
framework+0.063
Neg logit contributions
cles-0.071
 unrelated-0.069
minist-0.066
interstitial-0.065
 Beir-0.060
Token that
Token ID326
Feature activation-1.32e-01

Pos logit contributions
cles+1.139
 unrelated+1.129
minist+1.061
interstitial+1.047
 Beir+0.971
Neg logit contributions
ertodd-1.213
isconsin-1.169
alsa-1.139
framework-1.096
urdue-1.095
Token were
Token ID547
Feature activation-3.73e-01

Pos logit contributions
cles+0.239
 unrelated+0.234
minist+0.223
interstitial+0.220
 Beir+0.202
Neg logit contributions
ertodd-0.249
isconsin-0.240
alsa-0.235
urdue-0.226
framework-0.225
Token im
Token ID545
Feature activation+4.60e-01

Pos logit contributions
cles+0.626
 unrelated+0.611
minist+0.578
interstitial+0.575
 Beir+0.524
Neg logit contributions
ertodd-0.755
isconsin-0.735
alsa-0.718
framework-0.693
 Taj-0.693
Tokenmin
Token ID1084
Feature activation-7.84e-02

Pos logit contributions
ertodd+0.762
isconsin+0.744
alsa+0.730
framework+0.705
urdue+0.702
Neg logit contributions
cles-0.921
 unrelated-0.907
interstitial-0.851
minist-0.846
 Beir-0.801
Tokenently
Token ID1473
Feature activation-5.70e-01

Pos logit contributions
cles+0.119
 unrelated+0.118
minist+0.109
interstitial+0.108
 Beir+0.099
Neg logit contributions
ertodd-0.173
isconsin-0.167
alsa-0.163
cipled-0.158
urdue-0.158
Token know
Token ID760
Feature activation-7.37e-01

Pos logit contributions
cles+0.963
 unrelated+0.948
minist+0.893
interstitial+0.880
 Beir+0.810
Neg logit contributions
ertodd-1.152
isconsin-1.117
alsa-1.090
framework-1.053
urdue-1.051
Tokenable
Token ID540
Feature activation+2.23e-01

Pos logit contributions
cles+1.316
 unrelated+1.308
minist+1.225
interstitial+1.206
 Beir+1.118
Neg logit contributions
ertodd-1.422
isconsin-1.370
alsa-1.333
framework-1.285
urdue-1.283
Token were
Token ID547
Feature activation-2.74e-01

Pos logit contributions
ertodd+0.430
isconsin+0.417
alsa+0.407
 Taj+0.392
urdue+0.392
Neg logit contributions
cles-0.391
 unrelated-0.383
minist-0.364
interstitial-0.364
 Beir-0.333
Token him
Token ID683
Feature activation+4.10e-01

Pos logit contributions
ertodd+0.318
isconsin+0.306
alsa+0.298
urdue+0.285
framework+0.285
Neg logit contributions
cles-0.352
 unrelated-0.349
minist-0.330
interstitial-0.328
 Beir-0.304
Token for
Token ID329
Feature activation-1.73e-01

Pos logit contributions
ertodd+0.789
isconsin+0.761
alsa+0.742
urdue+0.714
framework+0.713
Neg logit contributions
cles-0.732
 unrelated-0.724
minist-0.682
interstitial-0.678
 Beir-0.625
Token you
Token ID345
Feature activation-7.81e-02

Pos logit contributions
cles+0.325
 unrelated+0.323
minist+0.304
interstitial+0.299
 Beir+0.280
Neg logit contributions
ertodd-0.317
isconsin-0.305
alsa-0.296
framework-0.285
urdue-0.284
Token.
Token ID13
Feature activation+6.17e-02

Pos logit contributions
cles+0.141
 unrelated+0.140
minist+0.132
interstitial+0.130
 Beir+0.121
Neg logit contributions
ertodd-0.149
isconsin-0.143
alsa-0.140
framework-0.134
urdue-0.134
Token<|endoftext|>
Token ID50256
Feature activation-7.45e-01

Pos logit contributions
ertodd+0.107
isconsin+0.102
alsa+0.099
framework+0.095
urdue+0.095
Neg logit contributions
cles-0.123
 unrelated-0.122
minist-0.115
interstitial-0.114
 Beir-0.106
TokenTan
Token ID45557
Feature activation+3.82e-02

Pos logit contributions
cles+1.327
 unrelated+1.318
minist+1.235
interstitial+1.217
 Beir+1.132
Neg logit contributions
ertodd-1.441
isconsin-1.390
alsa-1.355
framework-1.305
urdue-1.302
Tokenaka
Token ID8130
Feature activation+4.20e-01

Pos logit contributions
ertodd+0.079
isconsin+0.076
alsa+0.075
framework+0.072
 Taj+0.072
Neg logit contributions
cles-0.062
 unrelated-0.062
minist-0.058
interstitial-0.057
 Beir-0.053
Token's
Token ID338
Feature activation-4.60e-01

Pos logit contributions
ertodd+0.771
isconsin+0.743
alsa+0.726
 Taj+0.706
urdue+0.699
Neg logit contributions
cles-0.782
 unrelated-0.773
minist-0.736
interstitial-0.726
cle-0.667
Token artwork
Token ID16257
Feature activation+3.34e-01

Pos logit contributions
cles+0.869
 unrelated+0.863
minist+0.813
interstitial+0.803
 Beir+0.748
Neg logit contributions
ertodd-0.839
isconsin-0.807
alsa-0.785
framework-0.754
urdue-0.753
Token is
Token ID318
Feature activation+3.74e-02

Pos logit contributions
ertodd+0.618
isconsin+0.596
alsa+0.585
framework+0.565
 Taj+0.562
Neg logit contributions
cles-0.610
 unrelated-0.603
minist-0.572
interstitial-0.571
 Beir-0.524
Token,
Token ID11
Feature activation+1.58e-02

Pos logit contributions
ertodd+0.072
isconsin+0.070
alsa+0.068
framework+0.065
urdue+0.065
Neg logit contributions
cles-0.067
 unrelated-0.066
minist-0.062
interstitial-0.062
 Beir-0.057
Token
Token ID198
Feature activation+1.21e-01

Pos logit contributions
ertodd+0.529
isconsin+0.511
alsa+0.496
framework+0.479
 Taj+0.476
Neg logit contributions
cles-0.598
 unrelated-0.593
minist-0.562
interstitial-0.558
 Beir-0.515
Token
Token ID198
Feature activation+8.20e-02

Pos logit contributions
ertodd+0.230
isconsin+0.220
alsa+0.214
urdue+0.206
cipled+0.206
Neg logit contributions
cles-0.223
 unrelated-0.222
minist-0.207
interstitial-0.200
cle-0.193
TokenI
Token ID40
Feature activation+5.84e-02

Pos logit contributions
ertodd+0.173
isconsin+0.169
alsa+0.166
framework+0.162
urdue+0.159
Neg logit contributions
cles-0.129
 unrelated-0.129
minist-0.120
interstitial-0.119
 Beir-0.110
Token smile
Token ID8212
Feature activation+3.46e-01

Pos logit contributions
ertodd+0.103
isconsin+0.099
alsa+0.096
framework+0.092
urdue+0.092
Neg logit contributions
cles-0.113
 unrelated-0.112
minist-0.107
interstitial-0.106
 Beir-0.099
Token.
Token ID13
Feature activation+2.23e-01

Pos logit contributions
ertodd+0.664
isconsin+0.643
alsa+0.623
framework+0.607
urdue+0.603
Neg logit contributions
cles-0.615
 unrelated-0.599
interstitial-0.581
minist-0.573
 Beir-0.525
Token "
Token ID366
Feature activation+4.04e-01

Pos logit contributions
ertodd+0.455
isconsin+0.443
alsa+0.431
framework+0.419
 Taj+0.418
Neg logit contributions
cles-0.372
 unrelated-0.369
minist-0.346
interstitial-0.346
 Beir-0.311
TokenNow
Token ID3844
Feature activation+5.25e-02

Pos logit contributions
ertodd+0.785
isconsin+0.766
alsa+0.748
framework+0.731
 Taj+0.716
Neg logit contributions
cles-0.703
 unrelated-0.702
interstitial-0.657
minist-0.656
 Beir-0.604
Token,
Token ID11
Feature activation+4.52e-01

Pos logit contributions
ertodd+0.096
isconsin+0.093
alsa+0.090
framework+0.087
urdue+0.087
Neg logit contributions
cles-0.098
 unrelated-0.097
minist-0.092
interstitial-0.091
 Beir-0.085
Token I
Token ID314
Feature activation+1.77e-01

Pos logit contributions
ertodd+0.810
isconsin+0.786
alsa+0.766
 Taj+0.737
framework+0.735
Neg logit contributions
cles-0.859
 unrelated-0.843
minist-0.807
interstitial-0.804
 Beir-0.739
Token need
Token ID761
Feature activation+4.44e-02

Pos logit contributions
ertodd+0.312
isconsin+0.298
alsa+0.294
 Taj+0.280
urdue+0.280
Neg logit contributions
cles-0.339
 unrelated-0.335
interstitial-0.321
minist-0.320
 Beir-0.295
Token to
Token ID284
Feature activation+1.73e-02

Pos logit contributions
ertodd+0.078
isconsin+0.075
alsa+0.073
framework+0.070
urdue+0.070
Neg logit contributions
cles-0.086
 unrelated-0.085
minist-0.081
interstitial-0.080
 Beir-0.075
Token she
Token ID673
Feature activation-4.74e-01

Pos logit contributions
cles+0.076
 unrelated+0.075
minist+0.071
interstitial+0.070
 Beir+0.065
Neg logit contributions
ertodd-0.079
isconsin-0.077
alsa-0.074
 Taj-0.072
framework-0.072
Token can
Token ID460
Feature activation-2.20e-01

Pos logit contributions
cles+0.821
 unrelated+0.815
minist+0.760
interstitial+0.745
 Beir+0.694
Neg logit contributions
ertodd-0.941
isconsin-0.906
alsa-0.885
framework-0.852
urdue-0.851
Token
Token ID447
Feature activation+7.32e-02

Pos logit contributions
cles+0.381
 unrelated+0.377
minist+0.354
interstitial+0.350
 Beir+0.323
Neg logit contributions
ertodd-0.435
isconsin-0.420
alsa-0.410
framework-0.395
urdue-0.395
Token
Token ID247
Feature activation-5.90e-02

Pos logit contributions
ertodd+0.122
isconsin+0.117
alsa+0.114
framework+0.109
urdue+0.108
Neg logit contributions
cles-0.149
 unrelated-0.149
minist-0.141
interstitial-0.139
 Beir-0.131
Tokent
Token ID83
Feature activation+1.47e-01

Pos logit contributions
cles+0.108
 unrelated+0.107
minist+0.101
interstitial+0.100
 Beir+0.093
Neg logit contributions
ertodd-0.111
isconsin-0.107
alsa-0.104
framework-0.100
urdue-0.100
Token take
Token ID1011
Feature activation+6.19e-01

Pos logit contributions
ertodd+0.252
isconsin+0.242
alsa+0.235
framework+0.225
urdue+0.224
Neg logit contributions
cles-0.294
 unrelated-0.291
minist-0.276
interstitial-0.274
 Beir-0.255
Token a
Token ID257
Feature activation-8.69e-02

Pos logit contributions
ertodd+1.120
isconsin+1.108
alsa+1.063
 Taj+1.046
framework+1.030
Neg logit contributions
cles-1.142
 unrelated-1.119
minist-1.073
interstitial-1.068
leans-0.979
Token public
Token ID1171
Feature activation-3.61e-01

Pos logit contributions
cles+0.161
 unrelated+0.160
minist+0.151
interstitial+0.149
 Beir+0.139
Neg logit contributions
ertodd-0.161
isconsin-0.155
alsa-0.151
framework-0.145
urdue-0.145
Token stance
Token ID12046
Feature activation-7.18e-02

Pos logit contributions
cles+0.691
 unrelated+0.684
minist+0.646
interstitial+0.639
 Beir+0.596
Neg logit contributions
ertodd-0.648
isconsin-0.625
alsa-0.607
framework-0.585
urdue-0.584
Token on
Token ID319
Feature activation-1.87e-01

Pos logit contributions
cles+0.125
 unrelated+0.123
minist+0.117
interstitial+0.116
 Beir+0.107
Neg logit contributions
ertodd-0.140
isconsin-0.136
alsa-0.132
framework-0.128
urdue-0.128
Token any
Token ID597
Feature activation-3.99e-01

Pos logit contributions
cles+0.343
 unrelated+0.338
minist+0.320
interstitial+0.317
 Beir+0.294
Neg logit contributions
ertodd-0.348
isconsin-0.338
alsa-0.326
framework-0.315
 Taj-0.314
Token begin
Token ID2221
Feature activation+3.81e-02

Pos logit contributions
cles+0.515
 unrelated+0.509
minist+0.485
interstitial+0.481
 Beir+0.446
Neg logit contributions
ertodd-0.484
isconsin-0.471
alsa-0.458
framework-0.440
 Taj-0.440
Token the
Token ID262
Feature activation-1.80e-01

Pos logit contributions
ertodd+0.075
isconsin+0.073
alsa+0.071
 Taj+0.069
framework+0.069
Neg logit contributions
cles-0.065
 unrelated-0.065
minist-0.061
interstitial-0.060
 Beir-0.056
Token gallery
Token ID15604
Feature activation-4.49e-01

Pos logit contributions
cles+0.368
 unrelated+0.365
minist+0.346
interstitial+0.342
 Beir+0.320
Neg logit contributions
ertodd-0.301
isconsin-0.289
alsa-0.280
framework-0.268
urdue-0.268
Token)
Token ID8
Feature activation-3.59e-01

Pos logit contributions
cles+0.731
 unrelated+0.724
minist+0.676
interstitial+0.666
 Beir+0.613
Neg logit contributions
ertodd-0.937
isconsin-0.906
alsa-0.885
framework-0.855
urdue-0.854
Token
Token ID198
Feature activation-7.36e-02

Pos logit contributions
cles+0.675
 unrelated+0.670
minist+0.631
interstitial+0.622
 Beir+0.581
Neg logit contributions
ertodd-0.660
isconsin-0.635
alsa-0.617
framework-0.593
urdue-0.593
Token
Token ID198
Feature activation-7.43e-02

Pos logit contributions
cles+0.134
 unrelated+0.134
minist+0.125
interstitial+0.120
cle+0.116
Neg logit contributions
ertodd-0.141
isconsin-0.134
alsa-0.131
cipled-0.126
urdue-0.126
TokenYou
Token ID1639
Feature activation-1.63e-01

Pos logit contributions
cles+0.137
 unrelated+0.137
minist+0.128
interstitial+0.127
 Beir+0.119
Neg logit contributions
ertodd-0.137
isconsin-0.133
alsa-0.130
framework-0.125
urdue-0.124
Token can
Token ID460
Feature activation-9.11e-02

Pos logit contributions
cles+0.291
 unrelated+0.289
minist+0.272
interstitial+0.270
 Beir+0.249
Neg logit contributions
ertodd-0.313
isconsin-0.303
alsa-0.295
 Taj-0.284
framework-0.283
Token also
Token ID635
Feature activation+3.22e-01

Pos logit contributions
cles+0.175
 unrelated+0.173
interstitial+0.164
minist+0.164
 Beir+0.151
Neg logit contributions
ertodd-0.161
isconsin-0.155
alsa-0.152
framework-0.147
 Taj-0.146
Token check
Token ID2198
Feature activation-2.30e-01

Pos logit contributions
ertodd+0.552
isconsin+0.529
alsa+0.524
 Taj+0.505
framework+0.504
Neg logit contributions
cles-0.627
 unrelated-0.618
interstitial-0.594
minist-0.593
 Beir-0.546
Token out
Token ID503
Feature activation+2.46e-02

Pos logit contributions
cles+0.319
 unrelated+0.315
minist+0.291
interstitial+0.286
 Beir+0.258
Neg logit contributions
ertodd-0.534
isconsin-0.518
alsa-0.508
framework-0.492
urdue-0.491
TokenThis
Token ID1212
Feature activation+5.57e-01

Pos logit contributions
ertodd+0.615
isconsin+0.592
alsa+0.574
framework+0.555
 Taj+0.551
Neg logit contributions
cles-0.724
 unrelated-0.717
minist-0.678
interstitial-0.671
 Beir-0.627
Token is
Token ID318
Feature activation+2.40e-01

Pos logit contributions
ertodd+0.998
isconsin+0.960
alsa+0.935
framework+0.899
 Taj+0.898
Neg logit contributions
cles-1.069
 unrelated-1.051
minist-0.998
interstitial-0.986
 Beir-0.917
Token the
Token ID262
Feature activation+1.42e-01

Pos logit contributions
ertodd+0.448
isconsin+0.433
alsa+0.424
 Taj+0.410
urdue+0.406
Neg logit contributions
cles-0.440
 unrelated-0.429
minist-0.409
interstitial-0.407
 Beir-0.374
Token nightmare
Token ID17123
Feature activation-7.65e-02

Pos logit contributions
ertodd+0.258
isconsin+0.249
alsa+0.242
framework+0.233
urdue+0.232
Neg logit contributions
cles-0.267
 unrelated-0.264
minist-0.249
interstitial-0.247
 Beir-0.229
Token for
Token ID329
Feature activation-2.57e-01

Pos logit contributions
cles+0.144
 unrelated+0.142
minist+0.134
interstitial+0.134
leans+0.123
Neg logit contributions
ertodd-0.139
isconsin-0.134
alsa-0.131
 Taj-0.126
framework-0.126
Token the
Token ID262
Feature activation-1.36e-02

Pos logit contributions
cles+0.489
 unrelated+0.486
minist+0.457
interstitial+0.450
 Beir+0.422
Neg logit contributions
ertodd-0.467
isconsin-0.448
alsa-0.436
framework-0.418
urdue-0.418
Token Syrian
Token ID6318
Feature activation+2.29e-01

Pos logit contributions
cles+0.026
 unrelated+0.026
minist+0.025
interstitial+0.024
 Beir+0.023
Neg logit contributions
ertodd-0.024
isconsin-0.023
alsa-0.023
framework-0.022
urdue-0.022
Token regime
Token ID7142
Feature activation+3.48e-01

Pos logit contributions
ertodd+0.398
isconsin+0.386
alsa+0.380
 Taj+0.365
framework+0.363
Neg logit contributions
cles-0.443
 unrelated-0.437
interstitial-0.415
minist-0.413
 Beir-0.384
Token,
Token ID11
Feature activation-2.87e-02

Pos logit contributions
ertodd+0.648
isconsin+0.628
alsa+0.613
 Taj+0.590
framework+0.590
Neg logit contributions
cles-0.633
 unrelated-0.625
minist-0.591
interstitial-0.588
 Beir-0.542
Token to
Token ID284
Feature activation-5.95e-02

Pos logit contributions
cles+0.052
 unrelated+0.051
minist+0.048
interstitial+0.048
 Beir+0.044
Neg logit contributions
ertodd-0.055
isconsin-0.053
alsa-0.052
framework-0.050
urdue-0.049
Token have
Token ID423
Feature activation-2.44e-01

Pos logit contributions
cles+0.114
 unrelated+0.113
minist+0.106
interstitial+0.105
 Beir+0.098
Neg logit contributions
ertodd-0.107
isconsin-0.103
alsa-0.100
framework-0.096
urdue-0.096
TokenThis
Token ID1212
Feature activation+4.62e-01

Pos logit contributions
ertodd+0.348
isconsin+0.338
alsa+0.331
framework+0.318
urdue+0.313
Neg logit contributions
 unrelated-0.361
cles-0.361
minist-0.337
interstitial-0.335
 Beir-0.316
Token yields
Token ID19299
Feature activation+3.29e-01

Pos logit contributions
ertodd+0.820
isconsin+0.793
alsa+0.776
framework+0.745
 Taj+0.744
Neg logit contributions
cles-0.874
 unrelated-0.864
interstitial-0.826
minist-0.826
 Beir-0.757
Token
Token ID198
Feature activation+1.53e-01

Pos logit contributions
ertodd+0.569
isconsin+0.545
alsa+0.534
framework+0.509
 Taj+0.508
Neg logit contributions
cles-0.647
 unrelated-0.639
minist-0.609
interstitial-0.604
 Beir-0.561
Token
Token ID198
Feature activation+9.41e-02

Pos logit contributions
ertodd+0.290
isconsin+0.278
alsa+0.270
urdue+0.260
cipled+0.259
Neg logit contributions
cles-0.282
 unrelated-0.281
minist-0.262
interstitial-0.253
cle-0.243
Token{{
Token ID27007
Feature activation+2.07e-01

Pos logit contributions
ertodd+0.161
isconsin+0.155
alsa+0.152
framework+0.145
urdue+0.143
Neg logit contributions
cles-0.187
 unrelated-0.187
minist-0.176
interstitial-0.174
 Beir-0.164
Token1
Token ID16
Feature activation-1.10e-01

Pos logit contributions
ertodd+0.431
isconsin+0.417
alsa+0.408
framework+0.395
urdue+0.392
Neg logit contributions
cles-0.334
 unrelated-0.332
minist-0.310
interstitial-0.304
 Beir-0.283
Token,
Token ID11
Feature activation-4.13e-02

Pos logit contributions
cles+0.199
 unrelated+0.197
minist+0.185
interstitial+0.182
 Beir+0.170
Neg logit contributions
ertodd-0.211
isconsin-0.202
alsa-0.197
framework-0.190
urdue-0.190
Token 6
Token ID718
Feature activation+2.75e-01

Pos logit contributions
cles+0.073
 unrelated+0.072
minist+0.068
interstitial+0.067
 Beir+0.062
Neg logit contributions
ertodd-0.080
isconsin-0.078
alsa-0.076
framework-0.073
urdue-0.073
Token}
Token ID92
Feature activation-1.29e-02

Pos logit contributions
ertodd+0.323
isconsin+0.304
alsa+0.291
framework+0.272
urdue+0.272
Neg logit contributions
cles-0.699
 unrelated-0.695
minist-0.665
interstitial-0.659
 Beir-0.627
Token <
Token ID1279
Feature activation+9.45e-02

Pos logit contributions
cles+0.026
 unrelated+0.026
minist+0.025
interstitial+0.024
 Beir+0.023
Neg logit contributions
ertodd-0.022
isconsin-0.021
alsa-0.020
framework-0.019
urdue-0.019
Token->
Token ID3784
Feature activation-1.33e-01

Pos logit contributions
ertodd+0.135
isconsin+0.128
alsa+0.124
framework+0.117
urdue+0.117
Neg logit contributions
cles-0.216
 unrelated-0.215
minist-0.205
interstitial-0.203
 Beir-0.192
Token could
Token ID714
Feature activation-3.72e-01

Pos logit contributions
cles+0.389
 unrelated+0.386
minist+0.364
interstitial+0.362
 Beir+0.335
Neg logit contributions
ertodd-0.382
isconsin-0.368
alsa-0.359
framework-0.344
urdue-0.344
Token only
Token ID691
Feature activation+3.24e-01

Pos logit contributions
cles+0.722
 unrelated+0.716
minist+0.680
interstitial+0.676
 Beir+0.628
Neg logit contributions
ertodd-0.653
isconsin-0.628
alsa-0.614
framework-0.590
urdue-0.587
Token draw
Token ID3197
Feature activation-2.02e+00

Pos logit contributions
ertodd+0.511
isconsin+0.489
alsa+0.481
framework+0.462
urdue+0.456
Neg logit contributions
cles-0.679
 unrelated-0.671
interstitial-0.644
minist-0.642
 Beir-0.596
Token lines
Token ID3951
Feature activation-3.31e-01

Pos logit contributions
 unrelated+3.679
cles+3.662
minist+3.414
interstitial+3.289
 Beir+3.128
Neg logit contributions
ertodd-3.895
isconsin-3.688
alsa-3.559
framework-3.450
urdue-3.448
Token the
Token ID262
Feature activation-1.66e-01

Pos logit contributions
cles+0.562
 unrelated+0.555
minist+0.523
interstitial+0.519
 Beir+0.475
Neg logit contributions
ertodd-0.662
isconsin-0.642
alsa-0.627
framework-0.604
urdue-0.603
Token width
Token ID9647
Feature activation-4.98e-01

Pos logit contributions
cles+0.318
 unrelated+0.316
minist+0.298
interstitial+0.295
 Beir+0.275
Neg logit contributions
ertodd-0.296
isconsin-0.286
alsa-0.278
framework-0.267
urdue-0.266
Token of
Token ID286
Feature activation+2.43e-02

Pos logit contributions
cles+0.845
 unrelated+0.837
minist+0.783
interstitial+0.775
 Beir+0.713
Neg logit contributions
ertodd-1.003
isconsin-0.971
alsa-0.947
framework-0.913
urdue-0.912
Token pixels
Token ID17848
Feature activation-8.45e-01

Pos logit contributions
ertodd+0.043
isconsin+0.041
alsa+0.040
urdue+0.039
framework+0.039
Neg logit contributions
cles-0.047
 unrelated-0.047
minist-0.044
interstitial-0.044
 Beir-0.041
Token but
Token ID475
Feature activation-6.47e-02

Pos logit contributions
cles+1.486
 unrelated+1.478
minist+1.381
interstitial+1.354
 Beir+1.261
Neg logit contributions
ertodd-1.658
isconsin-1.595
alsa-1.552
framework-1.497
urdue-1.494
Token you
Token ID345
Feature activation+3.07e-01

Pos logit contributions
cles+0.118
 unrelated+0.116
minist+0.110
interstitial+0.110
 Beir+0.101
Neg logit contributions
ertodd-0.121
isconsin-0.118
alsa-0.115
urdue-0.110
framework-0.110
Token get
Token ID651
Feature activation+5.39e-01

Pos logit contributions
ertodd+0.570
isconsin+0.550
alsa+0.541
 Taj+0.521
framework+0.521
Neg logit contributions
cles-0.556
 unrelated-0.547
interstitial-0.526
minist-0.519
 Beir-0.480
Token acquired
Token ID9477
Feature activation+1.99e-01

Pos logit contributions
ertodd+0.463
isconsin+0.448
alsa+0.439
 Taj+0.427
urdue+0.427
Neg logit contributions
cles-0.437
 unrelated-0.431
minist-0.415
interstitial-0.413
 Beir-0.375
Token Pocket
Token ID27290
Feature activation-6.06e-01

Pos logit contributions
ertodd+0.360
isconsin+0.346
alsa+0.341
 Taj+0.330
framework+0.327
Neg logit contributions
cles-0.375
 unrelated-0.365
minist-0.351
interstitial-0.346
 Beir-0.319
Token,
Token ID11
Feature activation-3.84e-02

Pos logit contributions
cles+1.104
 unrelated+1.096
minist+1.032
interstitial+1.018
 Beir+0.945
Neg logit contributions
ertodd-1.146
isconsin-1.104
alsa-1.076
framework-1.037
urdue-1.034
Token a
Token ID257
Feature activation+1.85e-01

Pos logit contributions
cles+0.076
 unrelated+0.075
minist+0.072
interstitial+0.071
 Beir+0.066
Neg logit contributions
ertodd-0.066
isconsin-0.064
alsa-0.062
framework-0.060
urdue-0.060
Token service
Token ID2139
Feature activation+4.33e-01

Pos logit contributions
ertodd+0.335
isconsin+0.321
alsa+0.315
framework+0.304
urdue+0.303
Neg logit contributions
cles-0.351
 unrelated-0.344
minist-0.329
interstitial-0.324
 Beir-0.300
Token that
Token ID326
Feature activation-2.20e-01

Pos logit contributions
ertodd+0.784
isconsin+0.750
alsa+0.734
framework+0.711
 Taj+0.711
Neg logit contributions
cles-0.816
 unrelated-0.796
minist-0.764
interstitial-0.761
 Beir-0.697
Token lets
Token ID8781
Feature activation+1.80e-01

Pos logit contributions
cles+0.443
 unrelated+0.439
minist+0.418
interstitial+0.414
 Beir+0.386
Neg logit contributions
ertodd-0.371
isconsin-0.356
alsa-0.346
urdue-0.332
framework-0.332
Token you
Token ID345
Feature activation+1.11e-01

Pos logit contributions
ertodd+0.336
isconsin+0.324
alsa+0.317
 Taj+0.310
urdue+0.308
Neg logit contributions
cles-0.327
 unrelated-0.315
interstitial-0.304
minist-0.304
 Beir-0.280
Token save
Token ID3613
Feature activation+3.48e-01

Pos logit contributions
ertodd+0.196
isconsin+0.188
alsa+0.185
 Taj+0.179
framework+0.178
Neg logit contributions
cles-0.212
 unrelated-0.209
interstitial-0.201
minist-0.200
 Beir-0.185
Token websites
Token ID9293
Feature activation+4.98e-02

Pos logit contributions
ertodd+0.661
isconsin+0.641
alsa+0.629
 Taj+0.618
urdue+0.607
Neg logit contributions
cles-0.621
 unrelated-0.597
interstitial-0.580
minist-0.572
 Beir-0.533
Token and
Token ID290
Feature activation+2.66e-01

Pos logit contributions
ertodd+0.100
isconsin+0.096
alsa+0.094
urdue+0.091
framework+0.091
Neg logit contributions
cles-0.085
 unrelated-0.083
minist-0.079
interstitial-0.078
 Beir-0.071
Token suggestions
Token ID11776
Feature activation+6.31e-01

Pos logit contributions
ertodd+2.070
isconsin+1.988
alsa+1.948
framework+1.889
urdue+1.878
Neg logit contributions
cles-2.063
 unrelated-1.995
minist-1.933
interstitial-1.925
leans-1.753
Token on
Token ID319
Feature activation-1.16e-01

Pos logit contributions
ertodd+1.172
isconsin+1.124
alsa+1.107
 Taj+1.068
framework+1.067
Neg logit contributions
cles-1.151
 unrelated-1.107
interstitial-1.081
minist-1.076
 Beir-0.976
Token how
Token ID703
Feature activation-2.25e-03

Pos logit contributions
cles+0.236
 unrelated+0.233
minist+0.221
interstitial+0.220
 Beir+0.205
Neg logit contributions
ertodd-0.193
isconsin-0.185
alsa-0.180
framework-0.172
urdue-0.171
Token terror
Token ID3246
Feature activation+1.63e-01

Pos logit contributions
cles+0.004
 unrelated+0.004
minist+0.004
interstitial+0.004
 Beir+0.004
Neg logit contributions
ertodd-0.004
isconsin-0.004
alsa-0.004
 Taj-0.004
framework-0.004
Token in
Token ID287
Feature activation-1.83e-01

Pos logit contributions
ertodd+0.322
isconsin+0.313
alsa+0.303
urdue+0.293
framework+0.293
Neg logit contributions
cles-0.281
 unrelated-0.276
minist-0.262
interstitial-0.260
 Beir-0.239
Token Israel
Token ID2692
Feature activation-1.46e+00

Pos logit contributions
cles+0.345
 unrelated+0.341
minist+0.323
interstitial+0.319
 Beir+0.296
Neg logit contributions
ertodd-0.331
isconsin-0.320
alsa-0.311
framework-0.299
urdue-0.298
Token could
Token ID714
Feature activation-1.34e-01

Pos logit contributions
 unrelated+2.384
cles+2.382
minist+2.170
interstitial+2.108
 Beir+1.987
Neg logit contributions
ertodd-3.048
isconsin-2.934
alsa-2.880
framework-2.775
urdue-2.749
Token be
Token ID307
Feature activation+8.72e-01

Pos logit contributions
cles+0.262
 unrelated+0.259
minist+0.247
interstitial+0.246
 Beir+0.227
Neg logit contributions
ertodd-0.235
isconsin-0.225
alsa-0.219
framework-0.211
urdue-0.211
Token deter
Token ID2206
Feature activation-6.83e-01

Pos logit contributions
ertodd+1.733
isconsin+1.700
alsa+1.642
 Taj+1.605
framework+1.604
Neg logit contributions
cles-1.453
 unrelated-1.404
interstitial-1.379
minist-1.354
leans-1.235
Tokenred
Token ID445
Feature activation+1.59e-01

Pos logit contributions
cles+1.246
 unrelated+1.232
interstitial+1.158
minist+1.147
 Beir+1.071
Neg logit contributions
ertodd-1.290
isconsin-1.245
alsa-1.210
framework-1.164
urdue-1.163
Token.
Token ID13
Feature activation+7.03e-02

Pos logit contributions
ertodd+0.301
isconsin+0.292
alsa+0.282
urdue+0.272
framework+0.271
Neg logit contributions
cles-0.288
 unrelated-0.283
interstitial-0.272
minist-0.267
 Beir-0.247
Token guy
Token ID3516
Feature activation+3.65e-01

Pos logit contributions
cles+0.175
 unrelated+0.173
minist+0.163
interstitial+0.161
 Beir+0.150
Neg logit contributions
ertodd-0.168
isconsin-0.162
alsa-0.157
framework-0.151
urdue-0.151
Token with
Token ID351
Feature activation+3.91e-01

Pos logit contributions
ertodd+0.690
isconsin+0.668
alsa+0.654
 Taj+0.631
framework+0.626
Neg logit contributions
cles-0.655
 unrelated-0.649
minist-0.619
interstitial-0.610
 Beir-0.561
Token the
Token ID262
Feature activation-1.08e-01

Pos logit contributions
ertodd+0.673
isconsin+0.651
alsa+0.634
 Taj+0.607
urdue+0.605
Neg logit contributions
cles-0.769
 unrelated-0.763
minist-0.726
interstitial-0.720
 Beir-0.666
Token stage
Token ID3800
Feature activation-2.98e-01

Pos logit contributions
cles+0.200
 unrelated+0.199
minist+0.188
interstitial+0.186
 Beir+0.172
Neg logit contributions
ertodd-0.199
isconsin-0.192
alsa-0.187
framework-0.180
 Taj-0.179
Token win
Token ID1592
Feature activation-2.94e-02

Pos logit contributions
cles+0.650
 unrelated+0.647
minist+0.617
interstitial+0.610
 Beir+0.573
Neg logit contributions
ertodd-0.452
isconsin-0.433
alsa-0.420
framework-0.400
urdue-0.399
Token record
Token ID1700
Feature activation-1.51e+00

Pos logit contributions
cles+0.054
 unrelated+0.053
minist+0.050
interstitial+0.050
 Beir+0.046
Neg logit contributions
ertodd-0.055
isconsin-0.054
alsa-0.052
framework-0.050
urdue-0.050
Token at
Token ID379
Feature activation-3.55e-01

Pos logit contributions
cles+2.616
 unrelated+2.589
minist+2.398
interstitial+2.354
cle+2.212
Neg logit contributions
ertodd-3.013
isconsin-2.897
alsa-2.819
framework-2.724
urdue-2.713
Token the
Token ID262
Feature activation-2.05e-02

Pos logit contributions
cles+0.677
 unrelated+0.672
minist+0.633
interstitial+0.624
 Beir+0.583
Neg logit contributions
ertodd-0.643
isconsin-0.617
alsa-0.600
framework-0.576
urdue-0.576
Token Tour
Token ID9852
Feature activation+9.86e-03

Pos logit contributions
cles+0.035
 unrelated+0.035
minist+0.033
interstitial+0.032
 Beir+0.030
Neg logit contributions
ertodd-0.041
isconsin-0.040
alsa-0.039
 Taj-0.037
framework-0.037
Token Down
Token ID5588
Feature activation-1.39e-01

Pos logit contributions
ertodd+0.019
isconsin+0.018
alsa+0.018
framework+0.017
 Taj+0.017
Neg logit contributions
cles-0.018
 unrelated-0.018
minist-0.017
interstitial-0.017
 Beir-0.015
Token Under
Token ID4698
Feature activation+8.97e-01

Pos logit contributions
cles+0.225
 unrelated+0.221
minist+0.206
interstitial+0.202
cle+0.188
Neg logit contributions
ertodd-0.296
isconsin-0.284
alsa-0.277
urdue-0.270
framework-0.268
Token the
Token ID262
Feature activation+7.53e-02

Pos logit contributions
ertodd+0.203
isconsin+0.196
alsa+0.190
framework+0.183
 Taj+0.182
Neg logit contributions
cles-0.225
 unrelated-0.222
minist-0.210
interstitial-0.209
 Beir-0.194
Token bridge
Token ID7696
Feature activation+1.32e-01

Pos logit contributions
ertodd+0.128
isconsin+0.124
alsa+0.120
framework+0.115
 Taj+0.115
Neg logit contributions
cles-0.151
 unrelated-0.149
minist-0.142
interstitial-0.140
 Beir-0.131
Token would
Token ID561
Feature activation-5.00e-01

Pos logit contributions
ertodd+0.259
isconsin+0.251
alsa+0.244
framework+0.236
urdue+0.236
Neg logit contributions
cles-0.230
 unrelated-0.225
minist-0.215
interstitial-0.213
 Beir-0.195
Token allow
Token ID1249
Feature activation-5.66e-02

Pos logit contributions
cles+0.979
 unrelated+0.971
minist+0.919
interstitial+0.909
 Beir+0.848
Neg logit contributions
ertodd-0.879
isconsin-0.843
alsa-0.820
framework-0.788
urdue-0.786
Token the
Token ID262
Feature activation+8.97e-02

Pos logit contributions
cles+0.105
 unrelated+0.103
minist+0.098
interstitial+0.097
 Beir+0.090
Neg logit contributions
ertodd-0.105
isconsin-0.102
alsa-0.099
 Taj-0.095
framework-0.095
Token Park
Token ID3250
Feature activation-1.33e+00

Pos logit contributions
ertodd+0.150
isconsin+0.145
alsa+0.141
framework+0.136
 Taj+0.135
Neg logit contributions
cles-0.181
 unrelated-0.179
minist-0.170
interstitial-0.169
 Beir-0.157
Token Board
Token ID5926
Feature activation-4.60e-01

Pos logit contributions
cles+2.605
 unrelated+2.593
minist+2.436
interstitial+2.364
cle+2.255
Neg logit contributions
ertodd-2.365
isconsin-2.250
alsa-2.176
urdue-2.098
framework-2.086
Token to
Token ID284
Feature activation+2.20e-01

Pos logit contributions
cles+0.858
 unrelated+0.851
minist+0.801
interstitial+0.791
 Beir+0.736
Neg logit contributions
ertodd-0.851
isconsin-0.819
alsa-0.797
framework-0.766
urdue-0.765
Token take
Token ID1011
Feature activation+2.08e-01

Pos logit contributions
ertodd+0.385
isconsin+0.369
alsa+0.360
framework+0.349
urdue+0.347
Neg logit contributions
cles-0.429
 unrelated-0.422
interstitial-0.405
minist-0.403
 Beir-0.373
Token fuller
Token ID44757
Feature activation-1.77e-01

Pos logit contributions
ertodd+0.389
isconsin+0.380
alsa+0.368
framework+0.358
 Taj+0.356
Neg logit contributions
cles-0.379
 unrelated-0.371
minist-0.352
interstitial-0.350
 Beir-0.324
Token advantage
Token ID4621
Feature activation-4.46e-01

Pos logit contributions
cles+0.341
 unrelated+0.338
minist+0.319
interstitial+0.315
 Beir+0.294
Neg logit contributions
ertodd-0.316
isconsin-0.304
alsa-0.296
framework-0.284
urdue-0.283
Tokengan
Token ID1030
Feature activation-5.28e-01

Pos logit contributions
cles+2.298
 unrelated+2.282
minist+2.149
interstitial+2.120
 Beir+1.977
Neg logit contributions
ertodd-2.222
isconsin-2.137
alsa-2.077
framework-1.996
urdue-1.993
Token
Token ID447
Feature activation-1.08e-02

Pos logit contributions
cles+0.957
 unrelated+0.948
minist+0.892
interstitial+0.881
 Beir+0.818
Neg logit contributions
ertodd-1.007
isconsin-0.970
alsa-0.947
framework-0.909
urdue-0.907
Token
Token ID247
Feature activation-2.70e-03

Pos logit contributions
cles+0.022
 unrelated+0.021
minist+0.020
interstitial+0.020
cle+0.019
Neg logit contributions
ertodd-0.019
isconsin-0.018
alsa-0.017
urdue-0.017
framework-0.017
Tokens
Token ID82
Feature activation-1.29e-01

Pos logit contributions
cles+0.004
 unrelated+0.004
minist+0.004
interstitial+0.004
 Beir+0.003
Neg logit contributions
ertodd-0.006
isconsin-0.006
alsa-0.006
framework-0.005
 Taj-0.005
Token solo
Token ID12199
Feature activation-7.93e-01

Pos logit contributions
cles+0.247
 unrelated+0.245
minist+0.232
interstitial+0.229
 Beir+0.213
Neg logit contributions
ertodd-0.229
isconsin-0.221
alsa-0.216
framework-0.207
 Taj-0.206
Token record
Token ID1700
Feature activation-1.45e+00

Pos logit contributions
cles+1.448
 unrelated+1.444
minist+1.348
interstitial+1.329
 Beir+1.245
Neg logit contributions
ertodd-1.498
isconsin-1.441
alsa-1.398
urdue-1.348
framework-1.347
Token.
Token ID13
Feature activation-1.07e-03

Pos logit contributions
cles+2.555
 unrelated+2.552
minist+2.368
interstitial+2.318
 Beir+2.183
Neg logit contributions
ertodd-2.829
isconsin-2.718
alsa-2.635
urdue-2.555
framework-2.549
Token
Token ID564
Feature activation-2.94e-02

Pos logit contributions
cles+0.002
 unrelated+0.002
minist+0.002
interstitial+0.002
 Beir+0.002
Neg logit contributions
ertodd-0.002
isconsin-0.002
alsa-0.002
framework-0.001
urdue-0.001
Token
Token ID250
Feature activation+1.85e-01

Pos logit contributions
cles+0.053
 unrelated+0.053
minist+0.049
interstitial+0.048
cle+0.045
Neg logit contributions
ertodd-0.056
isconsin-0.054
alsa-0.053
urdue-0.051
framework-0.050
TokenHe
Token ID1544
Feature activation-1.53e-02

Pos logit contributions
ertodd+0.361
isconsin+0.353
alsa+0.345
framework+0.335
urdue+0.329
Neg logit contributions
cles-0.321
 unrelated-0.321
minist-0.299
interstitial-0.296
 Beir-0.274
Token has
Token ID468
Feature activation+2.85e-01

Pos logit contributions
cles+0.028
 unrelated+0.028
minist+0.026
interstitial+0.026
 Beir+0.024
Neg logit contributions
ertodd-0.029
isconsin-0.028
alsa-0.027
framework-0.026
urdue-0.026
Token distribution
Token ID6082
Feature activation+2.96e-01

Pos logit contributions
cles+2.811
 unrelated+2.789
minist+2.588
interstitial+2.471
cle+2.372
Neg logit contributions
ertodd-3.427
isconsin-3.249
alsa-3.174
framework-3.084
cipled-3.072
Token between
Token ID1022
Feature activation-4.97e-01

Pos logit contributions
ertodd+0.588
isconsin+0.573
alsa+0.559
 Taj+0.539
framework+0.535
Neg logit contributions
cles-0.497
 unrelated-0.489
interstitial-0.472
minist-0.463
 Beir-0.424
Token the
Token ID262
Feature activation-8.68e-02

Pos logit contributions
cles+0.923
 unrelated+0.914
minist+0.864
interstitial+0.854
 Beir+0.794
Neg logit contributions
ertodd-0.919
isconsin-0.885
alsa-0.865
framework-0.828
urdue-0.827
Token front
Token ID2166
Feature activation-6.10e-01

Pos logit contributions
cles+0.158
 unrelated+0.156
minist+0.149
interstitial+0.147
 Beir+0.136
Neg logit contributions
ertodd-0.160
isconsin-0.155
alsa-0.153
 Taj-0.147
framework-0.147
Token and
Token ID290
Feature activation-2.03e-01

Pos logit contributions
cles+1.008
 unrelated+0.998
minist+0.940
interstitial+0.923
 Beir+0.850
Neg logit contributions
ertodd-1.248
isconsin-1.214
alsa-1.186
framework-1.145
urdue-1.138
Token rear
Token ID8286
Feature activation-1.35e+00

Pos logit contributions
cles+0.400
 unrelated+0.396
minist+0.379
interstitial+0.374
 Beir+0.349
Neg logit contributions
ertodd-0.348
isconsin-0.338
alsa-0.329
framework-0.313
 Taj-0.312
Token wheels
Token ID13666
Feature activation-1.20e-01

Pos logit contributions
cles+2.305
 unrelated+2.288
minist+2.119
interstitial+2.090
 Beir+1.937
Neg logit contributions
ertodd-2.754
isconsin-2.638
alsa-2.572
urdue-2.488
framework-2.483
Token,
Token ID11
Feature activation+9.46e-02

Pos logit contributions
cles+0.214
 unrelated+0.212
minist+0.201
interstitial+0.199
 Beir+0.184
Neg logit contributions
ertodd-0.230
isconsin-0.222
alsa-0.217
framework-0.209
urdue-0.208
Token combines
Token ID21001
Feature activation-6.21e-01

Pos logit contributions
ertodd+0.169
isconsin+0.163
alsa+0.159
framework+0.153
 Taj+0.152
Neg logit contributions
cles-0.180
 unrelated-0.178
minist-0.169
interstitial-0.168
 Beir-0.156
Token the
Token ID262
Feature activation-8.84e-02

Pos logit contributions
cles+1.118
 unrelated+1.108
minist+1.042
interstitial+1.028
 Beir+0.953
Neg logit contributions
ertodd-1.189
isconsin-1.147
alsa-1.118
framework-1.075
urdue-1.074
Token best
Token ID1266
Feature activation-8.36e-02

Pos logit contributions
cles+0.162
 unrelated+0.160
minist+0.151
interstitial+0.150
 Beir+0.138
Neg logit contributions
ertodd-0.165
isconsin-0.159
alsa-0.156
framework-0.150
 Taj-0.150