TOP ACTIVATIONS
MAX = 6.771

& ' a Guard ) -> Option < Shared < '
as d Gu M ih o The Best T reek
0 . 5 ) ) = 0 . 1 // metres
( tem perature - am pl ifying ) and negative (
) could be re ph r ased as del
neutral music ological meaning with which he may well have agreed
void vert ( in out app data _ full v )
in haste the concepts with which the organic weaknesses of the
devices . First published Dec . 1 , 9
image Path ) image = im utils . resize ( image
i G : Ferrari _ 430 was up to play the
to gr ays cale image = c v 2 . im
s Format . Al ignment = [ system . draw ing
{ const float f Mass = ( m D ensity +
) $ Br ush 1 = New - Object Drawing .
app data _ full v ) { // Time component const
- 42 mile ) Date : 5 / 21
C , Y YR DS cent ering The Garg
{ // Time component const float TA U = 6 .
an additional hour of Fox & Friends co - host ed

MIN ACTIVATIONS
MIN = -6.711

at 8 13 - 247 - 86 22 .
to our free newsletters . If you put out
to our free newsletters . Update , 3 :
or call 03 30 333 68 46 . <|endoftext|> ( FIL
he 's only scored 20 Fantasy points once in six games
scenes . The new vehicle E ct o - 1 was
points . He had 19 Fantasy points against the Saints last
Tweet Pin 8 shares I was inspired
the National Museum of the United States Air Force in Dayton
of the dog - eat - dog world that is the
wrote : Show nested quote + On
one - man - one - woman , period . But
Guidelines . On the one hand , a generous tower separation
and Winston held under 20 Fantasy points over that span .
. Vi aches lav Pl ak as ov is
on Sat , 13 Sep , 2014 , 11 : 13
and Editor 's Picks . The seeds of this
display at the National Museum of the United States Air Force
g its amb ry / status / 9 175 669 15
. Google Scholar Crossref M asure ,

INTERVAL 3.401 - 6.771
CONTAINS 0.343%

toward extinction How Vera Rubin changed science
a phrase I still can t write without
R ig by , K . ( 2004 ). Add ressing
model civil rights program worthy of replication .
Read More : Dr . Se uss

INTERVAL 0.030 - 3.401
CONTAINS 48.534%

high road . T akeru Kob ay
­ mi ­ li ­ at ­ ing is the treat
First posted <|endoftext|> Screen cap via YouTube user Movie clips trailers
, $ rect 1 , $ s Format ) } else
Greenland will not go quietly , at least we will know

INTERVAL -3.341 - 0.030
CONTAINS 50.763%

annoying / dist ract ing and the one that I think
Ge isel once stated that he got all his ideas
ethnic groups . One of the goals with the Human Micro
faces with the evidence of so much sudden emotion
. Mor neau says he is sole owner of 20 70

INTERVAL -6.711 - -3.341
CONTAINS 0.360%

characterized by multiple tiny ker at otic plugs , mim icking
. files table SELECT * FROM [ big query - public
y Butt , who had scored a hat - tr ick
Six Sigma Ph ases and their descriptions You may
the fossil fuel industry . During the past fifteen
Token &
Token ID1222
Feature activation+2.10e+00

Pos logit contributions
 defer+2.525
 McMaster+2.506
oret+2.421
RW+2.373
ore+2.363
Neg logit contributions
prem-2.567
 pione-2.417
ducers-2.349
idth-2.259
-2.258
Token '
Token ID705
Feature activation-7.59e-01

Pos logit contributions
 defer+1.565
 McMaster+1.551
oret+1.507
RW+1.482
ore+1.480
Neg logit contributions
prem-1.531
 pione-1.416
ducers-1.397
idth-1.343
-1.328
Tokena
Token ID64
Feature activation+8.69e-01

Pos logit contributions
prem+0.554
ducers+0.512
 pione+0.506
idth+0.484
Untitled+0.474
Neg logit contributions
 defer-0.557
 McMaster-0.554
oret-0.539
RW-0.535
ore-0.527
Token Guard
Token ID4932
Feature activation+2.82e+00

Pos logit contributions
 defer+0.671
 McMaster+0.665
oret+0.649
RW+0.640
ore+0.634
Neg logit contributions
prem-0.610
ducers-0.560
 pione-0.559
idth-0.529
-0.521
Token )
Token ID1267
Feature activation+5.06e+00

Pos logit contributions
 defer+2.187
 McMaster+2.135
oret+2.088
RW+2.086
ore+2.051
Neg logit contributions
prem-1.962
 pione-1.814
ducers-1.793
idth-1.705
-1.692
Token ->
Token ID4613
Feature activation+6.77e+00

Pos logit contributions
 defer+3.735
 McMaster+3.571
RW+3.462
oret+3.458
ore+3.448
Neg logit contributions
prem-3.663
 pione-3.438
ducers-3.415
idth-3.239
Untitled-3.238
Token Option
Token ID16018
Feature activation+2.25e+00

Pos logit contributions
 defer+4.532
 McMaster+4.376
oret+4.219
ore+4.122
RW+4.093
Neg logit contributions
prem-5.507
 pione-5.291
ducers-5.062
-5.004
idth-4.932
Token <
Token ID1279
Feature activation+1.95e+00

Pos logit contributions
 defer+1.906
 McMaster+1.874
oret+1.843
RW+1.826
ore+1.810
Neg logit contributions
prem-1.394
 pione-1.273
ducers-1.269
idth-1.219
-1.181
Token Shared
Token ID39403
Feature activation+1.92e-01

Pos logit contributions
 defer+1.482
 McMaster+1.466
oret+1.427
RW+1.418
ore+1.398
Neg logit contributions
prem-1.386
 pione-1.278
ducers-1.273
idth-1.207
-1.198
Token <
Token ID1279
Feature activation+1.33e+00

Pos logit contributions
 defer+0.163
 McMaster+0.161
oret+0.158
RW+0.157
ore+0.156
Neg logit contributions
prem-0.119
 pione-0.108
ducers-0.107
idth-0.101
-0.100
Token '
Token ID705
Feature activation+1.60e-01

Pos logit contributions
 defer+1.073
 McMaster+1.062
oret+1.036
RW+1.026
ore+1.015
Neg logit contributions
prem-0.892
 pione-0.820
ducers-0.813
idth-0.770
-0.766
Token
Token ID198
Feature activation-1.30e+00

Pos logit contributions
prem+0.931
ducers+0.848
Untitled+0.779
humans+0.772
 ®+0.766
Neg logit contributions
 defer-1.085
 McMaster-1.079
 torches-1.046
oret-1.046
��-1.036
Tokenas
Token ID292
Feature activation-2.20e+00

Pos logit contributions
prem+0.955
ducers+0.878
 pione+0.851
idth+0.826
Untitled+0.821
Neg logit contributions
 defer-0.960
 McMaster-0.955
oret-0.923
RW-0.908
 torches-0.895
Tokend
Token ID67
Feature activation+4.62e+00

Pos logit contributions
prem+1.527
ducers+1.403
 pione+1.375
idth+1.323
Untitled+1.296
Neg logit contributions
 defer-1.697
 McMaster-1.688
oret-1.640
RW-1.624
ore-1.593
TokenGu
Token ID8205
Feature activation+1.53e+00

Pos logit contributions
 defer+3.203
 McMaster+3.195
oret+3.114
ore+3.111
RW+3.101
Neg logit contributions
prem-3.436
 pione-3.229
ducers-3.218
idth-3.062
-3.052
TokenM
Token ID44
Feature activation+2.68e+00

Pos logit contributions
 McMaster+1.318
 defer+1.315
RW+1.282
oret+1.281
ore+1.265
Neg logit contributions
prem-0.914
ducers-0.832
 pione-0.829
idth-0.783
-0.763
Tokenih
Token ID4449
Feature activation+6.70e+00

Pos logit contributions
 defer+1.814
 McMaster+1.803
oret+1.761
RW+1.742
ore+1.725
Neg logit contributions
prem-2.100
 pione-1.987
ducers-1.943
-1.858
idth-1.844
Tokeno
Token ID78
Feature activation+4.44e+00

Pos logit contributions
ore+4.010
oret+4.007
 defer+3.960
 McMaster+3.871
RW+3.847
Neg logit contributions
 pione-5.967
-5.770
-5.576
prem-5.532
ducers-5.230
TokenThe
Token ID464
Feature activation+1.68e+00

Pos logit contributions
 defer+3.137
 McMaster+3.116
RW+3.048
oret+3.023
ore+3.005
Neg logit contributions
prem-3.272
 pione-3.066
ducers-3.053
idth-2.934
-2.894
TokenBest
Token ID13014
Feature activation+2.17e+00

Pos logit contributions
 defer+1.217
 McMaster+1.216
oret+1.199
RW+1.183
ore+1.171
Neg logit contributions
prem-1.214
 pione-1.136
ducers-1.126
idth-1.078
-1.071
TokenT
Token ID51
Feature activation+2.40e+00

Pos logit contributions
 defer+1.558
 McMaster+1.548
oret+1.514
RW+1.503
ore+1.483
Neg logit contributions
prem-1.603
ducers-1.492
 pione-1.492
idth-1.423
-1.402
Tokenreek
Token ID10316
Feature activation+2.03e+00

Pos logit contributions
 defer+1.696
 McMaster+1.686
oret+1.656
RW+1.636
ore+1.632
Neg logit contributions
prem-1.809
 pione-1.684
ducers-1.678
idth-1.594
-1.586
Token 0
Token ID657
Feature activation-1.41e+00

Pos logit contributions
 defer+0.844
 McMaster+0.836
oret+0.809
RW+0.805
ore+0.789
Neg logit contributions
prem-1.120
ducers-1.047
 pione-1.018
idth-0.993
Untitled-0.979
Token.
Token ID13
Feature activation+2.54e-01

Pos logit contributions
prem+1.102
ducers+1.022
 ®+0.956
Untitled+0.953
idth+0.951
Neg logit contributions
 defer-0.961
 McMaster-0.947
oret-0.921
RW-0.919
 torches-0.911
Token5
Token ID20
Feature activation+2.70e+00

Pos logit contributions
 defer+0.199
 McMaster+0.197
oret+0.192
RW+0.191
ore+0.188
Neg logit contributions
prem-0.174
ducers-0.160
 pione-0.154
idth-0.150
Untitled-0.146
Token )
Token ID1267
Feature activation+2.50e+00

Pos logit contributions
 defer+2.200
 McMaster+2.182
oret+2.132
RW+2.108
ore+2.086
Neg logit contributions
prem-1.755
 pione-1.648
ducers-1.605
-1.531
idth-1.521
Token )
Token ID1267
Feature activation+3.97e+00

Pos logit contributions
 defer+2.065
 McMaster+2.050
oret+2.000
RW+1.984
ore+1.960
Neg logit contributions
prem-1.595
 pione-1.466
ducers-1.459
idth-1.372
-1.358
Token =
Token ID796
Feature activation+6.45e+00

Pos logit contributions
 defer+3.186
 McMaster+3.156
oret+3.074
RW+3.054
ore+3.027
Neg logit contributions
prem-2.622
 pione-2.572
ducers-2.410
-2.404
-2.337
Token 0
Token ID657
Feature activation+2.03e+00

Pos logit contributions
 defer+3.564
 McMaster+3.474
oret+3.387
RW+3.247
ore+3.235
Neg logit contributions
prem-5.873
 pione-5.868
-5.568
ducers-5.513
-5.457
Token.
Token ID13
Feature activation+1.06e+00

Pos logit contributions
 defer+1.300
 McMaster+1.291
oret+1.250
RW+1.238
ore+1.217
Neg logit contributions
prem-1.668
ducers-1.558
 pione-1.551
idth-1.485
-1.462
Token1
Token ID16
Feature activation+3.74e+00

Pos logit contributions
 defer+0.784
 McMaster+0.779
oret+0.758
RW+0.752
ore+0.740
Neg logit contributions
prem-0.775
ducers-0.717
 pione-0.708
idth-0.678
Untitled-0.663
Token //
Token ID3373
Feature activation+2.30e-01

Pos logit contributions
 defer+2.912
 McMaster+2.890
oret+2.811
RW+2.784
ore+2.754
Neg logit contributions
prem-2.575
 pione-2.404
ducers-2.371
idth-2.246
-2.237
Token metres
Token ID18985
Feature activation+2.26e+00

Pos logit contributions
 defer+0.114
 McMaster+0.113
oret+0.108
RW+0.107
ore+0.105
Neg logit contributions
prem-0.223
ducers-0.210
 pione-0.209
idth-0.202
-0.199
Token (
Token ID357
Feature activation+1.25e+00

Pos logit contributions
 defer+2.407
 McMaster+2.367
oret+2.319
RW+2.293
ore+2.279
Neg logit contributions
prem-2.473
 pione-2.313
ducers-2.277
idth-2.169
-2.164
Tokentem
Token ID11498
Feature activation+5.12e-01

Pos logit contributions
 defer+0.927
 McMaster+0.920
oret+0.900
RW+0.898
ore+0.884
Neg logit contributions
prem-0.896
 pione-0.835
ducers-0.831
idth-0.789
-0.781
Tokenperature
Token ID21069
Feature activation+5.57e-01

Pos logit contributions
 defer+0.174
 McMaster+0.171
oret+0.161
RW+0.158
ore+0.153
Neg logit contributions
prem-0.576
ducers-0.548
 pione-0.546
idth-0.530
-0.523
Token-
Token ID12
Feature activation+7.34e-01

Pos logit contributions
 defer+0.425
 McMaster+0.420
oret+0.411
RW+0.407
ore+0.401
Neg logit contributions
prem-0.395
ducers-0.363
 pione-0.362
idth-0.342
-0.337
Tokenam
Token ID321
Feature activation+2.36e+00

Pos logit contributions
 defer+0.555
 McMaster+0.551
oret+0.538
RW+0.534
ore+0.526
Neg logit contributions
prem-0.520
ducers-0.480
 pione-0.477
idth-0.454
-0.445
Tokenpl
Token ID489
Feature activation+6.31e+00

Pos logit contributions
 defer+2.098
 McMaster+2.082
oret+2.058
RW+2.030
ore+2.019
Neg logit contributions
prem-1.348
 pione-1.219
ducers-1.211
idth-1.129
-1.125
Tokenifying
Token ID4035
Feature activation+1.50e+00

Pos logit contributions
 defer+4.583
oret+4.569
 McMaster+4.554
ore+4.459
RW+4.406
Neg logit contributions
prem-4.481
 pione-4.224
ducers-4.071
-3.988
-3.891
Token)
Token ID8
Feature activation+2.14e+00

Pos logit contributions
 defer+1.165
 McMaster+1.144
oret+1.135
RW+1.115
ore+1.106
Neg logit contributions
prem-1.042
 pione-0.957
ducers-0.948
idth-0.894
-0.888
Token and
Token ID290
Feature activation+2.92e+00

Pos logit contributions
 defer+1.533
 McMaster+1.513
oret+1.475
RW+1.460
ore+1.445
Neg logit contributions
prem-1.605
 pione-1.491
ducers-1.486
idth-1.410
-1.397
Token negative
Token ID4633
Feature activation+1.29e+00

Pos logit contributions
 defer+1.711
 McMaster+1.664
oret+1.641
ore+1.606
RW+1.587
Neg logit contributions
prem-2.577
 pione-2.430
ducers-2.381
idth-2.311
-2.296
Token (
Token ID357
Feature activation+4.58e-01

Pos logit contributions
 defer+0.874
 McMaster+0.864
oret+0.840
RW+0.831
ore+0.821
Neg logit contributions
prem-1.020
 pione-0.947
ducers-0.946
idth-0.900
-0.890
Token)
Token ID8
Feature activation+1.13e-01

Pos logit contributions
 defer+0.863
 McMaster+0.849
oret+0.839
RW+0.819
ore+0.817
Neg logit contributions
prem-0.843
ducers-0.784
 pione-0.780
idth-0.744
Untitled-0.728
Token could
Token ID714
Feature activation-4.52e-01

Pos logit contributions
 defer+0.080
 McMaster+0.079
oret+0.077
RW+0.076
ore+0.075
Neg logit contributions
prem-0.086
ducers-0.080
 pione-0.079
idth-0.076
-0.074
Token be
Token ID307
Feature activation-5.46e-01

Pos logit contributions
prem+0.354
ducers+0.330
 pione+0.327
idth+0.313
+0.308
Neg logit contributions
 defer-0.308
 McMaster-0.306
oret-0.297
RW-0.294
ore-0.290
Token re
Token ID302
Feature activation+6.47e-01

Pos logit contributions
prem+0.404
ducers+0.376
 pione+0.375
idth+0.356
+0.349
Neg logit contributions
 defer-0.398
 McMaster-0.394
oret-0.383
RW-0.379
ore-0.375
Tokenph
Token ID746
Feature activation-1.47e+00

Pos logit contributions
 defer+0.496
 McMaster+0.493
oret+0.480
RW+0.475
ore+0.470
Neg logit contributions
prem-0.451
ducers-0.417
 pione-0.415
idth-0.394
-0.387
Tokenr
Token ID81
Feature activation+6.29e+00

Pos logit contributions
prem+1.228
ducers+1.155
 pione+1.131
idth+1.098
Untitled+1.073
Neg logit contributions
 defer-0.921
 McMaster-0.914
RW-0.881
oret-0.874
Bloom-0.859
Tokenased
Token ID839
Feature activation+2.75e+00

Pos logit contributions
 defer+3.420
 McMaster+3.397
oret+3.312
ore+3.291
RW+3.199
Neg logit contributions
prem-5.663
 pione-5.490
ducers-5.387
-5.233
-5.143
Token as
Token ID355
Feature activation+1.25e+00

Pos logit contributions
 defer+1.906
 McMaster+1.889
oret+1.819
RW+1.795
ore+1.778
Neg logit contributions
prem-2.133
 pione-2.006
ducers-1.997
idth-1.912
-1.868
Token
Token ID564
Feature activation+1.51e+00

Pos logit contributions
 defer+0.908
 McMaster+0.896
oret+0.866
RW+0.855
ore+0.849
Neg logit contributions
prem-0.924
ducers-0.863
 pione-0.862
idth-0.813
-0.802
Token
Token ID246
Feature activation-1.00e+00

Pos logit contributions
 defer+0.728
 McMaster+0.715
oret+0.694
RW+0.684
ore+0.672
Neg logit contributions
prem-1.481
ducers-1.410
 pione-1.401
idth-1.350
-1.329
Tokendel
Token ID12381
Feature activation-1.11e+00

Pos logit contributions
prem+0.676
ducers+0.621
 pione+0.614
idth+0.584
+0.571
Neg logit contributions
 defer-0.794
 McMaster-0.790
oret-0.770
RW-0.764
ore-0.753
Token neutral
Token ID8500
Feature activation-8.04e-01

Pos logit contributions
 defer+0.311
 McMaster+0.307
oret+0.299
RW+0.294
ore+0.291
Neg logit contributions
prem-0.356
 pione-0.331
ducers-0.331
idth-0.316
-0.311
Token music
Token ID2647
Feature activation-1.11e+00

Pos logit contributions
prem+0.624
ducers+0.580
 pione+0.574
idth+0.551
+0.539
Neg logit contributions
 defer-0.553
 McMaster-0.551
oret-0.534
RW-0.530
ore-0.521
Tokenological
Token ID2770
Feature activation-4.09e-01

Pos logit contributions
prem+0.890
ducers+0.830
 pione+0.823
idth+0.789
+0.775
Neg logit contributions
 defer-0.740
 McMaster-0.735
oret-0.713
RW-0.706
ore-0.695
Token meaning
Token ID3616
Feature activation+9.40e-01

Pos logit contributions
prem+0.320
ducers+0.297
 pione+0.294
idth+0.282
Untitled+0.277
Neg logit contributions
 defer-0.278
 McMaster-0.277
oret-0.268
RW-0.267
ore-0.262
Token with
Token ID351
Feature activation-6.95e-01

Pos logit contributions
 defer+0.643
 McMaster+0.632
oret+0.615
RW+0.608
ore+0.603
Neg logit contributions
prem-0.737
 pione-0.689
ducers-0.687
idth-0.656
-0.642
Token which
Token ID543
Feature activation+6.11e+00

Pos logit contributions
prem+0.555
ducers+0.518
 pione+0.513
idth+0.492
+0.483
Neg logit contributions
 defer-0.462
 McMaster-0.459
oret-0.445
RW-0.442
ore-0.434
Token he
Token ID339
Feature activation-1.08e-01

Pos logit contributions
 defer+4.200
 McMaster+4.085
ore+3.942
oret+3.878
RW+3.842
Neg logit contributions
prem-4.632
 pione-4.480
ducers-4.195
-4.146
apult-4.130
Token may
Token ID743
Feature activation-6.56e-01

Pos logit contributions
prem+0.081
ducers+0.075
 pione+0.074
idth+0.071
Untitled+0.069
Neg logit contributions
 defer-0.077
 McMaster-0.077
oret-0.075
RW-0.074
ore-0.073
Token well
Token ID880
Feature activation-2.40e-01

Pos logit contributions
prem+0.541
ducers+0.506
 pione+0.496
idth+0.482
Untitled+0.472
Neg logit contributions
 McMaster-0.417
 defer-0.414
oret-0.402
RW-0.401
ore-0.391
Token have
Token ID423
Feature activation+5.38e-01

Pos logit contributions
prem+0.192
ducers+0.179
 pione+0.175
idth+0.170
Untitled+0.166
Neg logit contributions
 McMaster-0.159
 defer-0.158
oret-0.154
RW-0.154
ore-0.150
Token agreed
Token ID4987
Feature activation+7.59e-01

Pos logit contributions
 defer+0.374
 McMaster+0.371
oret+0.360
RW+0.357
ore+0.352
Neg logit contributions
prem-0.416
ducers-0.386
 pione-0.385
idth-0.367
-0.361
Token void
Token ID7951
Feature activation+3.01e+00

Pos logit contributions
prem+3.155
ducers+2.964
 pione+2.913
idth+2.804
 ®+2.801
Neg logit contributions
 McMaster-2.297
 defer-2.241
RW-2.215
oret-2.178
Bloom-2.163
Token vert
Token ID9421
Feature activation-5.72e-01

Pos logit contributions
 defer+2.995
 McMaster+2.905
oret+2.892
ore+2.834
RW+2.818
Neg logit contributions
prem-1.444
 pione-1.364
ducers-1.292
-1.233
-1.189
Token (
Token ID357
Feature activation+2.01e+00

Pos logit contributions
prem+0.437
ducers+0.406
 pione+0.393
idth+0.384
Untitled+0.377
Neg logit contributions
 defer-0.399
 McMaster-0.398
oret-0.386
RW-0.385
ore-0.374
Token in
Token ID287
Feature activation+2.19e-01

Pos logit contributions
 defer+1.304
 McMaster+1.284
oret+1.253
RW+1.231
ore+1.221
Neg logit contributions
prem-1.646
ducers-1.537
 pione-1.536
idth-1.468
-1.452
Tokenout
Token ID448
Feature activation+1.19e+00

Pos logit contributions
 defer+0.155
 McMaster+0.154
oret+0.149
RW+0.148
ore+0.145
Neg logit contributions
prem-0.166
ducers-0.154
 pione-0.152
idth-0.146
Untitled-0.143
Token app
Token ID598
Feature activation+6.05e+00

Pos logit contributions
 defer+0.618
 McMaster+0.614
oret+0.590
RW+0.586
ore+0.571
Neg logit contributions
prem-1.121
ducers-1.056
 pione-1.043
idth-1.011
Untitled-0.996
Tokendata
Token ID7890
Feature activation+1.03e+00

Pos logit contributions
 defer+4.422
 McMaster+4.379
oret+4.332
ore+4.303
RW+4.233
Neg logit contributions
 pione-4.472
prem-4.289
-4.225
-4.090
ducers-3.989
Token _
Token ID4808
Feature activation+2.64e+00

Pos logit contributions
 defer+0.650
 McMaster+0.644
oret+0.623
RW+0.617
ore+0.606
Neg logit contributions
prem-0.868
ducers-0.811
 pione-0.785
idth-0.768
Untitled-0.758
Token full
Token ID1336
Feature activation+3.75e-01

Pos logit contributions
 defer+1.698
 McMaster+1.646
oret+1.623
RW+1.597
ore+1.592
Neg logit contributions
prem-2.152
ducers-2.036
 pione-2.018
idth-1.938
-1.907
Token v
Token ID410
Feature activation+3.80e+00

Pos logit contributions
 defer+0.261
 McMaster+0.257
oret+0.250
RW+0.248
ore+0.246
Neg logit contributions
prem-0.289
ducers-0.269
 pione-0.267
idth-0.256
-0.251
Token )
Token ID1267
Feature activation+4.67e+00

Pos logit contributions
 defer+3.008
 McMaster+2.914
oret+2.882
ore+2.823
RW+2.810
Neg logit contributions
prem-2.579
 pione-2.441
ducers-2.364
-2.303
-2.258
Token in
Token ID287
Feature activation-4.29e-01

Pos logit contributions
 defer+0.367
 McMaster+0.364
oret+0.354
RW+0.350
ore+0.345
Neg logit contributions
prem-0.426
ducers-0.397
 pione-0.393
idth-0.377
-0.370
Token haste
Token ID36797
Feature activation-1.02e+00

Pos logit contributions
prem+0.328
ducers+0.305
 pione+0.301
idth+0.288
+0.282
Neg logit contributions
 defer-0.300
 McMaster-0.298
oret-0.289
RW-0.288
ore-0.282
Token the
Token ID262
Feature activation+3.02e-01

Pos logit contributions
prem+0.783
ducers+0.725
 pione+0.716
idth+0.688
Untitled+0.675
Neg logit contributions
 defer-0.705
 McMaster-0.701
oret-0.680
RW-0.677
ore-0.662
Token concepts
Token ID10838
Feature activation-1.08e+00

Pos logit contributions
 defer+0.214
 McMaster+0.213
oret+0.207
RW+0.205
ore+0.202
Neg logit contributions
prem-0.228
ducers-0.212
 pione-0.210
idth-0.201
-0.197
Token with
Token ID351
Feature activation-2.24e-01

Pos logit contributions
prem+0.794
ducers+0.734
 pione+0.726
idth+0.694
+0.680
Neg logit contributions
 defer-0.791
 McMaster-0.785
oret-0.763
RW-0.758
ore-0.745
Token which
Token ID543
Feature activation+5.99e+00

Pos logit contributions
prem+0.190
ducers+0.178
 pione+0.176
idth+0.170
+0.166
Neg logit contributions
 defer-0.139
 McMaster-0.138
oret-0.133
RW-0.132
ore-0.129
Token the
Token ID262
Feature activation-2.31e-01

Pos logit contributions
 McMaster+3.941
 defer+3.940
ore+3.886
oret+3.849
RW+3.746
Neg logit contributions
prem-4.594
 pione-4.347
ducers-4.331
-4.115
Untitled-4.107
Token organic
Token ID10469
Feature activation+6.47e-01

Pos logit contributions
prem+0.179
ducers+0.166
 pione+0.164
idth+0.157
+0.154
Neg logit contributions
 defer-0.160
 McMaster-0.159
oret-0.154
RW-0.153
ore-0.150
Token weaknesses
Token ID20256
Feature activation+8.99e-01

Pos logit contributions
 defer+0.446
 McMaster+0.443
oret+0.430
RW+0.426
ore+0.420
Neg logit contributions
prem-0.503
ducers-0.468
 pione-0.464
idth-0.444
-0.436
Token of
Token ID286
Feature activation+1.59e+00

Pos logit contributions
 defer+0.651
 McMaster+0.646
oret+0.628
RW+0.621
ore+0.616
Neg logit contributions
prem-0.667
ducers-0.619
 pione-0.617
idth-0.587
-0.578
Token the
Token ID262
Feature activation+9.26e-01

Pos logit contributions
 defer+1.156
 McMaster+1.149
oret+1.121
RW+1.105
ore+1.101
Neg logit contributions
prem-1.170
ducers-1.086
 pione-1.082
idth-1.032
-1.015
Token devices
Token ID4410
Feature activation+1.81e-01

Pos logit contributions
 defer+0.122
 McMaster+0.121
oret+0.118
RW+0.117
ore+0.116
Neg logit contributions
prem-0.091
ducers-0.083
 pione-0.082
idth-0.078
-0.076
Token.
Token ID13
Feature activation-6.33e-01

Pos logit contributions
 defer+0.119
 McMaster+0.118
oret+0.114
RW+0.113
ore+0.112
Neg logit contributions
prem-0.147
ducers-0.138
 pione-0.137
idth-0.131
-0.129
Token
Token ID198
Feature activation-3.44e-01

Pos logit contributions
prem+0.464
 pione+0.432
ducers+0.432
idth+0.411
+0.405
Neg logit contributions
 defer-0.463
 McMaster-0.462
oret-0.447
RW-0.443
ore-0.438
Token
Token ID198
Feature activation-2.60e-01

Pos logit contributions
prem+0.244
ducers+0.224
idth+0.208
 pione+0.207
Untitled+0.207
Neg logit contributions
 defer-0.261
 McMaster-0.260
oret-0.252
RW-0.250
 torches-0.247
TokenFirst
Token ID5962
Feature activation+2.45e+00

Pos logit contributions
prem+0.185
ducers+0.171
 pione+0.170
idth+0.161
+0.159
Neg logit contributions
 defer-0.197
 McMaster-0.196
oret-0.191
RW-0.189
ore-0.186
Token published
Token ID3199
Feature activation+5.96e+00

Pos logit contributions
 defer+1.622
 McMaster+1.615
oret+1.550
Bloom+1.530
RW+1.520
Neg logit contributions
prem-1.923
 pione-1.827
ducers-1.820
idth-1.726
-1.718
Token Dec
Token ID4280
Feature activation+2.16e+00

Pos logit contributions
 defer+4.139
 McMaster+4.137
oret+3.999
RW+3.955
ore+3.920
Neg logit contributions
prem-4.505
 pione-4.296
ducers-4.211
idth-4.037
-4.012
Token.
Token ID13
Feature activation-5.59e-01

Pos logit contributions
 defer+1.414
 McMaster+1.408
oret+1.367
RW+1.349
ore+1.334
Neg logit contributions
prem-1.746
 pione-1.650
ducers-1.630
idth-1.556
-1.554
Token 1
Token ID352
Feature activation-1.21e+00

Pos logit contributions
prem+0.415
ducers+0.383
 pione+0.364
idth+0.359
Untitled+0.356
Neg logit contributions
 defer-0.405
 McMaster-0.399
oret-0.390
RW-0.387
 torches-0.380
Token,
Token ID11
Feature activation-2.57e+00

Pos logit contributions
prem+0.926
ducers+0.860
 pione+0.852
idth+0.817
+0.800
Neg logit contributions
 defer-0.847
 McMaster-0.842
oret-0.818
RW-0.811
ore-0.798
Token 9
Token ID860
Feature activation-1.54e+00

Pos logit contributions
prem+2.050
ducers+1.891
 pione+1.816
 ®+1.811
idth+1.788
Neg logit contributions
 defer-1.684
 McMaster-1.672
oret-1.646
RW-1.631
 torches-1.578
Token image
Token ID2939
Feature activation+8.27e-01

Pos logit contributions
 defer+2.108
 McMaster+2.094
oret+2.039
RW+2.022
ore+1.995
Neg logit contributions
prem-1.934
ducers-1.783
 pione-1.770
idth-1.683
-1.651
TokenPath
Token ID15235
Feature activation+2.22e+00

Pos logit contributions
 defer+0.493
 McMaster+0.490
oret+0.473
RW+0.466
ore+0.458
Neg logit contributions
prem-0.718
ducers-0.673
 pione-0.662
idth-0.642
Untitled-0.632
Token )
Token ID1267
Feature activation+2.67e+00

Pos logit contributions
 defer+1.829
 McMaster+1.817
oret+1.774
RW+1.760
ore+1.739
Neg logit contributions
prem-1.432
 pione-1.330
ducers-1.311
-1.237
idth-1.236
Token image
Token ID2939
Feature activation+2.16e+00

Pos logit contributions
 defer+2.046
 McMaster+2.034
oret+1.981
RW+1.966
ore+1.937
Neg logit contributions
prem-1.864
ducers-1.718
 pione-1.701
idth-1.621
-1.585
Token =
Token ID796
Feature activation+5.17e+00

Pos logit contributions
 defer+1.779
 McMaster+1.767
oret+1.722
RW+1.717
ore+1.694
Neg logit contributions
prem-1.381
 pione-1.295
ducers-1.264
-1.202
idth-1.190
Token im
Token ID545
Feature activation+5.92e+00

Pos logit contributions
 defer+2.936
 McMaster+2.830
oret+2.724
ore+2.660
 torches+2.583
Neg logit contributions
prem-4.722
 pione-4.656
ducers-4.442
-4.421
-4.350
Tokenutils
Token ID26791
Feature activation+4.57e+00

Pos logit contributions
 McMaster+4.247
 defer+4.200
oret+4.122
ore+4.091
RW+4.028
Neg logit contributions
 pione-4.467
prem-4.294
-4.285
-4.249
idth-3.887
Token.
Token ID764
Feature activation+3.72e+00

Pos logit contributions
 defer+2.629
 McMaster+2.613
oret+2.517
ore+2.470
RW+2.469
Neg logit contributions
 pione-4.080
prem-4.045
-3.882
ducers-3.808
-3.806
Token resize
Token ID47558
Feature activation+3.11e+00

Pos logit contributions
 defer+1.919
 McMaster+1.917
oret+1.857
RW+1.833
ore+1.781
Neg logit contributions
prem-3.513
ducers-3.312
 pione-3.230
idth-3.155
 ®-3.115
Token (
Token ID357
Feature activation+2.62e+00

Pos logit contributions
 defer+2.016
 McMaster+2.003
oret+1.940
RW+1.927
ore+1.896
Neg logit contributions
prem-2.537
 pione-2.460
ducers-2.363
-2.325
idth-2.274
Token image
Token ID2939
Feature activation+1.12e+00

Pos logit contributions
 defer+2.010
 McMaster+1.998
oret+1.946
RW+1.931
ore+1.903
Neg logit contributions
prem-1.833
ducers-1.690
 pione-1.673
idth-1.594
-1.560
Tokeni
Token ID72
Feature activation+1.15e-01

Pos logit contributions
 defer+1.065
 McMaster+1.060
RW+1.041
oret+1.036
ore+1.017
Neg logit contributions
prem-1.012
 pione-0.964
ducers-0.940
-0.902
idth-0.898
TokenG
Token ID38
Feature activation+2.32e+00

Pos logit contributions
 defer+0.083
 McMaster+0.082
oret+0.080
RW+0.080
ore+0.078
Neg logit contributions
prem-0.086
ducers-0.080
 pione-0.079
idth-0.076
-0.074
Token:
Token ID25
Feature activation+1.60e+00

Pos logit contributions
 defer+1.647
 McMaster+1.645
oret+1.594
RW+1.589
ore+1.573
Neg logit contributions
prem-1.735
ducers-1.624
 pione-1.613
idth-1.545
-1.516
Token Ferrari
Token ID23502
Feature activation+1.71e+00

Pos logit contributions
 defer+1.160
 McMaster+1.156
oret+1.118
RW+1.114
ore+1.095
Neg logit contributions
prem-1.180
 pione-1.102
ducers-1.095
idth-1.046
-1.031
Token_
Token ID62
Feature activation+1.46e+00

Pos logit contributions
 defer+1.203
 McMaster+1.200
oret+1.164
RW+1.157
ore+1.140
Neg logit contributions
prem-1.298
ducers-1.212
 pione-1.202
idth-1.149
-1.124
Token430
Token ID31794
Feature activation+5.75e+00

Pos logit contributions
 defer+1.062
 McMaster+1.058
RW+1.032
oret+1.030
ore+1.012
Neg logit contributions
prem-1.062
ducers-0.991
 pione-0.989
idth-0.940
-0.928
Token was
Token ID373
Feature activation+7.13e-01

Pos logit contributions
 McMaster+3.981
 defer+3.956
RW+3.931
oret+3.827
ore+3.811
Neg logit contributions
prem-4.255
 pione-4.029
ducers-4.010
idth-3.797
-3.747
Token up
Token ID510
Feature activation-1.48e-01

Pos logit contributions
 defer+0.498
 McMaster+0.495
oret+0.480
RW+0.477
ore+0.469
Neg logit contributions
prem-0.547
ducers-0.509
 pione-0.504
idth-0.483
-0.473
Token to
Token ID284
Feature activation+3.25e-03

Pos logit contributions
prem+0.108
ducers+0.100
 pione+0.099
idth+0.094
+0.092
Neg logit contributions
 defer-0.109
 McMaster-0.108
oret-0.106
RW-0.105
ore-0.103
Token play
Token ID711
Feature activation-6.82e-01

Pos logit contributions
 defer+0.002
 McMaster+0.002
oret+0.002
RW+0.002
ore+0.002
Neg logit contributions
prem-0.002
ducers-0.002
 pione-0.002
idth-0.002
-0.002
Token the
Token ID262
Feature activation-5.78e-01

Pos logit contributions
prem+0.523
ducers+0.484
 pione+0.477
idth+0.458
Untitled+0.450
Neg logit contributions
 defer-0.477
 McMaster-0.472
oret-0.460
RW-0.456
ore-0.448
Token to
Token ID284
Feature activation-1.62e+00

Pos logit contributions
 defer+0.736
 McMaster+0.733
oret+0.714
RW+0.710
ore+0.698
Neg logit contributions
prem-0.637
ducers-0.586
 pione-0.566
idth-0.549
Untitled-0.539
Token gr
Token ID1036
Feature activation+3.03e+00

Pos logit contributions
prem+1.391
ducers+1.313
 ®+1.236
idth+1.224
humans+1.219
Neg logit contributions
 McMaster-0.949
 defer-0.943
RW-0.917
oret-0.917
Bloom-0.904
Tokenays
Token ID592
Feature activation+3.16e+00

Pos logit contributions
 defer+1.966
 McMaster+1.950
oret+1.895
RW+1.879
ore+1.849
Neg logit contributions
prem-2.469
 pione-2.317
ducers-2.301
idth-2.189
-2.183
Tokencale
Token ID38765
Feature activation+7.87e-01

Pos logit contributions
 defer+1.952
 McMaster+1.940
oret+1.875
RW+1.857
ore+1.836
Neg logit contributions
prem-2.671
 pione-2.529
ducers-2.503
-2.398
idth-2.385
Token image
Token ID2939
Feature activation+2.73e+00

Pos logit contributions
 defer+0.626
 McMaster+0.625
oret+0.612
RW+0.610
Bloom+0.599
Neg logit contributions
prem-0.519
ducers-0.477
 pione-0.454
idth-0.447
Untitled-0.441
Token =
Token ID796
Feature activation+5.69e+00

Pos logit contributions
 defer+2.202
 McMaster+2.191
RW+2.138
oret+2.127
ore+2.101
Neg logit contributions
prem-1.783
 pione-1.717
ducers-1.633
-1.603
-1.556
Token c
Token ID269
Feature activation+3.92e+00

Pos logit contributions
 defer+3.849
 McMaster+3.695
oret+3.538
ore+3.500
RW+3.451
Neg logit contributions
 pione-4.632
prem-4.604
-4.408
-4.307
ducers-4.225
Tokenv
Token ID85
Feature activation+4.72e+00

Pos logit contributions
 defer+3.201
 McMaster+3.168
oret+3.165
ore+3.138
RW+3.089
Neg logit contributions
 pione-2.574
prem-2.448
-2.445
-2.361
ducers-2.254
Token2
Token ID17
Feature activation+4.47e+00

Pos logit contributions
 defer+3.349
 McMaster+3.324
oret+3.264
RW+3.223
ore+3.216
Neg logit contributions
 pione-3.521
prem-3.506
-3.319
ducers-3.271
-3.221
Token.
Token ID764
Feature activation+2.68e+00

Pos logit contributions
 defer+2.593
 McMaster+2.576
oret+2.484
RW+2.443
ore+2.430
Neg logit contributions
 pione-3.945
prem-3.932
-3.745
ducers-3.705
-3.670
Token im
Token ID545
Feature activation+3.85e+00

Pos logit contributions
 defer+1.620
 McMaster+1.598
oret+1.535
RW+1.508
ore+1.501
Neg logit contributions
prem-2.337
 pione-2.195
ducers-2.189
idth-2.097
-2.078
Tokens
Token ID82
Feature activation+1.84e-01

Pos logit contributions
prem+0.789
ducers+0.729
 pione+0.710
idth+0.694
Untitled+0.681
Neg logit contributions
 defer-0.710
 McMaster-0.705
oret-0.682
RW-0.670
ore-0.661
TokenFormat
Token ID26227
Feature activation+3.98e-01

Pos logit contributions
 defer+0.122
 McMaster+0.121
oret+0.117
RW+0.116
ore+0.114
Neg logit contributions
prem-0.149
ducers-0.139
 pione-0.138
idth-0.132
-0.130
Token.
Token ID13
Feature activation-1.32e-01

Pos logit contributions
 defer+0.305
 McMaster+0.303
oret+0.295
RW+0.294
ore+0.289
Neg logit contributions
prem-0.280
ducers-0.259
 pione-0.258
idth-0.243
-0.240
TokenAl
Token ID2348
Feature activation+3.26e-02

Pos logit contributions
prem+0.099
ducers+0.092
 pione+0.091
idth+0.087
+0.086
Neg logit contributions
 defer-0.094
 McMaster-0.093
oret-0.090
RW-0.090
ore-0.088
Tokenignment
Token ID16747
Feature activation+3.54e+00

Pos logit contributions
 defer+0.022
 McMaster+0.021
oret+0.021
RW+0.021
ore+0.020
Neg logit contributions
prem-0.026
ducers-0.024
 pione-0.024
idth-0.023
-0.023
Token =
Token ID796
Feature activation+5.68e+00

Pos logit contributions
 defer+2.729
 McMaster+2.721
RW+2.674
oret+2.660
ore+2.604
Neg logit contributions
prem-2.428
 pione-2.271
ducers-2.256
-2.095
idth-2.085
Token [
Token ID685
Feature activation+3.14e+00

Pos logit contributions
 McMaster+3.962
 defer+3.953
oret+3.815
RW+3.780
ore+3.727
Neg logit contributions
prem-4.306
 pione-4.065
ducers-4.054
idth-3.767
-3.753
Tokensystem
Token ID10057
Feature activation+1.21e+00

Pos logit contributions
 defer+2.110
 McMaster+2.107
RW+2.044
oret+2.042
ore+2.007
Neg logit contributions
prem-2.451
 pione-2.310
ducers-2.306
idth-2.170
-2.160
Token.
Token ID13
Feature activation+2.24e+00

Pos logit contributions
 defer+0.770
 McMaster+0.763
oret+0.739
RW+0.734
ore+0.725
Neg logit contributions
prem-1.000
 pione-0.947
ducers-0.938
idth-0.896
-0.889
Tokendraw
Token ID19334
Feature activation+3.13e+00

Pos logit contributions
 defer+1.463
 McMaster+1.453
oret+1.408
RW+1.407
ore+1.383
Neg logit contributions
prem-1.811
 pione-1.700
ducers-1.697
idth-1.613
-1.601
Tokening
Token ID278
Feature activation+2.72e+00

Pos logit contributions
 defer+2.007
 McMaster+1.980
oret+1.931
RW+1.908
ore+1.891
Neg logit contributions
prem-2.575
 pione-2.476
ducers-2.402
-2.342
idth-2.293
Token {
Token ID1391
Feature activation-6.91e-02

Pos logit contributions
 defer+1.259
 McMaster+1.234
oret+1.211
RW+1.200
ore+1.190
Neg logit contributions
prem-0.953
 pione-0.871
ducers-0.870
idth-0.818
Untitled-0.809
Token const
Token ID1500
Feature activation+2.80e+00

Pos logit contributions
prem+0.062
ducers+0.058
 pione+0.057
idth+0.055
+0.054
Neg logit contributions
 defer-0.040
 McMaster-0.039
oret-0.038
RW-0.038
ore-0.037
Token float
Token ID12178
Feature activation+4.79e+00

Pos logit contributions
 defer+1.716
 McMaster+1.681
oret+1.652
RW+1.618
ore+1.610
Neg logit contributions
prem-2.384
ducers-2.232
 pione-2.230
idth-2.129
-2.117
Token f
Token ID277
Feature activation+1.27e+00

Pos logit contributions
 defer+3.102
 McMaster+3.032
oret+2.988
RW+2.923
ore+2.914
Neg logit contributions
prem-3.849
ducers-3.651
 pione-3.628
humans-3.462
-3.448
TokenMass
Token ID20273
Feature activation+2.58e+00

Pos logit contributions
 defer+0.970
 McMaster+0.961
oret+0.940
RW+0.933
ore+0.920
Neg logit contributions
prem-0.890
ducers-0.822
 pione-0.819
idth-0.775
-0.764
Token =
Token ID796
Feature activation+5.68e+00

Pos logit contributions
 defer+2.061
 McMaster+2.025
oret+1.999
RW+1.988
ore+1.976
Neg logit contributions
prem-1.702
 pione-1.576
ducers-1.569
idth-1.473
-1.467
Token (
Token ID357
Feature activation+3.98e+00

Pos logit contributions
 defer+3.661
 McMaster+3.624
oret+3.564
ore+3.446
RW+3.404
Neg logit contributions
prem-4.528
 pione-4.321
ducers-4.245
idth-4.100
-4.082
Token m
Token ID285
Feature activation-4.44e-02

Pos logit contributions
 defer+2.238
 McMaster+2.205
oret+2.157
RW+2.109
ore+2.101
Neg logit contributions
prem-3.532
 pione-3.347
ducers-3.343
idth-3.214
-3.184
TokenD
Token ID35
Feature activation+1.75e+00

Pos logit contributions
prem+0.034
ducers+0.031
 pione+0.031
idth+0.029
Untitled+0.029
Neg logit contributions
 defer-0.032
 McMaster-0.031
oret-0.030
RW-0.030
ore-0.030
Tokenensity
Token ID6377
Feature activation+2.88e+00

Pos logit contributions
 defer+1.033
 McMaster+1.023
oret+0.990
RW+0.978
ore+0.963
Neg logit contributions
prem-1.532
ducers-1.438
 pione-1.429
idth-1.373
-1.354
Token +
Token ID1343
Feature activation+3.30e+00

Pos logit contributions
 defer+2.078
 McMaster+2.041
RW+1.999
oret+1.999
ore+1.957
Neg logit contributions
prem-2.142
 pione-1.992
ducers-1.980
idth-1.878
-1.869
Token)
Token ID8
Feature activation+2.12e+00

Pos logit contributions
prem+1.022
ducers+0.936
 pione+0.929
idth+0.892
Untitled+0.874
Neg logit contributions
 defer-1.076
 McMaster-1.070
oret-1.038
RW-1.030
ore-1.012
Token $
Token ID720
Feature activation+4.58e-01

Pos logit contributions
 defer+1.599
 McMaster+1.580
oret+1.545
RW+1.529
ore+1.515
Neg logit contributions
prem-1.505
ducers-1.400
 pione-1.387
idth-1.310
-1.292
TokenBr
Token ID9414
Feature activation+3.78e-01

Pos logit contributions
 defer+0.309
 McMaster+0.307
oret+0.296
RW+0.293
ore+0.288
Neg logit contributions
prem-0.364
ducers-0.338
 pione-0.332
idth-0.322
Untitled-0.316
Tokenush
Token ID1530
Feature activation+2.32e+00

Pos logit contributions
 defer+0.274
 McMaster+0.273
oret+0.265
RW+0.263
ore+0.259
Neg logit contributions
prem-0.279
ducers-0.259
 pione-0.256
idth-0.244
-0.240
Token1
Token ID16
Feature activation+1.82e+00

Pos logit contributions
 defer+1.693
 McMaster+1.676
RW+1.642
oret+1.639
ore+1.613
Neg logit contributions
prem-1.688
 pione-1.579
ducers-1.574
-1.478
idth-1.477
Token =
Token ID796
Feature activation+5.58e+00

Pos logit contributions
 defer+1.414
 McMaster+1.401
oret+1.373
RW+1.370
ore+1.351
Neg logit contributions
prem-1.252
 pione-1.166
ducers-1.163
idth-1.090
-1.082
Token New
Token ID968
Feature activation-7.35e-01

Pos logit contributions
 defer+3.877
 McMaster+3.846
oret+3.762
RW+3.705
ore+3.669
Neg logit contributions
prem-4.251
 pione-4.005
ducers-3.991
idth-3.775
-3.742
Token-
Token ID12
Feature activation-2.55e-01

Pos logit contributions
prem+0.607
ducers+0.566
Untitled+0.532
idth+0.531
 ®+0.527
Neg logit contributions
 defer-0.474
 McMaster-0.467
oret-0.450
 torches-0.446
RW-0.444
TokenObject
Token ID10267
Feature activation-4.00e-02

Pos logit contributions
prem+0.169
ducers+0.154
Untitled+0.145
idth+0.141
 pione+0.141
Neg logit contributions
 defer-0.207
 McMaster-0.205
oret-0.199
 torches-0.197
RW-0.194
Token Drawing
Token ID40027
Feature activation-9.38e-01

Pos logit contributions
prem+0.039
ducers+0.036
 pione+0.036
idth+0.035
Untitled+0.034
Neg logit contributions
 defer-0.020
 McMaster-0.020
oret-0.019
RW-0.019
ore-0.018
Token.
Token ID13
Feature activation-6.69e-01

Pos logit contributions
prem+0.735
ducers+0.681
 pione+0.665
idth+0.647
Untitled+0.644
Neg logit contributions
 defer-0.635
 McMaster-0.632
oret-0.612
RW-0.602
ore-0.595
Token app
Token ID598
Feature activation+5.25e+00

Pos logit contributions
 defer+0.588
 McMaster+0.584
oret+0.562
RW+0.557
ore+0.543
Neg logit contributions
prem-1.069
ducers-1.007
 pione-0.996
idth-0.965
Untitled-0.949
Tokendata
Token ID7890
Feature activation+1.87e+00

Pos logit contributions
 defer+3.920
 McMaster+3.882
oret+3.824
ore+3.785
RW+3.752
Neg logit contributions
 pione-3.714
prem-3.685
-3.501
ducers-3.400
-3.392
Token _
Token ID4808
Feature activation+4.10e+00

Pos logit contributions
 defer+1.202
 McMaster+1.189
oret+1.151
RW+1.138
ore+1.122
Neg logit contributions
prem-1.546
 pione-1.456
ducers-1.445
idth-1.384
-1.373
Token full
Token ID1336
Feature activation+6.57e-01

Pos logit contributions
 defer+2.549
 McMaster+2.422
oret+2.375
ore+2.326
RW+2.315
Neg logit contributions
prem-3.484
 pione-3.341
ducers-3.287
idth-3.178
-3.168
Token v
Token ID410
Feature activation+4.64e+00

Pos logit contributions
 defer+0.503
 McMaster+0.497
oret+0.484
RW+0.479
ore+0.474
Neg logit contributions
prem-0.463
 pione-0.428
ducers-0.426
idth-0.405
-0.399
Token )
Token ID1267
Feature activation+5.53e+00

Pos logit contributions
 defer+3.610
 McMaster+3.513
oret+3.467
ore+3.387
RW+3.359
Neg logit contributions
prem-3.189
 pione-3.162
-2.991
-2.927
ducers-2.917
Token {
Token ID1391
Feature activation+2.47e+00

Pos logit contributions
 defer+4.638
 McMaster+4.547
oret+4.457
ore+4.388
RW+4.381
Neg logit contributions
 pione-3.518
prem-3.462
-3.287
-3.212
ducers-3.130
Token //
Token ID3373
Feature activation+2.49e+00

Pos logit contributions
 defer+1.881
 McMaster+1.823
oret+1.786
RW+1.744
ore+1.740
Neg logit contributions
prem-1.774
ducers-1.634
 pione-1.621
idth-1.555
-1.524
Token Time
Token ID3862
Feature activation+1.51e+00

Pos logit contributions
 defer+1.737
 McMaster+1.704
oret+1.680
RW+1.630
ore+1.629
Neg logit contributions
prem-1.917
 pione-1.785
ducers-1.780
-1.684
idth-1.675
Token component
Token ID7515
Feature activation+2.09e+00

Pos logit contributions
 defer+0.882
 McMaster+0.879
oret+0.851
RW+0.844
ore+0.824
Neg logit contributions
prem-1.328
ducers-1.243
 pione-1.220
idth-1.187
Untitled-1.165
Token const
Token ID1500
Feature activation+4.26e+00

Pos logit contributions
 defer+1.089
 McMaster+1.064
oret+1.020
RW+1.000
ore+0.985
Neg logit contributions
prem-1.988
 pione-1.896
ducers-1.877
idth-1.805
-1.802
Token -
Token ID532
Feature activation-2.04e-01

Pos logit contributions
 defer+1.111
 McMaster+1.098
oret+1.075
RW+1.056
ore+1.051
Neg logit contributions
prem-1.253
ducers-1.167
 pione-1.161
idth-1.095
-1.094
Token 42
Token ID5433
Feature activation+3.39e-01

Pos logit contributions
prem+0.158
ducers+0.147
 pione+0.145
idth+0.139
+0.136
Neg logit contributions
 defer-0.141
 McMaster-0.140
oret-0.136
RW-0.135
ore-0.133
Token mile
Token ID10591
Feature activation+8.72e-01

Pos logit contributions
 defer+0.221
 McMaster+0.220
oret+0.213
RW+0.211
ore+0.208
Neg logit contributions
prem-0.276
ducers-0.257
 pione-0.255
idth-0.244
-0.240
Token)
Token ID8
Feature activation+1.84e+00

Pos logit contributions
 defer+0.614
 McMaster+0.609
oret+0.594
RW+0.586
ore+0.579
Neg logit contributions
prem-0.666
ducers-0.620
 pione-0.615
idth-0.587
-0.577
Token
Token ID198
Feature activation+5.14e+00

Pos logit contributions
 McMaster+1.276
 defer+1.276
oret+1.235
RW+1.225
ore+1.210
Neg logit contributions
prem-1.415
ducers-1.316
 pione-1.307
idth-1.246
-1.229
Token
Token ID198
Feature activation+5.52e+00

Pos logit contributions
RW+3.448
 McMaster+3.413
 defer+3.391
ore+3.337
Bloom+3.334
Neg logit contributions
prem-3.933
 pione-3.918
-3.725
ducers-3.718
-3.597
TokenDate
Token ID10430
Feature activation+1.55e+00

Pos logit contributions
RW+3.635
 defer+3.608
 McMaster+3.589
oret+3.571
ore+3.558
Neg logit contributions
prem-4.246
 pione-4.215
ducers-4.003
-3.977
idth-3.833
Token:
Token ID25
Feature activation+3.19e-01

Pos logit contributions
 McMaster+1.118
 defer+1.114
oret+1.082
RW+1.072
ore+1.064
Neg logit contributions
prem-1.146
 pione-1.065
ducers-1.064
idth-1.007
-0.999
Token 5
Token ID642
Feature activation+1.10e+00

Pos logit contributions
 defer+0.212
 McMaster+0.210
oret+0.204
RW+0.202
ore+0.199
Neg logit contributions
prem-0.256
ducers-0.238
 pione-0.234
idth-0.226
Untitled-0.222
Token/
Token ID14
Feature activation+1.57e+00

Pos logit contributions
 defer+0.698
 McMaster+0.694
oret+0.669
RW+0.664
ore+0.654
Neg logit contributions
prem-0.919
ducers-0.858
 pione-0.858
idth-0.820
-0.811
Token21
Token ID2481
Feature activation+1.49e+00

Pos logit contributions
 defer+1.175
 McMaster+1.168
oret+1.137
RW+1.129
ore+1.112
Neg logit contributions
prem-1.123
ducers-1.038
 pione-1.034
idth-0.983
-0.966
Token C
Token ID327
Feature activation+2.29e+00

Pos logit contributions
prem+1.430
ducers+1.320
 pione+1.283
idth+1.237
 ®+1.215
Neg logit contributions
 defer-1.710
 McMaster-1.696
oret-1.658
RW-1.645
Bloom-1.623
Token,
Token ID11
Feature activation-1.60e+00

Pos logit contributions
 McMaster+1.505
 defer+1.485
oret+1.434
RW+1.431
ore+1.420
Neg logit contributions
prem-1.846
 pione-1.716
ducers-1.715
idth-1.628
humans-1.617
Token Y
Token ID575
Feature activation-4.54e-01

Pos logit contributions
prem+0.823
ducers+0.736
 pione+0.722
idth+0.678
+0.654
Neg logit contributions
 defer-1.520
 McMaster-1.511
oret-1.482
RW-1.474
ore-1.454
TokenYR
Token ID38162
Feature activation+1.32e+00

Pos logit contributions
prem+0.346
ducers+0.321
 pione+0.318
idth+0.305
+0.298
Neg logit contributions
 defer-0.319
 McMaster-0.317
oret-0.308
RW-0.305
ore-0.300
Token DS
Token ID17400
Feature activation+2.62e+00

Pos logit contributions
 defer+0.941
 McMaster+0.941
oret+0.910
RW+0.908
ore+0.893
Neg logit contributions
prem-0.998
ducers-0.928
 pione-0.921
idth-0.873
-0.862
Token cent
Token ID1247
Feature activation+5.49e+00

Pos logit contributions
 McMaster+1.805
 defer+1.804
RW+1.756
oret+1.741
ore+1.716
Neg logit contributions
prem-2.029
 pione-1.885
ducers-1.882
idth-1.767
humans-1.760
Tokenering
Token ID1586
Feature activation+2.96e+00

Pos logit contributions
 McMaster+2.854
 defer+2.852
ore+2.714
oret+2.707
RW+2.703
Neg logit contributions
prem-5.029
 pione-4.874
ducers-4.700
idth-4.657
Untitled-4.627
Token
Token ID198
Feature activation+1.21e+00

Pos logit contributions
 defer+2.032
 McMaster+2.018
oret+1.951
RW+1.935
ore+1.930
Neg logit contributions
prem-2.294
 pione-2.147
ducers-2.132
idth-2.012
Untitled-2.005
Token
Token ID198
Feature activation+1.82e+00

Pos logit contributions
 defer+0.905
 McMaster+0.899
oret+0.874
RW+0.867
ore+0.853
Neg logit contributions
prem-0.874
ducers-0.807
 pione-0.775
idth-0.756
Untitled-0.745
TokenThe
Token ID464
Feature activation-9.61e-01

Pos logit contributions
 defer+1.205
 McMaster+1.201
oret+1.168
RW+1.166
ore+1.144
Neg logit contributions
prem-1.455
 pione-1.374
ducers-1.358
idth-1.297
-1.296
Token Garg
Token ID39013
Feature activation-1.39e+00

Pos logit contributions
prem+0.811
ducers+0.758
 pione+0.750
idth+0.723
+0.709
Neg logit contributions
 defer-0.596
 McMaster-0.591
oret-0.569
RW-0.569
ore-0.555
Token {
Token ID1391
Feature activation+2.47e+00

Pos logit contributions
 defer+4.638
 McMaster+4.547
oret+4.457
ore+4.388
RW+4.381
Neg logit contributions
 pione-3.518
prem-3.462
-3.287
-3.212
ducers-3.130
Token //
Token ID3373
Feature activation+2.49e+00

Pos logit contributions
 defer+1.881
 McMaster+1.823
oret+1.786
RW+1.744
ore+1.740
Neg logit contributions
prem-1.774
ducers-1.634
 pione-1.621
idth-1.555
-1.524
Token Time
Token ID3862
Feature activation+1.51e+00

Pos logit contributions
 defer+1.737
 McMaster+1.704
oret+1.680
RW+1.630
ore+1.629
Neg logit contributions
prem-1.917
 pione-1.785
ducers-1.780
-1.684
idth-1.675
Token component
Token ID7515
Feature activation+2.09e+00

Pos logit contributions
 defer+0.882
 McMaster+0.879
oret+0.851
RW+0.844
ore+0.824
Neg logit contributions
prem-1.328
ducers-1.243
 pione-1.220
idth-1.187
Untitled-1.165
Token const
Token ID1500
Feature activation+4.26e+00

Pos logit contributions
 defer+1.089
 McMaster+1.064
oret+1.020
RW+1.000
ore+0.985
Neg logit contributions
prem-1.988
 pione-1.896
ducers-1.877
idth-1.805
-1.802
Token float
Token ID12178
Feature activation+5.49e+00

Pos logit contributions
 defer+2.010
 McMaster+1.909
oret+1.845
RW+1.786
ore+1.763
Neg logit contributions
prem-4.267
 pione-4.192
ducers-4.034
-4.010
-3.900
Token TA
Token ID21664
Feature activation-1.35e+00

Pos logit contributions
 defer+3.943
 McMaster+3.888
oret+3.776
RW+3.687
ore+3.599
Neg logit contributions
prem-4.091
 pione-4.023
ducers-3.834
-3.801
idth-3.647
TokenU
Token ID52
Feature activation+6.31e-01

Pos logit contributions
prem+0.837
ducers+0.759
 pione+0.707
idth+0.704
Untitled+0.699
Neg logit contributions
 defer-1.138
 McMaster-1.129
oret-1.098
 torches-1.083
RW-1.083
Token =
Token ID796
Feature activation+4.82e+00

Pos logit contributions
 defer+0.540
 McMaster+0.537
oret+0.525
RW+0.520
ore+0.514
Neg logit contributions
prem-0.385
ducers-0.350
 pione-0.336
idth-0.326
Untitled-0.318
Token 6
Token ID718
Feature activation+3.10e+00

Pos logit contributions
 defer+2.976
 McMaster+2.853
oret+2.743
ore+2.728
RW+2.678
Neg logit contributions
prem-4.051
 pione-3.860
ducers-3.804
-3.708
Untitled-3.633
Token.
Token ID13
Feature activation+3.03e+00

Pos logit contributions
 defer+1.947
 McMaster+1.938
oret+1.875
RW+1.854
ore+1.828
Neg logit contributions
prem-2.585
 pione-2.494
ducers-2.421
-2.361
idth-2.323
Token an
Token ID281
Feature activation+1.70e-01

Pos logit contributions
prem+0.558
ducers+0.517
 pione+0.508
idth+0.488
Untitled+0.479
Neg logit contributions
 defer-0.482
 McMaster-0.479
oret-0.466
RW-0.464
ore-0.453
Token additional
Token ID3224
Feature activation+1.61e-01

Pos logit contributions
 defer+0.106
 McMaster+0.106
oret+0.102
RW+0.101
Bloom+0.098
Neg logit contributions
prem-0.143
ducers-0.134
 pione-0.132
idth-0.127
Untitled-0.125
Token hour
Token ID1711
Feature activation+8.86e-01

Pos logit contributions
 defer+0.110
 McMaster+0.109
oret+0.106
RW+0.105
ore+0.103
Neg logit contributions
prem-0.125
ducers-0.117
 pione-0.115
idth-0.110
Untitled-0.108
Token of
Token ID286
Feature activation-1.04e+00

Pos logit contributions
 defer+0.605
 McMaster+0.599
oret+0.581
RW+0.576
ore+0.568
Neg logit contributions
prem-0.692
ducers-0.646
 pione-0.644
idth-0.616
-0.607
Token Fox
Token ID5426
Feature activation+9.71e-01

Pos logit contributions
prem+0.840
ducers+0.777
 pione+0.762
idth+0.735
 ®+0.723
Neg logit contributions
 defer-0.682
 McMaster-0.677
oret-0.658
RW-0.654
ore-0.639
Token &
Token ID1222
Feature activation+5.45e+00

Pos logit contributions
 defer+0.546
 McMaster+0.541
oret+0.523
RW+0.516
ore+0.507
Neg logit contributions
prem-0.876
ducers-0.823
 pione-0.819
idth-0.789
-0.778
Token Friends
Token ID14213
Feature activation+1.24e+00

Pos logit contributions
 McMaster+2.817
 defer+2.789
oret+2.673
RW+2.634
ore+2.597
Neg logit contributions
prem-5.128
 pione-5.002
ducers-4.831
-4.766
idth-4.701
Token co
Token ID763
Feature activation+3.07e+00

Pos logit contributions
 defer+0.823
 McMaster+0.817
oret+0.792
RW+0.782
ore+0.773
Neg logit contributions
prem-0.992
ducers-0.926
 pione-0.923
idth-0.884
-0.869
Token-
Token ID12
Feature activation-1.96e-01

Pos logit contributions
 McMaster+1.724
 defer+1.719
oret+1.662
ore+1.653
RW+1.632
Neg logit contributions
prem-2.726
 pione-2.594
ducers-2.547
-2.466
idth-2.465
Tokenhost
Token ID4774
Feature activation+2.33e+00

Pos logit contributions
prem+0.163
ducers+0.152
 pione+0.151
idth+0.145
Untitled+0.142
Neg logit contributions
 defer-0.124
 McMaster-0.123
oret-0.119
RW-0.118
ore-0.116
Tokened
Token ID276
Feature activation+1.46e+00

Pos logit contributions
 defer+1.548
 McMaster+1.546
oret+1.510
ore+1.481
RW+1.476
Neg logit contributions
prem-1.840
 pione-1.728
ducers-1.714
idth-1.651
-1.636
Token at
Token ID379
Feature activation+8.85e-01

Pos logit contributions
prem+0.250
ducers+0.232
 pione+0.230
idth+0.220
+0.216
Neg logit contributions
 defer-0.234
 McMaster-0.232
oret-0.225
RW-0.224
ore-0.220
Token 8
Token ID807
Feature activation-7.71e-01

Pos logit contributions
 defer+0.600
 McMaster+0.596
oret+0.577
RW+0.571
ore+0.563
Neg logit contributions
prem-0.698
ducers-0.650
 pione-0.645
idth-0.618
-0.610
Token13
Token ID1485
Feature activation+8.15e-01

Pos logit contributions
prem+0.522
ducers+0.475
 pione+0.474
idth+0.452
Untitled+0.440
Neg logit contributions
 defer-0.605
 McMaster-0.602
oret-0.588
RW-0.580
ore-0.575
Token-
Token ID12
Feature activation-3.04e+00

Pos logit contributions
 defer+0.482
 McMaster+0.479
oret+0.464
RW+0.459
ore+0.452
Neg logit contributions
prem-0.713
ducers-0.671
 pione-0.664
idth-0.641
-0.632
Token247
Token ID23753
Feature activation-1.73e+00

Pos logit contributions
prem+2.302
ducers+2.096
 pione+2.048
idth+1.986
Untitled+1.962
Neg logit contributions
 defer-2.166
 McMaster-2.142
oret-2.091
RW-2.027
 torches-2.022
Token-
Token ID12
Feature activation-6.71e+00

Pos logit contributions
prem+1.416
ducers+1.309
Untitled+1.221
idth+1.218
 ®+1.217
Neg logit contributions
 defer-1.130
 McMaster-1.120
oret-1.075
 torches-1.067
RW-1.059
Token86
Token ID4521
Feature activation-1.79e+00

Pos logit contributions
prem+4.515
ducers+3.935
Untitled+3.816
Ku+3.663
humans+3.653
Neg logit contributions
 defer-5.363
 McMaster-5.213
 torches-5.137
oret-5.128
��-5.087
Token22
Token ID1828
Feature activation-5.24e-01

Pos logit contributions
prem+1.264
ducers+1.153
Untitled+1.071
idth+1.071
 pione+1.062
Neg logit contributions
 defer-1.381
 McMaster-1.359
oret-1.326
RW-1.307
 torches-1.305
Token.
Token ID13
Feature activation-1.47e+00

Pos logit contributions
prem+0.410
ducers+0.382
 pione+0.378
idth+0.363
+0.356
Neg logit contributions
 defer-0.358
 McMaster-0.355
oret-0.345
RW-0.342
ore-0.336
Token
Token ID198
Feature activation-5.16e-01

Pos logit contributions
prem+0.998
ducers+0.915
 pione+0.899
idth+0.857
 ®+0.845
Neg logit contributions
 defer-1.164
 McMaster-1.154
oret-1.126
RW-1.119
ore-1.098
Token
Token ID198
Feature activation-4.11e-01

Pos logit contributions
prem+0.360
ducers+0.330
Untitled+0.304
idth+0.302
 ®+0.301
Neg logit contributions
 defer-0.398
 McMaster-0.396
oret-0.384
RW-0.381
 torches-0.380
Token to
Token ID284
Feature activation+1.76e-03

Pos logit contributions
 defer+1.675
 McMaster+1.654
oret+1.612
RW+1.595
ore+1.582
Neg logit contributions
prem-1.601
 pione-1.546
ducers-1.490
-1.443
idth-1.419
Token our
Token ID674
Feature activation+1.46e+00

Pos logit contributions
 McMaster+0.001
 defer+0.001
RW+0.001
oret+0.001
 torches+0.001
Neg logit contributions
prem-0.001
ducers-0.001
 pione-0.001
humans-0.001
idth-0.001
Token free
Token ID1479
Feature activation-1.19e+00

Pos logit contributions
 defer+1.153
 McMaster+1.143
oret+1.113
RW+1.101
ore+1.088
Neg logit contributions
prem-0.985
 pione-0.927
ducers-0.911
idth-0.863
-0.862
Token newsletters
Token ID16983
Feature activation+2.74e-01

Pos logit contributions
prem+0.747
ducers+0.680
 pione+0.653
idth+0.627
Untitled+0.617
Neg logit contributions
 defer-0.995
 McMaster-0.994
oret-0.965
RW-0.961
ore-0.951
Token.
Token ID13
Feature activation-1.73e+00

Pos logit contributions
 McMaster+0.187
 defer+0.187
oret+0.183
RW+0.180
 torches+0.177
Neg logit contributions
prem-0.212
ducers-0.196
 pione-0.186
idth-0.185
 ®-0.183
Token
Token ID198
Feature activation-6.46e+00

Pos logit contributions
prem+1.079
ducers+0.985
 pione+0.974
idth+0.922
+0.899
Neg logit contributions
 defer-1.450
 McMaster-1.442
oret-1.408
RW-1.398
ore-1.379
Token
Token ID198
Feature activation-4.60e+00

Pos logit contributions
prem+3.809
ducers+3.336
Untitled+3.102
humans+3.003
 ®+2.952
Neg logit contributions
��-5.759
 torches-5.587
 defer-5.536
 McMaster-5.431
 cleansing-5.305
TokenIf
Token ID1532
Feature activation-4.45e-02

Pos logit contributions
prem+3.281
ducers+2.932
Untitled+2.883
humans+2.744
Ku+2.725
Neg logit contributions
 defer-3.533
 McMaster-3.459
 torches-3.351
oret-3.331
��-3.297
Token you
Token ID345
Feature activation+1.20e+00

Pos logit contributions
prem+0.033
ducers+0.030
 pione+0.030
idth+0.029
+0.028
Neg logit contributions
 defer-0.032
 McMaster-0.032
oret-0.031
RW-0.031
ore-0.031
Token put
Token ID1234
Feature activation+1.28e+00

Pos logit contributions
 defer+0.792
 McMaster+0.787
oret+0.763
RW+0.757
ore+0.743
Neg logit contributions
prem-0.970
ducers-0.904
 pione-0.894
idth-0.860
Untitled-0.842
Token out
Token ID503
Feature activation+4.62e-01

Pos logit contributions
 defer+0.867
 McMaster+0.861
oret+0.836
RW+0.829
ore+0.815
Neg logit contributions
prem-1.007
ducers-0.937
 pione-0.928
idth-0.890
-0.873
Token to
Token ID284
Feature activation-9.21e-02

Pos logit contributions
 defer+1.656
 McMaster+1.635
oret+1.594
RW+1.577
ore+1.564
Neg logit contributions
prem-1.584
 pione-1.529
ducers-1.473
-1.428
idth-1.402
Token our
Token ID674
Feature activation+1.48e+00

Pos logit contributions
prem+0.064
ducers+0.059
humans+0.054
 pione+0.054
idth+0.053
Neg logit contributions
 McMaster-0.071
 defer-0.071
RW-0.069
oret-0.069
 torches-0.068
Token free
Token ID1479
Feature activation-1.25e+00

Pos logit contributions
 defer+1.169
 McMaster+1.159
oret+1.130
RW+1.118
ore+1.105
Neg logit contributions
prem-0.996
 pione-0.935
ducers-0.920
idth-0.872
-0.870
Token newsletters
Token ID16983
Feature activation+3.42e-01

Pos logit contributions
prem+0.784
ducers+0.715
 pione+0.685
idth+0.659
Untitled+0.648
Neg logit contributions
 defer-1.048
 McMaster-1.047
oret-1.016
RW-1.013
ore-1.001
Token.
Token ID13
Feature activation-1.49e+00

Pos logit contributions
 McMaster+0.234
 defer+0.234
oret+0.228
RW+0.225
 torches+0.221
Neg logit contributions
prem-0.266
ducers-0.245
 pione-0.233
idth-0.231
 ®-0.229
Token
Token ID198
Feature activation-6.34e+00

Pos logit contributions
prem+0.935
ducers+0.855
 pione+0.850
idth+0.802
+0.786
Neg logit contributions
 defer-1.241
 McMaster-1.235
oret-1.204
RW-1.197
ore-1.182
Token
Token ID198
Feature activation-4.50e+00

Pos logit contributions
prem+3.753
ducers+3.295
Untitled+3.071
humans+2.972
 ®+2.928
Neg logit contributions
��-5.644
 torches-5.485
 defer-5.442
 McMaster-5.322
 cleansing-5.197
TokenUpdate
Token ID10260
Feature activation+3.17e+00

Pos logit contributions
prem+3.213
ducers+2.873
Untitled+2.821
humans+2.688
Ku+2.666
Neg logit contributions
 defer-3.458
 McMaster-3.385
 torches-3.283
oret-3.262
��-3.228
Token,
Token ID11
Feature activation-1.64e-01

Pos logit contributions
 defer+2.195
 McMaster+2.188
oret+2.112
RW+2.070
ore+2.069
Neg logit contributions
prem-2.445
 pione-2.328
ducers-2.282
idth-2.192
-2.170
Token 3
Token ID513
Feature activation+5.62e-01

Pos logit contributions
prem+0.134
ducers+0.125
 pione+0.123
idth+0.118
Untitled+0.117
Neg logit contributions
 defer-0.106
 McMaster-0.105
oret-0.102
RW-0.101
ore-0.099
Token:
Token ID25
Feature activation+6.15e-02

Pos logit contributions
 defer+0.423
 McMaster+0.419
oret+0.407
RW+0.405
ore+0.400
Neg logit contributions
prem-0.401
ducers-0.370
 pione-0.369
idth-0.351
-0.345
Token or
Token ID393
Feature activation+4.94e-01

Pos logit contributions
prem+0.344
 pione+0.327
ducers+0.327
idth+0.313
+0.308
Neg logit contributions
 defer-0.311
 McMaster-0.307
oret-0.301
RW-0.298
ore-0.298
Token call
Token ID869
Feature activation+5.78e-01

Pos logit contributions
 defer+0.344
 McMaster+0.341
oret+0.331
RW+0.328
ore+0.324
Neg logit contributions
prem-0.380
ducers-0.354
 pione-0.350
idth-0.336
-0.330
Token 03
Token ID7643
Feature activation-4.81e-01

Pos logit contributions
 defer+0.359
 McMaster+0.355
oret+0.344
RW+0.339
ore+0.337
Neg logit contributions
prem-0.490
ducers-0.459
 pione-0.454
idth-0.440
-0.432
Token30
Token ID1270
Feature activation+2.88e+00

Pos logit contributions
prem+0.392
ducers+0.364
 pione+0.361
idth+0.347
humans+0.342
Neg logit contributions
 defer-0.312
 McMaster-0.309
RW-0.299
oret-0.298
ore-0.291
Token 333
Token ID23460
Feature activation-2.26e+00

Pos logit contributions
 defer+2.070
 McMaster+2.064
oret+2.011
ore+1.978
RW+1.970
Neg logit contributions
prem-2.137
ducers-2.031
 pione-1.990
idth-1.889
-1.884
Token 68
Token ID8257
Feature activation-6.02e+00

Pos logit contributions
prem+1.626
ducers+1.461
 pione+1.458
 ®+1.403
idth+1.400
Neg logit contributions
 defer-1.667
 McMaster-1.646
Bloom-1.612
RW-1.593
oret-1.586
Token46
Token ID3510
Feature activation-1.01e+00

Pos logit contributions
prem+2.913
ducers+2.588
 pione+2.547
Untitled+2.450
idth+2.369
Neg logit contributions
 defer-5.791
 McMaster-5.711
oret-5.691
ore-5.568
RW-5.535
Token.
Token ID13
Feature activation-2.00e+00

Pos logit contributions
prem+0.848
ducers+0.805
 pione+0.795
idth+0.769
+0.756
Neg logit contributions
 defer-0.625
 McMaster-0.614
oret-0.599
ore-0.594
RW-0.591
Token<|endoftext|>
Token ID50256
Feature activation+2.31e-02

Pos logit contributions
prem+1.328
ducers+1.228
 pione+1.220
idth+1.163
+1.135
Neg logit contributions
 defer-1.596
 McMaster-1.586
oret-1.545
RW-1.535
ore-1.516
Token(
Token ID7
Feature activation+2.70e-02

Pos logit contributions
 defer+0.017
 McMaster+0.017
oret+0.016
RW+0.016
ore+0.016
Neg logit contributions
prem-0.017
ducers-0.016
 pione-0.015
idth-0.015
Untitled-0.014
TokenFIL
Token ID46700
Feature activation-1.84e+00

Pos logit contributions
 defer+0.020
 McMaster+0.020
oret+0.019
RW+0.019
ore+0.019
Neg logit contributions
prem-0.020
ducers-0.018
 pione-0.018
idth-0.017
Untitled-0.017
Token he
Token ID339
Feature activation+1.38e+00

Pos logit contributions
prem+1.215
ducers+1.121
 pione+1.086
idth+1.055
Untitled+1.034
Neg logit contributions
 defer-1.145
 McMaster-1.142
oret-1.116
RW-1.114
Bloom-1.087
Token's
Token ID338
Feature activation+1.90e-01

Pos logit contributions
 defer+0.935
 McMaster+0.927
oret+0.900
RW+0.891
ore+0.877
Neg logit contributions
prem-1.096
ducers-1.021
 pione-1.016
idth-0.971
-0.955
Token only
Token ID691
Feature activation+1.30e+00

Pos logit contributions
 defer+0.124
 McMaster+0.124
oret+0.120
RW+0.120
ore+0.117
Neg logit contributions
prem-0.153
ducers-0.142
 pione-0.140
idth-0.135
Untitled-0.132
Token scored
Token ID7781
Feature activation-1.83e+00

Pos logit contributions
 defer+0.889
 McMaster+0.883
oret+0.858
RW+0.851
ore+0.836
Neg logit contributions
prem-1.022
ducers-0.950
 pione-0.940
idth-0.902
-0.884
Token 20
Token ID1160
Feature activation+1.50e+00

Pos logit contributions
prem+1.360
ducers+1.247
 pione+1.204
idth+1.177
 ®+1.163
Neg logit contributions
 defer-1.303
 McMaster-1.297
RW-1.264
oret-1.259
Bloom-1.242
Token Fantasy
Token ID10982
Feature activation-5.99e+00

Pos logit contributions
 defer+1.070
 McMaster+1.060
oret+1.034
RW+1.023
ore+1.014
Neg logit contributions
prem-1.126
ducers-1.047
 pione-1.038
idth-0.992
-0.974
Token points
Token ID2173
Feature activation-2.80e+00

Pos logit contributions
prem+3.336
ducers+2.997
 pione+2.889
idth+2.749
 ®+2.743
Neg logit contributions
 McMaster-5.290
 defer-5.246
oret-5.161
RW-5.122
��-5.062
Token once
Token ID1752
Feature activation+7.74e-02

Pos logit contributions
prem+2.063
ducers+1.889
 pione+1.766
 ®+1.750
 Dak+1.744
Neg logit contributions
 McMaster-1.990
 defer-1.984
RW-1.952
oret-1.941
Bloom-1.923
Token in
Token ID287
Feature activation+5.07e-01

Pos logit contributions
 defer+0.054
 McMaster+0.053
oret+0.052
RW+0.052
ore+0.051
Neg logit contributions
prem-0.059
ducers-0.055
 pione-0.054
idth-0.052
Untitled-0.051
Token six
Token ID2237
Feature activation+4.44e-01

Pos logit contributions
 defer+0.356
 McMaster+0.353
oret+0.344
RW+0.343
ore+0.335
Neg logit contributions
prem-0.386
ducers-0.358
 pione-0.352
idth-0.339
 ®-0.331
Token games
Token ID1830
Feature activation-2.33e+00

Pos logit contributions
 defer+0.279
 McMaster+0.277
oret+0.269
RW+0.267
ore+0.261
Neg logit contributions
prem-0.371
ducers-0.347
 pione-0.342
idth-0.330
Untitled-0.324
Token scenes
Token ID8188
Feature activation-1.01e+00

Pos logit contributions
prem+0.747
ducers+0.707
Untitled+0.657
idth+0.651
humans+0.647
Neg logit contributions
 defer-0.678
 McMaster-0.670
oret-0.653
RW-0.643
Bloom-0.636
Token.
Token ID13
Feature activation-9.69e-01

Pos logit contributions
prem+0.777
ducers+0.714
idth+0.667
Untitled+0.666
humans+0.660
Neg logit contributions
 defer-0.703
 McMaster-0.695
oret-0.676
RW-0.666
 torches-0.663
Token The
Token ID383
Feature activation-8.75e-01

Pos logit contributions
prem+0.811
ducers+0.758
 ®+0.711
Untitled+0.711
idth+0.706
Neg logit contributions
 defer-0.616
 McMaster-0.595
oret-0.583
 torches-0.578
RW-0.577
Token new
Token ID649
Feature activation-1.88e+00

Pos logit contributions
prem+0.617
ducers+0.567
 pione+0.559
idth+0.535
Untitled+0.524
Neg logit contributions
 defer-0.667
 McMaster-0.663
oret-0.642
RW-0.640
Bloom-0.628
Token vehicle
Token ID4038
Feature activation-2.01e+00

Pos logit contributions
prem+1.257
ducers+1.131
 pione+1.092
idth+1.060
Untitled+1.046
Neg logit contributions
 defer-1.508
 McMaster-1.504
RW-1.461
oret-1.458
Bloom-1.431
Token E
Token ID412
Feature activation-5.98e+00

Pos logit contributions
prem+1.377
ducers+1.267
 pione+1.253
idth+1.193
+1.166
Neg logit contributions
 defer-1.566
 McMaster-1.556
oret-1.516
RW-1.504
ore-1.482
Tokenct
Token ID310
Feature activation-4.80e+00

Pos logit contributions
prem+3.628
ducers+3.348
idth+3.099
humans+3.029
Untitled+3.019
Neg logit contributions
 McMaster-5.061
 defer-5.037
 torches-4.827
RW-4.787
Bloom-4.745
Tokeno
Token ID78
Feature activation-4.20e+00

Pos logit contributions
prem+3.252
ducers+2.892
idth+2.675
Untitled+2.645
humans+2.630
Neg logit contributions
 defer-3.837
 McMaster-3.830
 torches-3.690
��-3.648
RW-3.611
Token-
Token ID12
Feature activation-4.05e+00

Pos logit contributions
prem+3.238
ducers+3.006
Untitled+2.792
 ®+2.778
humans+2.778
Neg logit contributions
 defer-2.872
 McMaster-2.861
 torches-2.766
��-2.757
oret-2.747
Token1
Token ID16
Feature activation-1.01e+00

Pos logit contributions
prem+2.720
ducers+2.461
Untitled+2.279
humans+2.262
idth+2.233
Neg logit contributions
 defer-3.253
 McMaster-3.241
oret-3.138
 torches-3.109
��-3.073
Token was
Token ID373
Feature activation-2.21e+00

Pos logit contributions
prem+0.730
ducers+0.673
idth+0.625
Untitled+0.625
 pione+0.621
Neg logit contributions
 defer-0.755
 McMaster-0.748
oret-0.726
RW-0.718
Bloom-0.713
Token points
Token ID2173
Feature activation-1.27e+00

Pos logit contributions
 defer+0.774
 McMaster+0.769
oret+0.744
RW+0.736
ore+0.725
Neg logit contributions
prem-0.913
ducers-0.853
 pione-0.852
idth-0.811
-0.801
Token.
Token ID13
Feature activation+7.75e-01

Pos logit contributions
prem+0.970
ducers+0.891
 pione+0.867
idth+0.837
 ®+0.827
Neg logit contributions
 defer-0.890
 McMaster-0.889
oret-0.867
RW-0.866
Bloom-0.847
Token He
Token ID679
Feature activation+1.47e+00

Pos logit contributions
 defer+0.551
 McMaster+0.550
oret+0.533
RW+0.528
ore+0.520
Neg logit contributions
prem-0.583
 pione-0.543
ducers-0.542
idth-0.517
-0.510
Token had
Token ID550
Feature activation+2.49e-01

Pos logit contributions
 defer+1.025
 McMaster+1.017
oret+0.989
RW+0.977
ore+0.964
Neg logit contributions
prem-1.126
ducers-1.047
 pione-1.046
idth-0.995
-0.982
Token 19
Token ID678
Feature activation+1.76e+00

Pos logit contributions
 defer+0.174
 McMaster+0.173
oret+0.168
RW+0.166
ore+0.164
Neg logit contributions
prem-0.191
ducers-0.177
 pione-0.175
idth-0.168
-0.165
Token Fantasy
Token ID10982
Feature activation-5.93e+00

Pos logit contributions
 defer+1.045
 McMaster+1.025
oret+1.000
RW+0.985
ore+0.976
Neg logit contributions
prem-1.537
ducers-1.443
 pione-1.436
idth-1.383
-1.362
Token points
Token ID2173
Feature activation-2.23e+00

Pos logit contributions
prem+3.285
ducers+2.908
 pione+2.794
idth+2.699
 Dak+2.696
Neg logit contributions
 McMaster-5.223
 defer-5.158
oret-5.121
RW-5.047
Bloom-5.021
Token against
Token ID1028
Feature activation-4.13e-01

Pos logit contributions
prem+1.670
ducers+1.533
 pione+1.453
idth+1.420
 ®+1.417
Neg logit contributions
 McMaster-1.578
 defer-1.565
RW-1.540
oret-1.530
Bloom-1.512
Token the
Token ID262
Feature activation-1.05e-01

Pos logit contributions
prem+0.303
ducers+0.281
 pione+0.278
idth+0.266
+0.260
Neg logit contributions
 defer-0.302
 McMaster-0.300
oret-0.292
RW-0.290
ore-0.285
Token Saints
Token ID13048
Feature activation+7.01e-01

Pos logit contributions
prem+0.079
 pione+0.074
ducers+0.074
idth+0.070
+0.069
Neg logit contributions
 defer-0.076
 McMaster-0.075
oret-0.073
RW-0.072
ore-0.071
Token last
Token ID938
Feature activation-1.53e+00

Pos logit contributions
 defer+0.476
 McMaster+0.472
oret+0.459
RW+0.454
ore+0.447
Neg logit contributions
prem-0.552
ducers-0.514
 pione-0.510
idth-0.489
-0.480
TokenTweet
Token ID47845
Feature activation-1.91e+00

Pos logit contributions
prem+2.281
ducers+2.064
Untitled+1.963
humans+1.923
idth+1.901
Neg logit contributions
 defer-2.362
 McMaster-2.349
oret-2.240
 torches-2.225
RW-2.180
Token
Token ID198
Feature activation-3.84e+00

Pos logit contributions
prem+1.315
ducers+1.211
 pione+1.195
idth+1.145
Untitled+1.114
Neg logit contributions
 defer-1.480
 McMaster-1.472
oret-1.436
RW-1.425
ore-1.400
Token
Token ID198
Feature activation-2.96e+00

Pos logit contributions
prem+2.448
ducers+2.199
Untitled+2.019
humans+2.004
 ®+1.971
Neg logit contributions
��-3.178
 defer-3.173
 McMaster-3.148
 torches-3.121
oret-3.056
TokenPin
Token ID28348
Feature activation-3.51e+00

Pos logit contributions
prem+2.239
ducers+2.052
Untitled+1.939
idth+1.923
 pione+1.920
Neg logit contributions
 defer-2.121
 McMaster-2.112
oret-2.032
 torches-1.993
RW-1.982
Token 8
Token ID807
Feature activation-3.03e+00

Pos logit contributions
prem+2.538
ducers+2.347
 pione+2.309
idth+2.229
 ®+2.199
Neg logit contributions
 defer-2.558
 McMaster-2.529
oret-2.471
RW-2.454
Bloom-2.407
Token shares
Token ID7303
Feature activation-5.89e+00

Pos logit contributions
prem+2.108
ducers+1.937
 pione+1.917
idth+1.837
 ®+1.801
Neg logit contributions
 defer-2.306
 McMaster-2.281
oret-2.236
RW-2.205
ore-2.177
Token
Token ID198
Feature activation-4.40e+00

Pos logit contributions
prem+4.001
ducers+3.631
 pione+3.543
 ®+3.419
idth+3.410
Neg logit contributions
 defer-4.445
 McMaster-4.383
oret-4.349
RW-4.269
Bloom-4.267
Token
Token ID198
Feature activation-3.63e+00

Pos logit contributions
prem+2.761
ducers+2.464
Untitled+2.250
humans+2.241
 ®+2.198
Neg logit contributions
��-3.694
 defer-3.655
 McMaster-3.641
 torches-3.624
oret-3.524
TokenI
Token ID40
Feature activation-1.01e+00

Pos logit contributions
prem+2.691
ducers+2.439
Untitled+2.309
humans+2.275
idth+2.268
Neg logit contributions
 defer-2.680
 McMaster-2.670
oret-2.566
 torches-2.527
RW-2.481
Token was
Token ID373
Feature activation+1.32e-01

Pos logit contributions
prem+0.795
ducers+0.737
 pione+0.727
idth+0.699
Untitled+0.687
Neg logit contributions
 McMaster-0.675
 defer-0.673
oret-0.653
RW-0.647
Bloom-0.634
Token inspired
Token ID7867
Feature activation-8.79e-02

Pos logit contributions
 McMaster+0.088
 defer+0.088
oret+0.086
RW+0.085
Bloom+0.084
Neg logit contributions
prem-0.104
ducers-0.097
 pione-0.095
idth-0.091
Untitled-0.091
Token the
Token ID262
Feature activation-1.64e-01

Pos logit contributions
 defer+0.613
 McMaster+0.613
oret+0.592
RW+0.586
ore+0.578
Neg logit contributions
prem-0.640
ducers-0.594
 pione-0.589
idth-0.564
-0.553
Token National
Token ID2351
Feature activation-6.40e-01

Pos logit contributions
prem+0.130
ducers+0.121
 pione+0.120
idth+0.115
+0.113
Neg logit contributions
 defer-0.111
 McMaster-0.110
oret-0.107
RW-0.106
ore-0.104
Token Museum
Token ID9594
Feature activation-1.62e+00

Pos logit contributions
prem+0.500
ducers+0.464
 pione+0.454
idth+0.438
Untitled+0.432
Neg logit contributions
 defer-0.439
 McMaster-0.434
RW-0.421
oret-0.421
ore-0.412
Token of
Token ID286
Feature activation-5.64e+00

Pos logit contributions
prem+1.149
ducers+1.063
 pione+1.050
idth+1.004
+0.983
Neg logit contributions
 defer-1.218
 McMaster-1.209
oret-1.178
RW-1.171
ore-1.150
Token the
Token ID262
Feature activation-3.77e+00

Pos logit contributions
prem+4.519
ducers+4.211
 pione+4.086
 Invention+3.975
 ®+3.938
Neg logit contributions
 defer-3.634
 McMaster-3.532
RW-3.528
oret-3.491
Bloom-3.446
Token United
Token ID1578
Feature activation-5.82e+00

Pos logit contributions
prem+2.639
ducers+2.412
 pione+2.266
 ®+2.231
 Dak+2.213
Neg logit contributions
 defer-2.867
Bloom-2.797
 McMaster-2.790
RW-2.774
oret-2.731
Token States
Token ID1829
Feature activation-2.46e+00

Pos logit contributions
prem+2.747
ducers+2.378
 Dak+2.111
 ®+2.081
humans+2.079
Neg logit contributions
 defer-5.675
 McMaster-5.644
RW-5.599
Bloom-5.548
 torches-5.522
Token Air
Token ID3701
Feature activation-1.31e+00

Pos logit contributions
prem+1.897
ducers+1.744
 pione+1.722
idth+1.651
 ®+1.642
Neg logit contributions
 defer-1.703
 McMaster-1.682
oret-1.644
RW-1.638
Bloom-1.611
Token Force
Token ID5221
Feature activation-2.11e+00

Pos logit contributions
prem+1.105
ducers+1.030
 pione+1.006
idth+0.976
 ®+0.976
Neg logit contributions
 defer-0.810
 McMaster-0.799
RW-0.771
Bloom-0.769
oret-0.767
Token in
Token ID287
Feature activation-1.79e+00

Pos logit contributions
prem+1.623
ducers+1.499
 pione+1.484
idth+1.423
 ®+1.406
Neg logit contributions
 defer-1.461
 McMaster-1.448
oret-1.406
RW-1.403
ore-1.373
Token Dayton
Token ID24450
Feature activation-7.50e-01

Pos logit contributions
prem+1.451
ducers+1.354
 pione+1.330
idth+1.281
 ®+1.261
Neg logit contributions
 defer-1.164
 McMaster-1.148
oret-1.119
RW-1.116
ore-1.091
Token of
Token ID286
Feature activation-1.14e+00

Pos logit contributions
prem+0.251
ducers+0.233
 pione+0.227
idth+0.218
 ®+0.213
Neg logit contributions
 defer-0.273
 McMaster-0.272
oret-0.265
RW-0.262
ore-0.257
Token the
Token ID262
Feature activation-2.82e-01

Pos logit contributions
prem+0.886
ducers+0.825
 pione+0.811
idth+0.780
Untitled+0.764
Neg logit contributions
 defer-0.784
 McMaster-0.779
oret-0.757
RW-0.750
ore-0.735
Token dog
Token ID3290
Feature activation+4.66e-01

Pos logit contributions
prem+0.225
ducers+0.209
 pione+0.207
idth+0.199
Untitled+0.195
Neg logit contributions
 defer-0.189
 McMaster-0.188
oret-0.182
RW-0.181
ore-0.177
Token-
Token ID12
Feature activation-7.87e-01

Pos logit contributions
 defer+0.315
 McMaster+0.313
oret+0.303
RW+0.300
ore+0.295
Neg logit contributions
prem-0.368
ducers-0.343
 pione-0.339
idth-0.325
-0.319
Tokeneat
Token ID4098
Feature activation+5.68e-02

Pos logit contributions
prem+0.558
ducers+0.514
 pione+0.507
idth+0.484
Untitled+0.473
Neg logit contributions
 defer-0.597
 McMaster-0.594
oret-0.577
RW-0.572
ore-0.563
Token-
Token ID12
Feature activation-5.81e+00

Pos logit contributions
 defer+0.034
 McMaster+0.034
oret+0.033
RW+0.032
ore+0.032
Neg logit contributions
prem-0.049
ducers-0.046
 pione-0.046
idth-0.044
-0.044
Tokendog
Token ID9703
Feature activation-1.10e+00

Pos logit contributions
prem+3.218
ducers+2.819
humans+2.676
 pione+2.646
apult+2.524
Neg logit contributions
 defer-5.345
 McMaster-5.316
oret-5.120
 torches-5.055
RW-5.037
Token world
Token ID995
Feature activation+2.88e-01

Pos logit contributions
prem+0.845
ducers+0.790
 pione+0.771
idth+0.741
humans+0.730
Neg logit contributions
 defer-0.762
 McMaster-0.758
oret-0.735
RW-0.729
ore-0.713
Token that
Token ID326
Feature activation-3.03e-01

Pos logit contributions
 defer+0.192
 McMaster+0.191
oret+0.184
RW+0.183
ore+0.181
Neg logit contributions
prem-0.231
 pione-0.215
ducers-0.214
idth-0.205
-0.202
Token is
Token ID318
Feature activation-5.83e-01

Pos logit contributions
prem+0.228
ducers+0.212
 pione+0.211
idth+0.201
+0.197
Neg logit contributions
 defer-0.216
 McMaster-0.215
oret-0.208
RW-0.207
ore-0.204
Token the
Token ID262
Feature activation-1.33e+00

Pos logit contributions
prem+0.447
ducers+0.416
 pione+0.415
idth+0.396
+0.390
Neg logit contributions
 defer-0.407
 McMaster-0.404
oret-0.392
RW-0.389
ore-0.384
Token wrote
Token ID2630
Feature activation+1.73e+00

Pos logit contributions
prem+0.312
ducers+0.291
 pione+0.288
idth+0.276
+0.271
Neg logit contributions
 defer-0.288
 McMaster-0.286
oret-0.277
RW-0.277
ore-0.272
Token:
Token ID25
Feature activation+2.62e+00

Pos logit contributions
 defer+1.312
 McMaster+1.306
oret+1.272
RW+1.263
ore+1.246
Neg logit contributions
prem-1.222
 pione-1.157
ducers-1.128
-1.081
idth-1.075
Token
Token ID198
Feature activation+1.54e+00

Pos logit contributions
 defer+1.845
 McMaster+1.834
oret+1.785
RW+1.774
ore+1.751
Neg logit contributions
prem-1.969
 pione-1.935
ducers-1.834
-1.820
idth-1.769
Token
Token ID198
Feature activation+2.09e+00

Pos logit contributions
 defer+1.144
 McMaster+1.136
oret+1.105
RW+1.095
ore+1.078
Neg logit contributions
prem-1.113
ducers-1.028
 pione-0.994
idth-0.966
Untitled-0.951
TokenShow
Token ID15307
Feature activation-2.03e+00

Pos logit contributions
 defer+1.717
 McMaster+1.700
RW+1.673
oret+1.671
ore+1.649
Neg logit contributions
prem-1.319
 pione-1.246
ducers-1.215
-1.153
idth-1.145
Token nested
Token ID28376
Feature activation-5.73e+00

Pos logit contributions
prem+1.253
ducers+1.145
 pione+1.088
 ®+1.066
Untitled+1.051
Neg logit contributions
 McMaster-1.704
 defer-1.687
oret-1.645
RW-1.641
ore-1.615
Token quote
Token ID9577
Feature activation-1.33e+00

Pos logit contributions
prem+5.077
ducers+4.687
 ®+4.488
Untitled+4.476
 architects+4.455
Neg logit contributions
 McMaster-3.279
RW-3.158
 defer-3.105
oret-3.082
��-3.069
Token +
Token ID1343
Feature activation+2.38e-01

Pos logit contributions
prem+0.713
ducers+0.644
 ®+0.592
idth+0.577
Untitled+0.576
Neg logit contributions
 McMaster-1.226
 defer-1.211
RW-1.203
oret-1.178
Bloom-1.171
Token
Token ID198
Feature activation-8.53e-01

Pos logit contributions
 defer+0.180
 McMaster+0.178
oret+0.174
RW+0.171
 torches+0.169
Neg logit contributions
prem-0.170
ducers-0.156
 pione-0.148
idth-0.146
Untitled-0.145
Token
Token ID198
Feature activation-8.33e-01

Pos logit contributions
prem+0.585
ducers+0.531
Untitled+0.491
humans+0.486
 ®+0.483
Neg logit contributions
 defer-0.669
 McMaster-0.664
oret-0.647
 torches-0.642
RW-0.638
TokenOn
Token ID2202
Feature activation-2.69e+00

Pos logit contributions
prem+0.718
ducers+0.668
 pione+0.645
idth+0.636
Untitled+0.635
Neg logit contributions
 defer-0.506
 McMaster-0.506
oret-0.485
RW-0.473
 torches-0.466
Token one
Token ID530
Feature activation-3.10e-01

Pos logit contributions
 defer+1.308
 McMaster+1.274
oret+1.236
RW+1.221
ore+1.200
Neg logit contributions
prem-1.572
 pione-1.495
ducers-1.468
-1.410
idth-1.409
Token-
Token ID12
Feature activation+3.12e-02

Pos logit contributions
prem+0.231
ducers+0.214
 pione+0.210
idth+0.202
 ®+0.198
Neg logit contributions
 McMaster-0.222
 defer-0.222
oret-0.215
RW-0.214
ore-0.210
Tokenman
Token ID805
Feature activation+1.25e-01

Pos logit contributions
 defer+0.022
 McMaster+0.022
oret+0.021
RW+0.021
ore+0.021
Neg logit contributions
prem-0.024
 pione-0.022
ducers-0.022
idth-0.021
-0.021
Token-
Token ID12
Feature activation-1.11e+00

Pos logit contributions
 defer+0.083
 McMaster+0.081
oret+0.079
RW+0.078
ore+0.077
Neg logit contributions
prem-0.101
ducers-0.094
 pione-0.093
idth-0.090
-0.088
Tokenone
Token ID505
Feature activation-2.09e+00

Pos logit contributions
prem+0.753
ducers+0.693
 pione+0.684
idth+0.652
Untitled+0.636
Neg logit contributions
 defer-0.871
 McMaster-0.867
oret-0.845
RW-0.837
ore-0.825
Token-
Token ID12
Feature activation-5.69e+00

Pos logit contributions
prem+1.697
ducers+1.590
 pione+1.548
idth+1.505
Untitled+1.480
Neg logit contributions
 McMaster-1.343
 defer-1.328
oret-1.304
RW-1.287
ore-1.254
Tokenwoman
Token ID8580
Feature activation+4.78e-02

Pos logit contributions
prem+3.365
ducers+2.981
humans+2.768
 pione+2.726
idth+2.723
Neg logit contributions
 McMaster-5.051
 defer-4.985
oret-4.822
 torches-4.796
RW-4.729
Token,
Token ID11
Feature activation+7.21e-01

Pos logit contributions
 defer+0.032
 McMaster+0.032
oret+0.031
RW+0.031
ore+0.030
Neg logit contributions
prem-0.038
ducers-0.035
 pione-0.035
idth-0.034
-0.033
Token period
Token ID2278
Feature activation+3.56e-01

Pos logit contributions
 defer+0.493
 McMaster+0.488
oret+0.473
RW+0.468
ore+0.461
Neg logit contributions
prem-0.566
ducers-0.528
 pione-0.526
idth-0.502
-0.495
Token.
Token ID13
Feature activation+1.13e+00

Pos logit contributions
 defer+0.241
 McMaster+0.239
oret+0.232
RW+0.229
ore+0.227
Neg logit contributions
prem-0.281
ducers-0.262
 pione-0.260
idth-0.249
-0.245
Token But
Token ID887
Feature activation+5.02e-01

Pos logit contributions
 McMaster+0.833
 defer+0.831
oret+0.807
RW+0.798
ore+0.787
Neg logit contributions
prem-0.829
 pione-0.780
ducers-0.768
idth-0.734
-0.729
Token Guidelines
Token ID31072
Feature activation-1.76e+00

Pos logit contributions
prem+0.569
ducers+0.523
 pione+0.515
 ®+0.494
idth+0.492
Neg logit contributions
 defer-0.553
 McMaster-0.545
RW-0.532
oret-0.532
ore-0.519
Token.
Token ID13
Feature activation-4.26e-01

Pos logit contributions
prem+1.334
ducers+1.229
 pione+1.208
idth+1.163
 ®+1.157
Neg logit contributions
 defer-1.234
 McMaster-1.223
oret-1.198
RW-1.186
ore-1.163
Token On
Token ID1550
Feature activation-5.71e-01

Pos logit contributions
prem+0.321
ducers+0.298
 pione+0.296
idth+0.283
+0.278
Neg logit contributions
 defer-0.302
 McMaster-0.300
oret-0.292
RW-0.289
ore-0.285
Token the
Token ID262
Feature activation-1.59e+00

Pos logit contributions
prem+0.423
ducers+0.392
 pione+0.389
idth+0.371
+0.364
Neg logit contributions
 defer-0.414
 McMaster-0.411
oret-0.400
RW-0.396
ore-0.390
Token one
Token ID530
Feature activation-1.12e+00

Pos logit contributions
prem+1.280
ducers+1.181
 pione+1.158
idth+1.128
 ®+1.103
Neg logit contributions
 defer-1.049
 McMaster-1.038
RW-1.009
oret-1.004
Bloom-0.994
Token hand
Token ID1021
Feature activation-5.69e+00

Pos logit contributions
prem+0.938
ducers+0.877
 pione+0.868
idth+0.836
+0.820
Neg logit contributions
 defer-0.696
 McMaster-0.691
oret-0.669
RW-0.663
ore-0.650
Token,
Token ID11
Feature activation-2.40e+00

Pos logit contributions
prem+4.101
ducers+3.764
 pione+3.717
idth+3.594
 architects+3.515
Neg logit contributions
 defer-4.145
 McMaster-4.108
RW-4.012
oret-4.008
Bloom-3.923
Token a
Token ID257
Feature activation-1.12e+00

Pos logit contributions
prem+1.736
ducers+1.600
 pione+1.572
idth+1.518
 ®+1.473
Neg logit contributions
 defer-1.771
 McMaster-1.761
oret-1.716
RW-1.710
ore-1.678
Token generous
Token ID14431
Feature activation+1.14e+00

Pos logit contributions
prem+0.858
ducers+0.796
 pione+0.788
idth+0.755
+0.739
Neg logit contributions
 defer-0.780
 McMaster-0.775
oret-0.753
RW-0.748
ore-0.736
Token tower
Token ID10580
Feature activation+3.45e-01

Pos logit contributions
 defer+0.753
 McMaster+0.746
oret+0.725
RW+0.714
ore+0.704
Neg logit contributions
prem-0.922
ducers-0.864
 pione-0.862
idth-0.821
-0.811
Token separation
Token ID14139
Feature activation-1.42e+00

Pos logit contributions
 defer+0.234
 McMaster+0.233
oret+0.226
RW+0.224
ore+0.220
Neg logit contributions
prem-0.271
ducers-0.252
 pione-0.249
idth-0.240
Untitled-0.234
Token and
Token ID290
Feature activation+1.32e+00

Pos logit contributions
 defer+0.219
 McMaster+0.218
oret+0.212
RW+0.211
ore+0.206
Neg logit contributions
prem-0.277
ducers-0.258
 pione-0.253
idth-0.244
Untitled-0.241
Token Winston
Token ID21400
Feature activation-6.13e-01

Pos logit contributions
 defer+0.928
 McMaster+0.921
oret+0.897
RW+0.880
ore+0.875
Neg logit contributions
prem-1.005
 pione-0.954
ducers-0.940
idth-0.898
-0.895
Token held
Token ID2714
Feature activation-8.43e-01

Pos logit contributions
prem+0.488
ducers+0.453
 pione+0.439
idth+0.425
 ®+0.421
Neg logit contributions
 defer-0.405
 McMaster-0.404
oret-0.395
RW-0.394
Bloom-0.384
Token under
Token ID739
Feature activation-6.66e-01

Pos logit contributions
prem+0.649
ducers+0.600
 pione+0.588
idth+0.565
humans+0.553
Neg logit contributions
 defer-0.582
 McMaster-0.580
oret-0.565
RW-0.562
Bloom-0.551
Token 20
Token ID1160
Feature activation-1.32e-02

Pos logit contributions
prem+0.525
ducers+0.488
 pione+0.481
idth+0.462
+0.451
Neg logit contributions
 defer-0.452
 McMaster-0.448
oret-0.435
RW-0.433
ore-0.423
Token Fantasy
Token ID10982
Feature activation-5.69e+00

Pos logit contributions
prem+0.010
ducers+0.010
 pione+0.009
idth+0.009
+0.009
Neg logit contributions
 defer-0.009
 McMaster-0.009
oret-0.009
RW-0.009
ore-0.009
Token points
Token ID2173
Feature activation-2.91e+00

Pos logit contributions
prem+3.214
ducers+2.883
 pione+2.785
idth+2.613
 Dak+2.594
Neg logit contributions
 McMaster-5.013
 defer-4.945
oret-4.880
RW-4.804
Bloom-4.801
Token over
Token ID625
Feature activation-1.27e+00

Pos logit contributions
prem+2.135
ducers+1.956
 pione+1.810
 Dak+1.809
humans+1.799
Neg logit contributions
 McMaster-2.066
 defer-2.051
RW-2.033
oret-2.018
Bloom-2.011
Token that
Token ID326
Feature activation+7.62e-02

Pos logit contributions
prem+0.907
ducers+0.837
 pione+0.818
idth+0.787
Untitled+0.767
Neg logit contributions
 defer-0.949
 McMaster-0.941
oret-0.919
RW-0.914
ore-0.895
Token span
Token ID11506
Feature activation-2.17e-01

Pos logit contributions
 defer+0.057
 McMaster+0.057
oret+0.055
RW+0.055
ore+0.054
Neg logit contributions
prem-0.054
ducers-0.050
 pione-0.048
idth-0.047
Untitled-0.046
Token.
Token ID13
Feature activation-8.40e-02

Pos logit contributions
prem+0.172
ducers+0.160
 pione+0.158
idth+0.152
Untitled+0.149
Neg logit contributions
 defer-0.145
 McMaster-0.144
oret-0.140
RW-0.139
ore-0.136
Token.
Token ID13
Feature activation-1.72e-01

Pos logit contributions
 defer+0.688
 McMaster+0.684
oret+0.668
RW+0.656
ore+0.654
Neg logit contributions
prem-0.768
ducers-0.717
 pione-0.716
idth-0.680
-0.676
Token
Token ID198
Feature activation-3.78e-01

Pos logit contributions
prem+0.127
 pione+0.119
ducers+0.118
idth+0.113
+0.111
Neg logit contributions
 McMaster-0.124
 defer-0.124
oret-0.120
RW-0.119
ore-0.117
Token
Token ID198
Feature activation-3.30e-01

Pos logit contributions
prem+0.264
ducers+0.242
Untitled+0.223
idth+0.222
humans+0.221
Neg logit contributions
 defer-0.292
 McMaster-0.290
oret-0.281
RW-0.280
 torches-0.279
TokenVi
Token ID38432
Feature activation-1.03e+00

Pos logit contributions
prem+0.234
ducers+0.216
 pione+0.213
idth+0.204
Untitled+0.199
Neg logit contributions
 defer-0.250
 McMaster-0.249
oret-0.242
RW-0.240
ore-0.237
Tokenaches
Token ID3694
Feature activation+5.42e-01

Pos logit contributions
prem+0.557
ducers+0.507
idth+0.463
 pione+0.457
humans+0.451
Neg logit contributions
 defer-0.954
 McMaster-0.946
RW-0.913
oret-0.910
 torches-0.897
Tokenlav
Token ID18809
Feature activation-5.65e+00

Pos logit contributions
 defer+0.525
 McMaster+0.520
oret+0.507
RW+0.504
 torches+0.498
Neg logit contributions
prem-0.275
ducers-0.243
 pione-0.226
idth-0.223
Untitled-0.215
Token Pl
Token ID1345
Feature activation-1.27e+00

Pos logit contributions
prem+3.049
ducers+2.682
 pione+2.557
idth+2.521
 ®+2.429
Neg logit contributions
 defer-5.190
 McMaster-5.156
RW-5.059
oret-4.999
Bloom-4.951
Tokenak
Token ID461
Feature activation-8.81e-01

Pos logit contributions
prem+0.839
ducers+0.770
 pione+0.755
idth+0.724
Untitled+0.705
Neg logit contributions
 defer-1.025
 McMaster-1.020
oret-0.991
RW-0.987
ore-0.971
Tokenas
Token ID292
Feature activation+9.14e-01

Pos logit contributions
prem+0.831
ducers+0.779
idth+0.746
humans+0.736
apult+0.728
Neg logit contributions
 defer-0.469
 McMaster-0.464
RW-0.444
oret-0.437
 torches-0.429
Tokenov
Token ID709
Feature activation-2.14e-01

Pos logit contributions
 defer+0.824
 McMaster+0.820
oret+0.801
RW+0.796
ore+0.786
Neg logit contributions
prem-0.515
ducers-0.465
 pione-0.459
idth-0.432
-0.419
Token is
Token ID318
Feature activation+2.11e-01

Pos logit contributions
prem+0.162
ducers+0.150
 pione+0.147
idth+0.142
 ®+0.140
Neg logit contributions
 defer-0.150
 McMaster-0.150
oret-0.145
RW-0.145
ore-0.142
Token on
Token ID319
Feature activation+3.40e-01

Pos logit contributions
 defer+0.025
 McMaster+0.025
oret+0.024
RW+0.024
ore+0.023
Neg logit contributions
prem-0.028
ducers-0.026
 pione-0.025
idth-0.024
 ®-0.024
Token Sat
Token ID7031
Feature activation-1.31e+00

Pos logit contributions
 defer+0.225
 McMaster+0.223
oret+0.217
RW+0.215
ore+0.211
Neg logit contributions
prem-0.273
ducers-0.255
 pione-0.251
idth-0.241
Untitled-0.237
Token,
Token ID11
Feature activation-3.57e+00

Pos logit contributions
prem+0.975
ducers+0.901
 pione+0.868
idth+0.852
Untitled+0.834
Neg logit contributions
 defer-0.945
 McMaster-0.937
RW-0.908
oret-0.905
 torches-0.885
Token 13
Token ID1511
Feature activation-1.38e+00

Pos logit contributions
prem+2.525
ducers+2.315
 ®+2.171
Untitled+2.153
)+2.130
Neg logit contributions
 defer-2.650
 McMaster-2.590
oret-2.550
RW-2.545
��-2.537
Token Sep
Token ID8621
Feature activation-3.02e+00

Pos logit contributions
prem+1.132
ducers+1.056
 pione+1.018
idth+0.998
Untitled+0.988
Neg logit contributions
 defer-0.891
 McMaster-0.882
oret-0.857
RW-0.852
ore-0.830
Token,
Token ID11
Feature activation-5.65e+00

Pos logit contributions
prem+2.354
ducers+2.190
 pione+2.091
 ®+2.073
idth+2.058
Neg logit contributions
 defer-2.039
 McMaster-2.012
RW-1.962
oret-1.951
 torches-1.915
Token 2014
Token ID1946
Feature activation-2.64e+00

Pos logit contributions
prem+4.385
ducers+4.044
 ®+3.900
idth+3.767
 pione+3.767
Neg logit contributions
 defer-3.719
 McMaster-3.650
RW-3.635
oret-3.587
��-3.558
Token,
Token ID11
Feature activation-2.22e+00

Pos logit contributions
prem+1.956
ducers+1.807
 pione+1.761
idth+1.707
 ®+1.701
Neg logit contributions
 defer-1.885
 McMaster-1.877
oret-1.827
RW-1.821
Bloom-1.779
Token 11
Token ID1367
Feature activation+3.02e-02

Pos logit contributions
prem+1.675
ducers+1.550
 pione+1.488
 ®+1.454
idth+1.452
Neg logit contributions
 defer-1.553
 McMaster-1.544
RW-1.513
oret-1.508
Bloom-1.478
Token:
Token ID25
Feature activation-1.23e+00

Pos logit contributions
 defer+0.023
 McMaster+0.023
oret+0.022
RW+0.022
ore+0.022
Neg logit contributions
prem-0.021
ducers-0.020
 pione-0.019
idth-0.018
-0.018
Token13
Token ID1485
Feature activation+3.98e+00

Pos logit contributions
prem+0.820
ducers+0.741
Untitled+0.693
humans+0.681
idth+0.677
Neg logit contributions
 defer-0.991
 McMaster-0.972
oret-0.952
 torches-0.941
RW-0.937
Token and
Token ID290
Feature activation-1.69e+00

Pos logit contributions
prem+0.316
ducers+0.294
idth+0.276
 pione+0.275
 ®+0.273
Neg logit contributions
 defer-0.262
 McMaster-0.262
oret-0.254
RW-0.253
Bloom-0.247
Token Editor
Token ID12058
Feature activation+1.08e+00

Pos logit contributions
prem+1.475
ducers+1.353
 pione+1.286
idth+1.282
 Invention+1.279
Neg logit contributions
 defer-0.991
 McMaster-0.980
oret-0.962
RW-0.955
Bloom-0.935
Token's
Token ID338
Feature activation+1.01e+00

Pos logit contributions
 defer+0.710
 McMaster+0.703
oret+0.681
RW+0.675
ore+0.667
Neg logit contributions
prem-0.874
 pione-0.823
ducers-0.817
idth-0.780
-0.775
Token Picks
Token ID33957
Feature activation-4.16e+00

Pos logit contributions
 defer+0.931
 McMaster+0.923
oret+0.901
RW+0.894
ore+0.888
Neg logit contributions
prem-0.544
 pione-0.498
ducers-0.491
idth-0.457
-0.452
Token.
Token ID13
Feature activation-3.81e+00

Pos logit contributions
prem+3.048
ducers+2.820
humans+2.608
Untitled+2.607
idth+2.601
Neg logit contributions
 McMaster-2.974
 defer-2.962
oret-2.898
RW-2.887
Bloom-2.881
Token
Token ID198
Feature activation-5.64e+00

Pos logit contributions
prem+2.080
ducers+1.845
 pione+1.699
 ®+1.687
idth+1.683
Neg logit contributions
 defer-3.483
 McMaster-3.431
oret-3.376
RW-3.373
 torches-3.337
Token
Token ID198
Feature activation-3.48e+00

Pos logit contributions
prem+3.469
ducers+3.055
Untitled+2.787
humans+2.774
 ®+2.745
Neg logit contributions
��-4.851
 defer-4.737
 torches-4.719
 McMaster-4.707
oret-4.520
TokenThe
Token ID464
Feature activation+9.68e-01

Pos logit contributions
prem+2.421
ducers+2.200
Untitled+2.071
idth+2.046
 pione+2.032
Neg logit contributions
 defer-2.715
 McMaster-2.696
oret-2.583
 torches-2.560
RW-2.537
Token seeds
Token ID11904
Feature activation+1.10e+00

Pos logit contributions
 defer+0.680
 McMaster+0.673
oret+0.663
RW+0.645
ore+0.643
Neg logit contributions
prem-0.741
ducers-0.688
 pione-0.688
idth-0.654
-0.643
Token of
Token ID286
Feature activation+6.08e-01

Pos logit contributions
 defer+0.787
 McMaster+0.784
oret+0.761
RW+0.753
ore+0.745
Neg logit contributions
prem-0.826
ducers-0.768
 pione-0.763
idth-0.730
-0.716
Token this
Token ID428
Feature activation+2.51e-01

Pos logit contributions
 defer+0.448
 McMaster+0.445
oret+0.435
RW+0.426
ore+0.424
Neg logit contributions
prem-0.444
ducers-0.412
 pione-0.412
idth-0.390
-0.384
Token display
Token ID3359
Feature activation+1.09e+00

Pos logit contributions
prem+0.359
ducers+0.331
 pione+0.326
idth+0.311
+0.303
Neg logit contributions
 defer-0.413
 McMaster-0.411
oret-0.401
RW-0.398
ore-0.392
Token at
Token ID379
Feature activation+8.55e-01

Pos logit contributions
 defer+0.751
 McMaster+0.744
oret+0.723
RW+0.715
ore+0.706
Neg logit contributions
prem-0.844
ducers-0.789
 pione-0.784
idth-0.748
-0.736
Token the
Token ID262
Feature activation-1.64e-01

Pos logit contributions
 defer+0.613
 McMaster+0.613
oret+0.592
RW+0.586
ore+0.578
Neg logit contributions
prem-0.640
ducers-0.594
 pione-0.589
idth-0.564
-0.553
Token National
Token ID2351
Feature activation-6.40e-01

Pos logit contributions
prem+0.130
ducers+0.121
 pione+0.120
idth+0.115
+0.113
Neg logit contributions
 defer-0.111
 McMaster-0.110
oret-0.107
RW-0.106
ore-0.104
Token Museum
Token ID9594
Feature activation-1.62e+00

Pos logit contributions
prem+0.500
ducers+0.464
 pione+0.454
idth+0.438
Untitled+0.432
Neg logit contributions
 defer-0.439
 McMaster-0.434
RW-0.421
oret-0.421
ore-0.412
Token of
Token ID286
Feature activation-5.64e+00

Pos logit contributions
prem+1.149
ducers+1.063
 pione+1.050
idth+1.004
+0.983
Neg logit contributions
 defer-1.218
 McMaster-1.209
oret-1.178
RW-1.171
ore-1.150
Token the
Token ID262
Feature activation-3.77e+00

Pos logit contributions
prem+4.519
ducers+4.211
 pione+4.086
 Invention+3.975
 ®+3.938
Neg logit contributions
 defer-3.634
 McMaster-3.532
RW-3.528
oret-3.491
Bloom-3.446
Token United
Token ID1578
Feature activation-5.82e+00

Pos logit contributions
prem+2.639
ducers+2.412
 pione+2.266
 ®+2.231
 Dak+2.213
Neg logit contributions
 defer-2.867
Bloom-2.797
 McMaster-2.790
RW-2.774
oret-2.731
Token States
Token ID1829
Feature activation-2.46e+00

Pos logit contributions
prem+2.747
ducers+2.378
 Dak+2.111
 ®+2.081
humans+2.079
Neg logit contributions
 defer-5.675
 McMaster-5.644
RW-5.599
Bloom-5.548
 torches-5.522
Token Air
Token ID3701
Feature activation-1.31e+00

Pos logit contributions
prem+1.897
ducers+1.744
 pione+1.722
idth+1.651
 ®+1.642
Neg logit contributions
 defer-1.703
 McMaster-1.682
oret-1.644
RW-1.638
Bloom-1.611
Token Force
Token ID5221
Feature activation-2.11e+00

Pos logit contributions
prem+1.105
ducers+1.030
 pione+1.006
idth+0.976
 ®+0.976
Neg logit contributions
 defer-0.810
 McMaster-0.799
RW-0.771
Bloom-0.769
oret-0.767
Tokeng
Token ID70
Feature activation-4.64e-01

Pos logit contributions
prem+2.269
ducers+2.111
 pione+2.039
idth+2.030
apult+1.947
Neg logit contributions
 defer-1.910
 McMaster-1.907
RW-1.819
oret-1.806
 torches-1.785
Tokenits
Token ID896
Feature activation-1.18e+00

Pos logit contributions
prem+0.361
ducers+0.335
 pione+0.329
idth+0.318
Untitled+0.311
Neg logit contributions
 defer-0.321
 McMaster-0.318
oret-0.308
RW-0.306
ore-0.299
Tokenamb
Token ID4131
Feature activation+1.45e+00

Pos logit contributions
prem+0.882
ducers+0.817
 pione+0.806
idth+0.774
Untitled+0.756
Neg logit contributions
 defer-0.845
 McMaster-0.838
oret-0.815
RW-0.808
ore-0.794
Tokenry
Token ID563
Feature activation+9.37e-01

Pos logit contributions
 defer+0.978
 McMaster+0.974
oret+0.952
RW+0.940
ore+0.932
Neg logit contributions
prem-1.144
 pione-1.067
ducers-1.064
idth-1.008
-1.004
Token/
Token ID14
Feature activation+8.58e-01

Pos logit contributions
 defer+0.640
 McMaster+0.638
oret+0.620
RW+0.613
ore+0.607
Neg logit contributions
prem-0.727
 pione-0.678
ducers-0.677
idth-0.644
-0.637
Tokenstatus
Token ID13376
Feature activation-5.60e+00

Pos logit contributions
 defer+0.599
 McMaster+0.595
oret+0.579
RW+0.575
ore+0.568
Neg logit contributions
prem-0.653
ducers-0.608
 pione-0.608
idth-0.579
-0.571
Token/
Token ID14
Feature activation-4.18e-01

Pos logit contributions
prem+4.062
ducers+3.684
Untitled+3.392
humans+3.344
)+3.313
Neg logit contributions
 defer-4.149
��-4.148
 McMaster-4.112
 torches-4.042
RW-3.920
Token9
Token ID24
Feature activation-2.08e-01

Pos logit contributions
prem+0.300
ducers+0.277
 pione+0.273
idth+0.262
Untitled+0.256
Neg logit contributions
 defer-0.312
 McMaster-0.310
oret-0.302
RW-0.299
ore-0.295
Token175
Token ID17430
Feature activation+3.55e+00

Pos logit contributions
prem+0.146
ducers+0.135
 pione+0.133
idth+0.127
Untitled+0.124
Neg logit contributions
 defer-0.158
 McMaster-0.157
oret-0.153
RW-0.152
ore-0.150
Token669
Token ID36657
Feature activation+2.98e+00

Pos logit contributions
 McMaster+2.534
 defer+2.532
RW+2.468
oret+2.460
ore+2.416
Neg logit contributions
prem-2.601
 pione-2.571
ducers-2.452
-2.433
-2.361
Token15
Token ID1314
Feature activation+2.55e+00

Pos logit contributions
 McMaster+2.162
 defer+2.158
oret+2.105
RW+2.102
ore+2.061
Neg logit contributions
prem-2.155
 pione-2.106
ducers-2.017
-1.989
-1.928
Token.
Token ID764
Feature activation-1.71e+00

Pos logit contributions
 defer+1.340
 McMaster+1.338
oret+1.291
RW+1.278
ore+1.261
Neg logit contributions
prem-1.620
ducers-1.510
 pione-1.507
idth-1.440
-1.421
Token
Token ID198
Feature activation-4.60e-01

Pos logit contributions
prem+1.408
ducers+1.295
 pione+1.279
idth+1.233
 ®+1.228
Neg logit contributions
 defer-1.099
 McMaster-1.076
oret-1.055
RW-1.040
 torches-1.027
Token
Token ID198
Feature activation-7.12e-02

Pos logit contributions
prem+0.324
ducers+0.297
Untitled+0.276
idth+0.273
 ®+0.272
Neg logit contributions
 defer-0.353
 McMaster-0.349
oret-0.340
 torches-0.337
RW-0.334
TokenGoogle
Token ID11708
Feature activation-5.59e-01

Pos logit contributions
prem+0.052
ducers+0.048
 pione+0.047
idth+0.045
Untitled+0.044
Neg logit contributions
 defer-0.053
 McMaster-0.053
oret-0.051
RW-0.051
ore-0.050
Token Scholar
Token ID11713
Feature activation-4.67e+00

Pos logit contributions
prem+0.393
ducers+0.364
 pione+0.359
idth+0.342
Untitled+0.336
Neg logit contributions
 defer-0.424
 McMaster-0.421
oret-0.411
RW-0.408
ore-0.401
Token Crossref
Token ID23613
Feature activation-5.58e+00

Pos logit contributions
prem+3.172
ducers+2.868
 pione+2.804
idth+2.765
 ®+2.760
Neg logit contributions
 defer-3.526
 McMaster-3.513
oret-3.499
 torches-3.410
ore-3.322
Token
Token ID198
Feature activation-5.89e-01

Pos logit contributions
prem+3.962
ducers+3.636
 pione+3.579
idth+3.477
 ®+3.448
Neg logit contributions
 defer-4.111
 McMaster-4.056
oret-3.993
RW-3.931
ore-3.864
Token
Token ID198
Feature activation-8.63e-01

Pos logit contributions
prem+0.410
ducers+0.375
Untitled+0.344
idth+0.343
humans+0.341
Neg logit contributions
 defer-0.457
 McMaster-0.453
oret-0.440
RW-0.437
 torches-0.437
TokenM
Token ID44
Feature activation-2.22e+00

Pos logit contributions
prem+0.640
ducers+0.590
 pione+0.573
idth+0.558
Untitled+0.551
Neg logit contributions
 defer-0.628
 McMaster-0.621
oret-0.604
RW-0.595
ore-0.588
Tokenasure
Token ID5015
Feature activation-1.37e+00

Pos logit contributions
prem+1.676
ducers+1.555
 pione+1.519
idth+1.500
Untitled+1.442
Neg logit contributions
 defer-1.579
 McMaster-1.565
RW-1.505
oret-1.498
 torches-1.474
Token,
Token ID11
Feature activation+7.72e-01

Pos logit contributions
prem+1.063
ducers+0.984
 pione+0.972
idth+0.938
 ®+0.914
Neg logit contributions
 defer-0.952
 McMaster-0.943
oret-0.918
RW-0.908
ore-0.892
Token toward
Token ID3812
Feature activation+5.44e-01

Pos logit contributions
 defer+0.136
 McMaster+0.136
oret+0.132
RW+0.131
ore+0.129
Neg logit contributions
prem-0.137
ducers-0.127
 pione-0.126
idth-0.120
-0.118
Token extinction
Token ID21935
Feature activation+1.76e+00

Pos logit contributions
 defer+0.350
 McMaster+0.348
oret+0.337
RW+0.334
ore+0.328
Neg logit contributions
prem-0.446
ducers-0.417
 pione-0.413
idth-0.397
-0.390
Token
Token ID198
Feature activation+7.44e-01

Pos logit contributions
 defer+1.204
 McMaster+1.195
oret+1.160
ore+1.143
RW+1.143
Neg logit contributions
prem-1.371
 pione-1.283
ducers-1.278
idth-1.215
-1.202
Token
Token ID198
Feature activation+1.93e+00

Pos logit contributions
 defer+0.554
 McMaster+0.550
oret+0.535
RW+0.530
ore+0.522
Neg logit contributions
prem-0.537
ducers-0.496
 pione-0.479
idth-0.465
Untitled-0.459
TokenHow
Token ID2437
Feature activation+2.34e+00

Pos logit contributions
 McMaster+1.417
 defer+1.416
RW+1.382
oret+1.381
ore+1.356
Neg logit contributions
prem-1.391
 pione-1.327
ducers-1.294
-1.245
idth-1.236
Token Vera
Token ID44413
Feature activation+3.59e+00

Pos logit contributions
 defer+1.693
 McMaster+1.686
oret+1.625
RW+1.596
ore+1.594
Neg logit contributions
prem-1.740
 pione-1.633
ducers-1.611
idth-1.537
-1.528
Token Rubin
Token ID34599
Feature activation+2.15e-01

Pos logit contributions
 McMaster+2.456
 defer+2.443
oret+2.366
RW+2.336
ore+2.317
Neg logit contributions
prem-2.796
ducers-2.614
 pione-2.613
idth-2.486
-2.458
Token changed
Token ID3421
Feature activation-6.17e-01

Pos logit contributions
 defer+0.150
 McMaster+0.148
oret+0.144
RW+0.143
ore+0.140
Neg logit contributions
prem-0.166
ducers-0.154
 pione-0.152
idth-0.146
 ®-0.143
Token science
Token ID3783
Feature activation+1.26e+00

Pos logit contributions
prem+0.470
ducers+0.437
 pione+0.432
idth+0.414
+0.405
Neg logit contributions
 defer-0.433
 McMaster-0.430
oret-0.418
RW-0.415
ore-0.408
Token
Token ID198
Feature activation+5.95e-01

Pos logit contributions
 defer+0.882
 McMaster+0.875
oret+0.847
RW+0.841
ore+0.828
Neg logit contributions
prem-0.969
ducers-0.903
 pione-0.897
idth-0.857
-0.843
Token
Token ID198
Feature activation+1.75e+00

Pos logit contributions
 defer+0.447
 McMaster+0.443
oret+0.431
RW+0.427
ore+0.421
Neg logit contributions
prem-0.426
ducers-0.393
 pione-0.373
idth-0.367
Untitled-0.363
Token
Token ID851
Feature activation+2.11e+00

Pos logit contributions
 defer+0.953
 McMaster+0.948
oret+0.921
RW+0.915
ore+0.906
Neg logit contributions
prem-1.040
 pione-0.980
ducers-0.970
idth-0.929
-0.914
Token a
Token ID257
Feature activation-8.68e-01

Pos logit contributions
 defer+1.406
 McMaster+1.394
oret+1.344
RW+1.332
ore+1.319
Neg logit contributions
prem-1.672
 pione-1.576
ducers-1.572
idth-1.506
-1.478
Token phrase
Token ID9546
Feature activation+3.21e-01

Pos logit contributions
prem+0.699
ducers+0.652
 pione+0.646
idth+0.620
+0.609
Neg logit contributions
 defer-0.573
 McMaster-0.569
oret-0.551
RW-0.547
ore-0.537
Token I
Token ID314
Feature activation+2.24e+00

Pos logit contributions
 defer+0.225
 McMaster+0.223
oret+0.216
RW+0.215
ore+0.212
Neg logit contributions
prem-0.246
ducers-0.228
 pione-0.228
idth-0.217
-0.213
Token still
Token ID991
Feature activation+2.62e+00

Pos logit contributions
 defer+1.505
 McMaster+1.475
oret+1.426
RW+1.406
ore+1.401
Neg logit contributions
prem-1.804
 pione-1.696
ducers-1.688
idth-1.611
-1.596
Token can
Token ID460
Feature activation+3.44e+00

Pos logit contributions
 defer+1.675
 McMaster+1.634
oret+1.585
ore+1.557
RW+1.557
Neg logit contributions
prem-2.183
 pione-2.059
ducers-2.045
idth-1.958
-1.948
Token
Token ID447
Feature activation+3.13e-01

Pos logit contributions
 defer+2.359
 McMaster+2.272
oret+2.237
ore+2.214
RW+2.201
Neg logit contributions
prem-2.695
 pione-2.551
ducers-2.529
-2.384
idth-2.364
Token
Token ID247
Feature activation-4.19e-01

Pos logit contributions
 defer+0.121
 McMaster+0.120
oret+0.114
RW+0.111
ore+0.108
Neg logit contributions
prem-0.338
ducers-0.320
 pione-0.314
idth-0.309
Untitled-0.305
Tokent
Token ID83
Feature activation-8.16e-01

Pos logit contributions
prem+0.301
ducers+0.279
 pione+0.276
idth+0.263
+0.258
Neg logit contributions
 defer-0.313
 McMaster-0.311
oret-0.303
RW-0.300
ore-0.296
Token write
Token ID3551
Feature activation-6.27e-01

Pos logit contributions
prem+0.628
ducers+0.583
 pione+0.566
idth+0.553
 ®+0.543
Neg logit contributions
 McMaster-0.562
 defer-0.558
oret-0.545
RW-0.544
Bloom-0.531
Token without
Token ID1231
Feature activation+1.84e-01

Pos logit contributions
prem+0.549
ducers+0.514
 pione+0.509
idth+0.491
+0.483
Neg logit contributions
 defer-0.370
 McMaster-0.366
oret-0.355
RW-0.351
ore-0.344
TokenR
Token ID49
Feature activation+5.18e-01

Pos logit contributions
 defer+0.657
 McMaster+0.652
oret+0.630
RW+0.623
ore+0.612
Neg logit contributions
prem-0.939
ducers-0.879
 pione-0.871
idth-0.839
Untitled-0.825
Tokenig
Token ID328
Feature activation-1.07e+00

Pos logit contributions
 defer+0.361
 McMaster+0.359
oret+0.349
RW+0.346
ore+0.340
Neg logit contributions
prem-0.399
ducers-0.370
 pione-0.367
idth-0.351
-0.345
Tokenby
Token ID1525
Feature activation+1.64e+00

Pos logit contributions
prem+0.864
ducers+0.805
 pione+0.787
idth+0.768
Untitled+0.746
Neg logit contributions
 defer-0.709
 McMaster-0.702
RW-0.676
oret-0.675
Bloom-0.657
Token,
Token ID11
Feature activation+3.96e-01

Pos logit contributions
 McMaster+1.090
 defer+1.085
oret+1.062
RW+1.047
ore+1.045
Neg logit contributions
prem-1.295
 pione-1.211
ducers-1.208
idth-1.150
-1.146
Token K
Token ID509
Feature activation+2.49e+00

Pos logit contributions
 defer+0.323
 McMaster+0.321
oret+0.313
RW+0.311
ore+0.307
Neg logit contributions
prem-0.257
ducers-0.236
 pione-0.234
idth-0.221
-0.217
Token.
Token ID13
Feature activation+4.39e+00

Pos logit contributions
 McMaster+1.502
 defer+1.496
oret+1.462
ore+1.436
RW+1.432
Neg logit contributions
prem-2.135
 pione-1.999
ducers-1.999
idth-1.898
-1.886
Token (
Token ID357
Feature activation+3.33e+00

Pos logit contributions
 McMaster+3.240
 defer+3.149
oret+3.083
RW+3.074
ore+3.017
Neg logit contributions
 pione-3.188
prem-3.187
-2.976
ducers-2.970
idth-2.863
Token 2004
Token ID5472
Feature activation-1.92e+00

Pos logit contributions
 McMaster+2.307
 defer+2.291
oret+2.233
RW+2.200
ore+2.180
Neg logit contributions
prem-2.550
 pione-2.464
ducers-2.393
-2.316
idth-2.295
Token ).
Token ID6739
Feature activation+2.50e+00

Pos logit contributions
prem+1.104
ducers+1.000
 pione+0.993
idth+0.932
 ®+0.907
Neg logit contributions
 defer-1.696
 McMaster-1.685
oret-1.652
RW-1.639
ore-1.615
Token Add
Token ID3060
Feature activation-2.23e-01

Pos logit contributions
 McMaster+1.775
 defer+1.763
oret+1.718
RW+1.693
ore+1.672
Neg logit contributions
prem-1.889
 pione-1.780
ducers-1.761
idth-1.678
-1.672
Tokenressing
Token ID11697
Feature activation-1.28e+00

Pos logit contributions
prem+0.211
ducers+0.199
 pione+0.197
idth+0.191
 ®+0.187
Neg logit contributions
 defer-0.115
 McMaster-0.115
oret-0.110
RW-0.109
ore-0.106
Token model
Token ID2746
Feature activation+2.20e+00

Pos logit contributions
 defer+0.163
 McMaster+0.162
oret+0.157
RW+0.156
ore+0.153
Neg logit contributions
prem-0.170
ducers-0.158
 pione-0.156
idth-0.149
-0.146
Token civil
Token ID3026
Feature activation-1.06e+00

Pos logit contributions
 defer+1.553
 McMaster+1.532
oret+1.484
RW+1.480
ore+1.457
Neg logit contributions
prem-1.681
ducers-1.563
 pione-1.553
idth-1.475
Untitled-1.454
Token rights
Token ID2489
Feature activation-5.12e-01

Pos logit contributions
prem+0.887
ducers+0.831
 pione+0.824
idth+0.793
+0.779
Neg logit contributions
 defer-0.660
 McMaster-0.658
oret-0.635
RW-0.630
ore-0.617
Token program
Token ID1430
Feature activation-1.17e+00

Pos logit contributions
prem+0.414
ducers+0.386
 pione+0.380
idth+0.367
 ®+0.360
Neg logit contributions
 McMaster-0.332
 defer-0.332
oret-0.322
RW-0.319
ore-0.312
Token worthy
Token ID12733
Feature activation-1.27e+00

Pos logit contributions
prem+0.871
ducers+0.808
 pione+0.796
idth+0.763
+0.749
Neg logit contributions
 defer-0.838
 McMaster-0.836
oret-0.815
RW-0.806
ore-0.791
Token of
Token ID286
Feature activation+4.25e+00

Pos logit contributions
prem+0.923
ducers+0.852
 pione+0.842
idth+0.808
Untitled+0.790
Neg logit contributions
 defer-0.941
 McMaster-0.933
oret-0.903
RW-0.902
ore-0.889
Token replication
Token ID30330
Feature activation+1.78e+00

Pos logit contributions
 defer+2.978
 McMaster+2.944
oret+2.800
RW+2.788
ore+2.783
Neg logit contributions
prem-3.223
 pione-3.037
ducers-3.004
idth-2.879
-2.820
Token.
Token ID13
Feature activation-1.43e+00

Pos logit contributions
 defer+1.204
 McMaster+1.196
oret+1.161
RW+1.153
ore+1.139
Neg logit contributions
prem-1.400
ducers-1.311
 pione-1.301
idth-1.243
-1.219
Token
Token ID447
Feature activation-1.29e+00

Pos logit contributions
prem+1.049
ducers+0.971
 pione+0.961
idth+0.918
+0.899
Neg logit contributions
 defer-1.041
 McMaster-1.034
oret-1.006
RW-0.998
ore-0.982
Token
Token ID251
Feature activation-1.31e-01

Pos logit contributions
prem+1.209
ducers+1.136
 pione+1.124
idth+1.087
 ®+1.078
Neg logit contributions
 defer-0.674
 McMaster-0.668
oret-0.648
RW-0.634
ore-0.625
Token
Token ID198
Feature activation-6.61e-01

Pos logit contributions
prem+0.098
ducers+0.091
 pione+0.090
idth+0.086
+0.085
Neg logit contributions
 defer-0.094
 McMaster-0.094
oret-0.091
RW-0.090
ore-0.089
Token
Token ID198
Feature activation+1.23e+00

Pos logit contributions
 defer+1.212
 McMaster+1.204
oret+1.172
RW+1.162
ore+1.145
Neg logit contributions
prem-1.214
ducers-1.125
 pione-1.122
idth-1.066
-1.050
TokenRead
Token ID5569
Feature activation+6.61e-01

Pos logit contributions
 defer+0.934
 McMaster+0.929
oret+0.912
RW+0.911
ore+0.897
Neg logit contributions
prem-0.847
 pione-0.803
ducers-0.785
-0.752
idth-0.746
Token More
Token ID3125
Feature activation+1.35e+00

Pos logit contributions
 defer+0.475
 McMaster+0.473
oret+0.460
RW+0.454
ore+0.450
Neg logit contributions
prem-0.491
ducers-0.456
 pione-0.454
idth-0.433
-0.427
Token:
Token ID25
Feature activation+1.21e+00

Pos logit contributions
 McMaster+1.003
 defer+1.000
oret+0.973
RW+0.973
ore+0.956
Neg logit contributions
prem-0.967
 pione-0.904
ducers-0.886
idth-0.850
-0.848
Token
Token ID198
Feature activation+2.95e+00

Pos logit contributions
 McMaster+0.876
 defer+0.872
oret+0.844
RW+0.842
ore+0.828
Neg logit contributions
prem-0.895
 pione-0.842
ducers-0.827
idth-0.791
-0.791
Token
Token ID198
Feature activation+3.84e+00

Pos logit contributions
 defer+2.074
 McMaster+2.067
oret+2.011
RW+2.005
ore+1.969
Neg logit contributions
prem-2.220
 pione-2.190
ducers-2.068
-2.059
idth-1.996
TokenDr
Token ID6187
Feature activation+1.98e+00

Pos logit contributions
RW+2.734
 McMaster+2.723
 defer+2.713
Bloom+2.662
oret+2.660
Neg logit contributions
 pione-2.832
prem-2.778
-2.660
ducers-2.595
idth-2.527
Token.
Token ID13
Feature activation+7.62e-01

Pos logit contributions
 defer+1.330
 McMaster+1.330
oret+1.294
RW+1.269
ore+1.268
Neg logit contributions
prem-1.550
 pione-1.450
ducers-1.445
-1.368
idth-1.366
Token Se
Token ID1001
Feature activation+1.01e+00

Pos logit contributions
 McMaster+0.532
 defer+0.528
oret+0.511
RW+0.506
ore+0.502
Neg logit contributions
prem-0.582
 pione-0.545
ducers-0.543
idth-0.516
-0.513
Tokenuss
Token ID1046
Feature activation+4.97e-01

Pos logit contributions
 defer+0.886
 McMaster+0.881
oret+0.861
RW+0.851
ore+0.845
Neg logit contributions
prem-0.597
ducers-0.548
 pione-0.542
idth-0.504
-0.496
Token
Token ID447
Feature activation+2.29e+00

Pos logit contributions
 defer+0.350
 McMaster+0.348
oret+0.338
RW+0.334
ore+0.330
Neg logit contributions
prem-0.379
ducers-0.352
 pione-0.351
idth-0.335
-0.329
Token high
Token ID1029
Feature activation-5.29e-01

Pos logit contributions
 defer+0.374
 McMaster+0.371
oret+0.360
RW+0.357
ore+0.351
Neg logit contributions
prem-0.448
ducers-0.417
 pione-0.413
idth-0.396
-0.389
Token road
Token ID2975
Feature activation-5.28e-01

Pos logit contributions
prem+0.417
ducers+0.386
 pione+0.381
idth+0.365
 ®+0.360
Neg logit contributions
 defer-0.357
 McMaster-0.355
oret-0.347
RW-0.344
ore-0.335
Token.
Token ID13
Feature activation-2.85e-01

Pos logit contributions
prem+0.407
ducers+0.378
 pione+0.373
idth+0.357
+0.351
Neg logit contributions
 defer-0.366
 McMaster-0.364
oret-0.354
RW-0.352
ore-0.345
Token
Token ID198
Feature activation-4.71e-01

Pos logit contributions
prem+0.208
ducers+0.193
 pione+0.192
idth+0.183
+0.180
Neg logit contributions
 defer-0.209
 McMaster-0.208
oret-0.202
RW-0.201
ore-0.198
Token
Token ID198
Feature activation-2.03e-01

Pos logit contributions
prem+0.329
ducers+0.301
Untitled+0.277
idth+0.275
humans+0.275
Neg logit contributions
 defer-0.364
 McMaster-0.362
oret-0.351
RW-0.348
 torches-0.348
Token
Token ID447
Feature activation+6.75e-01

Pos logit contributions
prem+0.138
ducers+0.127
 pione+0.126
idth+0.120
+0.118
Neg logit contributions
 defer-0.159
 McMaster-0.158
oret-0.154
RW-0.153
ore-0.151
Token
Token ID250
Feature activation-1.21e+00

Pos logit contributions
 defer+0.348
 McMaster+0.346
oret+0.331
RW+0.326
ore+0.320
Neg logit contributions
prem-0.641
ducers-0.602
 pione-0.587
idth-0.576
Untitled-0.572
TokenT
Token ID51
Feature activation-4.42e-01

Pos logit contributions
prem+0.823
ducers+0.754
 pione+0.736
idth+0.707
Untitled+0.696
Neg logit contributions
 defer-0.949
 McMaster-0.942
oret-0.917
RW-0.907
ore-0.895
Tokenakeru
Token ID43246
Feature activation-2.63e+00

Pos logit contributions
prem+0.339
ducers+0.315
 pione+0.312
idth+0.299
+0.293
Neg logit contributions
 defer-0.309
 McMaster-0.307
oret-0.298
RW-0.295
ore-0.290
Token Kob
Token ID23403
Feature activation-5.31e-01

Pos logit contributions
prem+1.933
ducers+1.781
 pione+1.760
idth+1.684
 ®+1.656
Neg logit contributions
 defer-1.912
 McMaster-1.892
oret-1.851
RW-1.830
ore-1.799
Tokenay
Token ID323
Feature activation+1.06e+00

Pos logit contributions
prem+0.350
ducers+0.321
 pione+0.318
idth+0.301
+0.295
Neg logit contributions
 defer-0.428
 McMaster-0.426
oret-0.416
RW-0.412
ore-0.407
Token­
Token ID3907
Feature activation+6.36e-01

Pos logit contributions
 defer+0.097
 McMaster+0.097
oret+0.093
RW+0.093
ore+0.090
Neg logit contributions
prem-0.134
ducers-0.125
 pione-0.124
idth-0.120
Untitled-0.117
Tokenmi
Token ID11632
Feature activation-3.88e-01

Pos logit contributions
 defer+0.533
 McMaster+0.530
oret+0.520
RW+0.511
ore+0.509
Neg logit contributions
prem-0.397
 pione-0.366
ducers-0.363
-0.342
idth-0.340
Token­
Token ID3907
Feature activation-1.35e-01

Pos logit contributions
prem+0.331
ducers+0.311
 pione+0.309
idth+0.297
Untitled+0.292
Neg logit contributions
 defer-0.238
 McMaster-0.236
oret-0.229
RW-0.225
ore-0.223
Tokenli
Token ID4528
Feature activation+9.37e-02

Pos logit contributions
prem+0.109
ducers+0.102
 pione+0.100
idth+0.097
humans+0.094
Neg logit contributions
 defer-0.089
 McMaster-0.088
oret-0.085
RW-0.085
ore-0.082
Token­
Token ID3907
Feature activation+1.71e+00

Pos logit contributions
 defer+0.056
 McMaster+0.056
oret+0.054
RW+0.053
ore+0.053
Neg logit contributions
prem-0.081
ducers-0.076
 pione-0.076
idth-0.073
-0.072
Tokenat
Token ID265
Feature activation+4.81e-01

Pos logit contributions
 defer+1.129
 McMaster+1.123
oret+1.098
RW+1.075
ore+1.074
Neg logit contributions
prem-1.360
 pione-1.291
ducers-1.275
-1.225
idth-1.209
Token­
Token ID3907
Feature activation+6.88e-01

Pos logit contributions
 defer+0.292
 McMaster+0.290
oret+0.281
RW+0.277
ore+0.273
Neg logit contributions
prem-0.413
ducers-0.388
 pione-0.385
idth-0.370
Untitled-0.365
Tokening
Token ID278
Feature activation-5.07e-01

Pos logit contributions
 defer+0.471
 McMaster+0.467
oret+0.457
RW+0.450
ore+0.446
Neg logit contributions
prem-0.536
ducers-0.499
 pione-0.499
idth-0.475
-0.470
Token is
Token ID318
Feature activation+1.72e+00

Pos logit contributions
prem+0.394
ducers+0.367
 pione+0.365
idth+0.349
+0.343
Neg logit contributions
 defer-0.349
 McMaster-0.347
oret-0.336
RW-0.333
ore-0.328
Token the
Token ID262
Feature activation+1.07e+00

Pos logit contributions
 defer+1.213
 McMaster+1.211
oret+1.157
RW+1.139
ore+1.133
Neg logit contributions
prem-1.305
 pione-1.223
ducers-1.222
idth-1.182
Untitled-1.150
Token treat
Token ID2190
Feature activation+7.66e-01

Pos logit contributions
 defer+0.738
 McMaster+0.733
oret+0.712
RW+0.697
ore+0.693
Neg logit contributions
prem-0.837
ducers-0.782
 pione-0.779
idth-0.749
-0.732
TokenFirst
Token ID5962
Feature activation+1.78e+00

Pos logit contributions
 defer+1.343
 McMaster+1.328
RW+1.311
oret+1.303
ore+1.280
Neg logit contributions
prem-1.451
 pione-1.415
ducers-1.355
-1.334
idth-1.306
Token posted
Token ID4481
Feature activation+2.18e+00

Pos logit contributions
 defer+1.138
 McMaster+1.089
RW+1.081
oret+1.054
Bloom+1.053
Neg logit contributions
prem-1.439
 pione-1.402
ducers-1.381
idth-1.331
-1.308
Token<|endoftext|>
Token ID50256
Feature activation-8.66e-02

Pos logit contributions
 defer+1.783
 McMaster+1.775
oret+1.738
RW+1.725
ore+1.715
Neg logit contributions
prem-1.394
 pione-1.327
ducers-1.280
-1.233
idth-1.210
TokenScreen
Token ID23901
Feature activation+3.26e+00

Pos logit contributions
prem+0.063
ducers+0.059
 pione+0.057
idth+0.055
Untitled+0.055
Neg logit contributions
 defer-0.064
 McMaster-0.063
oret-0.062
RW-0.061
ore-0.060
Tokencap
Token ID11128
Feature activation-1.72e+00

Pos logit contributions
 defer+2.249
 McMaster+2.230
oret+2.156
RW+2.155
ore+2.122
Neg logit contributions
prem-2.523
ducers-2.346
 pione-2.340
idth-2.233
-2.193
Token via
Token ID2884
Feature activation+1.58e-01

Pos logit contributions
prem+1.264
ducers+1.172
 pione+1.154
idth+1.110
 ®+1.091
Neg logit contributions
 defer-1.247
 McMaster-1.238
oret-1.210
RW-1.196
ore-1.176
Token YouTube
Token ID7444
Feature activation-4.05e-01

Pos logit contributions
 defer+0.104
 McMaster+0.103
oret+0.100
RW+0.099
ore+0.097
Neg logit contributions
prem-0.127
ducers-0.118
 pione-0.117
idth-0.113
Untitled-0.110
Token user
Token ID2836
Feature activation-9.00e-01

Pos logit contributions
prem+0.302
ducers+0.280
 pione+0.275
idth+0.264
Untitled+0.260
Neg logit contributions
 defer-0.291
 McMaster-0.289
oret-0.282
RW-0.279
ore-0.275
Token Movie
Token ID15875
Feature activation+8.89e-01

Pos logit contributions
prem+0.704
ducers+0.654
 pione+0.646
idth+0.620
Untitled+0.610
Neg logit contributions
 defer-0.613
 McMaster-0.609
oret-0.592
RW-0.587
ore-0.577
Tokenclips
Token ID31945
Feature activation-3.71e+00

Pos logit contributions
 defer+0.638
 McMaster+0.634
oret+0.616
RW+0.612
ore+0.602
Neg logit contributions
prem-0.664
ducers-0.616
 pione-0.612
idth-0.584
-0.573
Token trailers
Token ID33122
Feature activation-4.14e-01

Pos logit contributions
prem+2.758
ducers+2.537
 pione+2.472
idth+2.393
Untitled+2.371
Neg logit contributions
 defer-2.678
 McMaster-2.648
oret-2.587
RW-2.550
 torches-2.500
Token,
Token ID11
Feature activation-5.71e-01

Pos logit contributions
 defer+0.194
 McMaster+0.192
oret+0.188
RW+0.187
ore+0.184
Neg logit contributions
prem-0.181
ducers-0.168
 pione-0.168
idth-0.158
-0.156
Token $
Token ID720
Feature activation+6.14e-01

Pos logit contributions
prem+0.378
ducers+0.345
 pione+0.341
idth+0.325
Untitled+0.318
Neg logit contributions
 defer-0.459
 McMaster-0.457
oret-0.445
RW-0.441
ore-0.435
Tokenrect
Token ID2554
Feature activation-2.92e-01

Pos logit contributions
 defer+0.393
 McMaster+0.391
oret+0.377
RW+0.372
ore+0.365
Neg logit contributions
prem-0.510
ducers-0.474
 pione-0.466
idth-0.453
Untitled-0.445
Token1
Token ID16
Feature activation-6.74e-01

Pos logit contributions
prem+0.216
ducers+0.200
 pione+0.199
idth+0.189
+0.187
Neg logit contributions
 defer-0.212
 McMaster-0.210
oret-0.205
RW-0.203
ore-0.201
Token,
Token ID11
Feature activation-1.37e+00

Pos logit contributions
prem+0.470
ducers+0.435
 pione+0.432
idth+0.409
+0.402
Neg logit contributions
 defer-0.519
 McMaster-0.515
oret-0.503
RW-0.499
ore-0.492
Token $
Token ID720
Feature activation+9.49e-01

Pos logit contributions
prem+0.907
ducers+0.825
 pione+0.816
idth+0.781
Untitled+0.766
Neg logit contributions
 defer-1.093
 McMaster-1.087
oret-1.058
RW-1.048
ore-1.034
Tokens
Token ID82
Feature activation-1.85e-01

Pos logit contributions
 defer+0.612
 McMaster+0.608
oret+0.587
RW+0.580
ore+0.570
Neg logit contributions
prem-0.782
ducers-0.728
 pione-0.718
idth-0.695
Untitled-0.682
TokenFormat
Token ID26227
Feature activation+6.40e-01

Pos logit contributions
prem+0.118
ducers+0.108
 pione+0.108
idth+0.101
+0.100
Neg logit contributions
 defer-0.152
 McMaster-0.151
oret-0.148
RW-0.147
ore-0.145
Token)
Token ID8
Feature activation+6.58e-01

Pos logit contributions
 defer+0.454
 McMaster+0.451
oret+0.439
RW+0.437
ore+0.431
Neg logit contributions
prem-0.484
ducers-0.453
 pione-0.451
idth-0.426
-0.422
Token }
Token ID1782
Feature activation-1.95e+00

Pos logit contributions
 defer+0.493
 McMaster+0.486
oret+0.475
RW+0.470
ore+0.465
Neg logit contributions
prem-0.475
ducers-0.442
 pione-0.437
idth-0.414
-0.409
Token else
Token ID2073
Feature activation+3.31e+00

Pos logit contributions
prem+1.358
ducers+1.247
 pione+1.220
idth+1.178
 ®+1.167
Neg logit contributions
 McMaster-1.472
 defer-1.465
oret-1.434
RW-1.421
Bloom-1.405
Token Greenland
Token ID30155
Feature activation+2.22e-01

Pos logit contributions
prem+0.013
ducers+0.012
 pione+0.012
idth+0.012
Untitled+0.011
Neg logit contributions
 defer-0.013
 McMaster-0.013
oret-0.013
RW-0.013
ore-0.012
Token will
Token ID481
Feature activation+7.14e-01

Pos logit contributions
 defer+0.154
 McMaster+0.153
oret+0.149
RW+0.147
ore+0.145
Neg logit contributions
prem-0.171
ducers-0.159
 pione-0.158
idth-0.151
-0.148
Token not
Token ID407
Feature activation+1.30e-01

Pos logit contributions
 McMaster+0.464
 defer+0.463
oret+0.448
RW+0.446
ore+0.436
Neg logit contributions
prem-0.579
ducers-0.540
 pione-0.532
idth-0.515
 ®-0.503
Token go
Token ID467
Feature activation+8.82e-01

Pos logit contributions
 McMaster+0.081
 defer+0.080
RW+0.078
oret+0.078
Bloom+0.076
Neg logit contributions
prem-0.108
ducers-0.101
 pione-0.098
idth-0.097
 ®-0.095
Token quietly
Token ID12703
Feature activation+1.94e+00

Pos logit contributions
 defer+0.517
 McMaster+0.513
oret+0.496
RW+0.491
ore+0.481
Neg logit contributions
prem-0.774
ducers-0.726
 pione-0.720
idth-0.694
-0.682
Token,
Token ID11
Feature activation+8.88e-01

Pos logit contributions
 defer+1.298
 McMaster+1.287
oret+1.245
RW+1.234
ore+1.217
Neg logit contributions
prem-1.544
ducers-1.434
 pione-1.433
idth-1.370
-1.348
Token at
Token ID379
Feature activation-4.01e-02

Pos logit contributions
 defer+0.629
 McMaster+0.624
oret+0.606
RW+0.601
ore+0.593
Neg logit contributions
prem-0.673
ducers-0.624
 pione-0.621
idth-0.592
-0.582
Token least
Token ID1551
Feature activation+8.55e-01

Pos logit contributions
prem+0.031
ducers+0.029
 pione+0.029
idth+0.028
+0.027
Neg logit contributions
 defer-0.027
 McMaster-0.027
oret-0.026
RW-0.026
ore-0.026
Token we
Token ID356
Feature activation-7.54e-03

Pos logit contributions
 defer+0.598
 McMaster+0.593
oret+0.576
RW+0.570
ore+0.562
Neg logit contributions
prem-0.658
ducers-0.610
 pione-0.608
idth-0.580
-0.570
Token will
Token ID481
Feature activation+6.27e-01

Pos logit contributions
prem+0.006
ducers+0.006
 pione+0.006
idth+0.005
Untitled+0.005
Neg logit contributions
 defer-0.005
 McMaster-0.005
oret-0.005
RW-0.005
ore-0.005
Token know
Token ID760
Feature activation+7.92e-01

Pos logit contributions
 McMaster+0.397
 defer+0.396
oret+0.383
RW+0.380
ore+0.373
Neg logit contributions
prem-0.518
ducers-0.485
 pione-0.477
idth-0.461
 ®-0.452
Token annoying
Token ID15774
Feature activation+5.38e-01

Pos logit contributions
prem+0.177
ducers+0.167
Untitled+0.155
idth+0.155
 pione+0.154
Neg logit contributions
 defer-0.152
 McMaster-0.151
RW-0.147
oret-0.146
Bloom-0.141
Token/
Token ID14
Feature activation+3.48e-01

Pos logit contributions
 defer+0.351
 McMaster+0.349
oret+0.336
RW+0.334
ore+0.326
Neg logit contributions
prem-0.439
ducers-0.409
 pione-0.392
idth-0.385
Untitled-0.381
Tokendist
Token ID17080
Feature activation+1.95e+00

Pos logit contributions
 McMaster+0.253
 defer+0.253
RW+0.243
oret+0.243
 torches+0.240
Neg logit contributions
prem-0.262
ducers-0.240
humans-0.223
Untitled-0.221
idth-0.220
Tokenract
Token ID974
Feature activation+2.10e+00

Pos logit contributions
 McMaster+1.281
 defer+1.274
RW+1.226
oret+1.216
 torches+1.190
Neg logit contributions
prem-1.585
ducers-1.493
idth-1.410
 pione-1.405
humans-1.375
Tokening
Token ID278
Feature activation+7.47e-01

Pos logit contributions
 defer+1.390
 McMaster+1.379
oret+1.338
RW+1.326
ore+1.304
Neg logit contributions
prem-1.692
ducers-1.577
 pione-1.567
idth-1.501
-1.476
Token and
Token ID290
Feature activation-1.52e+00

Pos logit contributions
 defer+0.479
 McMaster+0.476
oret+0.460
RW+0.456
ore+0.447
Neg logit contributions
prem-0.617
ducers-0.576
 pione-0.558
idth-0.546
Untitled-0.537
Token the
Token ID262
Feature activation+1.39e-01

Pos logit contributions
prem+0.991
ducers+0.910
idth+0.837
Untitled+0.825
 ®+0.821
Neg logit contributions
 defer-1.230
 McMaster-1.224
oret-1.196
RW-1.191
 torches-1.175
Token one
Token ID530
Feature activation+2.54e+00

Pos logit contributions
 defer+0.097
 McMaster+0.097
oret+0.093
RW+0.093
ore+0.091
Neg logit contributions
prem-0.107
ducers-0.099
 pione-0.096
idth-0.094
Untitled-0.092
Token that
Token ID326
Feature activation-6.80e-01

Pos logit contributions
 defer+1.709
 McMaster+1.677
oret+1.647
RW+1.618
ore+1.600
Neg logit contributions
prem-2.019
 pione-1.974
ducers-1.870
-1.854
-1.800
Token I
Token ID314
Feature activation-1.42e+00

Pos logit contributions
prem+0.507
ducers+0.473
idth+0.444
 pione+0.440
Untitled+0.437
Neg logit contributions
 defer-0.486
 McMaster-0.482
oret-0.467
RW-0.466
Bloom-0.456
Token think
Token ID892
Feature activation-1.24e+00

Pos logit contributions
prem+0.901
ducers+0.823
 pione+0.775
idth+0.763
humans+0.742
Neg logit contributions
 McMaster-1.180
 defer-1.176
RW-1.148
oret-1.137
 torches-1.117
Token
Token ID198
Feature activation+4.41e-01

Pos logit contributions
 defer+0.508
 McMaster+0.505
oret+0.491
RW+0.486
 torches+0.479
Neg logit contributions
prem-0.486
ducers-0.448
 pione-0.424
idth-0.418
Untitled-0.414
TokenGe
Token ID10082
Feature activation+8.97e-01

Pos logit contributions
 defer+0.311
 McMaster+0.309
oret+0.301
RW+0.300
ore+0.294
Neg logit contributions
prem-0.333
 pione-0.312
ducers-0.310
idth-0.295
-0.292
Tokenisel
Token ID36811
Feature activation+1.19e+00

Pos logit contributions
 defer+0.755
 McMaster+0.751
oret+0.733
RW+0.728
ore+0.719
Neg logit contributions
prem-0.559
ducers-0.510
 pione-0.504
idth-0.477
-0.465
Token once
Token ID1752
Feature activation+1.03e+00

Pos logit contributions
 defer+0.852
 McMaster+0.847
oret+0.819
RW+0.813
ore+0.803
Neg logit contributions
prem-0.903
 pione-0.839
ducers-0.837
idth-0.797
-0.783
Token stated
Token ID5081
Feature activation+4.60e-01

Pos logit contributions
 defer+0.813
 McMaster+0.805
oret+0.782
RW+0.774
ore+0.769
Neg logit contributions
prem-0.704
 pione-0.653
ducers-0.650
idth-0.617
-0.607
Token that
Token ID326
Feature activation-6.17e-01

Pos logit contributions
 defer+0.318
 McMaster+0.316
oret+0.306
RW+0.303
ore+0.300
Neg logit contributions
prem-0.357
 pione-0.332
ducers-0.332
idth-0.317
-0.310
Token he
Token ID339
Feature activation+1.24e-01

Pos logit contributions
prem+0.476
ducers+0.442
 pione+0.439
idth+0.420
+0.412
Neg logit contributions
 defer-0.428
 McMaster-0.425
oret-0.413
RW-0.409
ore-0.403
Token got
Token ID1392
Feature activation-2.44e-02

Pos logit contributions
 defer+0.085
 McMaster+0.084
oret+0.082
RW+0.081
ore+0.080
Neg logit contributions
prem-0.096
ducers-0.090
 pione-0.089
idth-0.085
-0.083
Token all
Token ID477
Feature activation+3.10e-01

Pos logit contributions
prem+0.019
ducers+0.018
 pione+0.018
idth+0.017
+0.017
Neg logit contributions
 defer-0.017
 McMaster-0.017
oret-0.016
RW-0.016
ore-0.016
Token his
Token ID465
Feature activation+3.79e-01

Pos logit contributions
 defer+0.228
 McMaster+0.227
oret+0.220
RW+0.219
ore+0.215
Neg logit contributions
prem-0.226
ducers-0.209
 pione-0.207
idth-0.198
-0.194
Token ideas
Token ID4213
Feature activation+7.33e-01

Pos logit contributions
 defer+0.265
 McMaster+0.263
oret+0.256
RW+0.253
ore+0.249
Neg logit contributions
prem-0.290
ducers-0.270
 pione-0.267
idth-0.256
-0.251
Token ethnic
Token ID9450
Feature activation-1.85e-01

Pos logit contributions
prem+1.948
ducers+1.830
 pione+1.742
idth+1.695
humans+1.676
Neg logit contributions
 defer-2.024
 McMaster-2.014
oret-1.957
RW-1.954
Bloom-1.912
Token groups
Token ID2628
Feature activation-1.25e+00

Pos logit contributions
prem+0.119
ducers+0.109
 pione+0.108
idth+0.102
+0.100
Neg logit contributions
 defer-0.152
 McMaster-0.151
oret-0.147
RW-0.146
ore-0.144
Token.
Token ID13
Feature activation-1.18e+00

Pos logit contributions
prem+0.940
ducers+0.872
 pione+0.861
idth+0.824
+0.809
Neg logit contributions
 defer-0.893
 McMaster-0.887
oret-0.862
RW-0.856
ore-0.841
Token One
Token ID1881
Feature activation-2.22e+00

Pos logit contributions
prem+0.848
ducers+0.783
 pione+0.752
idth+0.729
 ®+0.726
Neg logit contributions
 defer-0.883
 McMaster-0.866
oret-0.847
RW-0.842
 torches-0.831
Token of
Token ID286
Feature activation-9.03e-01

Pos logit contributions
prem+1.639
ducers+1.520
 pione+1.477
idth+1.425
 ®+1.413
Neg logit contributions
 defer-1.590
 McMaster-1.575
RW-1.527
oret-1.523
ore-1.491
Token the
Token ID262
Feature activation-1.26e+00

Pos logit contributions
prem+0.627
ducers+0.578
 pione+0.572
idth+0.545
+0.533
Neg logit contributions
 defer-0.697
 McMaster-0.693
oret-0.675
RW-0.670
ore-0.660
Token goals
Token ID4661
Feature activation-2.61e+00

Pos logit contributions
prem+0.868
ducers+0.801
 pione+0.788
idth+0.753
Untitled+0.735
Neg logit contributions
 defer-0.971
 McMaster-0.965
oret-0.938
RW-0.934
ore-0.918
Token with
Token ID351
Feature activation-2.32e+00

Pos logit contributions
prem+1.819
ducers+1.683
 pione+1.651
idth+1.569
+1.546
Neg logit contributions
 defer-1.992
 McMaster-1.977
oret-1.929
RW-1.919
ore-1.880
Token the
Token ID262
Feature activation-6.32e-01

Pos logit contributions
prem+1.746
ducers+1.639
 pione+1.598
idth+1.538
 ®+1.521
Neg logit contributions
 defer-1.621
 McMaster-1.603
oret-1.575
RW-1.569
ore-1.528
Token Human
Token ID5524
Feature activation+1.68e+00

Pos logit contributions
prem+0.475
ducers+0.442
 pione+0.435
idth+0.418
 ®+0.411
Neg logit contributions
 defer-0.448
 McMaster-0.443
RW-0.431
oret-0.430
ore-0.421
Token Micro
Token ID4527
Feature activation+8.70e-01

Pos logit contributions
 defer+1.000
 McMaster+0.999
oret+0.966
RW+0.946
ore+0.936
Neg logit contributions
prem-1.456
ducers-1.361
 pione-1.359
idth-1.304
Untitled-1.285
Token faces
Token ID6698
Feature activation+1.62e+00

Pos logit contributions
 defer+0.198
 McMaster+0.197
oret+0.190
RW+0.189
ore+0.185
Neg logit contributions
prem-0.257
ducers-0.240
 pione-0.238
idth-0.229
-0.224
Token with
Token ID351
Feature activation+7.37e-01

Pos logit contributions
 defer+1.052
 McMaster+1.040
oret+1.007
RW+0.999
ore+0.985
Neg logit contributions
prem-1.333
ducers-1.244
 pione-1.239
idth-1.189
-1.170
Token the
Token ID262
Feature activation+1.62e+00

Pos logit contributions
 defer+0.500
 McMaster+0.496
oret+0.481
RW+0.477
ore+0.470
Neg logit contributions
prem-0.581
ducers-0.540
 pione-0.538
idth-0.515
-0.506
Token
Token ID564
Feature activation+8.96e-01

Pos logit contributions
 defer+1.041
 McMaster+1.031
oret+1.004
RW+0.985
ore+0.978
Neg logit contributions
prem-1.329
 pione-1.244
ducers-1.236
idth-1.188
-1.172
Token
Token ID250
Feature activation-2.36e-02

Pos logit contributions
 defer+0.465
 McMaster+0.461
oret+0.443
RW+0.438
ore+0.428
Neg logit contributions
prem-0.848
ducers-0.798
 pione-0.792
idth-0.766
-0.754
Tokenevidence
Token ID46817
Feature activation-1.98e+00

Pos logit contributions
prem+0.018
ducers+0.017
 pione+0.016
idth+0.016
+0.015
Neg logit contributions
 defer-0.017
 McMaster-0.017
oret-0.016
RW-0.016
ore-0.016
Token of
Token ID286
Feature activation+1.40e+00

Pos logit contributions
prem+1.207
ducers+1.100
 pione+1.080
idth+1.027
+0.998
Neg logit contributions
 defer-1.697
 McMaster-1.686
oret-1.647
RW-1.634
ore-1.611
Token so
Token ID523
Feature activation+1.55e+00

Pos logit contributions
 defer+0.928
 McMaster+0.920
oret+0.891
RW+0.882
ore+0.870
Neg logit contributions
prem-1.125
 pione-1.049
ducers-1.048
idth-1.002
-0.987
Token much
Token ID881
Feature activation-7.92e-01

Pos logit contributions
 defer+1.196
 McMaster+1.185
oret+1.156
RW+1.148
ore+1.144
Neg logit contributions
prem-1.074
ducers-0.989
 pione-0.988
idth-0.941
-0.917
Token sudden
Token ID4802
Feature activation+1.01e+00

Pos logit contributions
prem+0.670
ducers+0.628
 pione+0.618
idth+0.596
Untitled+0.587
Neg logit contributions
 defer-0.487
 McMaster-0.484
oret-0.470
RW-0.464
ore-0.454
Token emotion
Token ID9942
Feature activation-3.83e-01

Pos logit contributions
 defer+0.630
 McMaster+0.624
oret+0.604
RW+0.598
ore+0.588
Neg logit contributions
prem-0.856
ducers-0.800
 pione-0.796
idth-0.764
-0.753
Token.
Token ID13
Feature activation-9.76e-01

Pos logit contributions
prem+0.290
ducers+0.267
idth+0.247
humans+0.247
Untitled+0.247
Neg logit contributions
 defer-0.265
 McMaster-0.258
 torches-0.253
RW-0.252
oret-0.252
Token Mor
Token ID3461
Feature activation+9.80e-01

Pos logit contributions
prem+1.126
ducers+1.070
 pione+1.060
idth+1.034
 ®+1.019
Neg logit contributions
 defer-0.304
 McMaster-0.296
oret-0.281
RW-0.277
ore-0.264
Tokenneau
Token ID46533
Feature activation-1.59e+00

Pos logit contributions
 defer+0.693
 McMaster+0.690
oret+0.670
RW+0.662
ore+0.656
Neg logit contributions
prem-0.742
 pione-0.694
ducers-0.688
idth-0.654
-0.653
Token says
Token ID1139
Feature activation+1.45e+00

Pos logit contributions
prem+1.153
ducers+1.064
 pione+1.032
idth+1.003
 ®+1.000
Neg logit contributions
 McMaster-1.153
 defer-1.151
oret-1.127
RW-1.118
Bloom-1.103
Token he
Token ID339
Feature activation+4.43e-02

Pos logit contributions
 defer+1.015
 McMaster+1.002
oret+0.972
RW+0.958
ore+0.947
Neg logit contributions
prem-1.117
 pione-1.048
ducers-1.043
idth-0.988
-0.980
Token is
Token ID318
Feature activation-9.14e-02

Pos logit contributions
 McMaster+0.031
 defer+0.030
RW+0.030
oret+0.030
Bloom+0.029
Neg logit contributions
prem-0.034
ducers-0.031
 pione-0.030
idth-0.030
 ®-0.029
Token sole
Token ID6195
Feature activation-6.95e-01

Pos logit contributions
prem+0.072
ducers+0.067
 pione+0.065
idth+0.063
Untitled+0.062
Neg logit contributions
 McMaster-0.062
 defer-0.062
oret-0.060
RW-0.060
ore-0.058
Token owner
Token ID4870
Feature activation+1.23e+00

Pos logit contributions
prem+0.402
ducers+0.364
 pione+0.359
idth+0.339
+0.329
Neg logit contributions
 defer-0.615
 McMaster-0.613
oret-0.599
RW-0.595
ore-0.587
Token of
Token ID286
Feature activation-3.87e-01

Pos logit contributions
 defer+0.886
 McMaster+0.872
oret+0.845
RW+0.832
ore+0.828
Neg logit contributions
prem-0.929
ducers-0.867
 pione-0.867
idth-0.823
-0.812
Token 20
Token ID1160
Feature activation+9.99e-01

Pos logit contributions
prem+0.299
ducers+0.278
 pione+0.276
idth+0.264
+0.259
Neg logit contributions
 defer-0.268
 McMaster-0.266
oret-0.259
RW-0.256
ore-0.252
Token70
Token ID2154
Feature activation-2.07e-02

Pos logit contributions
 defer+0.727
 McMaster+0.718
oret+0.694
RW+0.688
ore+0.680
Neg logit contributions
prem-0.743
ducers-0.695
 pione-0.691
idth-0.654
-0.647
Token characterized
Token ID16264
Feature activation+4.99e-01

Pos logit contributions
 defer+0.071
 McMaster+0.071
RW+0.069
oret+0.069
ore+0.068
Neg logit contributions
prem-0.049
ducers-0.044
 pione-0.042
idth-0.040
Untitled-0.040
Token by
Token ID416
Feature activation+1.55e+00

Pos logit contributions
 defer+0.362
 McMaster+0.361
oret+0.351
RW+0.347
 torches+0.346
Neg logit contributions
prem-0.370
ducers-0.343
humans-0.315
Untitled-0.313
idth-0.312
Token multiple
Token ID3294
Feature activation-5.21e-01

Pos logit contributions
 defer+0.849
 McMaster+0.846
oret+0.819
RW+0.818
Bloom+0.793
Neg logit contributions
prem-1.415
ducers-1.348
 pione-1.256
humans-1.244
Untitled-1.243
Token tiny
Token ID7009
Feature activation+9.59e-02

Pos logit contributions
prem+0.310
ducers+0.289
 pione+0.261
idth+0.261
Untitled+0.261
Neg logit contributions
 McMaster-0.448
 defer-0.447
RW-0.435
oret-0.433
Bloom-0.430
Token ker
Token ID41927
Feature activation-2.38e+00

Pos logit contributions
 defer+0.064
 McMaster+0.064
oret+0.062
RW+0.062
Bloom+0.061
Neg logit contributions
prem-0.076
ducers-0.070
idth-0.065
Untitled-0.065
 ®-0.065
Tokenat
Token ID265
Feature activation-3.62e+00

Pos logit contributions
prem+1.764
ducers+1.619
idth+1.523
humans+1.484
apult+1.476
Neg logit contributions
 defer-1.743
 McMaster-1.741
RW-1.676
 torches-1.656
oret-1.639
Tokenotic
Token ID6210
Feature activation-3.24e+00

Pos logit contributions
prem+1.620
ducers+1.459
idth+1.321
humans+1.245
Untitled+1.237
Neg logit contributions
 defer-3.700
 McMaster-3.676
RW-3.556
Bloom-3.508
oret-3.502
Token plugs
Token ID37008
Feature activation-8.58e-01

Pos logit contributions
prem+2.639
ducers+2.512
 architects+2.316
 ®+2.292
idth+2.289
Neg logit contributions
 McMaster-2.080
 defer-2.045
oret-2.005
RW-1.980
Bloom-1.957
Token,
Token ID11
Feature activation-8.48e-01

Pos logit contributions
prem+0.621
ducers+0.574
Untitled+0.531
idth+0.526
humans+0.525
Neg logit contributions
 defer-0.640
 McMaster-0.630
oret-0.612
RW-0.609
 torches-0.605
Token mim
Token ID17007
Feature activation-3.06e-01

Pos logit contributions
prem+0.496
ducers+0.462
Untitled+0.413
 ®+0.413
 pione+0.410
Neg logit contributions
 defer-0.733
 McMaster-0.727
RW-0.719
oret-0.717
Bloom-0.703
Tokenicking
Token ID7958
Feature activation-2.26e-01

Pos logit contributions
prem+0.243
ducers+0.232
idth+0.215
Untitled+0.213
apult+0.211
Neg logit contributions
 defer-0.203
 McMaster-0.201
RW-0.196
oret-0.194
Bloom-0.192
Token.
Token ID13
Feature activation+9.45e-01

Pos logit contributions
prem+1.599
ducers+1.488
 pione+1.456
idth+1.404
Untitled+1.387
Neg logit contributions
 McMaster-1.347
 defer-1.344
oret-1.302
RW-1.289
ore-1.268
Tokenfiles
Token ID16624
Feature activation-2.94e+00

Pos logit contributions
 defer+0.856
 McMaster+0.849
oret+0.832
RW+0.826
ore+0.818
Neg logit contributions
prem-0.529
ducers-0.477
 pione-0.475
idth-0.445
-0.436
Token table
Token ID3084
Feature activation+2.95e+00

Pos logit contributions
prem+2.341
ducers+2.181
 pione+2.134
idth+2.063
 ®+2.035
Neg logit contributions
 McMaster-1.940
 defer-1.937
oret-1.865
RW-1.863
Bloom-1.825
Token SELECT
Token ID33493
Feature activation-7.62e-01

Pos logit contributions
 defer+2.059
 McMaster+2.005
oret+1.938
RW+1.933
ore+1.902
Neg logit contributions
prem-2.279
 pione-2.125
ducers-2.103
idth-2.023
-1.978
Token *
Token ID1635
Feature activation+1.25e+00

Pos logit contributions
prem+0.586
ducers+0.545
 pione+0.540
idth+0.517
Untitled+0.507
Neg logit contributions
 defer-0.529
 McMaster-0.527
oret-0.512
RW-0.508
ore-0.499
Token FROM
Token ID16034
Feature activation-3.44e+00

Pos logit contributions
 defer+0.848
 McMaster+0.838
oret+0.813
RW+0.810
ore+0.794
Neg logit contributions
prem-0.985
ducers-0.915
 pione-0.912
idth-0.873
-0.853
Token [
Token ID685
Feature activation+2.92e+00

Pos logit contributions
prem+2.624
ducers+2.469
 pione+2.408
idth+2.322
 ®+2.306
Neg logit contributions
 McMaster-2.339
 defer-2.334
oret-2.284
RW-2.280
Bloom-2.226
Token big
Token ID1263
Feature activation+1.68e+00

Pos logit contributions
 defer+2.145
 McMaster+2.122
oret+2.053
RW+2.052
ore+2.023
Neg logit contributions
prem-2.131
 pione-1.979
ducers-1.964
idth-1.874
-1.850
Tokenquery
Token ID22766
Feature activation+3.23e+00

Pos logit contributions
 defer+0.958
 McMaster+0.942
oret+0.914
ore+0.902
RW+0.902
Neg logit contributions
prem-1.493
 pione-1.407
ducers-1.401
idth-1.347
-1.333
Token -
Token ID532
Feature activation+9.13e-01

Pos logit contributions
 defer+2.114
 McMaster+2.072
oret+2.001
RW+1.983
ore+1.980
Neg logit contributions
prem-2.624
 pione-2.466
ducers-2.436
-2.329
idth-2.324
Token public
Token ID1171
Feature activation+3.14e+00

Pos logit contributions
 defer+0.640
 McMaster+0.634
oret+0.616
RW+0.611
ore+0.602
Neg logit contributions
prem-0.700
ducers-0.650
 pione-0.645
idth-0.616
-0.606
Tokeny
Token ID88
Feature activation+7.81e-01

Pos logit contributions
 defer+0.046
 McMaster+0.046
oret+0.045
RW+0.044
Bloom+0.043
Neg logit contributions
prem-0.054
ducers-0.050
 pione-0.049
idth-0.048
 ®-0.047
Token Butt
Token ID36041
Feature activation+5.19e-01

Pos logit contributions
 defer+0.498
 McMaster+0.498
oret+0.481
RW+0.473
ore+0.470
Neg logit contributions
prem-0.646
 pione-0.603
ducers-0.603
idth-0.576
-0.570
Token,
Token ID11
Feature activation+4.84e-01

Pos logit contributions
 defer+0.351
 McMaster+0.349
oret+0.338
RW+0.336
ore+0.328
Neg logit contributions
prem-0.410
ducers-0.381
 pione-0.377
idth-0.361
Untitled-0.354
Token who
Token ID508
Feature activation-1.65e+00

Pos logit contributions
 defer+0.330
 McMaster+0.328
oret+0.319
RW+0.316
ore+0.310
Neg logit contributions
prem-0.380
ducers-0.353
 pione-0.349
idth-0.335
Untitled-0.328
Token had
Token ID550
Feature activation-1.16e+00

Pos logit contributions
prem+1.272
ducers+1.181
 pione+1.137
idth+1.110
 ®+1.094
Neg logit contributions
 defer-1.121
 McMaster-1.116
oret-1.086
RW-1.082
Bloom-1.062
Token scored
Token ID7781
Feature activation-3.38e+00

Pos logit contributions
prem+0.899
ducers+0.835
 pione+0.811
idth+0.789
Untitled+0.772
Neg logit contributions
 defer-0.789
 McMaster-0.787
oret-0.762
RW-0.761
Bloom-0.746
Token a
Token ID257
Feature activation-1.32e+00

Pos logit contributions
prem+2.492
ducers+2.279
 pione+2.151
idth+2.117
 architects+2.111
Neg logit contributions
 defer-2.415
 McMaster-2.406
RW-2.365
oret-2.320
Bloom-2.314
Token hat
Token ID6877
Feature activation-1.08e+00

Pos logit contributions
prem+1.059
ducers+0.985
 pione+0.970
idth+0.931
Untitled+0.914
Neg logit contributions
 defer-0.871
 McMaster-0.866
oret-0.839
RW-0.836
ore-0.817
Token-
Token ID12
Feature activation-2.06e-01

Pos logit contributions
prem+0.891
ducers+0.831
 pione+0.817
idth+0.781
 ®+0.775
Neg logit contributions
 defer-0.691
 McMaster-0.686
RW-0.662
oret-0.660
ore-0.642
Tokentr
Token ID2213
Feature activation+2.62e+00

Pos logit contributions
prem+0.151
ducers+0.139
 pione+0.135
idth+0.130
Untitled+0.128
Neg logit contributions
 defer-0.152
 McMaster-0.152
oret-0.146
RW-0.146
 torches-0.143
Tokenick
Token ID624
Feature activation+7.23e-01

Pos logit contributions
 defer+1.733
 McMaster+1.723
oret+1.673
RW+1.656
ore+1.640
Neg logit contributions
prem-2.101
 pione-1.969
ducers-1.960
idth-1.874
-1.861
Token Six
Token ID9699
Feature activation-1.24e+00

Pos logit contributions
prem+1.711
ducers+1.586
 pione+1.553
idth+1.497
 ®+1.473
Neg logit contributions
 defer-1.666
 McMaster-1.653
oret-1.610
RW-1.601
ore-1.571
Token Sigma
Token ID31669
Feature activation+6.90e-01

Pos logit contributions
prem+0.948
ducers+0.881
 pione+0.870
idth+0.835
+0.817
Neg logit contributions
 defer-0.863
 McMaster-0.858
oret-0.832
RW-0.827
ore-0.812
Token Ph
Token ID1380
Feature activation-5.79e-01

Pos logit contributions
 defer+0.512
 McMaster+0.509
oret+0.495
RW+0.488
ore+0.484
Neg logit contributions
prem-0.502
 pione-0.467
ducers-0.463
idth-0.440
-0.435
Tokenases
Token ID1386
Feature activation-1.52e-01

Pos logit contributions
prem+0.479
ducers+0.447
 pione+0.443
idth+0.426
+0.418
Neg logit contributions
 defer-0.370
 McMaster-0.367
oret-0.356
RW-0.353
ore-0.346
Token and
Token ID290
Feature activation-1.39e+00

Pos logit contributions
prem+0.114
ducers+0.105
 pione+0.105
idth+0.100
+0.098
Neg logit contributions
 defer-0.110
 McMaster-0.109
oret-0.106
RW-0.105
ore-0.104
Token their
Token ID511
Feature activation-3.44e+00

Pos logit contributions
prem+0.989
ducers+0.914
 pione+0.900
idth+0.862
Untitled+0.842
Neg logit contributions
 defer-1.042
 McMaster-1.035
oret-1.008
RW-1.003
ore-0.985
Token descriptions
Token ID16969
Feature activation-1.75e+00

Pos logit contributions
prem+2.547
ducers+2.376
 pione+2.269
idth+2.235
 ®+2.211
Neg logit contributions
 defer-2.433
 McMaster-2.416
RW-2.371
oret-2.329
Bloom-2.315
Token
Token ID198
Feature activation-5.75e-01

Pos logit contributions
prem+1.292
ducers+1.195
 pione+1.172
idth+1.129
 ®+1.113
Neg logit contributions
 defer-1.265
 McMaster-1.258
oret-1.226
RW-1.215
ore-1.194
Token
Token ID198
Feature activation+1.01e-01

Pos logit contributions
prem+0.400
ducers+0.366
Untitled+0.337
idth+0.334
humans+0.334
Neg logit contributions
 defer-0.445
 McMaster-0.443
oret-0.430
 torches-0.427
RW-0.426
TokenYou
Token ID1639
Feature activation-1.42e+00

Pos logit contributions
 defer+0.073
 McMaster+0.072
oret+0.070
RW+0.070
ore+0.069
Neg logit contributions
prem-0.075
 pione-0.071
ducers-0.070
idth-0.067
-0.066
Token may
Token ID743
Feature activation-2.38e+00

Pos logit contributions
prem+1.118
ducers+1.040
 pione+1.026
idth+0.988
 ®+0.969
Neg logit contributions
 defer-0.952
 McMaster-0.949
oret-0.921
RW-0.912
ore-0.896
Token the
Token ID262
Feature activation-1.30e+00

Pos logit contributions
prem+1.885
ducers+1.776
 pione+1.723
idth+1.666
Untitled+1.645
Neg logit contributions
 defer-1.560
 McMaster-1.542
oret-1.510
RW-1.494
Bloom-1.466
Token fossil
Token ID12584
Feature activation+2.04e-01

Pos logit contributions
prem+1.000
ducers+0.934
 pione+0.912
idth+0.881
Untitled+0.869
Neg logit contributions
 defer-0.887
 McMaster-0.878
oret-0.854
RW-0.851
Bloom-0.835
Token fuel
Token ID5252
Feature activation+3.69e-01

Pos logit contributions
 defer+0.123
 McMaster+0.122
oret+0.118
RW+0.117
ore+0.115
Neg logit contributions
prem-0.176
ducers-0.165
 pione-0.163
idth-0.157
-0.155
Token industry
Token ID2831
Feature activation-2.30e-02

Pos logit contributions
 defer+0.250
 McMaster+0.248
oret+0.240
RW+0.238
ore+0.235
Neg logit contributions
prem-0.292
ducers-0.270
 pione-0.269
idth-0.258
-0.253
Token.
Token ID13
Feature activation-8.25e-01

Pos logit contributions
prem+0.018
ducers+0.017
 pione+0.017
idth+0.016
+0.016
Neg logit contributions
 defer-0.016
 McMaster-0.016
oret-0.015
RW-0.015
ore-0.015
Token
Token ID198
Feature activation-3.74e+00

Pos logit contributions
prem+0.610
ducers+0.567
 pione+0.556
idth+0.532
Untitled+0.524
Neg logit contributions
 defer-0.599
 McMaster-0.592
oret-0.580
RW-0.574
ore-0.563
Token
Token ID198
Feature activation-3.06e+00

Pos logit contributions
prem+2.382
ducers+2.139
Untitled+1.954
humans+1.930
 ®+1.907
Neg logit contributions
��-3.081
 defer-3.073
 McMaster-3.052
 torches-3.044
oret-2.953
TokenDuring
Token ID7191
Feature activation-1.11e+00

Pos logit contributions
prem+2.310
ducers+2.127
Untitled+2.025
humans+1.970
idth+1.968
Neg logit contributions
 defer-2.206
 McMaster-2.167
oret-2.105
 torches-2.073
ore-2.026
Token the
Token ID262
Feature activation-1.27e+00

Pos logit contributions
prem+0.848
ducers+0.787
 pione+0.774
idth+0.744
Untitled+0.727
Neg logit contributions
 defer-0.782
 McMaster-0.776
oret-0.757
RW-0.752
ore-0.737
Token past
Token ID1613
Feature activation+2.22e-01

Pos logit contributions
prem+1.206
ducers+1.134
 pione+1.108
idth+1.084
Untitled+1.066
Neg logit contributions
 defer-0.647
 McMaster-0.642
oret-0.617
RW-0.617
ore-0.597
Token fifteen
Token ID17280
Feature activation-4.98e-01

Pos logit contributions
 defer+0.151
 McMaster+0.150
oret+0.146
RW+0.145
ore+0.142
Neg logit contributions
prem-0.173
ducers-0.161
 pione-0.158
idth-0.153
Untitled-0.149