TOP ACTIVATIONS
MAX = 5.197

with dust removal - fan type / size : Pro pe
6 - 8 SS N type - 93 Shang - class
Mid n ighter doesn 't exactly jump to mind since he
. L ooting wasn 't exactly at an LA R iots
safety ." It wasn 't exactly the w is est choice
B rig adier General Chuck Ye ager : Official
is not going to be exactly the same as how we
4 - 5 SS BN type - 94 Jin - class
OC Kit Dim ensions : 277 x 120 x
AH VA ( IPS - type ) @ 144 Hz (
that we don 't know exactly how this disruption is going
Data analysis included a tim el ag analysis comparing ( 1
horror , as the overwhelmed replacement NFL referee who called a
out of 5 by d anc erg ur ly from K
1 . Wild Type 02 : 41
The aim point then drifted west ward by about thirteen degrees
OF TRAN SM ISSION /// ---------------------------------------------------------------- ---------------------------------------------------------------- ------------------------ -- /// L
93 Shang - class and type - 95 , 4 -
treaties . Any reproduction , copying , or redistribution ( elect
94 Jin - class and type - 96 ), and was

MIN ACTIVATIONS
MIN = -4.788

Continue reading the main story Please verify you 're not a
Continue reading the main story Please verify you 're not a
Sche el signed the unconditional instrument of surrender for all Axis
- d iscover the Green Line . Israel becomes
Continue reading the main story Please verify you 're not a
like this . For the sake of comple teness , here
Continue reading the main story Please verify you 're not a
f rit ters on each side for about 2 / 3
fried - rice dish with esc olar and Chinese sausage that
For the most part , Fowler has kept the
all ethnic ities . This seems clear to many of us
in that bill that was worth the Democratic votes . Georgia
f rit ters on each side for about 2 / 3
)( 3 ) nonprofit that appears to have been created with
t a federal judge and doesn t
OL . That seems to be the case with
N - cyclop rop yl methyl - 7 -( 2 ,
This article originally appeared on HuffPost . <|endoftext|> Russia
. Invalid email address . Please re - enter . You
; no , nor woman neither . . .

INTERVAL 2.701 - 5.197
CONTAINS 0.168%

in Massachusetts were the Y aw key Center at Emmanuel College
ups are a tax you pay for the luxury of a
93 Shang - class and type - 95 , 4 -
( 15 th among running backs ) Finding an
What if you have digital copies of books that you want

INTERVAL 0.204 - 2.701
CONTAINS 37.622%

trip matters , too . Most tourists are really ready to
people and never condesc ends to them , evidenced by the
( SN ES , 1995 ) Before the gameplay
confident their failures will be shifted to the American people again
ong Stadium , and forced to watch eight people , who

INTERVAL -2.292 - 0.204
CONTAINS 61.563%

General Manager , making this a significant transitional summer for the
If your vote was from another show , or other medium
x 8 90 ce c 83 Because system ()
restriction of the Token since you ll primarily be
policy for Candidate Trump than Clinton . He isn

INTERVAL -4.788 - -2.292
CONTAINS 0.647%

. " I 've had a lot going on
D Y AR ( total value at his position ), third
and reboot endlessly . That means that if Odin fails after
friend start running again . Part Four General Medical Station ,
| [ return address ] | + -------------------- --+ + --------------------
Token with
Token ID351
Feature activation-4.44e-02

Pos logit contributions
 Vert+1.222
 depos+1.161
antam+1.152
 premiere+1.082
 deb+1.049
Neg logit contributions
isine-1.413
alty-1.406
tical-1.390
vious-1.234
itiz-1.228
Token dust
Token ID8977
Feature activation+1.46e+00

Pos logit contributions
isine+0.040
tical+0.039
alty+0.039
vious+0.035
itiz+0.035
Neg logit contributions
 Vert-0.031
 depos-0.030
antam-0.030
 premiere-0.028
sterdam-0.027
Token removal
Token ID9934
Feature activation+1.54e+00

Pos logit contributions
 Vert+0.958
 depos+0.924
antam+0.886
 premiere+0.851
 deb+0.817
Neg logit contributions
isine-1.385
tical-1.370
alty-1.365
vious-1.214
itiz-1.207
Token -
Token ID532
Feature activation-6.39e-02

Pos logit contributions
 Vert+1.110
 depos+1.065
antam+1.040
 premiere+0.984
 deb+0.955
Neg logit contributions
isine-1.357
tical-1.346
alty-1.343
vious-1.193
itiz-1.182
Token fan
Token ID4336
Feature activation+1.89e-02

Pos logit contributions
isine+0.059
tical+0.058
alty+0.058
vious+0.052
itiz+0.052
Neg logit contributions
 Vert-0.043
 depos-0.041
antam-0.041
 premiere-0.038
sterdam-0.037
Token type
Token ID2099
Feature activation+5.20e+00

Pos logit contributions
 Vert+0.013
 depos+0.012
antam+0.012
 premiere+0.011
sterdam+0.011
Neg logit contributions
isine-0.017
tical-0.017
alty-0.017
vious-0.015
itiz-0.015
Token/
Token ID14
Feature activation+4.87e-01

Pos logit contributions
 Vert+3.796
 depos+3.565
antam+3.464
 premiere+3.310
 deb+3.236
Neg logit contributions
isine-4.553
alty-4.473
tical-4.459
vious-3.963
irin-3.901
Tokensize
Token ID7857
Feature activation+2.58e+00

Pos logit contributions
 Vert+0.415
 depos+0.400
antam+0.397
 premiere+0.375
sterdam+0.368
Neg logit contributions
isine-0.360
tical-0.358
alty-0.358
vious-0.311
itiz-0.309
Token:
Token ID25
Feature activation+7.57e-01

Pos logit contributions
 Vert+1.859
 depos+1.769
antam+1.731
 premiere+1.644
 deb+1.599
Neg logit contributions
isine-2.262
tical-2.237
alty-2.231
vious-1.998
itiz-1.961
Token Pro
Token ID1041
Feature activation+2.88e-01

Pos logit contributions
 Vert+0.538
 depos+0.512
antam+0.509
 premiere+0.474
sterdam+0.460
Neg logit contributions
isine-0.671
tical-0.667
alty-0.667
vious-0.594
itiz-0.592
Tokenpe
Token ID431
Feature activation+1.72e+00

Pos logit contributions
 Vert+0.221
 depos+0.213
antam+0.211
 premiere+0.198
sterdam+0.193
Neg logit contributions
isine-0.237
alty-0.236
tical-0.236
itiz-0.208
vious-0.208
Token6
Token ID21
Feature activation+9.67e-01

Pos logit contributions
 Vert+0.922
 depos+0.889
antam+0.885
 premiere+0.833
sterdam+0.818
Neg logit contributions
isine-0.837
tical-0.834
alty-0.830
vious-0.726
itiz-0.720
Token-
Token ID12
Feature activation-1.60e-01

Pos logit contributions
 Vert+0.667
 depos+0.641
antam+0.636
 premiere+0.591
sterdam+0.580
Neg logit contributions
isine-0.867
tical-0.866
alty-0.865
vious-0.774
itiz-0.767
Token8
Token ID23
Feature activation-8.31e-01

Pos logit contributions
alty+0.119
tical+0.119
isine+0.118
vious+0.103
itiz+0.102
Neg logit contributions
 Vert-0.135
 depos-0.131
antam-0.130
 premiere-0.123
sterdam-0.122
Token SS
Token ID6723
Feature activation+1.41e+00

Pos logit contributions
tical+0.763
alty+0.762
isine+0.761
vious+0.686
itiz+0.676
Neg logit contributions
 Vert-0.548
 depos-0.530
antam-0.525
 premiere-0.485
sterdam-0.480
TokenN
Token ID45
Feature activation+7.81e-01

Pos logit contributions
 Vert+1.505
antam+1.460
 depos+1.458
 premiere+1.385
sterdam+1.368
Neg logit contributions
isine-0.745
tical-0.743
alty-0.734
vious-0.604
itiz-0.596
Token type
Token ID2099
Feature activation+5.04e+00

Pos logit contributions
 Vert+0.532
 depos+0.511
antam+0.507
 premiere+0.470
sterdam+0.461
Neg logit contributions
isine-0.707
tical-0.707
alty-0.706
vious-0.632
itiz-0.627
Token-
Token ID12
Feature activation-3.92e-01

Pos logit contributions
 Vert+3.343
 depos+3.170
antam+3.148
 premiere+2.908
sterdam+2.819
Neg logit contributions
isine-4.697
tical-4.665
alty-4.613
vious-4.144
itiz-4.125
Token93
Token ID6052
Feature activation-9.83e-01

Pos logit contributions
alty+0.302
tical+0.300
isine+0.300
vious+0.265
itiz+0.261
Neg logit contributions
 Vert-0.320
 depos-0.310
antam-0.306
 premiere-0.290
sterdam-0.286
Token Shang
Token ID45797
Feature activation-4.92e-01

Pos logit contributions
tical+0.870
alty+0.868
isine+0.864
vious+0.775
itiz+0.767
Neg logit contributions
 Vert-0.679
 depos-0.660
antam-0.653
 premiere-0.605
sterdam-0.600
Token-
Token ID12
Feature activation-5.74e-01

Pos logit contributions
isine+0.379
tical+0.378
alty+0.377
vious+0.331
itiz+0.328
Neg logit contributions
 Vert-0.403
 depos-0.389
antam-0.386
 premiere-0.363
sterdam-0.358
Tokenclass
Token ID4871
Feature activation+1.27e+00

Pos logit contributions
isine+0.475
tical+0.474
alty+0.473
vious+0.419
itiz+0.415
Neg logit contributions
 Vert-0.438
 depos-0.423
antam-0.415
 premiere-0.390
sterdam-0.384
Token Mid
Token ID7215
Feature activation+6.25e-01

Pos logit contributions
 Vert+0.147
 depos+0.141
antam+0.140
 premiere+0.131
sterdam+0.128
Neg logit contributions
isine-0.185
tical-0.184
alty-0.184
vious-0.164
itiz-0.163
Tokenn
Token ID77
Feature activation+1.21e-01

Pos logit contributions
 Vert+0.539
antam+0.517
 depos+0.512
 premiere+0.488
sterdam+0.483
Neg logit contributions
isine-0.458
alty-0.452
tical-0.450
itiz-0.386
vious-0.386
Tokenighter
Token ID4799
Feature activation-5.60e-01

Pos logit contributions
 Vert+0.135
antam+0.132
 depos+0.131
 premiere+0.125
sterdam+0.124
Neg logit contributions
isine-0.057
tical-0.057
alty-0.057
vious-0.045
itiz-0.044
Token doesn
Token ID1595
Feature activation+1.24e-02

Pos logit contributions
isine+0.474
tical+0.473
alty+0.472
vious+0.419
itiz+0.416
Neg logit contributions
 Vert-0.416
 depos-0.400
antam-0.397
 premiere-0.371
sterdam-0.364
Token't
Token ID470
Feature activation+4.50e-01

Pos logit contributions
 Vert+0.010
 depos+0.009
antam+0.009
 premiere+0.009
sterdam+0.009
Neg logit contributions
isine-0.010
alty-0.010
tical-0.010
vious-0.009
itiz-0.009
Token exactly
Token ID3446
Feature activation+4.99e+00

Pos logit contributions
 Vert+0.307
 depos+0.294
antam+0.292
 premiere+0.270
sterdam+0.266
Neg logit contributions
isine-0.408
tical-0.408
alty-0.407
vious-0.364
itiz-0.361
Token jump
Token ID4391
Feature activation-4.94e-03

Pos logit contributions
 Vert+3.148
 depos+3.006
antam+2.949
 premiere+2.851
 deb+2.700
Neg logit contributions
isine-4.769
alty-4.719
tical-4.711
itiz-4.286
vious-4.252
Token to
Token ID284
Feature activation-2.17e-01

Pos logit contributions
tical+0.004
isine+0.004
alty+0.004
vious+0.004
itiz+0.004
Neg logit contributions
 Vert-0.003
 depos-0.003
antam-0.003
 premiere-0.003
sterdam-0.003
Token mind
Token ID2000
Feature activation-7.29e-02

Pos logit contributions
isine+0.201
tical+0.201
alty+0.201
vious+0.180
itiz+0.179
Neg logit contributions
 Vert-0.143
 depos-0.137
antam-0.135
 premiere-0.125
sterdam-0.123
Token since
Token ID1201
Feature activation+3.96e-01

Pos logit contributions
isine+0.067
alty+0.067
tical+0.067
vious+0.060
itiz+0.060
Neg logit contributions
 Vert-0.049
 depos-0.047
antam-0.046
 premiere-0.043
sterdam-0.042
Token he
Token ID339
Feature activation-5.40e-01

Pos logit contributions
 Vert+0.287
 depos+0.275
antam+0.273
 premiere+0.255
sterdam+0.250
Neg logit contributions
isine-0.342
tical-0.342
alty-0.341
vious-0.303
itiz-0.301
Token.
Token ID13
Feature activation+1.53e-01

Pos logit contributions
 Vert+1.320
 depos+1.282
antam+1.232
 premiere+1.193
 deb+1.149
Neg logit contributions
isine-1.789
tical-1.775
alty-1.769
vious-1.589
itiz-1.564
Token L
Token ID406
Feature activation+5.11e-01

Pos logit contributions
 Vert+0.117
 depos+0.112
antam+0.110
 premiere+0.104
sterdam+0.102
Neg logit contributions
isine-0.128
alty-0.127
tical-0.127
vious-0.112
itiz-0.112
Tokenooting
Token ID12494
Feature activation+3.27e-02

Pos logit contributions
 Vert+0.431
 depos+0.417
antam+0.416
 premiere+0.392
sterdam+0.387
Neg logit contributions
tical-0.379
isine-0.379
alty-0.377
vious-0.330
itiz-0.326
Token wasn
Token ID2492
Feature activation-2.21e-01

Pos logit contributions
 Vert+0.024
 depos+0.023
antam+0.023
 premiere+0.021
sterdam+0.021
Neg logit contributions
isine-0.028
tical-0.028
alty-0.028
vious-0.025
itiz-0.025
Token't
Token ID470
Feature activation-5.14e-01

Pos logit contributions
isine+0.175
tical+0.174
alty+0.174
vious+0.153
itiz+0.151
Neg logit contributions
 Vert-0.176
 depos-0.170
antam-0.169
 premiere-0.159
sterdam-0.156
Token exactly
Token ID3446
Feature activation+4.77e+00

Pos logit contributions
tical+0.453
alty+0.451
isine+0.451
vious+0.402
itiz+0.400
Neg logit contributions
 Vert-0.362
antam-0.349
 depos-0.347
 premiere-0.320
sterdam-0.317
Token at
Token ID379
Feature activation-1.15e-01

Pos logit contributions
 Vert+3.249
 depos+3.099
antam+2.980
 premiere+2.881
 deb+2.785
Neg logit contributions
isine-4.363
alty-4.304
tical-4.292
vious-3.863
irin-3.828
Token an
Token ID281
Feature activation+9.91e-02

Pos logit contributions
isine+0.105
tical+0.105
alty+0.105
vious+0.094
itiz+0.093
Neg logit contributions
 Vert-0.077
 depos-0.074
antam-0.074
 premiere-0.068
sterdam-0.067
Token LA
Token ID9131
Feature activation+1.51e-01

Pos logit contributions
 Vert+0.060
 depos+0.057
antam+0.056
 premiere+0.052
sterdam+0.050
Neg logit contributions
isine-0.098
tical-0.098
alty-0.098
vious-0.088
itiz-0.088
Token R
Token ID371
Feature activation+1.03e+00

Pos logit contributions
 Vert+0.106
 depos+0.102
antam+0.102
 premiere+0.094
sterdam+0.093
Neg logit contributions
isine-0.134
tical-0.133
alty-0.133
vious-0.119
itiz-0.118
Tokeniots
Token ID16228
Feature activation+3.66e-02

Pos logit contributions
 Vert+0.831
 depos+0.803
antam+0.801
 premiere+0.754
sterdam+0.737
Neg logit contributions
isine-0.805
tical-0.804
alty-0.798
vious-0.703
itiz-0.695
Token safety
Token ID3747
Feature activation-2.89e-02

Pos logit contributions
 Vert+0.473
 depos+0.455
antam+0.450
 premiere+0.420
sterdam+0.411
Neg logit contributions
isine-0.604
tical-0.603
alty-0.602
vious-0.538
itiz-0.533
Token."
Token ID526
Feature activation-6.31e-01

Pos logit contributions
isine+0.028
tical+0.028
alty+0.028
vious+0.025
itiz+0.025
Neg logit contributions
 Vert-0.018
 depos-0.017
antam-0.017
 premiere-0.015
sterdam-0.015
Token It
Token ID632
Feature activation+1.58e-02

Pos logit contributions
isine+0.521
tical+0.518
alty+0.518
vious+0.457
itiz+0.455
Neg logit contributions
 Vert-0.485
 depos-0.465
antam-0.461
 premiere-0.433
sterdam-0.423
Token wasn
Token ID2492
Feature activation-1.96e-01

Pos logit contributions
 Vert+0.012
 depos+0.012
antam+0.012
 premiere+0.011
sterdam+0.011
Neg logit contributions
isine-0.013
tical-0.013
alty-0.013
vious-0.011
itiz-0.011
Token't
Token ID470
Feature activation-2.32e-02

Pos logit contributions
isine+0.155
alty+0.154
tical+0.154
vious+0.135
itiz+0.134
Neg logit contributions
 Vert-0.156
 depos-0.150
antam-0.149
 premiere-0.140
sterdam-0.137
Token exactly
Token ID3446
Feature activation+4.69e+00

Pos logit contributions
isine+0.021
tical+0.021
alty+0.021
vious+0.018
itiz+0.018
Neg logit contributions
 Vert-0.016
 depos-0.016
antam-0.015
 premiere-0.014
sterdam-0.014
Token the
Token ID262
Feature activation-5.64e-01

Pos logit contributions
 Vert+3.127
 depos+3.003
antam+2.921
 premiere+2.799
 deb+2.723
Neg logit contributions
isine-4.304
alty-4.240
tical-4.237
itiz-3.819
vious-3.813
Token w
Token ID266
Feature activation+8.15e-01

Pos logit contributions
isine+0.512
tical+0.510
alty+0.510
vious+0.457
itiz+0.453
Neg logit contributions
 Vert-0.385
 depos-0.370
antam-0.366
 premiere-0.342
sterdam-0.333
Tokenis
Token ID271
Feature activation+2.92e+00

Pos logit contributions
 Vert+0.717
 depos+0.693
antam+0.693
 premiere+0.655
sterdam+0.642
Neg logit contributions
isine-0.575
tical-0.574
alty-0.568
vious-0.494
itiz-0.490
Tokenest
Token ID395
Feature activation+5.82e-01

Pos logit contributions
 Vert+2.375
antam+2.288
 depos+2.285
 premiere+2.197
sterdam+2.152
Neg logit contributions
tical-2.222
alty-2.201
isine-2.181
vious-1.867
itiz-1.844
Token choice
Token ID3572
Feature activation+8.31e-01

Pos logit contributions
 Vert+0.401
 depos+0.385
antam+0.379
 premiere+0.357
sterdam+0.344
Neg logit contributions
isine-0.526
tical-0.523
alty-0.521
vious-0.468
itiz-0.465
Token
Token ID447
Feature activation+2.01e+00

Pos logit contributions
 Vert+0.232
 depos+0.224
antam+0.222
 premiere+0.209
sterdam+0.206
Neg logit contributions
tical-0.235
isine-0.234
alty-0.234
vious-0.206
itiz-0.204
Token
Token ID250
Feature activation+1.38e+00

Pos logit contributions
 Vert+1.946
 depos+1.891
antam+1.880
 premiere+1.786
sterdam+1.757
Neg logit contributions
isine-1.247
tical-1.239
alty-1.235
vious-1.040
itiz-1.038
TokenB
Token ID33
Feature activation+8.79e-01

Pos logit contributions
 Vert+1.104
 depos+1.065
antam+1.057
 premiere+0.994
sterdam+0.976
Neg logit contributions
isine-1.091
tical-1.088
alty-1.086
vious-0.955
itiz-0.947
Tokenrig
Token ID4359
Feature activation+9.12e-01

Pos logit contributions
 Vert+0.735
 depos+0.710
antam+0.706
 premiere+0.665
sterdam+0.654
Neg logit contributions
isine-0.662
tical-0.661
alty-0.659
vious-0.576
itiz-0.571
Tokenadier
Token ID38868
Feature activation+2.01e+00

Pos logit contributions
 Vert+0.719
 depos+0.692
antam+0.690
 premiere+0.646
sterdam+0.636
Neg logit contributions
isine-0.729
tical-0.727
alty-0.725
vious-0.640
itiz-0.633
Token General
Token ID3611
Feature activation+4.45e+00

Pos logit contributions
 Vert+1.282
 depos+1.210
antam+1.205
 premiere+1.110
sterdam+1.070
Neg logit contributions
isine-1.930
tical-1.920
alty-1.909
vious-1.721
itiz-1.716
Token Chuck
Token ID14663
Feature activation-1.18e+00

Pos logit contributions
 Vert+3.044
 depos+2.841
antam+2.777
 premiere+2.615
 deb+2.532
Neg logit contributions
isine-4.061
tical-3.999
alty-3.975
vious-3.589
itiz-3.557
Token Ye
Token ID11609
Feature activation+2.01e-01

Pos logit contributions
isine+0.895
tical+0.895
alty+0.894
vious+0.784
itiz+0.774
Neg logit contributions
 Vert-0.968
 depos-0.940
antam-0.935
 premiere-0.879
sterdam-0.865
Tokenager
Token ID3536
Feature activation-4.61e-01

Pos logit contributions
 Vert+0.155
 depos+0.150
antam+0.149
 premiere+0.139
sterdam+0.137
Neg logit contributions
isine-0.163
tical-0.163
alty-0.163
vious-0.144
itiz-0.143
Token:
Token ID25
Feature activation+7.31e-01

Pos logit contributions
isine+0.405
tical+0.404
alty+0.403
vious+0.360
itiz+0.357
Neg logit contributions
 Vert-0.327
 depos-0.315
antam-0.313
 premiere-0.291
sterdam-0.286
Token Official
Token ID15934
Feature activation+1.45e+00

Pos logit contributions
 Vert+0.513
 depos+0.492
antam+0.488
 premiere+0.454
sterdam+0.445
Neg logit contributions
isine-0.649
tical-0.648
alty-0.647
vious-0.577
itiz-0.573
Token is
Token ID318
Feature activation+1.11e+00

Pos logit contributions
 Vert+0.018
 depos+0.017
antam+0.017
 premiere+0.016
sterdam+0.015
Neg logit contributions
tical-0.020
isine-0.020
alty-0.020
vious-0.018
itiz-0.018
Token not
Token ID407
Feature activation+7.50e-01

Pos logit contributions
 Vert+0.777
 depos+0.747
antam+0.739
 premiere+0.691
sterdam+0.675
Neg logit contributions
isine-0.982
alty-0.975
tical-0.975
vious-0.871
itiz-0.863
Token going
Token ID1016
Feature activation+5.16e-01

Pos logit contributions
 Vert+0.511
 depos+0.490
antam+0.486
 premiere+0.451
sterdam+0.442
Neg logit contributions
isine-0.682
tical-0.680
alty-0.679
vious-0.608
itiz-0.603
Token to
Token ID284
Feature activation+1.04e+00

Pos logit contributions
 Vert+0.358
 depos+0.344
antam+0.341
 premiere+0.317
sterdam+0.311
Neg logit contributions
isine-0.461
tical-0.461
alty-0.460
vious-0.411
itiz-0.408
Token be
Token ID307
Feature activation+7.48e-01

Pos logit contributions
 Vert+0.736
 depos+0.708
antam+0.701
 premiere+0.655
sterdam+0.639
Neg logit contributions
isine-0.913
tical-0.911
alty-0.909
vious-0.811
itiz-0.805
Token exactly
Token ID3446
Feature activation+4.37e+00

Pos logit contributions
 Vert+0.530
 depos+0.510
antam+0.505
 premiere+0.471
sterdam+0.462
Neg logit contributions
isine-0.659
tical-0.657
alty-0.656
vious-0.586
itiz-0.581
Token the
Token ID262
Feature activation-3.76e-01

Pos logit contributions
 Vert+2.863
 depos+2.732
antam+2.661
 premiere+2.526
 deb+2.458
Neg logit contributions
isine-4.106
alty-4.048
tical-4.040
vious-3.639
itiz-3.624
Token same
Token ID976
Feature activation-7.15e-01

Pos logit contributions
isine+0.331
tical+0.331
alty+0.330
vious+0.294
itiz+0.292
Neg logit contributions
 Vert-0.266
 depos-0.255
antam-0.253
 premiere-0.236
sterdam-0.231
Token as
Token ID355
Feature activation-1.20e-01

Pos logit contributions
tical+0.642
isine+0.641
alty+0.640
vious+0.572
itiz+0.569
Neg logit contributions
 Vert-0.492
 depos-0.472
antam-0.470
 premiere-0.434
sterdam-0.429
Token how
Token ID703
Feature activation-3.71e-01

Pos logit contributions
isine+0.102
tical+0.102
alty+0.102
vious+0.090
itiz+0.090
Neg logit contributions
 Vert-0.088
 depos-0.085
antam-0.084
 premiere-0.078
sterdam-0.077
Token we
Token ID356
Feature activation+4.93e-01

Pos logit contributions
isine+0.353
tical+0.353
alty+0.352
vious+0.317
itiz+0.315
Neg logit contributions
 Vert-0.236
 depos-0.226
antam-0.224
 premiere-0.207
sterdam-0.203
Token 4
Token ID604
Feature activation-6.76e-02

Pos logit contributions
alty+0.366
isine+0.365
tical+0.365
vious+0.327
itiz+0.325
Neg logit contributions
 Vert-0.275
 depos-0.266
antam-0.264
 premiere-0.244
sterdam-0.241
Token-
Token ID12
Feature activation-6.25e-01

Pos logit contributions
tical+0.054
alty+0.054
isine+0.054
vious+0.048
itiz+0.047
Neg logit contributions
 Vert-0.052
 depos-0.051
antam-0.050
 premiere-0.047
sterdam-0.047
Token5
Token ID20
Feature activation+6.64e-01

Pos logit contributions
alty+0.439
tical+0.439
isine+0.436
vious+0.380
itiz+0.374
Neg logit contributions
 Vert-0.551
 depos-0.537
antam-0.531
 premiere-0.503
sterdam-0.497
Token SS
Token ID6723
Feature activation+1.66e+00

Pos logit contributions
 Vert+0.422
 depos+0.406
antam+0.402
 premiere+0.371
sterdam+0.364
Neg logit contributions
isine-0.631
tical-0.630
alty-0.630
vious-0.567
itiz-0.562
TokenBN
Token ID15766
Feature activation+7.30e-02

Pos logit contributions
 Vert+1.583
antam+1.526
 depos+1.525
 premiere+1.441
sterdam+1.417
Neg logit contributions
isine-1.067
tical-1.064
alty-1.054
vious-0.899
itiz-0.893
Token type
Token ID2099
Feature activation+4.33e+00

Pos logit contributions
 Vert+0.048
 depos+0.046
antam+0.046
 premiere+0.042
sterdam+0.042
Neg logit contributions
alty-0.067
isine-0.067
tical-0.067
vious-0.060
itiz-0.060
Token-
Token ID12
Feature activation-4.44e-01

Pos logit contributions
 Vert+3.226
 depos+3.079
antam+3.076
 premiere+2.870
sterdam+2.784
Neg logit contributions
isine-3.649
tical-3.643
alty-3.610
itiz-3.206
vious-3.205
Token94
Token ID5824
Feature activation-1.45e+00

Pos logit contributions
tical+0.323
isine+0.323
alty+0.323
vious+0.281
itiz+0.277
Neg logit contributions
 Vert-0.381
 depos-0.370
antam-0.367
 premiere-0.346
sterdam-0.342
Token Jin
Token ID17297
Feature activation-4.00e-01

Pos logit contributions
tical+1.324
alty+1.317
isine+1.314
vious+1.180
itiz+1.171
Neg logit contributions
 Vert-0.968
 depos-0.944
antam-0.931
 premiere-0.863
sterdam-0.852
Token-
Token ID12
Feature activation-1.67e-01

Pos logit contributions
isine+0.318
tical+0.318
alty+0.317
vious+0.280
itiz+0.277
Neg logit contributions
 Vert-0.316
 depos-0.306
antam-0.303
 premiere-0.284
sterdam-0.280
Tokenclass
Token ID4871
Feature activation+2.05e+00

Pos logit contributions
isine+0.140
tical+0.140
alty+0.140
vious+0.124
itiz+0.123
Neg logit contributions
 Vert-0.125
 depos-0.121
antam-0.119
 premiere-0.112
sterdam-0.110
Token OC
Token ID24775
Feature activation+3.28e-01

Pos logit contributions
 Vert+1.000
 depos+0.956
antam+0.947
 premiere+0.888
sterdam+0.866
Neg logit contributions
isine-1.092
tical-1.087
alty-1.086
vious-0.959
itiz-0.957
Token Kit
Token ID10897
Feature activation+1.53e+00

Pos logit contributions
 Vert+0.248
 depos+0.239
antam+0.237
 premiere+0.221
sterdam+0.218
Neg logit contributions
isine-0.274
tical-0.273
alty-0.273
vious-0.241
itiz-0.239
Token
Token ID198
Feature activation+4.73e-01

Pos logit contributions
 Vert+1.113
 depos+1.059
antam+1.051
 premiere+0.980
sterdam+0.962
Neg logit contributions
isine-1.322
alty-1.318
tical-1.313
vious-1.170
itiz-1.159
Token
Token ID198
Feature activation+3.25e-01

Pos logit contributions
 Vert+0.371
 depos+0.353
antam+0.351
 premiere+0.331
 deb+0.321
Neg logit contributions
isine-0.386
tical-0.381
alty-0.381
vious-0.335
itiz-0.335
TokenDim
Token ID29271
Feature activation+3.55e+00

Pos logit contributions
 Vert+0.276
 depos+0.267
antam+0.266
 premiere+0.251
sterdam+0.247
Neg logit contributions
isine-0.239
tical-0.239
alty-0.238
vious-0.207
itiz-0.205
Tokenensions
Token ID5736
Feature activation+4.26e+00

Pos logit contributions
 Vert+2.757
 depos+2.620
antam+2.592
 premiere+2.439
sterdam+2.386
Neg logit contributions
tical-2.914
isine-2.880
alty-2.861
vious-2.546
itiz-2.510
Token:
Token ID25
Feature activation+6.40e-01

Pos logit contributions
 Vert+2.746
 depos+2.568
antam+2.519
 premiere+2.368
 deb+2.256
Neg logit contributions
isine-4.008
tical-4.005
alty-3.979
itiz-3.609
vious-3.597
Token 277
Token ID38703
Feature activation+4.77e-01

Pos logit contributions
 Vert+0.453
 depos+0.432
antam+0.428
 premiere+0.400
sterdam+0.388
Neg logit contributions
isine-0.568
tical-0.566
alty-0.565
vious-0.504
itiz-0.502
Tokenx
Token ID87
Feature activation+7.25e-01

Pos logit contributions
 Vert+0.355
 depos+0.342
antam+0.340
 premiere+0.318
sterdam+0.314
Neg logit contributions
isine-0.402
tical-0.402
alty-0.401
vious-0.356
itiz-0.353
Token120
Token ID10232
Feature activation+7.93e-01

Pos logit contributions
 Vert+0.621
 depos+0.597
antam+0.595
 premiere+0.561
sterdam+0.550
Neg logit contributions
isine-0.534
tical-0.530
alty-0.529
vious-0.460
itiz-0.458
Tokenx
Token ID87
Feature activation+4.97e-01

Pos logit contributions
 Vert+0.609
 depos+0.587
antam+0.583
 premiere+0.546
sterdam+0.537
Neg logit contributions
isine-0.650
tical-0.649
alty-0.648
vious-0.573
itiz-0.568
Token AH
Token ID28159
Feature activation-4.50e-01

Pos logit contributions
 Vert+0.452
 depos+0.433
antam+0.429
 premiere+0.400
sterdam+0.391
Neg logit contributions
isine-0.575
tical-0.573
alty-0.573
vious-0.512
itiz-0.508
TokenVA
Token ID11731
Feature activation+3.22e-01

Pos logit contributions
isine+0.351
tical+0.350
alty+0.347
vious+0.307
itiz+0.303
Neg logit contributions
 Vert-0.362
 depos-0.351
antam-0.348
 premiere-0.327
sterdam-0.324
Token (
Token ID357
Feature activation+1.28e+00

Pos logit contributions
 Vert+0.226
 depos+0.217
antam+0.216
 premiere+0.200
sterdam+0.197
Neg logit contributions
isine-0.284
tical-0.284
alty-0.283
vious-0.253
itiz-0.251
TokenIPS
Token ID47643
Feature activation+3.32e-01

Pos logit contributions
 Vert+1.075
antam+1.032
 depos+1.031
 premiere+0.969
sterdam+0.948
Neg logit contributions
isine-0.960
tical-0.952
alty-0.948
vious-0.828
itiz-0.824
Token-
Token ID12
Feature activation+3.34e-01

Pos logit contributions
 Vert+0.245
 depos+0.237
antam+0.235
 premiere+0.219
sterdam+0.216
Neg logit contributions
tical-0.282
isine-0.281
alty-0.280
vious-0.250
itiz-0.247
Tokentype
Token ID4906
Feature activation+4.18e+00

Pos logit contributions
 Vert+0.288
 depos+0.279
antam+0.277
 premiere+0.262
sterdam+0.258
Neg logit contributions
isine-0.242
tical-0.241
alty-0.240
vious-0.209
itiz-0.207
Token)
Token ID8
Feature activation-4.43e-01

Pos logit contributions
 Vert+2.901
 depos+2.741
antam+2.684
 premiere+2.539
 deb+2.441
Neg logit contributions
isine-3.804
tical-3.770
alty-3.767
vious-3.363
itiz-3.324
Token @
Token ID2488
Feature activation+3.06e-01

Pos logit contributions
isine+0.396
tical+0.396
alty+0.395
vious+0.354
itiz+0.351
Neg logit contributions
 Vert-0.304
 depos-0.293
antam-0.292
 premiere-0.269
sterdam-0.267
Token 144
Token ID20224
Feature activation-9.21e-01

Pos logit contributions
 Vert+0.208
 depos+0.199
antam+0.198
 premiere+0.184
sterdam+0.180
Neg logit contributions
isine-0.278
tical-0.278
alty-0.277
vious-0.248
itiz-0.247
TokenHz
Token ID7399
Feature activation+4.90e-01

Pos logit contributions
isine+0.664
tical+0.664
alty+0.661
vious+0.575
itiz+0.569
Neg logit contributions
 Vert-0.795
 depos-0.774
antam-0.768
 premiere-0.724
sterdam-0.716
Token (
Token ID357
Feature activation+1.24e-01

Pos logit contributions
 Vert+0.351
 depos+0.336
antam+0.333
 premiere+0.311
sterdam+0.304
Neg logit contributions
isine-0.430
tical-0.429
alty-0.428
vious-0.381
itiz-0.379
Token that
Token ID326
Feature activation+5.13e-01

Pos logit contributions
 Vert+0.409
 depos+0.393
antam+0.390
 premiere+0.363
sterdam+0.356
Neg logit contributions
isine-0.521
tical-0.520
alty-0.519
vious-0.463
itiz-0.460
Token we
Token ID356
Feature activation-5.27e-01

Pos logit contributions
 Vert+0.354
 depos+0.340
antam+0.335
 premiere+0.312
sterdam+0.306
Neg logit contributions
isine-0.463
tical-0.462
alty-0.460
vious-0.412
itiz-0.408
Token don
Token ID836
Feature activation+1.79e+00

Pos logit contributions
isine+0.437
tical+0.437
alty+0.437
vious+0.386
itiz+0.383
Neg logit contributions
 Vert-0.399
 depos-0.384
antam-0.382
 premiere-0.356
sterdam-0.351
Token't
Token ID470
Feature activation+1.34e+00

Pos logit contributions
 Vert+1.367
 depos+1.301
antam+1.300
 premiere+1.223
 deb+1.184
Neg logit contributions
isine-1.487
alty-1.457
tical-1.454
vious-1.288
itiz-1.277
Token know
Token ID760
Feature activation+1.07e+00

Pos logit contributions
 Vert+0.894
 depos+0.857
antam+0.849
 premiere+0.788
sterdam+0.771
Neg logit contributions
isine-1.237
tical-1.235
alty-1.232
vious-1.106
itiz-1.097
Token exactly
Token ID3446
Feature activation+4.13e+00

Pos logit contributions
 Vert+0.742
 depos+0.713
antam+0.705
 premiere+0.657
sterdam+0.643
Neg logit contributions
isine-0.960
tical-0.958
alty-0.955
vious-0.855
itiz-0.848
Token how
Token ID703
Feature activation-2.86e-02

Pos logit contributions
 Vert+2.776
 depos+2.669
antam+2.598
 premiere+2.442
 deb+2.372
Neg logit contributions
isine-3.772
tical-3.751
alty-3.716
vious-3.338
itiz-3.323
Token this
Token ID428
Feature activation+9.79e-03

Pos logit contributions
isine+0.026
tical+0.026
alty+0.025
vious+0.023
itiz+0.023
Neg logit contributions
 Vert-0.020
 depos-0.019
antam-0.019
 premiere-0.018
sterdam-0.017
Token disruption
Token ID19911
Feature activation+1.08e-01

Pos logit contributions
 Vert+0.007
 depos+0.007
antam+0.007
 premiere+0.006
sterdam+0.006
Neg logit contributions
isine-0.009
tical-0.009
alty-0.009
vious-0.008
itiz-0.008
Token is
Token ID318
Feature activation+4.97e-01

Pos logit contributions
 Vert+0.078
 depos+0.075
antam+0.074
 premiere+0.070
sterdam+0.068
Neg logit contributions
isine-0.094
tical-0.094
alty-0.094
vious-0.083
itiz-0.083
Token going
Token ID1016
Feature activation+6.52e-01

Pos logit contributions
 Vert+0.371
 depos+0.358
antam+0.352
 premiere+0.331
sterdam+0.323
Neg logit contributions
isine-0.423
alty-0.419
tical-0.419
vious-0.372
itiz-0.369
Token Data
Token ID6060
Feature activation-8.66e-01

Pos logit contributions
isine+0.205
tical+0.204
alty+0.204
vious+0.182
itiz+0.181
Neg logit contributions
 Vert-0.164
 depos-0.157
antam-0.156
 premiere-0.145
sterdam-0.142
Token analysis
Token ID3781
Feature activation-8.02e-01

Pos logit contributions
isine+0.704
tical+0.703
alty+0.701
vious+0.619
itiz+0.614
Neg logit contributions
 Vert-0.672
 depos-0.647
antam-0.643
 premiere-0.603
sterdam-0.593
Token included
Token ID3017
Feature activation-9.51e-01

Pos logit contributions
isine+0.626
tical+0.625
alty+0.624
vious+0.548
itiz+0.543
Neg logit contributions
 Vert-0.646
 depos-0.624
antam-0.621
 premiere-0.583
sterdam-0.574
Token a
Token ID257
Feature activation-4.60e-01

Pos logit contributions
tical+0.876
isine+0.875
alty+0.872
vious+0.784
itiz+0.778
Neg logit contributions
 Vert-0.629
antam-0.603
 depos-0.601
 premiere-0.553
sterdam-0.546
Token tim
Token ID4628
Feature activation-8.83e-01

Pos logit contributions
isine+0.424
tical+0.424
alty+0.423
vious+0.380
itiz+0.376
Neg logit contributions
 Vert-0.305
 depos-0.292
antam-0.291
 premiere-0.268
sterdam-0.264
Tokenel
Token ID417
Feature activation+4.12e+00

Pos logit contributions
isine+0.806
tical+0.806
alty+0.804
vious+0.721
itiz+0.715
Neg logit contributions
 Vert-0.596
 depos-0.572
antam-0.567
 premiere-0.525
sterdam-0.515
Tokenag
Token ID363
Feature activation+2.37e-01

Pos logit contributions
 Vert+3.668
antam+3.569
 depos+3.556
 premiere+3.387
sterdam+3.294
Neg logit contributions
isine-2.789
tical-2.782
alty-2.760
vious-2.345
itiz-2.311
Token analysis
Token ID3781
Feature activation-7.98e-02

Pos logit contributions
 Vert+0.180
 depos+0.173
antam+0.171
 premiere+0.162
 deb+0.157
Neg logit contributions
isine-0.196
tical-0.194
alty-0.194
vious-0.171
itiz-0.170
Token comparing
Token ID14176
Feature activation-3.62e-01

Pos logit contributions
isine+0.071
tical+0.071
alty+0.071
vious+0.063
itiz+0.063
Neg logit contributions
 Vert-0.056
 depos-0.054
antam-0.053
 premiere-0.050
sterdam-0.049
Token (
Token ID357
Feature activation+1.27e-01

Pos logit contributions
isine+0.337
tical+0.337
alty+0.336
vious+0.302
itiz+0.300
Neg logit contributions
 Vert-0.237
 depos-0.227
antam-0.227
 premiere-0.209
sterdam-0.206
Token1
Token ID16
Feature activation-4.14e-02

Pos logit contributions
 Vert+0.108
 depos+0.104
antam+0.103
 premiere+0.097
sterdam+0.096
Neg logit contributions
isine-0.094
tical-0.094
alty-0.094
vious-0.082
itiz-0.081
Token horror
Token ID9961
Feature activation+3.89e-01

Pos logit contributions
 Vert+0.200
 depos+0.192
antam+0.190
 premiere+0.178
sterdam+0.174
Neg logit contributions
isine-0.230
tical-0.229
alty-0.228
vious-0.203
itiz-0.201
Token,
Token ID11
Feature activation+7.35e-01

Pos logit contributions
 Vert+0.253
 depos+0.243
antam+0.239
 premiere+0.224
sterdam+0.216
Neg logit contributions
isine-0.365
tical-0.364
alty-0.363
vious-0.326
itiz-0.325
Token as
Token ID355
Feature activation+4.51e-01

Pos logit contributions
 Vert+0.454
 depos+0.431
antam+0.428
 premiere+0.395
sterdam+0.383
Neg logit contributions
isine-0.716
tical-0.713
alty-0.711
vious-0.642
itiz-0.640
Token the
Token ID262
Feature activation+2.26e-01

Pos logit contributions
 Vert+0.304
 depos+0.291
antam+0.288
 premiere+0.268
sterdam+0.261
Neg logit contributions
isine-0.414
tical-0.413
alty-0.412
vious-0.369
itiz-0.367
Token overwhelmed
Token ID20974
Feature activation+1.51e+00

Pos logit contributions
 Vert+0.156
 depos+0.150
antam+0.148
 premiere+0.138
sterdam+0.135
Neg logit contributions
isine-0.204
tical-0.204
alty-0.203
vious-0.182
itiz-0.181
Token replacement
Token ID9014
Feature activation+4.12e+00

Pos logit contributions
 Vert+1.052
 depos+1.008
antam+0.996
 premiere+0.933
sterdam+0.905
Neg logit contributions
isine-1.359
tical-1.353
alty-1.347
vious-1.205
itiz-1.197
Token NFL
Token ID5134
Feature activation+6.20e-01

Pos logit contributions
 Vert+2.976
 depos+2.850
antam+2.822
 premiere+2.663
 deb+2.593
Neg logit contributions
isine-3.586
tical-3.562
alty-3.485
itiz-3.129
irin-3.111
Token referee
Token ID22957
Feature activation-4.15e-01

Pos logit contributions
 Vert+0.464
 depos+0.446
antam+0.443
 premiere+0.415
sterdam+0.406
Neg logit contributions
isine-0.522
tical-0.522
alty-0.520
vious-0.461
itiz-0.457
Token who
Token ID508
Feature activation+8.57e-02

Pos logit contributions
isine+0.346
tical+0.345
alty+0.342
vious+0.305
itiz+0.302
Neg logit contributions
 Vert-0.313
 depos-0.302
antam-0.300
 premiere-0.281
sterdam-0.275
Token called
Token ID1444
Feature activation-2.03e+00

Pos logit contributions
 Vert+0.066
 depos+0.064
antam+0.063
 premiere+0.059
sterdam+0.058
Neg logit contributions
isine-0.070
tical-0.070
alty-0.070
vious-0.062
itiz-0.061
Token a
Token ID257
Feature activation-1.10e+00

Pos logit contributions
alty+1.788
tical+1.781
isine+1.780
vious+1.590
itiz+1.579
Neg logit contributions
 Vert-1.416
antam-1.364
 depos-1.360
 premiere-1.259
sterdam-1.246
Token out
Token ID503
Feature activation+6.93e-01

Pos logit contributions
 Vert+1.161
 depos+1.097
antam+1.074
 premiere+1.030
 deb+0.997
Neg logit contributions
isine-1.628
tical-1.602
alty-1.597
vious-1.430
itiz-1.420
Token of
Token ID286
Feature activation+6.59e-01

Pos logit contributions
 Vert+0.515
 depos+0.489
antam+0.485
 premiere+0.457
 deb+0.442
Neg logit contributions
isine-0.595
tical-0.586
alty-0.585
vious-0.520
itiz-0.518
Token 5
Token ID642
Feature activation+2.16e+00

Pos logit contributions
 Vert+0.365
 depos+0.347
antam+0.342
 premiere+0.315
sterdam+0.301
Neg logit contributions
isine-0.685
tical-0.682
alty-0.680
vious-0.618
itiz-0.613
Token by
Token ID416
Feature activation+1.41e+00

Pos logit contributions
 Vert+1.050
 depos+0.964
antam+0.943
 premiere+0.872
 deb+0.831
Neg logit contributions
isine-2.405
tical-2.387
alty-2.380
vious-2.176
itiz-2.164
Token d
Token ID288
Feature activation+4.29e-01

Pos logit contributions
 Vert+0.998
 depos+0.954
antam+0.943
 premiere+0.882
sterdam+0.860
Neg logit contributions
isine-1.244
tical-1.239
alty-1.236
vious-1.103
itiz-1.097
Tokenanc
Token ID1192
Feature activation+4.11e+00

Pos logit contributions
 Vert+0.365
 depos+0.353
antam+0.351
 premiere+0.331
sterdam+0.326
Neg logit contributions
isine-0.317
tical-0.315
alty-0.314
vious-0.274
itiz-0.272
Tokenerg
Token ID6422
Feature activation+1.66e+00

Pos logit contributions
 Vert+3.517
antam+3.394
 depos+3.361
 premiere+3.188
sterdam+3.156
Neg logit contributions
tical-2.936
alty-2.925
isine-2.922
vious-2.512
itiz-2.487
Tokenur
Token ID333
Feature activation+7.98e-01

Pos logit contributions
 Vert+1.354
antam+1.304
 depos+1.300
 premiere+1.219
sterdam+1.212
Neg logit contributions
tical-1.272
isine-1.262
alty-1.260
vious-1.099
itiz-1.094
Tokenly
Token ID306
Feature activation-8.18e-02

Pos logit contributions
 Vert+0.619
antam+0.594
 depos+0.591
 premiere+0.553
sterdam+0.545
Neg logit contributions
tical-0.646
isine-0.643
alty-0.640
vious-0.564
itiz-0.563
Token from
Token ID422
Feature activation+1.16e+00

Pos logit contributions
isine+0.068
tical+0.068
alty+0.068
vious+0.060
itiz+0.060
Neg logit contributions
 Vert-0.062
 depos-0.059
antam-0.059
 premiere-0.055
sterdam-0.054
Token K
Token ID509
Feature activation+1.70e-02

Pos logit contributions
 Vert+0.912
 depos+0.872
antam+0.864
 premiere+0.817
sterdam+0.795
Neg logit contributions
isine-0.943
tical-0.939
alty-0.936
vious-0.826
itiz-0.819
Token
Token ID198
Feature activation+4.24e-01

Pos logit contributions
 Vert+0.382
 depos+0.367
antam+0.364
 premiere+0.340
sterdam+0.334
Neg logit contributions
isine-0.454
tical-0.453
alty-0.452
vious-0.403
itiz-0.400
Token
Token ID198
Feature activation+2.13e-01

Pos logit contributions
 Vert+0.334
 depos+0.319
antam+0.317
 premiere+0.299
 deb+0.290
Neg logit contributions
isine-0.344
tical-0.340
alty-0.340
vious-0.299
itiz-0.298
Token1
Token ID16
Feature activation+1.32e+00

Pos logit contributions
 Vert+0.174
 depos+0.168
antam+0.167
 premiere+0.157
sterdam+0.154
Neg logit contributions
isine-0.164
tical-0.164
alty-0.164
vious-0.144
itiz-0.143
Token.
Token ID13
Feature activation+1.09e+00

Pos logit contributions
 Vert+0.906
 depos+0.868
antam+0.860
 premiere+0.800
sterdam+0.783
Neg logit contributions
isine-1.190
tical-1.186
alty-1.183
vious-1.060
itiz-1.052
Token Wild
Token ID6183
Feature activation-8.82e-01

Pos logit contributions
 Vert+0.792
 depos+0.759
antam+0.754
 premiere+0.704
sterdam+0.690
Neg logit contributions
isine-0.947
tical-0.944
alty-0.942
vious-0.839
itiz-0.833
Token Type
Token ID5994
Feature activation+4.11e+00

Pos logit contributions
isine+0.734
tical+0.734
alty+0.732
vious+0.649
itiz+0.643
Neg logit contributions
 Vert-0.665
 depos-0.641
antam-0.636
 premiere-0.595
sterdam-0.584
Token 02
Token ID7816
Feature activation+1.79e+00

Pos logit contributions
 Vert+3.081
 depos+2.905
antam+2.885
 premiere+2.709
sterdam+2.651
Neg logit contributions
isine-3.444
tical-3.443
alty-3.443
vious-3.054
itiz-3.010
Token:
Token ID25
Feature activation+6.66e-01

Pos logit contributions
 Vert+1.285
 depos+1.227
antam+1.215
 premiere+1.142
sterdam+1.117
Neg logit contributions
isine-1.561
tical-1.552
alty-1.548
vious-1.383
itiz-1.370
Token41
Token ID3901
Feature activation+8.84e-01

Pos logit contributions
 Vert+0.492
 depos+0.473
antam+0.469
 premiere+0.439
sterdam+0.430
Neg logit contributions
isine-0.567
tical-0.565
alty-0.564
vious-0.502
itiz-0.498
Token
Token ID198
Feature activation+2.59e-02

Pos logit contributions
 Vert+0.665
 depos+0.640
antam+0.636
 premiere+0.595
sterdam+0.584
Neg logit contributions
isine-0.739
tical-0.737
alty-0.736
vious-0.653
itiz-0.647
Token
Token ID198
Feature activation+2.06e-02

Pos logit contributions
 Vert+0.021
 depos+0.020
antam+0.020
 premiere+0.019
sterdam+0.018
Neg logit contributions
isine-0.021
tical-0.021
alty-0.020
vious-0.018
itiz-0.018
Token The
Token ID383
Feature activation+6.50e-01

Pos logit contributions
 Vert+0.205
 depos+0.197
antam+0.195
 premiere+0.183
sterdam+0.179
Neg logit contributions
isine-0.219
tical-0.218
alty-0.218
vious-0.192
itiz-0.191
Token aim
Token ID4031
Feature activation+1.25e-01

Pos logit contributions
 Vert+0.422
 depos+0.404
antam+0.400
 premiere+0.370
sterdam+0.362
Neg logit contributions
isine-0.611
tical-0.610
alty-0.609
vious-0.547
itiz-0.543
Token point
Token ID966
Feature activation+1.54e+00

Pos logit contributions
 Vert+0.092
 depos+0.089
antam+0.088
 premiere+0.082
sterdam+0.081
Neg logit contributions
isine-0.106
tical-0.106
alty-0.106
vious-0.094
itiz-0.093
Token then
Token ID788
Feature activation-1.48e+00

Pos logit contributions
 Vert+1.163
 depos+1.120
antam+1.106
 premiere+1.041
sterdam+1.017
Neg logit contributions
isine-1.296
tical-1.286
alty-1.279
vious-1.138
itiz-1.124
Token drifted
Token ID38648
Feature activation+1.62e+00

Pos logit contributions
alty+1.232
tical+1.230
isine+1.222
vious+1.091
itiz+1.090
Neg logit contributions
 Vert-1.099
antam-1.060
 depos-1.057
 premiere-0.981
sterdam-0.975
Token west
Token ID7421
Feature activation+4.09e+00

Pos logit contributions
 Vert+1.169
 depos+1.123
antam+1.108
 premiere+1.037
sterdam+1.014
Neg logit contributions
isine-1.418
tical-1.409
alty-1.407
vious-1.254
itiz-1.242
Tokenward
Token ID904
Feature activation+8.21e-01

Pos logit contributions
 Vert+2.681
 depos+2.586
antam+2.530
 premiere+2.359
sterdam+2.286
Neg logit contributions
isine-3.797
alty-3.738
tical-3.729
itiz-3.344
vious-3.344
Token by
Token ID416
Feature activation+1.99e-01

Pos logit contributions
 Vert+0.570
 depos+0.547
antam+0.542
 premiere+0.504
sterdam+0.494
Neg logit contributions
isine-0.736
tical-0.734
alty-0.732
vious-0.655
itiz-0.650
Token about
Token ID546
Feature activation+1.91e-01

Pos logit contributions
 Vert+0.136
 depos+0.130
antam+0.130
 premiere+0.120
sterdam+0.119
Neg logit contributions
tical-0.179
isine-0.178
alty-0.178
vious-0.159
itiz-0.158
Token thirteen
Token ID28306
Feature activation+3.02e-01

Pos logit contributions
 Vert+0.126
 depos+0.121
antam+0.120
 premiere+0.111
sterdam+0.109
Neg logit contributions
tical-0.177
isine-0.176
alty-0.176
vious-0.158
itiz-0.157
Token degrees
Token ID7370
Feature activation+6.37e-01

Pos logit contributions
 Vert+0.216
 depos+0.208
antam+0.206
 premiere+0.192
sterdam+0.189
Neg logit contributions
isine-0.264
tical-0.264
alty-0.263
vious-0.234
itiz-0.233
Token OF
Token ID3963
Feature activation-1.09e+00

Pos logit contributions
 Vert+0.212
 depos+0.203
antam+0.201
 premiere+0.189
sterdam+0.184
Neg logit contributions
isine-0.259
alty-0.257
tical-0.257
vious-0.228
itiz-0.228
Token TRAN
Token ID48213
Feature activation-3.94e-02

Pos logit contributions
tical+0.977
isine+0.976
alty+0.974
vious+0.874
itiz+0.864
Neg logit contributions
 Vert-0.747
 depos-0.718
antam-0.716
 premiere-0.660
sterdam-0.653
TokenSM
Token ID12310
Feature activation-1.59e+00

Pos logit contributions
isine+0.032
tical+0.032
alty+0.032
vious+0.029
itiz+0.028
Neg logit contributions
 Vert-0.030
 depos-0.029
antam-0.029
 premiere-0.027
sterdam-0.027
TokenISSION
Token ID40373
Feature activation-6.44e-01

Pos logit contributions
isine+1.023
tical+1.021
alty+1.018
vious+0.868
itiz+0.858
Neg logit contributions
 Vert-1.503
 depos-1.459
antam-1.451
 premiere-1.376
sterdam-1.358
Token ///
Token ID34013
Feature activation+5.56e-01

Pos logit contributions
tical+0.538
isine+0.537
alty+0.536
vious+0.476
itiz+0.470
Neg logit contributions
 Vert-0.484
 depos-0.467
antam-0.464
 premiere-0.433
sterdam-0.426
Token----------------------------------------------------------------
Token ID10097
Feature activation+4.07e+00

Pos logit contributions
 Vert+0.421
 depos+0.407
antam+0.403
 premiere+0.377
sterdam+0.371
Neg logit contributions
isine-0.461
tical-0.461
alty-0.460
vious-0.408
itiz-0.403
Token----------------------------------------------------------------
Token ID10097
Feature activation+3.42e+00

Pos logit contributions
 Vert+2.344
 depos+2.209
antam+2.207
 premiere+2.027
sterdam+1.953
Neg logit contributions
tical-4.086
isine-4.065
alty-4.056
itiz-3.673
vious-3.636
Token------------------------
Token ID22369
Feature activation+3.17e+00

Pos logit contributions
 Vert+2.097
 depos+1.977
antam+1.977
 premiere+1.828
sterdam+1.760
Neg logit contributions
tical-3.316
isine-3.310
alty-3.294
itiz-2.981
vious-2.948
Token--
Token ID438
Feature activation+1.20e+00

Pos logit contributions
 Vert+2.186
 depos+2.082
antam+2.070
 premiere+1.932
sterdam+1.872
Neg logit contributions
isine-2.835
tical-2.817
alty-2.807
itiz-2.519
vious-2.504
Token///
Token ID20379
Feature activation+1.11e+00

Pos logit contributions
 Vert+0.937
 depos+0.902
antam+0.896
 premiere+0.842
sterdam+0.826
Neg logit contributions
isine-0.965
tical-0.962
alty-0.961
vious-0.847
itiz-0.841
Token L
Token ID406
Feature activation-3.70e-01

Pos logit contributions
 Vert+0.842
 depos+0.811
antam+0.805
 premiere+0.754
sterdam+0.741
Neg logit contributions
isine-0.914
tical-0.912
alty-0.910
vious-0.806
itiz-0.799
Token93
Token ID6052
Feature activation-9.83e-01

Pos logit contributions
alty+0.302
tical+0.300
isine+0.300
vious+0.265
itiz+0.261
Neg logit contributions
 Vert-0.320
 depos-0.310
antam-0.306
 premiere-0.290
sterdam-0.286
Token Shang
Token ID45797
Feature activation-4.92e-01

Pos logit contributions
tical+0.870
alty+0.868
isine+0.864
vious+0.775
itiz+0.767
Neg logit contributions
 Vert-0.679
 depos-0.660
antam-0.653
 premiere-0.605
sterdam-0.600
Token-
Token ID12
Feature activation-5.74e-01

Pos logit contributions
isine+0.379
tical+0.378
alty+0.377
vious+0.331
itiz+0.328
Neg logit contributions
 Vert-0.403
 depos-0.389
antam-0.386
 premiere-0.363
sterdam-0.358
Tokenclass
Token ID4871
Feature activation+1.27e+00

Pos logit contributions
isine+0.475
tical+0.474
alty+0.473
vious+0.419
itiz+0.415
Neg logit contributions
 Vert-0.438
 depos-0.423
antam-0.415
 premiere-0.390
sterdam-0.384
Token and
Token ID290
Feature activation+1.38e-01

Pos logit contributions
 Vert+0.771
 depos+0.735
antam+0.729
 premiere+0.670
sterdam+0.654
Neg logit contributions
isine-1.240
tical-1.238
alty-1.235
vious-1.116
itiz-1.108
Token type
Token ID2099
Feature activation+4.07e+00

Pos logit contributions
 Vert+0.091
 depos+0.088
antam+0.087
 premiere+0.080
sterdam+0.079
Neg logit contributions
tical-0.128
isine-0.128
alty-0.127
vious-0.114
itiz-0.113
Token-
Token ID12
Feature activation-1.75e-01

Pos logit contributions
 Vert+3.007
 depos+2.871
antam+2.865
 premiere+2.694
 deb+2.590
Neg logit contributions
tical-3.440
isine-3.438
alty-3.402
itiz-3.027
vious-3.021
Token95
Token ID3865
Feature activation-5.11e-01

Pos logit contributions
isine+0.123
tical+0.123
alty+0.123
vious+0.106
itiz+0.105
Neg logit contributions
 Vert-0.154
 depos-0.149
antam-0.148
 premiere-0.140
sterdam-0.138
Token,
Token ID11
Feature activation-4.06e-01

Pos logit contributions
tical+0.464
isine+0.463
alty+0.462
vious+0.415
itiz+0.411
Neg logit contributions
 Vert-0.344
 depos-0.333
antam-0.330
 premiere-0.305
sterdam-0.301
Token 4
Token ID604
Feature activation-6.76e-02

Pos logit contributions
alty+0.366
isine+0.365
tical+0.365
vious+0.327
itiz+0.325
Neg logit contributions
 Vert-0.275
 depos-0.266
antam-0.264
 premiere-0.244
sterdam-0.241
Token-
Token ID12
Feature activation-6.25e-01

Pos logit contributions
tical+0.054
alty+0.054
isine+0.054
vious+0.048
itiz+0.047
Neg logit contributions
 Vert-0.052
 depos-0.051
antam-0.050
 premiere-0.047
sterdam-0.047
Token treaties
Token ID30734
Feature activation+2.45e-01

Pos logit contributions
 Vert+0.215
 depos+0.205
antam+0.203
 premiere+0.186
sterdam+0.182
Neg logit contributions
isine-0.360
tical-0.360
alty-0.360
vious-0.325
itiz-0.323
Token.
Token ID13
Feature activation+6.77e-01

Pos logit contributions
 Vert+0.165
 depos+0.158
antam+0.157
 premiere+0.146
sterdam+0.143
Neg logit contributions
isine-0.224
tical-0.224
alty-0.224
vious-0.200
itiz-0.199
Token Any
Token ID4377
Feature activation+1.81e+00

Pos logit contributions
 Vert+0.522
 depos+0.499
antam+0.493
 premiere+0.465
sterdam+0.454
Neg logit contributions
isine-0.558
tical-0.554
alty-0.554
vious-0.488
itiz-0.486
Token reproduction
Token ID20728
Feature activation+3.46e+00

Pos logit contributions
 Vert+1.160
 depos+1.116
antam+1.090
 premiere+1.019
sterdam+0.993
Neg logit contributions
isine-1.715
tical-1.706
alty-1.703
itiz-1.534
vious-1.532
Token,
Token ID11
Feature activation-4.56e-01

Pos logit contributions
 Vert+2.356
 depos+2.276
antam+2.212
 premiere+2.091
 deb+2.030
Neg logit contributions
isine-3.130
alty-3.072
tical-3.064
vious-2.776
itiz-2.733
Token copying
Token ID23345
Feature activation+4.06e+00

Pos logit contributions
isine+0.488
tical+0.487
alty+0.486
vious+0.443
itiz+0.440
Neg logit contributions
 Vert-0.237
 depos-0.223
antam-0.223
 premiere-0.199
sterdam-0.196
Token,
Token ID11
Feature activation+4.21e-01

Pos logit contributions
 Vert+2.501
 depos+2.402
antam+2.340
 premiere+2.183
sterdam+2.105
Neg logit contributions
isine-3.930
alty-3.918
tical-3.865
itiz-3.522
vious-3.520
Token or
Token ID393
Feature activation+1.22e+00

Pos logit contributions
 Vert+0.267
 depos+0.256
antam+0.254
 premiere+0.234
sterdam+0.230
Neg logit contributions
isine-0.400
tical-0.400
alty-0.399
vious-0.359
itiz-0.356
Token redistribution
Token ID41425
Feature activation+2.25e+00

Pos logit contributions
 Vert+0.693
 depos+0.661
antam+0.651
 premiere+0.597
sterdam+0.581
Neg logit contributions
isine-1.238
tical-1.236
alty-1.234
vious-1.118
itiz-1.112
Token (
Token ID357
Feature activation+1.36e+00

Pos logit contributions
 Vert+1.724
 depos+1.663
antam+1.633
 premiere+1.548
sterdam+1.504
Neg logit contributions
isine-1.855
alty-1.831
tical-1.821
vious-1.625
itiz-1.612
Tokenelect
Token ID9509
Feature activation+2.25e-01

Pos logit contributions
 Vert+1.171
 depos+1.135
antam+1.125
 premiere+1.063
sterdam+1.041
Neg logit contributions
isine-0.984
tical-0.979
alty-0.976
vious-0.847
itiz-0.841
Token94
Token ID5824
Feature activation-1.45e+00

Pos logit contributions
tical+0.323
isine+0.323
alty+0.323
vious+0.281
itiz+0.277
Neg logit contributions
 Vert-0.381
 depos-0.370
antam-0.367
 premiere-0.346
sterdam-0.342
Token Jin
Token ID17297
Feature activation-4.00e-01

Pos logit contributions
tical+1.324
alty+1.317
isine+1.314
vious+1.180
itiz+1.171
Neg logit contributions
 Vert-0.968
 depos-0.944
antam-0.931
 premiere-0.863
sterdam-0.852
Token-
Token ID12
Feature activation-1.67e-01

Pos logit contributions
isine+0.318
tical+0.318
alty+0.317
vious+0.280
itiz+0.277
Neg logit contributions
 Vert-0.316
 depos-0.306
antam-0.303
 premiere-0.284
sterdam-0.280
Tokenclass
Token ID4871
Feature activation+2.05e+00

Pos logit contributions
isine+0.140
tical+0.140
alty+0.140
vious+0.124
itiz+0.123
Neg logit contributions
 Vert-0.125
 depos-0.121
antam-0.119
 premiere-0.112
sterdam-0.110
Token and
Token ID290
Feature activation+3.71e-01

Pos logit contributions
 Vert+1.335
 depos+1.274
antam+1.264
 premiere+1.169
sterdam+1.141
Neg logit contributions
isine-1.921
tical-1.914
alty-1.908
vious-1.717
itiz-1.704
Token type
Token ID2099
Feature activation+4.06e+00

Pos logit contributions
 Vert+0.243
 depos+0.233
antam+0.231
 premiere+0.213
sterdam+0.210
Neg logit contributions
isine-0.345
tical-0.345
alty-0.344
vious-0.309
itiz-0.307
Token-
Token ID12
Feature activation-2.87e-02

Pos logit contributions
 Vert+2.958
 depos+2.803
antam+2.786
 premiere+2.633
 deb+2.539
Neg logit contributions
isine-3.532
tical-3.475
alty-3.451
itiz-3.077
vious-3.070
Token96
Token ID4846
Feature activation-5.27e-01

Pos logit contributions
isine+0.022
tical+0.022
alty+0.022
vious+0.020
itiz+0.019
Neg logit contributions
 Vert-0.023
 depos-0.022
antam-0.022
 premiere-0.021
sterdam-0.020
Token),
Token ID828
Feature activation+4.94e-01

Pos logit contributions
tical+0.463
alty+0.461
isine+0.461
vious+0.412
itiz+0.409
Neg logit contributions
 Vert-0.371
 depos-0.359
antam-0.356
 premiere-0.330
sterdam-0.327
Token and
Token ID290
Feature activation+1.60e-02

Pos logit contributions
 Vert+0.343
 depos+0.330
antam+0.327
 premiere+0.304
sterdam+0.298
Neg logit contributions
isine-0.441
tical-0.440
alty-0.440
vious-0.393
itiz-0.390
Token was
Token ID373
Feature activation+4.19e-02

Pos logit contributions
 Vert+0.011
 depos+0.011
antam+0.011
 premiere+0.010
sterdam+0.010
Neg logit contributions
tical-0.014
alty-0.014
isine-0.014
vious-0.012
itiz-0.012
Token Continue
Token ID10054
Feature activation-2.13e+00

Pos logit contributions
tical+0.964
alty+0.954
isine+0.946
vious+0.791
itiz+0.788
Neg logit contributions
 Vert-1.606
 depos-1.567
antam-1.564
 premiere-1.477
sterdam-1.469
Token reading
Token ID3555
Feature activation-2.57e-01

Pos logit contributions
tical+1.539
alty+1.534
isine+1.522
vious+1.331
itiz+1.312
Neg logit contributions
 Vert-1.823
antam-1.779
 depos-1.759
sterdam-1.650
 premiere-1.645
Token the
Token ID262
Feature activation-1.29e+00

Pos logit contributions
isine+0.239
tical+0.239
alty+0.238
vious+0.214
itiz+0.212
Neg logit contributions
 Vert-0.170
 depos-0.163
antam-0.161
 premiere-0.150
sterdam-0.145
Token main
Token ID1388
Feature activation+5.10e-02

Pos logit contributions
alty+1.393
tical+1.385
isine+1.381
vious+1.267
itiz+1.257
Neg logit contributions
 Vert-0.652
antam-0.618
 depos-0.615
sterdam-0.548
 premiere-0.541
Token story
Token ID1621
Feature activation-5.14e-01

Pos logit contributions
 Vert+0.036
 depos+0.035
antam+0.035
 premiere+0.033
sterdam+0.032
Neg logit contributions
isine-0.045
tical-0.045
alty-0.044
vious-0.040
itiz-0.039
Token Please
Token ID4222
Feature activation-4.79e+00

Pos logit contributions
isine+0.369
tical+0.369
alty+0.368
vious+0.319
itiz+0.316
Neg logit contributions
 Vert-0.447
 depos-0.433
antam-0.431
 premiere-0.406
sterdam-0.401
Token verify
Token ID11767
Feature activation-8.03e-01

Pos logit contributions
alty+4.256
tical+4.211
isine+4.093
vious+3.644
atsuki+3.599
Neg logit contributions
 Vert-3.315
antam-3.213
 depos-3.079
sterdam-2.962
 premiere-2.862
Token you
Token ID345
Feature activation-1.92e+00

Pos logit contributions
tical+0.650
isine+0.650
alty+0.649
vious+0.572
itiz+0.567
Neg logit contributions
 Vert-0.625
 depos-0.602
antam-0.600
 premiere-0.560
sterdam-0.553
Token're
Token ID821
Feature activation-1.47e+00

Pos logit contributions
tical+1.135
alty+1.134
isine+1.123
vious+0.944
itiz+0.916
Neg logit contributions
 Vert-1.918
 depos-1.858
antam-1.849
sterdam-1.760
 premiere-1.743
Token not
Token ID407
Feature activation-6.59e-02

Pos logit contributions
alty+1.083
tical+1.080
isine+1.076
vious+0.933
itiz+0.923
Neg logit contributions
 Vert-1.245
 depos-1.203
antam-1.201
 premiere-1.128
sterdam-1.119
Token a
Token ID257
Feature activation-3.03e-01

Pos logit contributions
isine+0.062
tical+0.062
alty+0.062
vious+0.055
itiz+0.055
Neg logit contributions
 Vert-0.043
 depos-0.041
antam-0.041
 premiere-0.038
sterdam-0.037
Token Continue
Token ID10054
Feature activation-2.53e+00

Pos logit contributions
tical+1.068
alty+1.054
isine+1.044
vious+0.878
itiz+0.872
Neg logit contributions
 Vert-1.746
 depos-1.705
antam-1.696
 premiere-1.606
sterdam-1.594
Token reading
Token ID3555
Feature activation-7.76e-02

Pos logit contributions
tical+1.812
alty+1.805
isine+1.780
vious+1.557
itiz+1.538
Neg logit contributions
 Vert-2.191
antam-2.139
 depos-2.102
sterdam-1.986
 premiere-1.972
Token the
Token ID262
Feature activation-1.15e+00

Pos logit contributions
isine+0.073
tical+0.073
alty+0.072
vious+0.065
itiz+0.065
Neg logit contributions
 Vert-0.051
 depos-0.049
antam-0.048
 premiere-0.045
sterdam-0.043
Token main
Token ID1388
Feature activation-2.49e-01

Pos logit contributions
alty+1.249
tical+1.244
isine+1.241
vious+1.137
itiz+1.130
Neg logit contributions
 Vert-0.576
antam-0.541
 depos-0.541
sterdam-0.478
 premiere-0.477
Token story
Token ID1621
Feature activation-4.62e-01

Pos logit contributions
isine+0.217
tical+0.217
alty+0.216
vious+0.192
itiz+0.191
Neg logit contributions
 Vert-0.179
 depos-0.173
antam-0.171
 premiere-0.160
sterdam-0.156
Token Please
Token ID4222
Feature activation-4.74e+00

Pos logit contributions
tical+0.330
isine+0.330
alty+0.329
vious+0.285
itiz+0.282
Neg logit contributions
 Vert-0.402
 depos-0.390
antam-0.388
 premiere-0.365
sterdam-0.361
Token verify
Token ID11767
Feature activation-6.29e-01

Pos logit contributions
alty+4.204
tical+4.167
isine+4.061
vious+3.585
atsuki+3.561
Neg logit contributions
 Vert-3.298
antam-3.180
 depos-3.051
sterdam-2.923
 premiere-2.833
Token you
Token ID345
Feature activation-1.97e+00

Pos logit contributions
isine+0.511
tical+0.511
alty+0.509
vious+0.449
itiz+0.446
Neg logit contributions
 Vert-0.488
 depos-0.470
antam-0.468
 premiere-0.437
sterdam-0.431
Token're
Token ID821
Feature activation-1.39e+00

Pos logit contributions
alty+1.150
tical+1.150
isine+1.135
vious+0.953
itiz+0.925
Neg logit contributions
 Vert-1.982
 depos-1.920
antam-1.911
sterdam-1.824
 premiere-1.798
Token not
Token ID407
Feature activation+2.69e-01

Pos logit contributions
alty+1.026
tical+1.024
isine+1.020
vious+0.885
itiz+0.875
Neg logit contributions
 Vert-1.183
 depos-1.143
antam-1.141
 premiere-1.072
sterdam-1.062
Token a
Token ID257
Feature activation-2.71e-01

Pos logit contributions
 Vert+0.174
 depos+0.167
antam+0.165
 premiere+0.153
sterdam+0.149
Neg logit contributions
isine-0.254
tical-0.253
alty-0.253
vious-0.227
itiz-0.226
TokenSche
Token ID27054
Feature activation-4.43e-02

Pos logit contributions
isine+0.604
tical+0.603
alty+0.601
vious+0.527
itiz+0.521
Neg logit contributions
 Vert-0.649
 depos-0.628
antam-0.623
 premiere-0.587
sterdam-0.579
Tokenel
Token ID417
Feature activation+1.96e+00

Pos logit contributions
isine+0.035
tical+0.035
alty+0.035
vious+0.030
itiz+0.030
Neg logit contributions
 Vert-0.036
 depos-0.035
antam-0.034
 premiere-0.032
sterdam-0.032
Token signed
Token ID4488
Feature activation-7.00e-01

Pos logit contributions
 Vert+1.498
 depos+1.451
antam+1.432
 premiere+1.352
sterdam+1.318
Neg logit contributions
isine-1.613
tical-1.604
alty-1.603
vious-1.414
itiz-1.402
Token the
Token ID262
Feature activation-8.25e-01

Pos logit contributions
isine+0.644
tical+0.644
alty+0.642
vious+0.577
itiz+0.573
Neg logit contributions
 Vert-0.465
 depos-0.445
antam-0.445
 premiere-0.410
sterdam-0.404
Token unconditional
Token ID42423
Feature activation-2.66e+00

Pos logit contributions
tical+0.762
alty+0.761
isine+0.760
vious+0.682
itiz+0.675
Neg logit contributions
 Vert-0.543
antam-0.521
 depos-0.520
 premiere-0.477
sterdam-0.471
Token instrument
Token ID8875
Feature activation-4.72e+00

Pos logit contributions
alty+2.616
tical+2.603
isine+2.590
vious+2.362
itiz+2.350
Neg logit contributions
 Vert-1.553
antam-1.508
 depos-1.474
sterdam-1.350
 premiere-1.339
Token of
Token ID286
Feature activation-1.00e+00

Pos logit contributions
tical+3.865
alty+3.864
isine+3.831
vious+3.396
itiz+3.378
Neg logit contributions
 Vert-3.526
antam-3.448
 depos-3.386
sterdam-3.175
 premiere-3.157
Token surrender
Token ID16908
Feature activation-1.41e+00

Pos logit contributions
isine+1.009
tical+1.009
alty+1.006
vious+0.913
itiz+0.910
Neg logit contributions
 Vert-0.572
antam-0.548
 depos-0.546
 premiere-0.492
sterdam-0.487
Token for
Token ID329
Feature activation-3.77e-01

Pos logit contributions
isine+1.246
tical+1.244
alty+1.242
vious+1.108
itiz+1.100
Neg logit contributions
 Vert-0.996
 depos-0.956
antam-0.951
 premiere-0.883
sterdam-0.868
Token all
Token ID477
Feature activation+1.39e-01

Pos logit contributions
isine+0.351
tical+0.350
alty+0.350
vious+0.314
itiz+0.311
Neg logit contributions
 Vert-0.249
 depos-0.238
antam-0.235
 premiere-0.219
sterdam-0.213
Token Axis
Token ID38349
Feature activation-7.51e-03

Pos logit contributions
 Vert+0.088
 depos+0.084
antam+0.082
 premiere+0.076
sterdam+0.074
Neg logit contributions
isine-0.134
tical-0.133
alty-0.133
vious-0.120
itiz-0.119
Token-
Token ID12
Feature activation-7.54e-02

Pos logit contributions
isine+0.406
tical+0.405
alty+0.405
vious+0.353
itiz+0.349
Neg logit contributions
 Vert-0.462
 depos-0.447
antam-0.444
 premiere-0.419
sterdam-0.413
Tokend
Token ID67
Feature activation-5.77e-01

Pos logit contributions
isine+0.057
tical+0.057
alty+0.057
vious+0.050
itiz+0.050
Neg logit contributions
 Vert-0.062
 depos-0.060
antam-0.060
 premiere-0.056
sterdam-0.055
Tokeniscover
Token ID29392
Feature activation-5.88e-01

Pos logit contributions
isine+0.460
tical+0.459
alty+0.458
vious+0.403
itiz+0.400
Neg logit contributions
 Vert-0.456
 depos-0.441
antam-0.437
 premiere-0.410
sterdam-0.404
Token the
Token ID262
Feature activation-3.28e-01

Pos logit contributions
tical+0.541
isine+0.541
alty+0.540
vious+0.484
itiz+0.481
Neg logit contributions
 Vert-0.392
 depos-0.375
antam-0.373
 premiere-0.345
sterdam-0.338
Token Green
Token ID3469
Feature activation-1.28e+00

Pos logit contributions
isine+0.294
tical+0.293
alty+0.293
vious+0.262
itiz+0.260
Neg logit contributions
 Vert-0.227
 depos-0.218
antam-0.216
 premiere-0.201
sterdam-0.197
Token Line
Token ID6910
Feature activation-4.66e+00

Pos logit contributions
isine+1.320
tical+1.318
alty+1.317
vious+1.197
itiz+1.189
Neg logit contributions
 Vert-0.704
 depos-0.670
antam-0.665
 premiere-0.603
sterdam-0.588
Token.
Token ID13
Feature activation+1.45e-01

Pos logit contributions
alty+4.083
tical+4.081
isine+4.042
vious+3.629
itiz+3.621
Neg logit contributions
 Vert-3.236
antam-3.142
 depos-3.104
 premiere-2.850
sterdam-2.827
Token
Token ID198
Feature activation+2.76e-02

Pos logit contributions
 Vert+0.112
 depos+0.107
antam+0.106
 premiere+0.099
sterdam+0.097
Neg logit contributions
isine-0.120
tical-0.119
alty-0.119
vious-0.105
itiz-0.104
Token
Token ID198
Feature activation-1.06e-01

Pos logit contributions
 Vert+0.022
 depos+0.021
antam+0.021
 premiere+0.019
 deb+0.019
Neg logit contributions
isine-0.022
tical-0.022
alty-0.022
vious-0.019
itiz-0.019
TokenIsrael
Token ID14040
Feature activation+5.66e-01

Pos logit contributions
isine+0.082
tical+0.082
alty+0.082
vious+0.072
itiz+0.071
Neg logit contributions
 Vert-0.087
 depos-0.084
antam-0.083
 premiere-0.078
sterdam-0.077
Token becomes
Token ID4329
Feature activation+5.67e-01

Pos logit contributions
 Vert+0.428
 depos+0.413
antam+0.409
 premiere+0.383
sterdam+0.377
Neg logit contributions
isine-0.471
tical-0.469
alty-0.468
vious-0.415
itiz-0.409
Token Continue
Token ID10054
Feature activation-2.08e+00

Pos logit contributions
tical+1.015
alty+1.004
isine+0.998
vious+0.837
itiz+0.831
Neg logit contributions
 Vert-1.666
 depos-1.625
antam-1.616
 premiere-1.531
sterdam-1.519
Token reading
Token ID3555
Feature activation+1.07e-02

Pos logit contributions
tical+1.505
alty+1.498
isine+1.487
vious+1.300
itiz+1.282
Neg logit contributions
 Vert-1.782
antam-1.736
 depos-1.719
sterdam-1.612
 premiere-1.609
Token the
Token ID262
Feature activation-1.06e+00

Pos logit contributions
 Vert+0.007
 depos+0.007
antam+0.007
 premiere+0.006
sterdam+0.006
Neg logit contributions
isine-0.010
tical-0.010
alty-0.010
vious-0.009
itiz-0.009
Token main
Token ID1388
Feature activation+2.94e-01

Pos logit contributions
alty+1.147
tical+1.140
isine+1.138
vious+1.044
itiz+1.036
Neg logit contributions
 Vert-0.538
antam-0.509
 depos-0.509
sterdam-0.454
 premiere-0.447
Token story
Token ID1621
Feature activation-2.83e-01

Pos logit contributions
 Vert+0.210
 depos+0.202
antam+0.200
 premiere+0.188
sterdam+0.182
Neg logit contributions
isine-0.258
tical-0.256
alty-0.256
vious-0.228
itiz-0.226
Token Please
Token ID4222
Feature activation-4.65e+00

Pos logit contributions
isine+0.205
tical+0.204
alty+0.204
vious+0.177
itiz+0.176
Neg logit contributions
 Vert-0.244
 depos-0.236
antam-0.235
 premiere-0.222
sterdam-0.218
Token verify
Token ID11767
Feature activation-5.74e-01

Pos logit contributions
alty+4.091
tical+4.052
isine+3.950
vious+3.493
atsuki+3.442
Neg logit contributions
 Vert-3.253
antam-3.150
 depos-3.017
sterdam-2.929
 premiere-2.810
Token you
Token ID345
Feature activation-1.89e+00

Pos logit contributions
isine+0.465
tical+0.465
alty+0.464
vious+0.410
itiz+0.406
Neg logit contributions
 Vert-0.445
 depos-0.429
antam-0.427
 premiere-0.399
sterdam-0.393
Token're
Token ID821
Feature activation-1.25e+00

Pos logit contributions
tical+1.101
alty+1.099
isine+1.083
vious+0.912
itiz+0.884
Neg logit contributions
 Vert-1.907
 depos-1.849
antam-1.838
sterdam-1.757
 premiere-1.728
Token not
Token ID407
Feature activation+2.22e-01

Pos logit contributions
alty+0.924
tical+0.923
isine+0.919
vious+0.798
itiz+0.789
Neg logit contributions
 Vert-1.055
 depos-1.020
antam-1.017
 premiere-0.956
sterdam-0.947
Token a
Token ID257
Feature activation-1.37e-01

Pos logit contributions
 Vert+0.144
 depos+0.138
antam+0.137
 premiere+0.127
sterdam+0.124
Neg logit contributions
isine-0.209
tical-0.208
alty-0.208
vious-0.187
itiz-0.186
Token like
Token ID588
Feature activation+2.26e-02

Pos logit contributions
isine+0.003
tical+0.003
alty+0.003
vious+0.002
itiz+0.002
Neg logit contributions
 Vert-0.002
 depos-0.002
antam-0.002
 premiere-0.002
sterdam-0.002
Token this
Token ID428
Feature activation+3.56e-01

Pos logit contributions
 Vert+0.015
 depos+0.015
antam+0.015
 premiere+0.013
sterdam+0.013
Neg logit contributions
isine-0.021
tical-0.021
alty-0.021
vious-0.018
itiz-0.018
Token.
Token ID13
Feature activation-4.13e-01

Pos logit contributions
 Vert+0.240
 depos+0.230
antam+0.227
 premiere+0.212
sterdam+0.207
Neg logit contributions
isine-0.326
alty-0.325
tical-0.324
vious-0.290
itiz-0.288
Token For
Token ID1114
Feature activation-1.09e-02

Pos logit contributions
isine+0.335
tical+0.334
alty+0.333
vious+0.294
itiz+0.292
Neg logit contributions
 Vert-0.322
 depos-0.310
antam-0.308
 premiere-0.289
sterdam-0.284
Token the
Token ID262
Feature activation-3.51e-01

Pos logit contributions
isine+0.010
tical+0.010
alty+0.010
vious+0.009
itiz+0.009
Neg logit contributions
 Vert-0.007
 depos-0.007
antam-0.007
 premiere-0.007
sterdam-0.006
Token sake
Token ID11060
Feature activation-4.40e+00

Pos logit contributions
isine+0.297
tical+0.297
alty+0.296
vious+0.263
itiz+0.261
Neg logit contributions
 Vert-0.261
 depos-0.251
antam-0.249
 premiere-0.233
sterdam-0.229
Token of
Token ID286
Feature activation-1.89e-02

Pos logit contributions
alty+3.333
tical+3.317
isine+3.266
vious+2.929
itiz+2.889
Neg logit contributions
 Vert-3.577
antam-3.480
 depos-3.446
sterdam-3.219
 premiere-3.204
Token comple
Token ID1224
Feature activation-6.66e-01

Pos logit contributions
isine+0.017
tical+0.017
alty+0.017
vious+0.015
itiz+0.015
Neg logit contributions
 Vert-0.013
 depos-0.012
antam-0.012
 premiere-0.011
sterdam-0.011
Tokenteness
Token ID43205
Feature activation-1.31e+00

Pos logit contributions
tical+0.476
isine+0.475
alty+0.474
vious+0.412
itiz+0.406
Neg logit contributions
 Vert-0.584
 depos-0.565
antam-0.561
 premiere-0.530
sterdam-0.522
Token,
Token ID11
Feature activation+1.66e-01

Pos logit contributions
isine+1.189
tical+1.187
alty+1.185
vious+1.061
itiz+1.053
Neg logit contributions
 Vert-0.886
 depos-0.850
antam-0.843
 premiere-0.782
sterdam-0.767
Token here
Token ID994
Feature activation-1.16e+00

Pos logit contributions
 Vert+0.121
 depos+0.116
antam+0.114
 premiere+0.107
sterdam+0.105
Neg logit contributions
isine-0.145
tical-0.144
alty-0.144
vious-0.128
itiz-0.127
Token Continue
Token ID10054
Feature activation-1.94e+00

Pos logit contributions
tical+0.865
alty+0.851
isine+0.842
vious+0.703
itiz+0.701
Neg logit contributions
 Vert-1.451
 depos-1.416
antam-1.410
 premiere-1.333
sterdam-1.321
Token reading
Token ID3555
Feature activation-1.20e-01

Pos logit contributions
tical+1.408
alty+1.403
isine+1.392
vious+1.216
itiz+1.202
Neg logit contributions
 Vert-1.663
antam-1.618
 depos-1.598
sterdam-1.500
 premiere-1.499
Token the
Token ID262
Feature activation-1.23e+00

Pos logit contributions
isine+0.113
tical+0.112
alty+0.112
vious+0.101
itiz+0.100
Neg logit contributions
 Vert-0.079
 depos-0.075
antam-0.074
 premiere-0.069
sterdam-0.067
Token main
Token ID1388
Feature activation+2.08e-01

Pos logit contributions
alty+1.340
tical+1.335
isine+1.332
vious+1.220
itiz+1.212
Neg logit contributions
 Vert-0.618
antam-0.582
 depos-0.581
sterdam-0.514
 premiere-0.513
Token story
Token ID1621
Feature activation-4.99e-01

Pos logit contributions
 Vert+0.147
 depos+0.141
antam+0.139
 premiere+0.131
sterdam+0.126
Neg logit contributions
isine-0.184
tical-0.183
alty-0.182
vious-0.163
itiz-0.162
Token Please
Token ID4222
Feature activation-4.39e+00

Pos logit contributions
isine+0.360
tical+0.359
alty+0.358
vious+0.311
itiz+0.308
Neg logit contributions
 Vert-0.432
 depos-0.418
antam-0.416
 premiere-0.392
sterdam-0.387
Token verify
Token ID11767
Feature activation-4.72e-01

Pos logit contributions
alty+3.913
tical+3.877
isine+3.803
vious+3.366
atsuki+3.340
Neg logit contributions
 Vert-3.033
antam-2.914
 depos-2.797
sterdam-2.673
 premiere-2.604
Token you
Token ID345
Feature activation-1.93e+00

Pos logit contributions
isine+0.383
tical+0.383
alty+0.382
vious+0.337
itiz+0.335
Neg logit contributions
 Vert-0.366
 depos-0.353
antam-0.351
 premiere-0.328
sterdam-0.324
Token're
Token ID821
Feature activation-1.20e+00

Pos logit contributions
tical+1.115
alty+1.114
isine+1.097
vious+0.920
itiz+0.895
Neg logit contributions
 Vert-1.954
 depos-1.890
antam-1.880
sterdam-1.803
 premiere-1.770
Token not
Token ID407
Feature activation+2.55e-01

Pos logit contributions
alty+0.886
tical+0.886
isine+0.883
vious+0.767
itiz+0.759
Neg logit contributions
 Vert-1.015
 depos-0.980
antam-0.978
 premiere-0.919
sterdam-0.910
Token a
Token ID257
Feature activation-2.19e-01

Pos logit contributions
 Vert+0.165
 depos+0.158
antam+0.156
 premiere+0.145
sterdam+0.142
Neg logit contributions
isine-0.240
tical-0.239
alty-0.239
vious-0.215
itiz-0.213
Token f
Token ID277
Feature activation-4.83e-01

Pos logit contributions
isine+0.447
tical+0.446
alty+0.445
vious+0.394
itiz+0.391
Neg logit contributions
 Vert-0.420
 depos-0.404
antam-0.403
 premiere-0.375
sterdam-0.371
Tokenrit
Token ID799
Feature activation-2.39e-01

Pos logit contributions
isine+0.360
tical+0.359
alty+0.357
vious+0.313
itiz+0.306
Neg logit contributions
 Vert-0.404
 depos-0.391
antam-0.391
 premiere-0.365
sterdam-0.360
Tokenters
Token ID1010
Feature activation+3.56e-01

Pos logit contributions
isine+0.202
tical+0.200
alty+0.200
vious+0.177
itiz+0.176
Neg logit contributions
 Vert-0.179
 depos-0.172
antam-0.171
 premiere-0.160
sterdam-0.157
Token on
Token ID319
Feature activation-4.40e-01

Pos logit contributions
 Vert+0.252
 depos+0.242
antam+0.240
 premiere+0.224
sterdam+0.219
Neg logit contributions
isine-0.314
tical-0.313
alty-0.312
vious-0.279
itiz-0.276
Token each
Token ID1123
Feature activation-9.46e-01

Pos logit contributions
isine+0.408
tical+0.407
alty+0.406
vious+0.364
itiz+0.362
Neg logit contributions
 Vert-0.292
 depos-0.280
antam-0.276
 premiere-0.257
sterdam-0.250
Token side
Token ID1735
Feature activation-4.39e+00

Pos logit contributions
alty+0.783
tical+0.783
isine+0.781
vious+0.694
itiz+0.688
Neg logit contributions
 Vert-0.716
antam-0.689
 depos-0.688
 premiere-0.639
sterdam-0.637
Token for
Token ID329
Feature activation-2.13e-02

Pos logit contributions
tical+3.280
alty+3.277
isine+3.235
vious+2.869
itiz+2.858
Neg logit contributions
 Vert-3.619
antam-3.513
 depos-3.501
sterdam-3.291
 premiere-3.244
Token about
Token ID546
Feature activation-8.96e-01

Pos logit contributions
isine+0.017
tical+0.017
alty+0.017
vious+0.015
itiz+0.015
Neg logit contributions
 Vert-0.017
 depos-0.016
antam-0.016
 premiere-0.015
sterdam-0.015
Token 2
Token ID362
Feature activation-1.42e+00

Pos logit contributions
tical+0.850
isine+0.848
alty+0.848
vious+0.764
itiz+0.758
Neg logit contributions
 Vert-0.568
 depos-0.546
antam-0.543
 premiere-0.498
sterdam-0.493
Token/
Token ID14
Feature activation-3.12e-01

Pos logit contributions
tical+1.355
isine+1.354
alty+1.353
vious+1.220
itiz+1.209
Neg logit contributions
 Vert-0.894
 depos-0.853
antam-0.850
 premiere-0.780
sterdam-0.771
Token3
Token ID18
Feature activation-1.16e+00

Pos logit contributions
isine+0.239
tical+0.237
alty+0.237
vious+0.207
itiz+0.206
Neg logit contributions
 Vert-0.258
 depos-0.249
antam-0.247
 premiere-0.233
sterdam-0.228
Tokenfried
Token ID25520
Feature activation-5.55e-01

Pos logit contributions
 Vert+0.767
 depos+0.743
antam+0.740
 premiere+0.697
sterdam+0.681
Neg logit contributions
isine-0.742
alty-0.737
tical-0.736
vious-0.647
itiz-0.638
Token-
Token ID12
Feature activation+3.84e-01

Pos logit contributions
isine+0.467
alty+0.466
tical+0.465
vious+0.412
itiz+0.410
Neg logit contributions
 Vert-0.411
 depos-0.398
antam-0.395
 premiere-0.368
sterdam-0.364
Tokenrice
Token ID20970
Feature activation-2.94e-01

Pos logit contributions
 Vert+0.319
 depos+0.308
antam+0.307
 premiere+0.289
sterdam+0.284
Neg logit contributions
isine-0.290
tical-0.289
alty-0.288
vious-0.252
itiz-0.250
Token dish
Token ID9433
Feature activation-8.29e-01

Pos logit contributions
isine+0.244
tical+0.243
alty+0.242
vious+0.215
itiz+0.213
Neg logit contributions
 Vert-0.222
 depos-0.215
antam-0.213
 premiere-0.199
sterdam-0.196
Token with
Token ID351
Feature activation-1.87e+00

Pos logit contributions
isine+0.742
tical+0.740
alty+0.739
vious+0.660
itiz+0.656
Neg logit contributions
 Vert-0.574
 depos-0.551
antam-0.548
 premiere-0.507
sterdam-0.500
Token esc
Token ID3671
Feature activation-4.37e+00

Pos logit contributions
alty+1.580
isine+1.579
tical+1.574
vious+1.397
itiz+1.389
Neg logit contributions
 Vert-1.379
 depos-1.330
antam-1.324
 premiere-1.232
sterdam-1.218
Tokenolar
Token ID6192
Feature activation-7.26e-01

Pos logit contributions
alty+2.940
isine+2.915
tical+2.848
vious+2.490
itiz+2.468
Neg logit contributions
 Vert-4.052
 depos-3.959
antam-3.818
 premiere-3.675
sterdam-3.600
Token and
Token ID290
Feature activation-1.12e-01

Pos logit contributions
isine+0.605
tical+0.604
alty+0.603
vious+0.534
itiz+0.530
Neg logit contributions
 Vert-0.549
 depos-0.528
antam-0.525
 premiere-0.491
sterdam-0.483
Token Chinese
Token ID3999
Feature activation-2.03e+00

Pos logit contributions
isine+0.094
tical+0.094
alty+0.094
vious+0.083
itiz+0.082
Neg logit contributions
 Vert-0.084
 depos-0.081
antam-0.080
 premiere-0.075
sterdam-0.073
Token sausage
Token ID31889
Feature activation-1.80e+00

Pos logit contributions
isine+1.686
alty+1.677
tical+1.676
vious+1.483
itiz+1.473
Neg logit contributions
 Vert-1.544
 depos-1.486
antam-1.478
 premiere-1.378
sterdam-1.364
Token that
Token ID326
Feature activation-3.15e-01

Pos logit contributions
isine+1.589
alty+1.586
tical+1.579
vious+1.404
itiz+1.399
Neg logit contributions
 Vert-1.256
 depos-1.205
antam-1.202
 premiere-1.112
sterdam-1.098
Token
Token ID198
Feature activation-2.90e-01

Pos logit contributions
isine+0.474
alty+0.471
tical+0.470
vious+0.414
itiz+0.412
Neg logit contributions
 Vert-0.475
 depos-0.456
antam-0.452
 premiere-0.427
sterdam-0.417
Token
Token ID198
Feature activation-3.97e-01

Pos logit contributions
isine+0.233
tical+0.231
alty+0.231
vious+0.203
itiz+0.202
Neg logit contributions
 Vert-0.229
 depos-0.220
antam-0.219
 premiere-0.206
sterdam-0.200
TokenFor
Token ID1890
Feature activation-6.52e-01

Pos logit contributions
isine+0.301
tical+0.300
alty+0.299
vious+0.262
itiz+0.260
Neg logit contributions
 Vert-0.330
 depos-0.319
antam-0.317
 premiere-0.298
sterdam-0.294
Token the
Token ID262
Feature activation-1.14e+00

Pos logit contributions
isine+0.603
tical+0.602
alty+0.601
vious+0.540
itiz+0.536
Neg logit contributions
 Vert-0.431
 depos-0.413
antam-0.410
 premiere-0.379
sterdam-0.372
Token most
Token ID749
Feature activation-2.08e+00

Pos logit contributions
isine+0.968
tical+0.966
alty+0.964
vious+0.856
itiz+0.849
Neg logit contributions
 Vert-0.843
 depos-0.812
antam-0.806
 premiere-0.753
sterdam-0.739
Token part
Token ID636
Feature activation-4.37e+00

Pos logit contributions
alty+1.705
isine+1.700
tical+1.700
vious+1.510
itiz+1.497
Neg logit contributions
 Vert-1.581
antam-1.519
 depos-1.517
 premiere-1.409
sterdam-1.403
Token,
Token ID11
Feature activation-3.19e-01

Pos logit contributions
isine+3.889
alty+3.886
tical+3.884
vious+3.462
itiz+3.445
Neg logit contributions
 Vert-2.996
antam-2.886
 depos-2.864
 premiere-2.650
sterdam-2.637
Token Fowler
Token ID33693
Feature activation+5.62e-01

Pos logit contributions
isine+0.279
tical+0.279
alty+0.277
vious+0.247
itiz+0.245
Neg logit contributions
 Vert-0.230
 depos-0.221
antam-0.217
 premiere-0.204
sterdam-0.198
Token has
Token ID468
Feature activation-1.05e+00

Pos logit contributions
 Vert+0.428
 depos+0.415
antam+0.408
 premiere+0.386
sterdam+0.376
Neg logit contributions
isine-0.464
tical-0.462
alty-0.459
vious-0.408
itiz-0.401
Token kept
Token ID4030
Feature activation-4.50e-01

Pos logit contributions
isine+0.867
tical+0.865
alty+0.863
vious+0.764
itiz+0.757
Neg logit contributions
 Vert-0.801
 depos-0.772
antam-0.765
 premiere-0.718
sterdam-0.704
Token the
Token ID262
Feature activation-5.40e-01

Pos logit contributions
tical+0.394
isine+0.394
alty+0.392
vious+0.350
itiz+0.345
Neg logit contributions
 Vert-0.322
 depos-0.310
antam-0.304
 premiere-0.287
sterdam-0.278
Token all
Token ID477
Feature activation+3.77e-01

Pos logit contributions
isine+0.727
tical+0.726
alty+0.725
vious+0.651
itiz+0.646
Neg logit contributions
 Vert-0.508
 depos-0.486
antam-0.483
 premiere-0.446
sterdam-0.437
Token ethnic
Token ID9450
Feature activation-1.50e+00

Pos logit contributions
 Vert+0.319
 depos+0.308
antam+0.304
 premiere+0.288
sterdam+0.281
Neg logit contributions
isine-0.282
tical-0.282
alty-0.281
vious-0.246
itiz-0.243
Tokenities
Token ID871
Feature activation-1.66e+00

Pos logit contributions
isine+1.103
tical+1.101
alty+1.098
vious+0.953
itiz+0.951
Neg logit contributions
 Vert-1.268
 depos-1.226
antam-1.222
 premiere-1.152
sterdam-1.140
Token.
Token ID13
Feature activation-3.44e-01

Pos logit contributions
tical+1.509
isine+1.509
alty+1.504
vious+1.346
itiz+1.336
Neg logit contributions
 Vert-1.122
 depos-1.073
antam-1.070
 premiere-0.989
sterdam-0.975
Token This
Token ID770
Feature activation+3.13e-01

Pos logit contributions
isine+0.278
alty+0.276
tical+0.275
vious+0.242
itiz+0.241
Neg logit contributions
 Vert-0.272
 depos-0.259
antam-0.257
 premiere-0.242
sterdam-0.236
Token seems
Token ID2331
Feature activation-4.37e+00

Pos logit contributions
 Vert+0.243
 depos+0.234
antam+0.231
 premiere+0.218
sterdam+0.213
Neg logit contributions
isine-0.256
tical-0.254
alty-0.254
vious-0.225
itiz-0.222
Token clear
Token ID1598
Feature activation-1.26e+00

Pos logit contributions
tical+3.753
isine+3.664
alty+3.661
vious+3.301
itiz+3.263
Neg logit contributions
 Vert-3.176
 depos-3.048
antam-3.039
 premiere-2.801
sterdam-2.792
Token to
Token ID284
Feature activation-2.34e-01

Pos logit contributions
tical+1.104
isine+1.097
alty+1.095
vious+0.980
itiz+0.971
Neg logit contributions
 Vert-0.905
 depos-0.868
antam-0.864
 premiere-0.801
sterdam-0.790
Token many
Token ID867
Feature activation+1.90e-01

Pos logit contributions
isine+0.185
tical+0.185
alty+0.184
vious+0.162
itiz+0.161
Neg logit contributions
 Vert-0.187
 depos-0.180
antam-0.179
 premiere-0.168
sterdam-0.165
Token of
Token ID286
Feature activation-3.70e-01

Pos logit contributions
 Vert+0.138
 depos+0.133
antam+0.132
 premiere+0.123
sterdam+0.121
Neg logit contributions
isine-0.164
tical-0.163
alty-0.163
vious-0.145
itiz-0.144
Token us
Token ID514
Feature activation+4.51e-01

Pos logit contributions
isine+0.330
tical+0.330
alty+0.329
vious+0.295
itiz+0.292
Neg logit contributions
 Vert-0.256
 depos-0.246
antam-0.245
 premiere-0.227
sterdam-0.223
Token in
Token ID287
Feature activation-7.01e-01

Pos logit contributions
tical+1.309
isine+1.309
alty+1.307
vious+1.166
itiz+1.159
Neg logit contributions
 Vert-1.019
 depos-0.977
antam-0.976
 premiere-0.902
sterdam-0.889
Token that
Token ID326
Feature activation-4.74e-02

Pos logit contributions
isine+0.641
tical+0.640
alty+0.639
vious+0.574
itiz+0.569
Neg logit contributions
 Vert-0.471
 depos-0.450
antam-0.449
 premiere-0.415
sterdam-0.409
Token bill
Token ID2855
Feature activation-1.64e+00

Pos logit contributions
isine+0.043
tical+0.043
alty+0.043
vious+0.038
itiz+0.038
Neg logit contributions
 Vert-0.032
 depos-0.031
antam-0.031
 premiere-0.029
sterdam-0.028
Token that
Token ID326
Feature activation-4.89e-01

Pos logit contributions
isine+1.467
tical+1.467
alty+1.460
vious+1.308
itiz+1.296
Neg logit contributions
 Vert-1.132
 depos-1.083
antam-1.079
 premiere-0.999
sterdam-0.981
Token was
Token ID373
Feature activation-1.01e+00

Pos logit contributions
isine+0.392
tical+0.391
alty+0.390
vious+0.344
itiz+0.341
Neg logit contributions
 Vert-0.385
 depos-0.371
antam-0.369
 premiere-0.346
sterdam-0.340
Token worth
Token ID2861
Feature activation-4.31e+00

Pos logit contributions
isine+0.860
tical+0.858
alty+0.857
vious+0.762
itiz+0.755
Neg logit contributions
 Vert-0.737
 depos-0.710
antam-0.704
 premiere-0.657
sterdam-0.646
Token the
Token ID262
Feature activation-4.53e-01

Pos logit contributions
alty+3.525
isine+3.525
tical+3.517
vious+3.116
itiz+3.114
Neg logit contributions
 Vert-3.258
antam-3.122
 depos-3.077
 premiere-2.916
sterdam-2.883
Token Democratic
Token ID4390
Feature activation+1.13e+00

Pos logit contributions
isine+0.411
tical+0.410
alty+0.409
vious+0.366
itiz+0.364
Neg logit contributions
 Vert-0.310
 depos-0.298
antam-0.295
 premiere-0.274
sterdam-0.268
Token votes
Token ID5690
Feature activation-8.28e-01

Pos logit contributions
 Vert+0.906
 depos+0.876
antam+0.868
 premiere+0.817
sterdam+0.801
Neg logit contributions
isine-0.890
tical-0.886
alty-0.883
vious-0.778
itiz-0.769
Token.
Token ID13
Feature activation-8.02e-01

Pos logit contributions
isine+0.743
tical+0.742
alty+0.741
vious+0.662
itiz+0.657
Neg logit contributions
 Vert-0.572
 depos-0.549
antam-0.545
 premiere-0.506
sterdam-0.496
Token Georgia
Token ID7859
Feature activation-1.28e+00

Pos logit contributions
isine+0.635
tical+0.633
alty+0.633
vious+0.556
itiz+0.552
Neg logit contributions
 Vert-0.639
 depos-0.617
antam-0.612
 premiere-0.575
sterdam-0.565
Token f
Token ID277
Feature activation-5.95e-01

Pos logit contributions
isine+0.386
tical+0.385
alty+0.385
vious+0.343
itiz+0.340
Neg logit contributions
 Vert-0.312
 depos-0.300
antam-0.297
 premiere-0.277
sterdam-0.270
Tokenrit
Token ID799
Feature activation-5.25e-01

Pos logit contributions
isine+0.438
tical+0.436
alty+0.434
vious+0.379
itiz+0.374
Neg logit contributions
 Vert-0.507
 depos-0.490
antam-0.489
 premiere-0.459
sterdam-0.452
Tokenters
Token ID1010
Feature activation+2.51e-01

Pos logit contributions
tical+0.438
isine+0.438
alty+0.437
vious+0.387
itiz+0.384
Neg logit contributions
 Vert-0.396
 depos-0.381
antam-0.379
 premiere-0.354
sterdam-0.348
Token on
Token ID319
Feature activation-3.41e-01

Pos logit contributions
 Vert+0.179
 depos+0.172
antam+0.170
 premiere+0.159
sterdam+0.155
Neg logit contributions
isine-0.220
tical-0.219
alty-0.219
vious-0.195
itiz-0.194
Token each
Token ID1123
Feature activation-7.88e-01

Pos logit contributions
isine+0.298
tical+0.298
alty+0.297
vious+0.264
itiz+0.262
Neg logit contributions
 Vert-0.244
 depos-0.234
antam-0.232
 premiere-0.216
sterdam-0.212
Token side
Token ID1735
Feature activation-4.30e+00

Pos logit contributions
isine+0.664
tical+0.663
alty+0.663
vious+0.589
itiz+0.582
Neg logit contributions
 Vert-0.585
 depos-0.561
antam-0.560
 premiere-0.522
sterdam-0.519
Token for
Token ID329
Feature activation+5.93e-02

Pos logit contributions
tical+3.566
alty+3.554
isine+3.541
vious+3.155
itiz+3.133
Neg logit contributions
 Vert-3.204
antam-3.083
 depos-3.059
 premiere-2.861
sterdam-2.858
Token about
Token ID546
Feature activation-6.94e-01

Pos logit contributions
 Vert+0.041
 depos+0.039
antam+0.039
 premiere+0.036
sterdam+0.035
Neg logit contributions
isine-0.053
tical-0.053
alty-0.053
vious-0.048
itiz-0.047
Token 2
Token ID362
Feature activation-1.19e+00

Pos logit contributions
isine+0.654
tical+0.653
alty+0.652
vious+0.586
itiz+0.582
Neg logit contributions
 Vert-0.448
 depos-0.429
antam-0.426
 premiere-0.393
sterdam-0.386
Token/
Token ID14
Feature activation-3.11e-01

Pos logit contributions
isine+0.807
tical+0.806
alty+0.804
vious+0.692
itiz+0.684
Neg logit contributions
 Vert-1.086
 depos-1.050
antam-1.046
 premiere-0.990
sterdam-0.979
Token3
Token ID18
Feature activation-1.12e+00

Pos logit contributions
isine+0.231
tical+0.231
alty+0.231
vious+0.201
itiz+0.199
Neg logit contributions
 Vert-0.263
 depos-0.254
antam-0.253
 premiere-0.238
sterdam-0.235
Token)(
Token ID5769
Feature activation+1.57e-01

Pos logit contributions
 Vert+0.070
 depos+0.067
antam+0.066
 premiere+0.061
sterdam+0.060
Neg logit contributions
isine-0.099
tical-0.099
alty-0.098
vious-0.088
itiz-0.088
Token3
Token ID18
Feature activation-1.58e-01

Pos logit contributions
 Vert+0.142
 depos+0.138
antam+0.136
 premiere+0.129
sterdam+0.127
Neg logit contributions
isine-0.108
tical-0.108
alty-0.108
vious-0.093
itiz-0.092
Token)
Token ID8
Feature activation-7.23e-01

Pos logit contributions
isine+0.137
tical+0.137
alty+0.137
vious+0.122
itiz+0.121
Neg logit contributions
 Vert-0.114
 depos-0.110
antam-0.109
 premiere-0.102
sterdam-0.100
Token nonprofit
Token ID15346
Feature activation+1.80e-01

Pos logit contributions
tical+0.601
alty+0.599
isine+0.597
vious+0.530
itiz+0.526
Neg logit contributions
 Vert-0.548
 depos-0.527
antam-0.525
 premiere-0.488
sterdam-0.482
Token that
Token ID326
Feature activation-7.29e-01

Pos logit contributions
 Vert+0.128
 depos+0.123
antam+0.122
 premiere+0.114
sterdam+0.112
Neg logit contributions
tical-0.157
isine-0.157
alty-0.157
vious-0.140
itiz-0.139
Token appears
Token ID3568
Feature activation-4.30e+00

Pos logit contributions
tical+0.617
alty+0.616
isine+0.614
itiz+0.545
vious+0.545
Neg logit contributions
 Vert-0.539
antam-0.517
 depos-0.517
 premiere-0.480
sterdam-0.474
Token to
Token ID284
Feature activation-6.46e-01

Pos logit contributions
tical+3.680
alty+3.648
isine+3.594
vious+3.228
itiz+3.218
Neg logit contributions
 Vert-3.131
antam-3.001
 depos-2.979
 premiere-2.766
sterdam-2.741
Token have
Token ID423
Feature activation-5.16e-01

Pos logit contributions
isine+0.586
tical+0.586
alty+0.585
vious+0.523
itiz+0.519
Neg logit contributions
 Vert-0.439
 depos-0.421
antam-0.418
 premiere-0.386
sterdam-0.381
Token been
Token ID587
Feature activation-7.46e-01

Pos logit contributions
tical+0.445
alty+0.445
isine+0.443
vious+0.395
itiz+0.393
Neg logit contributions
 Vert-0.373
 depos-0.358
antam-0.358
 premiere-0.332
sterdam-0.328
Token created
Token ID2727
Feature activation-1.03e+00

Pos logit contributions
isine+0.610
tical+0.608
alty+0.606
vious+0.536
itiz+0.532
Neg logit contributions
 Vert-0.577
 depos-0.556
antam-0.551
 premiere-0.518
sterdam-0.508
Token with
Token ID351
Feature activation+1.65e-02

Pos logit contributions
tical+0.950
alty+0.947
isine+0.945
vious+0.849
itiz+0.841
Neg logit contributions
 Vert-0.682
 depos-0.653
antam-0.652
 premiere-0.598
sterdam-0.589
Token
Token ID447
Feature activation-2.76e-01

Pos logit contributions
isine+0.484
tical+0.483
alty+0.482
vious+0.422
itiz+0.418
Neg logit contributions
 Vert-0.513
 depos-0.495
antam-0.492
 premiere-0.463
sterdam-0.455
Token
Token ID247
Feature activation-2.41e-01

Pos logit contributions
alty+0.151
isine+0.151
tical+0.151
vious+0.125
itiz+0.122
Neg logit contributions
 Vert-0.288
 depos-0.280
antam-0.278
 premiere-0.266
sterdam-0.262
Tokent
Token ID83
Feature activation-2.38e-01

Pos logit contributions
alty+0.200
tical+0.200
isine+0.199
vious+0.176
itiz+0.175
Neg logit contributions
 Vert-0.184
 depos-0.178
antam-0.176
 premiere-0.165
sterdam-0.162
Token a
Token ID257
Feature activation-2.28e-01

Pos logit contributions
isine+0.209
tical+0.208
alty+0.208
vious+0.186
itiz+0.184
Neg logit contributions
 Vert-0.169
 depos-0.163
antam-0.161
 premiere-0.150
sterdam-0.147
Token federal
Token ID2717
Feature activation+1.21e+00

Pos logit contributions
isine+0.195
tical+0.195
alty+0.194
vious+0.173
itiz+0.172
Neg logit contributions
 Vert-0.167
 depos-0.161
antam-0.160
 premiere-0.149
sterdam-0.146
Token judge
Token ID5052
Feature activation-4.29e+00

Pos logit contributions
 Vert+0.716
 depos+0.687
antam+0.673
 premiere+0.627
sterdam+0.602
Neg logit contributions
isine-1.208
tical-1.208
alty-1.199
vious-1.090
itiz-1.080
Token and
Token ID290
Feature activation-6.91e-01

Pos logit contributions
alty+3.742
tical+3.728
isine+3.712
vious+3.283
itiz+3.283
Neg logit contributions
 Vert-3.068
antam-2.912
 depos-2.872
 premiere-2.682
sterdam-2.669
Token doesn
Token ID1595
Feature activation-1.04e+00

Pos logit contributions
isine+0.580
tical+0.579
alty+0.577
vious+0.512
itiz+0.507
Neg logit contributions
 Vert-0.519
 depos-0.500
antam-0.496
 premiere-0.464
sterdam-0.455
Token
Token ID447
Feature activation-6.46e-01

Pos logit contributions
tical+0.792
isine+0.792
alty+0.789
vious+0.691
itiz+0.685
Neg logit contributions
 Vert-0.858
 depos-0.829
antam-0.823
 premiere-0.775
sterdam-0.764
Token
Token ID247
Feature activation-4.24e-01

Pos logit contributions
alty+0.352
isine+0.352
tical+0.352
vious+0.291
itiz+0.286
Neg logit contributions
 Vert-0.674
 depos-0.655
antam-0.651
 premiere-0.622
sterdam-0.615
Tokent
Token ID83
Feature activation-2.21e-01

Pos logit contributions
isine+0.356
tical+0.355
alty+0.354
vious+0.314
itiz+0.312
Neg logit contributions
 Vert-0.318
 depos-0.306
antam-0.304
 premiere-0.285
sterdam-0.279
TokenOL
Token ID3535
Feature activation-7.31e-01

Pos logit contributions
isine+0.259
alty+0.258
tical+0.258
vious+0.232
itiz+0.230
Neg logit contributions
 Vert-0.187
 depos-0.179
antam-0.177
 premiere-0.164
sterdam-0.161
Token.
Token ID13
Feature activation-1.37e-01

Pos logit contributions
isine+0.660
tical+0.659
alty+0.657
vious+0.588
itiz+0.583
Neg logit contributions
 Vert-0.501
 depos-0.480
antam-0.477
 premiere-0.443
sterdam-0.434
Token
Token ID198
Feature activation-5.40e-01

Pos logit contributions
isine+0.111
alty+0.110
tical+0.110
vious+0.097
itiz+0.096
Neg logit contributions
 Vert-0.107
 depos-0.103
antam-0.102
 premiere-0.096
sterdam-0.094
Token
Token ID198
Feature activation-5.59e-01

Pos logit contributions
isine+0.427
tical+0.424
alty+0.423
vious+0.372
itiz+0.370
Neg logit contributions
 Vert-0.433
 depos-0.416
antam-0.414
 premiere-0.389
sterdam-0.381
TokenThat
Token ID2504
Feature activation-3.83e-01

Pos logit contributions
tical+0.423
isine+0.422
alty+0.422
vious+0.369
itiz+0.365
Neg logit contributions
 Vert-0.465
 depos-0.451
antam-0.446
 premiere-0.421
sterdam-0.415
Token seems
Token ID2331
Feature activation-4.27e+00

Pos logit contributions
tical+0.315
alty+0.314
isine+0.313
vious+0.277
itiz+0.275
Neg logit contributions
 Vert-0.293
 depos-0.283
antam-0.281
 premiere-0.263
sterdam-0.259
Token to
Token ID284
Feature activation+4.31e-01

Pos logit contributions
tical+3.679
alty+3.610
isine+3.596
vious+3.241
itiz+3.203
Neg logit contributions
 Vert-3.090
 depos-2.975
antam-2.969
 premiere-2.725
sterdam-2.697
Token be
Token ID307
Feature activation+8.00e-03

Pos logit contributions
 Vert+0.322
 depos+0.310
antam+0.307
 premiere+0.288
sterdam+0.282
Neg logit contributions
isine-0.364
tical-0.362
alty-0.362
vious-0.321
itiz-0.319
Token the
Token ID262
Feature activation-1.97e-01

Pos logit contributions
 Vert+0.005
 depos+0.005
antam+0.005
 premiere+0.005
sterdam+0.005
Neg logit contributions
isine-0.007
tical-0.007
alty-0.007
vious-0.006
itiz-0.006
Token case
Token ID1339
Feature activation+6.93e-01

Pos logit contributions
isine+0.189
tical+0.188
alty+0.188
vious+0.169
itiz+0.168
Neg logit contributions
 Vert-0.123
 depos-0.118
antam-0.117
 premiere-0.108
sterdam-0.106
Token with
Token ID351
Feature activation+1.40e-02

Pos logit contributions
 Vert+0.467
 depos+0.448
antam+0.444
 premiere+0.413
sterdam+0.404
Neg logit contributions
isine-0.634
tical-0.632
alty-0.632
vious-0.566
itiz-0.563
Token N
Token ID399
Feature activation-1.33e+00

Pos logit contributions
isine+0.749
tical+0.747
alty+0.746
vious+0.668
itiz+0.663
Neg logit contributions
 Vert-0.553
 depos-0.531
antam-0.526
 premiere-0.488
sterdam-0.478
Token-
Token ID12
Feature activation-1.53e+00

Pos logit contributions
isine+1.040
alty+1.037
tical+1.036
vious+0.907
itiz+0.902
Neg logit contributions
 Vert-1.073
 depos-1.037
antam-1.027
 premiere-0.969
sterdam-0.952
Tokencyclop
Token ID22873
Feature activation-2.24e+00

Pos logit contributions
isine+1.280
tical+1.278
alty+1.275
vious+1.131
itiz+1.122
Neg logit contributions
 Vert-1.154
 depos-1.111
antam-1.104
 premiere-1.031
sterdam-1.013
Tokenrop
Token ID1773
Feature activation-3.00e+00

Pos logit contributions
isine+1.588
tical+1.582
alty+1.578
vious+1.368
itiz+1.355
Neg logit contributions
 Vert-1.972
 depos-1.913
antam-1.899
 premiere-1.795
sterdam-1.769
Tokenyl
Token ID2645
Feature activation-1.00e+00

Pos logit contributions
isine+1.896
tical+1.890
alty+1.885
vious+1.603
itiz+1.584
Neg logit contributions
 Vert-2.867
 depos-2.785
antam-2.768
 premiere-2.630
sterdam-2.594
Tokenmethyl
Token ID43654
Feature activation-4.22e+00

Pos logit contributions
isine+0.797
tical+0.795
alty+0.793
vious+0.699
itiz+0.693
Neg logit contributions
 Vert-0.794
 depos-0.766
antam-0.761
 premiere-0.714
sterdam-0.702
Token-
Token ID12
Feature activation-2.80e+00

Pos logit contributions
isine+3.364
tical+3.334
alty+3.327
vious+2.929
itiz+2.905
Neg logit contributions
 Vert-3.300
 depos-3.189
antam-3.146
 premiere-2.991
sterdam-2.938
Token7
Token ID22
Feature activation-2.54e+00

Pos logit contributions
isine+2.102
tical+2.094
alty+2.092
vious+1.824
itiz+1.805
Neg logit contributions
 Vert-2.347
 depos-2.270
antam-2.245
 premiere-2.128
sterdam-2.094
Token-(
Token ID30420
Feature activation-1.50e+00

Pos logit contributions
isine+1.995
tical+1.994
alty+1.990
vious+1.744
itiz+1.724
Neg logit contributions
 Vert-2.035
 depos-1.966
antam-1.954
 premiere-1.835
sterdam-1.815
Token2
Token ID17
Feature activation-2.27e+00

Pos logit contributions
isine+1.106
tical+1.106
alty+1.105
vious+0.961
itiz+0.953
Neg logit contributions
 Vert-1.279
 depos-1.242
antam-1.236
 premiere-1.153
sterdam-1.136
Token,
Token ID11
Feature activation-2.21e+00

Pos logit contributions
isine+1.872
tical+1.870
alty+1.866
vious+1.651
itiz+1.637
Neg logit contributions
 Vert-1.733
 depos-1.663
antam-1.652
 premiere-1.551
sterdam-1.534
Token
Token ID198
Feature activation-3.74e-01

Pos logit contributions
isine+0.214
tical+0.213
alty+0.213
vious+0.187
itiz+0.186
Neg logit contributions
 Vert-0.215
 depos-0.207
antam-0.206
 premiere-0.193
sterdam-0.190
Token
Token ID198
Feature activation-4.40e-01

Pos logit contributions
isine+0.297
tical+0.295
alty+0.295
vious+0.259
itiz+0.257
Neg logit contributions
 Vert-0.299
 depos-0.288
antam-0.286
 premiere-0.269
sterdam-0.263
TokenThis
Token ID1212
Feature activation-4.00e-01

Pos logit contributions
tical+0.354
isine+0.353
alty+0.353
vious+0.312
itiz+0.308
Neg logit contributions
 Vert-0.346
 depos-0.334
antam-0.331
 premiere-0.311
sterdam-0.306
Token article
Token ID2708
Feature activation-5.51e-01

Pos logit contributions
isine+0.348
tical+0.347
alty+0.347
vious+0.309
itiz+0.306
Neg logit contributions
 Vert-0.287
 depos-0.277
antam-0.274
 premiere-0.256
sterdam-0.250
Token originally
Token ID6198
Feature activation-1.93e+00

Pos logit contributions
isine+0.426
alty+0.425
tical+0.422
itiz+0.369
vious+0.369
Neg logit contributions
 Vert-0.450
 depos-0.436
antam-0.432
 premiere-0.410
sterdam-0.401
Token appeared
Token ID4120
Feature activation-4.21e+00

Pos logit contributions
isine+1.690
tical+1.690
alty+1.684
vious+1.508
itiz+1.494
Neg logit contributions
 Vert-1.372
 depos-1.318
antam-1.309
 premiere-1.214
sterdam-1.196
Token on
Token ID319
Feature activation-7.87e-01

Pos logit contributions
tical+3.640
isine+3.601
alty+3.596
vious+3.194
itiz+3.165
Neg logit contributions
 Vert-3.020
 depos-2.931
antam-2.891
 premiere-2.671
sterdam-2.630
Token HuffPost
Token ID35130
Feature activation-1.54e+00

Pos logit contributions
tical+0.686
isine+0.686
alty+0.685
vious+0.610
itiz+0.605
Neg logit contributions
 Vert-0.561
 depos-0.541
antam-0.537
 premiere-0.499
sterdam-0.491
Token.
Token ID13
Feature activation-5.55e-01

Pos logit contributions
tical+1.367
isine+1.366
alty+1.363
vious+1.217
itiz+1.207
Neg logit contributions
 Vert-1.079
 depos-1.041
antam-1.031
 premiere-0.957
sterdam-0.939
Token<|endoftext|>
Token ID50256
Feature activation-6.87e-01

Pos logit contributions
isine+0.423
tical+0.422
alty+0.422
vious+0.369
itiz+0.366
Neg logit contributions
 Vert-0.457
 depos-0.444
antam-0.440
 premiere-0.414
sterdam-0.408
TokenRussia
Token ID16347
Feature activation+9.15e-01

Pos logit contributions
isine+0.523
tical+0.523
alty+0.522
vious+0.458
itiz+0.452
Neg logit contributions
 Vert-0.568
 depos-0.550
antam-0.545
 premiere-0.513
sterdam-0.505
Token.
Token ID13
Feature activation-1.31e-01

Pos logit contributions
tical+2.676
alty+2.675
isine+2.629
vious+2.361
itiz+2.339
Neg logit contributions
 Vert-2.196
 depos-2.142
antam-2.136
 premiere-1.970
sterdam-1.969
Token Invalid
Token ID17665
Feature activation-2.63e+00

Pos logit contributions
isine+0.097
tical+0.096
alty+0.096
vious+0.084
itiz+0.083
Neg logit contributions
 Vert-0.112
 depos-0.108
antam-0.108
 premiere-0.101
sterdam-0.100
Token email
Token ID3053
Feature activation-1.60e+00

Pos logit contributions
isine+2.593
tical+2.592
alty+2.589
vious+2.339
itiz+2.322
Neg logit contributions
 Vert-1.575
 depos-1.499
antam-1.493
 premiere-1.365
sterdam-1.344
Token address
Token ID2209
Feature activation-2.01e-01

Pos logit contributions
isine+1.395
tical+1.394
alty+1.393
vious+1.240
itiz+1.230
Neg logit contributions
 Vert-1.150
 depos-1.106
antam-1.099
 premiere-1.021
sterdam-1.005
Token.
Token ID13
Feature activation-3.18e-01

Pos logit contributions
isine+0.185
tical+0.184
alty+0.184
vious+0.165
itiz+0.164
Neg logit contributions
 Vert-0.136
 depos-0.129
antam-0.128
 premiere-0.119
sterdam-0.117
Token Please
Token ID4222
Feature activation-4.18e+00

Pos logit contributions
isine+0.240
alty+0.237
tical+0.237
vious+0.207
itiz+0.206
Neg logit contributions
 Vert-0.268
 depos-0.257
antam-0.255
 premiere-0.242
sterdam-0.235
Token re
Token ID302
Feature activation-1.12e+00

Pos logit contributions
tical+4.187
alty+4.161
isine+4.072
vious+3.685
itiz+3.681
Neg logit contributions
 Vert-2.424
antam-2.308
 depos-2.259
sterdam-2.101
 premiere-1.993
Token-
Token ID12
Feature activation-1.20e-01

Pos logit contributions
tical+0.885
isine+0.885
alty+0.884
vious+0.779
itiz+0.770
Neg logit contributions
 Vert-0.889
 depos-0.858
antam-0.854
 premiere-0.800
sterdam-0.789
Tokenenter
Token ID9255
Feature activation-1.99e+00

Pos logit contributions
alty+0.086
tical+0.086
isine+0.085
vious+0.075
itiz+0.074
Neg logit contributions
 Vert-0.104
 depos-0.100
antam-0.100
 premiere-0.094
sterdam-0.094
Token.
Token ID13
Feature activation-5.52e-01

Pos logit contributions
tical+1.764
alty+1.757
isine+1.748
vious+1.568
itiz+1.550
Neg logit contributions
 Vert-1.399
 depos-1.350
antam-1.349
 premiere-1.245
sterdam-1.237
Token You
Token ID921
Feature activation-1.60e+00

Pos logit contributions
isine+0.374
tical+0.373
alty+0.372
vious+0.320
itiz+0.317
Neg logit contributions
 Vert-0.503
 depos-0.487
antam-0.484
 premiere-0.458
sterdam-0.451
Token;
Token ID26
Feature activation+9.06e-03

Pos logit contributions
tical+0.188
isine+0.188
alty+0.187
vious+0.167
itiz+0.166
Neg logit contributions
 Vert-0.145
 depos-0.139
antam-0.138
 premiere-0.128
sterdam-0.126
Token no
Token ID645
Feature activation-1.13e+00

Pos logit contributions
 Vert+0.007
 depos+0.007
antam+0.007
 premiere+0.006
sterdam+0.006
Neg logit contributions
isine-0.007
tical-0.007
alty-0.007
vious-0.007
itiz-0.007
Token,
Token ID11
Feature activation-2.16e+00

Pos logit contributions
alty+0.988
tical+0.988
isine+0.987
vious+0.880
itiz+0.874
Neg logit contributions
 Vert-0.798
 depos-0.767
antam-0.766
 premiere-0.710
sterdam-0.699
Token nor
Token ID4249
Feature activation-1.15e+00

Pos logit contributions
tical+1.798
alty+1.795
isine+1.789
vious+1.589
itiz+1.578
Neg logit contributions
 Vert-1.611
 depos-1.554
antam-1.553
 premiere-1.445
sterdam-1.425
Token woman
Token ID2415
Feature activation-6.65e-01

Pos logit contributions
tical+0.991
alty+0.990
isine+0.989
vious+0.878
itiz+0.872
Neg logit contributions
 Vert-0.835
 depos-0.803
antam-0.802
 premiere-0.745
sterdam-0.730
Token neither
Token ID6159
Feature activation-4.18e+00

Pos logit contributions
isine+0.611
tical+0.611
alty+0.610
vious+0.546
itiz+0.543
Neg logit contributions
 Vert-0.445
 depos-0.426
antam-0.424
 premiere-0.392
sterdam-0.385
Token.
Token ID764
Feature activation+1.22e+00

Pos logit contributions
alty+3.537
tical+3.503
isine+3.496
itiz+3.130
vious+3.095
Neg logit contributions
 Vert-2.989
antam-2.928
 depos-2.869
sterdam-2.681
 premiere-2.642
Token.
Token ID764
Feature activation-8.55e-02

Pos logit contributions
 Vert+0.982
 depos+0.944
antam+0.937
 premiere+0.882
sterdam+0.863
Neg logit contributions
isine-0.964
tical-0.954
alty-0.952
vious-0.838
itiz-0.835
Token.
Token ID764
Feature activation-5.76e-01

Pos logit contributions
isine+0.068
tical+0.068
alty+0.068
vious+0.060
itiz+0.059
Neg logit contributions
 Vert-0.068
 depos-0.065
antam-0.065
 premiere-0.061
sterdam-0.060
Token
Token ID198
Feature activation-5.85e-01

Pos logit contributions
isine+0.467
tical+0.466
alty+0.465
vious+0.410
itiz+0.407
Neg logit contributions
 Vert-0.449
 depos-0.432
antam-0.429
 premiere-0.403
sterdam-0.396
Token
Token ID198
Feature activation-7.56e-01

Pos logit contributions
isine+0.461
tical+0.459
alty+0.458
vious+0.402
itiz+0.399
Neg logit contributions
 Vert-0.470
 depos-0.453
antam-0.450
 premiere-0.423
sterdam-0.415
Token in
Token ID287
Feature activation-3.98e-01

Pos logit contributions
 Vert+0.433
 depos+0.417
antam+0.414
 premiere+0.389
sterdam+0.382
Neg logit contributions
isine-0.449
tical-0.447
alty-0.447
vious-0.394
itiz-0.391
Token Massachusetts
Token ID10140
Feature activation+7.84e-01

Pos logit contributions
isine+0.362
tical+0.362
alty+0.362
vious+0.325
itiz+0.322
Neg logit contributions
 Vert-0.268
 depos-0.258
antam-0.256
 premiere-0.237
sterdam-0.233
Token were
Token ID547
Feature activation+6.67e-01

Pos logit contributions
 Vert+0.606
 depos+0.584
antam+0.580
 premiere+0.544
sterdam+0.534
Neg logit contributions
isine-0.641
tical-0.639
alty-0.638
vious-0.563
itiz-0.559
Token the
Token ID262
Feature activation-2.15e-01

Pos logit contributions
 Vert+0.477
 depos+0.457
antam+0.453
 premiere+0.424
sterdam+0.415
Neg logit contributions
isine-0.587
tical-0.583
alty-0.582
vious-0.519
itiz-0.516
Token Y
Token ID575
Feature activation+1.20e+00

Pos logit contributions
tical+0.195
isine+0.195
alty+0.195
vious+0.175
itiz+0.173
Neg logit contributions
 Vert-0.144
 depos-0.139
antam-0.138
 premiere-0.127
sterdam-0.125
Tokenaw
Token ID707
Feature activation+3.05e+00

Pos logit contributions
 Vert+0.991
 depos+0.958
antam+0.957
 premiere+0.897
sterdam+0.884
Neg logit contributions
isine-0.910
tical-0.908
alty-0.901
vious-0.792
itiz-0.785
Tokenkey
Token ID2539
Feature activation-3.62e-01

Pos logit contributions
 Vert+2.540
antam+2.422
 depos+2.415
 premiere+2.291
sterdam+2.271
Neg logit contributions
isine-2.317
tical-2.284
alty-2.270
vious-1.983
itiz-1.952
Token Center
Token ID3337
Feature activation+4.52e-01

Pos logit contributions
isine+0.306
tical+0.306
alty+0.305
vious+0.272
itiz+0.269
Neg logit contributions
 Vert-0.268
 depos-0.259
antam-0.256
 premiere-0.239
sterdam-0.235
Token at
Token ID379
Feature activation+3.55e-01

Pos logit contributions
 Vert+0.311
 depos+0.298
antam+0.295
 premiere+0.276
sterdam+0.270
Neg logit contributions
isine-0.408
tical-0.407
alty-0.406
vious-0.363
itiz-0.361
Token Emmanuel
Token ID32390
Feature activation+3.49e-01

Pos logit contributions
 Vert+0.239
 depos+0.228
antam+0.227
 premiere+0.210
sterdam+0.206
Neg logit contributions
isine-0.327
tical-0.326
alty-0.325
vious-0.291
itiz-0.290
Token College
Token ID5535
Feature activation+4.30e-01

Pos logit contributions
 Vert+0.267
 depos+0.258
antam+0.256
 premiere+0.240
sterdam+0.235
Neg logit contributions
isine-0.287
tical-0.286
alty-0.285
vious-0.253
itiz-0.250
Tokenups
Token ID4739
Feature activation+8.07e-01

Pos logit contributions
isine+0.017
tical+0.017
alty+0.017
vious+0.015
itiz+0.015
Neg logit contributions
 Vert-0.014
 depos-0.014
antam-0.014
 premiere-0.013
sterdam-0.012
Token are
Token ID389
Feature activation-1.30e-01

Pos logit contributions
 Vert+0.579
 depos+0.556
antam+0.550
 premiere+0.514
sterdam+0.502
Neg logit contributions
isine-0.706
tical-0.702
alty-0.702
vious-0.627
itiz-0.621
Token a
Token ID257
Feature activation-1.29e-01

Pos logit contributions
isine+0.115
tical+0.114
alty+0.114
vious+0.102
itiz+0.101
Neg logit contributions
 Vert-0.093
 depos-0.089
antam-0.088
 premiere-0.082
sterdam-0.081
Token tax
Token ID1687
Feature activation+1.64e+00

Pos logit contributions
isine+0.113
tical+0.112
alty+0.112
vious+0.100
itiz+0.099
Neg logit contributions
 Vert-0.092
 depos-0.088
antam-0.087
 premiere-0.082
sterdam-0.080
Token you
Token ID345
Feature activation+1.59e-01

Pos logit contributions
 Vert+1.324
 depos+1.280
antam+1.254
 premiere+1.190
sterdam+1.160
Neg logit contributions
isine-1.275
alty-1.274
tical-1.264
vious-1.115
itiz-1.106
Token pay
Token ID1414
Feature activation+3.04e+00

Pos logit contributions
 Vert+0.098
 depos+0.094
antam+0.093
 premiere+0.085
sterdam+0.084
Neg logit contributions
isine-0.155
tical-0.155
alty-0.155
vious-0.140
itiz-0.139
Token for
Token ID329
Feature activation+4.91e-01

Pos logit contributions
 Vert+2.199
 depos+2.130
antam+2.079
 premiere+1.953
sterdam+1.926
Neg logit contributions
isine-2.617
alty-2.604
tical-2.590
vious-2.316
itiz-2.297
Token the
Token ID262
Feature activation-1.08e-01

Pos logit contributions
 Vert+0.359
 depos+0.345
antam+0.342
 premiere+0.319
sterdam+0.313
Neg logit contributions
isine-0.422
tical-0.421
alty-0.420
vious-0.374
itiz-0.371
Token luxury
Token ID13064
Feature activation+4.03e-01

Pos logit contributions
isine+0.101
tical+0.101
alty+0.101
vious+0.090
itiz+0.090
Neg logit contributions
 Vert-0.070
 depos-0.067
antam-0.067
 premiere-0.062
sterdam-0.060
Token of
Token ID286
Feature activation-1.56e-01

Pos logit contributions
 Vert+0.301
 depos+0.290
antam+0.286
 premiere+0.269
sterdam+0.264
Neg logit contributions
isine-0.339
tical-0.339
alty-0.338
vious-0.300
itiz-0.296
Token a
Token ID257
Feature activation+4.90e-01

Pos logit contributions
isine+0.137
tical+0.137
alty+0.137
vious+0.122
itiz+0.122
Neg logit contributions
 Vert-0.110
antam-0.105
 depos-0.105
 premiere-0.098
sterdam-0.096
Token93
Token ID6052
Feature activation-9.83e-01

Pos logit contributions
alty+0.302
tical+0.300
isine+0.300
vious+0.265
itiz+0.261
Neg logit contributions
 Vert-0.320
 depos-0.310
antam-0.306
 premiere-0.290
sterdam-0.286
Token Shang
Token ID45797
Feature activation-4.92e-01

Pos logit contributions
tical+0.870
alty+0.868
isine+0.864
vious+0.775
itiz+0.767
Neg logit contributions
 Vert-0.679
 depos-0.660
antam-0.653
 premiere-0.605
sterdam-0.600
Token-
Token ID12
Feature activation-5.74e-01

Pos logit contributions
isine+0.379
tical+0.378
alty+0.377
vious+0.331
itiz+0.328
Neg logit contributions
 Vert-0.403
 depos-0.389
antam-0.386
 premiere-0.363
sterdam-0.358
Tokenclass
Token ID4871
Feature activation+1.27e+00

Pos logit contributions
isine+0.475
tical+0.474
alty+0.473
vious+0.419
itiz+0.415
Neg logit contributions
 Vert-0.438
 depos-0.423
antam-0.415
 premiere-0.390
sterdam-0.384
Token and
Token ID290
Feature activation+1.38e-01

Pos logit contributions
 Vert+0.771
 depos+0.735
antam+0.729
 premiere+0.670
sterdam+0.654
Neg logit contributions
isine-1.240
tical-1.238
alty-1.235
vious-1.116
itiz-1.108
Token type
Token ID2099
Feature activation+4.07e+00

Pos logit contributions
 Vert+0.091
 depos+0.088
antam+0.087
 premiere+0.080
sterdam+0.079
Neg logit contributions
tical-0.128
isine-0.128
alty-0.127
vious-0.114
itiz-0.113
Token-
Token ID12
Feature activation-1.75e-01

Pos logit contributions
 Vert+3.007
 depos+2.871
antam+2.865
 premiere+2.694
 deb+2.590
Neg logit contributions
tical-3.440
isine-3.438
alty-3.402
itiz-3.027
vious-3.021
Token95
Token ID3865
Feature activation-5.11e-01

Pos logit contributions
isine+0.123
tical+0.123
alty+0.123
vious+0.106
itiz+0.105
Neg logit contributions
 Vert-0.154
 depos-0.149
antam-0.148
 premiere-0.140
sterdam-0.138
Token,
Token ID11
Feature activation-4.06e-01

Pos logit contributions
tical+0.464
isine+0.463
alty+0.462
vious+0.415
itiz+0.411
Neg logit contributions
 Vert-0.344
 depos-0.333
antam-0.330
 premiere-0.305
sterdam-0.301
Token 4
Token ID604
Feature activation-6.76e-02

Pos logit contributions
alty+0.366
isine+0.365
tical+0.365
vious+0.327
itiz+0.325
Neg logit contributions
 Vert-0.275
 depos-0.266
antam-0.264
 premiere-0.244
sterdam-0.241
Token-
Token ID12
Feature activation-6.25e-01

Pos logit contributions
tical+0.054
alty+0.054
isine+0.054
vious+0.048
itiz+0.047
Neg logit contributions
 Vert-0.052
 depos-0.051
antam-0.050
 premiere-0.047
sterdam-0.047
Token (
Token ID357
Feature activation+2.54e-01

Pos logit contributions
 Vert+0.197
 depos+0.191
antam+0.189
 premiere+0.178
sterdam+0.174
Neg logit contributions
tical-0.200
isine-0.200
alty-0.199
vious-0.176
itiz-0.175
Token15
Token ID1314
Feature activation-6.45e-01

Pos logit contributions
 Vert+0.205
 depos+0.198
antam+0.196
 premiere+0.184
sterdam+0.181
Neg logit contributions
isine-0.198
tical-0.198
alty-0.198
vious-0.174
itiz-0.172
Tokenth
Token ID400
Feature activation+1.69e+00

Pos logit contributions
tical+0.584
alty+0.580
isine+0.577
vious+0.522
itiz+0.514
Neg logit contributions
 Vert-0.441
 depos-0.424
antam-0.421
 premiere-0.387
sterdam-0.385
Token among
Token ID1871
Feature activation+6.44e-01

Pos logit contributions
 Vert+1.078
 depos+1.030
antam+1.018
 premiere+0.947
sterdam+0.920
Neg logit contributions
isine-1.604
alty-1.599
tical-1.594
vious-1.431
itiz-1.425
Token running
Token ID2491
Feature activation+5.15e-01

Pos logit contributions
 Vert+0.428
 depos+0.410
antam+0.406
 premiere+0.377
sterdam+0.367
Neg logit contributions
isine-0.597
tical-0.596
alty-0.594
vious-0.533
itiz-0.529
Token backs
Token ID12983
Feature activation+2.81e+00

Pos logit contributions
 Vert+0.400
 depos+0.386
antam+0.383
 premiere+0.360
sterdam+0.352
Neg logit contributions
isine-0.419
tical-0.417
alty-0.416
vious-0.368
itiz-0.364
Token)
Token ID8
Feature activation+5.43e-02

Pos logit contributions
 Vert+1.905
 depos+1.837
antam+1.803
 premiere+1.688
sterdam+1.642
Neg logit contributions
isine-2.531
tical-2.526
alty-2.518
vious-2.251
itiz-2.237
Token
Token ID198
Feature activation-2.42e-01

Pos logit contributions
 Vert+0.043
 depos+0.042
antam+0.041
 premiere+0.039
sterdam+0.038
Neg logit contributions
isine-0.043
tical-0.043
alty-0.043
vious-0.038
itiz-0.038
Token
Token ID198
Feature activation-3.43e-01

Pos logit contributions
isine+0.194
tical+0.192
alty+0.192
vious+0.169
itiz+0.168
Neg logit contributions
 Vert-0.192
 depos-0.184
antam-0.183
 premiere-0.172
sterdam-0.167
TokenFinding
Token ID36276
Feature activation+5.24e-01

Pos logit contributions
isine+0.227
tical+0.226
alty+0.225
vious+0.193
itiz+0.191
Neg logit contributions
 Vert-0.318
 depos-0.309
antam-0.307
 premiere-0.291
sterdam-0.287
Token an
Token ID281
Feature activation-1.31e+00

Pos logit contributions
 Vert+0.360
 depos+0.345
antam+0.341
 premiere+0.318
sterdam+0.310
Neg logit contributions
isine-0.474
tical-0.474
alty-0.471
vious-0.422
itiz-0.419
TokenWhat
Token ID2061
Feature activation+9.75e-01

Pos logit contributions
 Vert+0.484
 depos+0.468
antam+0.465
 premiere+0.438
sterdam+0.432
Neg logit contributions
isine-0.426
tical-0.426
alty-0.425
vious-0.371
itiz-0.367
Token if
Token ID611
Feature activation+2.86e-01

Pos logit contributions
 Vert+0.736
 depos+0.709
antam+0.702
 premiere+0.658
sterdam+0.645
Neg logit contributions
isine-0.813
alty-0.811
tical-0.810
vious-0.717
itiz-0.712
Token you
Token ID345
Feature activation+1.49e-01

Pos logit contributions
 Vert+0.214
 depos+0.206
antam+0.205
 premiere+0.192
sterdam+0.188
Neg logit contributions
isine-0.240
tical-0.239
alty-0.239
vious-0.212
itiz-0.210
Token have
Token ID423
Feature activation+8.83e-01

Pos logit contributions
 Vert+0.116
 depos+0.112
antam+0.111
 premiere+0.104
sterdam+0.102
Neg logit contributions
isine-0.121
tical-0.121
alty-0.121
vious-0.107
itiz-0.106
Token digital
Token ID4875
Feature activation+1.19e+00

Pos logit contributions
 Vert+0.599
 depos+0.574
antam+0.568
 premiere+0.528
sterdam+0.515
Neg logit contributions
isine-0.807
alty-0.805
tical-0.803
vious-0.719
itiz-0.713
Token copies
Token ID9088
Feature activation+2.87e+00

Pos logit contributions
 Vert+0.745
 depos+0.713
antam+0.706
 premiere+0.651
sterdam+0.637
Neg logit contributions
isine-1.141
tical-1.138
alty-1.137
vious-1.024
itiz-1.017
Token of
Token ID286
Feature activation+1.15e-01

Pos logit contributions
 Vert+2.101
 depos+2.037
antam+1.985
 premiere+1.870
sterdam+1.823
Neg logit contributions
isine-2.470
alty-2.459
tical-2.438
vious-2.178
itiz-2.161
Token books
Token ID3835
Feature activation+1.79e+00

Pos logit contributions
 Vert+0.076
 depos+0.073
antam+0.072
 premiere+0.067
sterdam+0.066
Neg logit contributions
tical-0.107
isine-0.106
alty-0.106
vious-0.095
itiz-0.094
Token that
Token ID326
Feature activation-3.22e-01

Pos logit contributions
 Vert+1.218
 depos+1.174
antam+1.151
 premiere+1.077
sterdam+1.052
Neg logit contributions
alty-1.619
isine-1.617
tical-1.606
vious-1.444
itiz-1.432
Token you
Token ID345
Feature activation-1.76e-01

Pos logit contributions
isine+0.270
tical+0.270
alty+0.269
vious+0.239
itiz+0.237
Neg logit contributions
 Vert-0.241
 depos-0.232
antam-0.231
 premiere-0.215
sterdam-0.212
Token want
Token ID765
Feature activation+1.98e+00

Pos logit contributions
isine+0.144
tical+0.144
alty+0.143
vious+0.127
itiz+0.126
Neg logit contributions
 Vert-0.136
 depos-0.131
antam-0.130
 premiere-0.122
sterdam-0.120
Token trip
Token ID5296
Feature activation-5.45e-01

Pos logit contributions
 Vert+0.162
 depos+0.156
antam+0.153
 premiere+0.143
sterdam+0.140
Neg logit contributions
isine-0.214
tical-0.214
alty-0.213
vious-0.191
itiz-0.189
Token matters
Token ID6067
Feature activation+1.35e+00

Pos logit contributions
isine+0.445
tical+0.444
alty+0.444
vious+0.392
itiz+0.389
Neg logit contributions
 Vert-0.421
 depos-0.405
antam-0.404
 premiere-0.377
sterdam-0.371
Token,
Token ID11
Feature activation+8.36e-02

Pos logit contributions
 Vert+0.916
 depos+0.880
antam+0.867
 premiere+0.811
sterdam+0.790
Neg logit contributions
isine-1.227
alty-1.220
tical-1.216
vious-1.094
itiz-1.083
Token too
Token ID1165
Feature activation+1.39e-01

Pos logit contributions
 Vert+0.059
 depos+0.057
antam+0.056
 premiere+0.053
sterdam+0.051
Neg logit contributions
isine-0.074
tical-0.074
alty-0.073
vious-0.066
itiz-0.065
Token.
Token ID13
Feature activation+5.07e-01

Pos logit contributions
 Vert+0.093
 depos+0.089
antam+0.088
 premiere+0.082
sterdam+0.080
Neg logit contributions
isine-0.128
alty-0.128
tical-0.128
vious-0.115
itiz-0.114
Token Most
Token ID4042
Feature activation+4.44e-01

Pos logit contributions
 Vert+0.395
 depos+0.375
antam+0.371
 premiere+0.350
sterdam+0.341
Neg logit contributions
isine-0.419
tical-0.414
alty-0.414
vious-0.366
itiz-0.365
Token tourists
Token ID15930
Feature activation-8.98e-01

Pos logit contributions
 Vert+0.324
 depos+0.312
antam+0.307
 premiere+0.289
sterdam+0.282
Neg logit contributions
isine-0.384
tical-0.383
alty-0.381
vious-0.338
itiz-0.337
Token are
Token ID389
Feature activation+4.05e-01

Pos logit contributions
alty+0.798
isine+0.797
tical+0.797
vious+0.712
itiz+0.705
Neg logit contributions
 Vert-0.628
 depos-0.600
antam-0.598
 premiere-0.553
sterdam-0.546
Token really
Token ID1107
Feature activation-8.94e-01

Pos logit contributions
 Vert+0.302
 depos+0.291
antam+0.288
 premiere+0.270
sterdam+0.265
Neg logit contributions
isine-0.341
tical-0.340
alty-0.339
vious-0.301
itiz-0.299
Token ready
Token ID3492
Feature activation+1.93e+00

Pos logit contributions
isine+0.713
tical+0.713
alty+0.713
vious+0.627
itiz+0.622
Neg logit contributions
 Vert-0.703
 depos-0.676
antam-0.676
 premiere-0.631
sterdam-0.622
Token to
Token ID284
Feature activation+2.28e-01

Pos logit contributions
 Vert+1.326
 depos+1.281
antam+1.261
 premiere+1.182
sterdam+1.155
Neg logit contributions
isine-1.737
alty-1.723
tical-1.723
vious-1.549
itiz-1.537
Token people
Token ID661
Feature activation+2.81e-01

Pos logit contributions
 Vert+0.663
 depos+0.638
antam+0.629
 premiere+0.591
sterdam+0.575
Neg logit contributions
isine-0.798
tical-0.793
alty-0.791
vious-0.707
itiz-0.698
Token and
Token ID290
Feature activation-2.44e-01

Pos logit contributions
 Vert+0.189
 depos+0.182
antam+0.180
 premiere+0.168
sterdam+0.164
Neg logit contributions
isine-0.256
alty-0.255
tical-0.254
vious-0.229
itiz-0.226
Token never
Token ID1239
Feature activation-1.02e+00

Pos logit contributions
isine+0.211
tical+0.210
alty+0.210
vious+0.187
itiz+0.185
Neg logit contributions
 Vert-0.178
 depos-0.171
antam-0.169
 premiere-0.158
sterdam-0.155
Token condesc
Token ID41466
Feature activation+4.26e-01

Pos logit contributions
isine+0.852
tical+0.848
alty+0.847
vious+0.751
itiz+0.744
Neg logit contributions
 Vert-0.763
 depos-0.735
antam-0.728
 premiere-0.682
sterdam-0.670
Tokenends
Token ID2412
Feature activation+5.32e-01

Pos logit contributions
 Vert+0.311
antam+0.299
 depos+0.298
 premiere+0.277
sterdam+0.272
Neg logit contributions
isine-0.363
tical-0.363
alty-0.361
vious-0.319
itiz-0.314
Token to
Token ID284
Feature activation+3.12e-01

Pos logit contributions
 Vert+0.357
 depos+0.343
antam+0.339
 premiere+0.315
sterdam+0.306
Neg logit contributions
isine-0.489
tical-0.485
alty-0.485
vious-0.435
itiz-0.431
Token them
Token ID606
Feature activation+8.57e-01

Pos logit contributions
 Vert+0.244
 depos+0.235
antam+0.232
 premiere+0.219
sterdam+0.214
Neg logit contributions
isine-0.252
tical-0.251
alty-0.251
vious-0.220
itiz-0.219
Token,
Token ID11
Feature activation-3.13e-01

Pos logit contributions
 Vert+0.562
 depos+0.541
antam+0.532
 premiere+0.496
sterdam+0.483
Neg logit contributions
isine-0.795
alty-0.792
tical-0.789
vious-0.713
itiz-0.708
Token evidenced
Token ID30204
Feature activation-2.07e-02

Pos logit contributions
isine+0.274
tical+0.273
alty+0.272
vious+0.243
itiz+0.240
Neg logit contributions
 Vert-0.225
 depos-0.217
antam-0.214
 premiere-0.200
sterdam-0.196
Token by
Token ID416
Feature activation+6.00e-01

Pos logit contributions
isine+0.021
tical+0.021
alty+0.021
vious+0.019
itiz+0.018
Neg logit contributions
 Vert-0.012
 depos-0.012
antam-0.012
 premiere-0.011
sterdam-0.010
Token the
Token ID262
Feature activation-7.61e-02

Pos logit contributions
 Vert+0.408
 depos+0.392
antam+0.384
 premiere+0.361
sterdam+0.350
Neg logit contributions
isine-0.547
tical-0.547
alty-0.546
vious-0.487
itiz-0.484
Token(
Token ID7
Feature activation+1.43e+00

Pos logit contributions
 Vert+0.360
 depos+0.346
antam+0.345
 premiere+0.320
sterdam+0.313
Neg logit contributions
isine-0.451
tical-0.450
alty-0.449
vious-0.400
itiz-0.398
TokenSN
Token ID15571
Feature activation+2.50e+00

Pos logit contributions
 Vert+1.385
antam+1.334
 depos+1.328
 premiere+1.262
sterdam+1.233
Neg logit contributions
isine-0.906
tical-0.893
alty-0.893
itiz-0.749
vious-0.748
TokenES
Token ID1546
Feature activation-9.41e-01

Pos logit contributions
 Vert+1.844
antam+1.762
 depos+1.746
 premiere+1.626
sterdam+1.588
Neg logit contributions
isine-2.156
tical-2.123
alty-2.113
vious-1.874
itiz-1.862
Token,
Token ID11
Feature activation-6.98e-01

Pos logit contributions
isine+0.865
tical+0.864
alty+0.862
vious+0.773
itiz+0.768
Neg logit contributions
 Vert-0.627
 depos-0.602
antam-0.597
 premiere-0.553
sterdam-0.543
Token 1995
Token ID8735
Feature activation+1.09e+00

Pos logit contributions
isine+0.715
tical+0.714
alty+0.713
vious+0.647
itiz+0.642
Neg logit contributions
 Vert-0.394
 depos-0.374
antam-0.371
 premiere-0.338
sterdam-0.330
Token)
Token ID8
Feature activation+6.27e-01

Pos logit contributions
 Vert+0.766
 depos+0.737
antam+0.728
 premiere+0.685
sterdam+0.662
Neg logit contributions
isine-0.966
alty-0.962
tical-0.962
vious-0.857
itiz-0.850
Token
Token ID198
Feature activation-8.69e-01

Pos logit contributions
 Vert+0.493
 depos+0.470
antam+0.467
 premiere+0.440
 deb+0.427
Neg logit contributions
isine-0.509
alty-0.505
tical-0.504
vious-0.443
itiz-0.442
Token
Token ID198
Feature activation-6.77e-01

Pos logit contributions
isine+0.681
tical+0.678
alty+0.677
vious+0.594
itiz+0.590
Neg logit contributions
 Vert-0.701
 depos-0.676
antam-0.671
 premiere-0.631
sterdam-0.620
TokenBefore
Token ID8421
Feature activation-1.12e+00

Pos logit contributions
isine+0.518
tical+0.517
alty+0.517
vious+0.453
itiz+0.448
Neg logit contributions
 Vert-0.557
 depos-0.539
antam-0.535
 premiere-0.504
sterdam-0.496
Token the
Token ID262
Feature activation+9.95e-02

Pos logit contributions
isine+0.962
tical+0.962
alty+0.961
vious+0.860
itiz+0.851
Neg logit contributions
 Vert-0.798
antam-0.771
 depos-0.765
 premiere-0.711
sterdam-0.705
Token gameplay
Token ID11327
Feature activation+1.33e+00

Pos logit contributions
 Vert+0.067
 depos+0.064
antam+0.063
 premiere+0.059
sterdam+0.057
Neg logit contributions
isine-0.092
tical-0.092
alty-0.091
vious-0.082
itiz-0.081
Token confident
Token ID6563
Feature activation+1.44e+00

Pos logit contributions
 Vert+0.295
 depos+0.284
antam+0.280
 premiere+0.262
sterdam+0.257
Neg logit contributions
isine-0.365
tical-0.364
alty-0.363
vious-0.324
itiz-0.322
Token their
Token ID511
Feature activation+1.67e-01

Pos logit contributions
 Vert+0.940
 depos+0.902
antam+0.891
 premiere+0.826
sterdam+0.807
Neg logit contributions
isine-1.354
tical-1.350
alty-1.347
vious-1.211
itiz-1.202
Token failures
Token ID15536
Feature activation-8.77e-01

Pos logit contributions
 Vert+0.114
 depos+0.110
antam+0.109
 premiere+0.101
sterdam+0.099
Neg logit contributions
isine-0.151
tical-0.151
alty-0.151
vious-0.135
itiz-0.134
Token will
Token ID481
Feature activation+6.28e-01

Pos logit contributions
tical+0.749
isine+0.746
alty+0.745
vious+0.662
itiz+0.656
Neg logit contributions
 Vert-0.645
antam-0.618
 depos-0.616
 premiere-0.572
sterdam-0.567
Token be
Token ID307
Feature activation+9.66e-01

Pos logit contributions
 Vert+0.453
 depos+0.434
antam+0.434
 premiere+0.401
sterdam+0.398
Neg logit contributions
isine-0.545
tical-0.544
alty-0.543
vious-0.483
itiz-0.478
Token shifted
Token ID14869
Feature activation+2.14e+00

Pos logit contributions
 Vert+0.715
 depos+0.688
antam+0.681
 premiere+0.637
sterdam+0.625
Neg logit contributions
isine-0.820
tical-0.818
alty-0.816
vious-0.725
itiz-0.720
Token to
Token ID284
Feature activation+5.77e-01

Pos logit contributions
 Vert+1.495
 depos+1.437
antam+1.416
 premiere+1.321
sterdam+1.287
Neg logit contributions
isine-1.913
tical-1.906
alty-1.905
vious-1.705
itiz-1.690
Token the
Token ID262
Feature activation+2.26e-01

Pos logit contributions
 Vert+0.385
 depos+0.369
antam+0.366
 premiere+0.339
sterdam+0.333
Neg logit contributions
isine-0.531
tical-0.530
alty-0.529
vious-0.475
itiz-0.471
Token American
Token ID1605
Feature activation-7.89e-02

Pos logit contributions
 Vert+0.164
 depos+0.158
antam+0.155
 premiere+0.145
sterdam+0.142
Neg logit contributions
isine-0.197
tical-0.196
alty-0.195
vious-0.174
itiz-0.172
Token people
Token ID661
Feature activation+4.45e-01

Pos logit contributions
isine+0.064
tical+0.064
alty+0.063
vious+0.056
itiz+0.056
Neg logit contributions
 Vert-0.062
 depos-0.060
antam-0.059
 premiere-0.055
sterdam-0.054
Token again
Token ID757
Feature activation+1.79e-01

Pos logit contributions
 Vert+0.303
 depos+0.291
antam+0.287
 premiere+0.268
sterdam+0.262
Neg logit contributions
isine-0.404
tical-0.403
alty-0.402
vious-0.361
itiz-0.358
Tokenong
Token ID506
Feature activation-2.05e-01

Pos logit contributions
 Vert+0.105
 depos+0.101
antam+0.100
 premiere+0.093
sterdam+0.091
Neg logit contributions
isine-0.139
tical-0.139
alty-0.139
vious-0.124
itiz-0.123
Token Stadium
Token ID10499
Feature activation+2.51e-01

Pos logit contributions
isine+0.182
tical+0.181
alty+0.181
vious+0.161
itiz+0.160
Neg logit contributions
 Vert-0.145
 depos-0.139
antam-0.138
 premiere-0.129
sterdam-0.126
Token,
Token ID11
Feature activation-1.27e-01

Pos logit contributions
 Vert+0.173
 depos+0.166
antam+0.164
 premiere+0.153
sterdam+0.149
Neg logit contributions
isine-0.226
tical-0.225
alty-0.224
vious-0.201
itiz-0.200
Token and
Token ID290
Feature activation+3.24e-01

Pos logit contributions
isine+0.116
tical+0.116
alty+0.116
vious+0.104
itiz+0.103
Neg logit contributions
 Vert-0.086
 depos-0.083
antam-0.082
 premiere-0.076
sterdam-0.074
Token forced
Token ID4137
Feature activation+1.90e-03

Pos logit contributions
 Vert+0.222
 depos+0.212
antam+0.212
 premiere+0.196
sterdam+0.193
Neg logit contributions
isine-0.293
tical-0.293
alty-0.292
vious-0.261
itiz-0.260
Token to
Token ID284
Feature activation+4.38e-01

Pos logit contributions
 Vert+0.001
 depos+0.001
antam+0.001
 premiere+0.001
sterdam+0.001
Neg logit contributions
isine-0.002
tical-0.002
alty-0.002
vious-0.002
itiz-0.001
Token watch
Token ID2342
Feature activation+1.87e+00

Pos logit contributions
 Vert+0.281
 depos+0.269
antam+0.267
 premiere+0.246
sterdam+0.242
Neg logit contributions
isine-0.415
tical-0.414
alty-0.413
vious-0.372
itiz-0.369
Token eight
Token ID3624
Feature activation-4.27e-01

Pos logit contributions
 Vert+1.232
 depos+1.183
antam+1.158
 premiere+1.087
sterdam+1.055
Neg logit contributions
isine-1.738
alty-1.735
tical-1.733
vious-1.556
itiz-1.544
Token people
Token ID661
Feature activation-2.81e-01

Pos logit contributions
isine+0.351
tical+0.350
alty+0.350
vious+0.309
itiz+0.307
Neg logit contributions
 Vert-0.326
antam-0.314
 depos-0.314
 premiere-0.291
sterdam-0.288
Token,
Token ID11
Feature activation+3.85e-02

Pos logit contributions
isine+0.283
tical+0.282
alty+0.281
vious+0.255
itiz+0.253
Neg logit contributions
 Vert-0.164
 depos-0.156
antam-0.155
 premiere-0.142
sterdam-0.138
Token who
Token ID508
Feature activation+2.06e-01

Pos logit contributions
 Vert+0.028
 depos+0.027
antam+0.026
 premiere+0.025
sterdam+0.024
Neg logit contributions
isine-0.034
tical-0.033
alty-0.033
vious-0.030
itiz-0.030
Token General
Token ID3611
Feature activation+2.35e+00

Pos logit contributions
 Vert+1.027
 depos+0.986
antam+0.978
 premiere+0.910
sterdam+0.890
Neg logit contributions
isine-1.321
tical-1.320
alty-1.315
vious-1.176
itiz-1.166
Token Manager
Token ID9142
Feature activation-8.65e-01

Pos logit contributions
 Vert+1.400
 depos+1.324
antam+1.303
 premiere+1.201
sterdam+1.157
Neg logit contributions
tical-2.328
isine-2.328
alty-2.324
vious-2.097
itiz-2.082
Token,
Token ID11
Feature activation-7.28e-01

Pos logit contributions
isine+0.779
tical+0.777
alty+0.776
vious+0.694
itiz+0.689
Neg logit contributions
 Vert-0.595
 depos-0.571
antam-0.566
 premiere-0.526
sterdam-0.516
Token making
Token ID1642
Feature activation-8.18e-01

Pos logit contributions
isine+0.649
tical+0.648
alty+0.647
vious+0.578
itiz+0.573
Neg logit contributions
 Vert-0.507
 depos-0.486
antam-0.483
 premiere-0.449
sterdam-0.441
Token this
Token ID428
Feature activation-3.80e-01

Pos logit contributions
isine+0.704
tical+0.703
alty+0.701
vious+0.624
itiz+0.619
Neg logit contributions
 Vert-0.596
 depos-0.574
antam-0.569
 premiere-0.531
sterdam-0.521
Token a
Token ID257
Feature activation-4.90e-01

Pos logit contributions
isine+0.346
tical+0.345
alty+0.344
vious+0.308
itiz+0.306
Neg logit contributions
 Vert-0.258
 depos-0.247
antam-0.245
 premiere-0.229
sterdam-0.222
Token significant
Token ID2383
Feature activation-1.29e+00

Pos logit contributions
isine+0.439
tical+0.439
alty+0.438
vious+0.391
itiz+0.389
Neg logit contributions
 Vert-0.338
 depos-0.325
antam-0.322
 premiere-0.299
sterdam-0.294
Token transitional
Token ID35577
Feature activation+6.54e-01

Pos logit contributions
isine+1.184
tical+1.183
alty+1.182
vious+1.059
itiz+1.053
Neg logit contributions
 Vert-0.865
 depos-0.830
antam-0.826
 premiere-0.760
sterdam-0.754
Token summer
Token ID3931
Feature activation-4.88e-01

Pos logit contributions
 Vert+0.405
 depos+0.388
antam+0.382
 premiere+0.356
sterdam+0.342
Neg logit contributions
isine-0.638
tical-0.636
alty-0.633
vious-0.571
itiz-0.566
Token for
Token ID329
Feature activation-1.71e-01

Pos logit contributions
isine+0.411
tical+0.410
alty+0.409
vious+0.362
itiz+0.360
Neg logit contributions
 Vert-0.365
 depos-0.352
antam-0.349
 premiere-0.327
sterdam-0.320
Token the
Token ID262
Feature activation-5.06e-01

Pos logit contributions
isine+0.156
tical+0.156
alty+0.155
vious+0.139
itiz+0.138
Neg logit contributions
 Vert-0.116
 depos-0.111
antam-0.110
 premiere-0.103
sterdam-0.100
TokenIf
Token ID1532
Feature activation+5.66e-01

Pos logit contributions
isine+0.301
tical+0.300
alty+0.299
vious+0.262
itiz+0.260
Neg logit contributions
 Vert-0.318
 depos-0.307
antam-0.304
 premiere-0.286
sterdam-0.281
Token your
Token ID534
Feature activation-1.00e+00

Pos logit contributions
 Vert+0.427
 depos+0.412
antam+0.406
 premiere+0.381
sterdam+0.372
Neg logit contributions
isine-0.476
alty-0.472
tical-0.470
vious-0.416
itiz-0.415
Token vote
Token ID3015
Feature activation+5.64e-02

Pos logit contributions
isine+0.875
tical+0.872
alty+0.870
vious+0.775
itiz+0.770
Neg logit contributions
 Vert-0.721
 depos-0.694
antam-0.687
 premiere-0.642
sterdam-0.627
Token was
Token ID373
Feature activation-2.15e-01

Pos logit contributions
 Vert+0.046
 depos+0.044
antam+0.044
 premiere+0.041
sterdam+0.041
Neg logit contributions
isine-0.044
tical-0.044
alty-0.044
vious-0.038
itiz-0.038
Token from
Token ID422
Feature activation+2.60e-02

Pos logit contributions
isine+0.184
tical+0.182
alty+0.181
vious+0.161
itiz+0.160
Neg logit contributions
 Vert-0.160
 depos-0.154
antam-0.152
 premiere-0.143
sterdam-0.140
Token another
Token ID1194
Feature activation-3.96e-01

Pos logit contributions
 Vert+0.017
 depos+0.017
antam+0.017
 premiere+0.015
sterdam+0.015
Neg logit contributions
isine-0.024
tical-0.024
alty-0.024
vious-0.021
itiz-0.021
Token show
Token ID905
Feature activation-6.56e-01

Pos logit contributions
isine+0.375
tical+0.374
alty+0.374
vious+0.336
itiz+0.334
Neg logit contributions
 Vert-0.255
 depos-0.244
antam-0.242
 premiere-0.224
sterdam-0.218
Token,
Token ID11
Feature activation+8.61e-03

Pos logit contributions
isine+0.599
tical+0.596
alty+0.595
vious+0.532
itiz+0.529
Neg logit contributions
 Vert-0.446
 depos-0.428
antam-0.422
 premiere-0.396
sterdam-0.385
Token or
Token ID393
Feature activation-1.16e+00

Pos logit contributions
 Vert+0.006
 depos+0.006
antam+0.006
 premiere+0.006
sterdam+0.006
Neg logit contributions
isine-0.007
tical-0.007
alty-0.007
vious-0.006
itiz-0.006
Token other
Token ID584
Feature activation-1.69e+00

Pos logit contributions
isine+1.027
tical+1.023
alty+1.021
vious+0.910
itiz+0.904
Neg logit contributions
 Vert-0.822
 depos-0.790
antam-0.781
 premiere-0.731
sterdam-0.712
Token medium
Token ID7090
Feature activation-4.11e-01

Pos logit contributions
tical+1.501
isine+1.500
alty+1.496
vious+1.339
itiz+1.329
Neg logit contributions
 Vert-1.175
antam-1.128
 depos-1.128
 premiere-1.038
sterdam-1.031
Tokenx
Token ID87
Feature activation-1.82e-01

Pos logit contributions
isine+1.108
tical+1.107
alty+1.105
vious+0.971
itiz+0.956
Neg logit contributions
 Vert-1.153
 depos-1.120
antam-1.117
 premiere-1.044
sterdam-1.031
Token8
Token ID23
Feature activation-8.79e-01

Pos logit contributions
isine+0.139
tical+0.139
alty+0.139
vious+0.121
itiz+0.120
Neg logit contributions
 Vert-0.151
 depos-0.146
antam-0.145
 premiere-0.136
sterdam-0.134
Token90
Token ID3829
Feature activation-2.39e-01

Pos logit contributions
isine+0.712
tical+0.710
alty+0.709
vious+0.628
itiz+0.619
Neg logit contributions
 Vert-0.682
 depos-0.658
antam-0.656
 premiere-0.613
sterdam-0.605
Tokence
Token ID344
Feature activation-1.35e+00

Pos logit contributions
isine+0.199
tical+0.198
alty+0.198
vious+0.175
itiz+0.174
Neg logit contributions
 Vert-0.181
 depos-0.174
antam-0.173
 premiere-0.162
sterdam-0.159
Tokenc
Token ID66
Feature activation-1.41e+00

Pos logit contributions
isine+1.044
tical+1.041
alty+1.040
vious+0.916
itiz+0.901
Neg logit contributions
 Vert-1.099
 depos-1.064
antam-1.059
 premiere-0.993
sterdam-0.982
Token83
Token ID5999
Feature activation-1.36e+00

Pos logit contributions
isine+1.076
tical+1.072
alty+1.071
vious+0.941
itiz+0.927
Neg logit contributions
 Vert-1.160
 depos-1.123
antam-1.118
 premiere-1.049
sterdam-1.037
Token
Token ID198
Feature activation-5.93e-01

Pos logit contributions
isine+1.161
tical+1.160
alty+1.159
vious+1.033
itiz+1.020
Neg logit contributions
 Vert-0.988
 depos-0.953
antam-0.950
 premiere-0.882
sterdam-0.869
Token
Token ID198
Feature activation-8.16e-01

Pos logit contributions
isine+0.469
tical+0.466
alty+0.465
vious+0.409
itiz+0.406
Neg logit contributions
 Vert-0.476
 depos-0.457
antam-0.454
 premiere-0.427
sterdam-0.419
TokenBecause
Token ID8128
Feature activation-1.03e+00

Pos logit contributions
isine+0.615
tical+0.615
alty+0.614
vious+0.537
itiz+0.531
Neg logit contributions
 Vert-0.680
 depos-0.658
antam-0.653
 premiere-0.616
sterdam-0.606
Token system
Token ID1080
Feature activation+4.97e-01

Pos logit contributions
isine+0.921
tical+0.920
alty+0.919
vious+0.821
itiz+0.815
Neg logit contributions
 Vert-0.713
 depos-0.685
antam-0.682
 premiere-0.632
sterdam-0.621
Token()
Token ID3419
Feature activation-6.88e-01

Pos logit contributions
 Vert+0.412
 depos+0.399
antam+0.395
 premiere+0.373
sterdam+0.367
Neg logit contributions
isine-0.378
tical-0.377
alty-0.375
vious-0.328
itiz-0.325
Token restriction
Token ID17504
Feature activation+2.89e-01

Pos logit contributions
tical+0.567
isine+0.567
alty+0.566
vious+0.503
itiz+0.499
Neg logit contributions
 Vert-0.484
 depos-0.466
antam-0.463
 premiere-0.432
sterdam-0.425
Token of
Token ID286
Feature activation-1.17e+00

Pos logit contributions
 Vert+0.209
 depos+0.201
antam+0.199
 premiere+0.186
sterdam+0.182
Neg logit contributions
isine-0.251
tical-0.250
alty-0.250
vious-0.223
itiz-0.221
Token the
Token ID262
Feature activation-4.70e-01

Pos logit contributions
tical+1.034
isine+1.032
alty+1.031
vious+0.921
itiz+0.915
Neg logit contributions
 Vert-0.824
 depos-0.791
antam-0.790
 premiere-0.732
sterdam-0.723
Token Token
Token ID29130
Feature activation-5.43e-01

Pos logit contributions
tical+0.410
isine+0.408
alty+0.408
vious+0.364
itiz+0.361
Neg logit contributions
 Vert-0.335
 depos-0.323
antam-0.322
 premiere-0.298
sterdam-0.295
Token since
Token ID1201
Feature activation+1.26e-01

Pos logit contributions
isine+0.484
alty+0.484
tical+0.484
vious+0.432
itiz+0.429
Neg logit contributions
 Vert-0.377
 depos-0.361
antam-0.360
 premiere-0.334
sterdam-0.329
Token you
Token ID345
Feature activation+1.13e-03

Pos logit contributions
 Vert+0.092
 depos+0.089
antam+0.088
 premiere+0.082
sterdam+0.081
Neg logit contributions
isine-0.108
tical-0.107
alty-0.107
vious-0.095
itiz-0.095
Token
Token ID447
Feature activation+2.95e-01

Pos logit contributions
 Vert+0.001
 depos+0.001
antam+0.001
 premiere+0.001
sterdam+0.001
Neg logit contributions
isine-0.001
tical-0.001
alty-0.001
vious-0.001
itiz-0.001
Token
Token ID247
Feature activation-3.63e-01

Pos logit contributions
 Vert+0.306
 depos+0.298
antam+0.296
 premiere+0.283
sterdam+0.279
Neg logit contributions
isine-0.162
tical-0.162
alty-0.162
vious-0.134
itiz-0.132
Tokenll
Token ID297
Feature activation+6.76e-01

Pos logit contributions
tical+0.258
isine+0.258
alty+0.258
vious+0.223
itiz+0.221
Neg logit contributions
 Vert-0.319
 depos-0.309
antam-0.307
 premiere-0.289
sterdam-0.286
Token primarily
Token ID7525
Feature activation+6.52e-01

Pos logit contributions
 Vert+0.489
 depos+0.470
antam+0.466
 premiere+0.436
sterdam+0.425
Neg logit contributions
isine-0.586
tical-0.584
alty-0.583
vious-0.520
itiz-0.515
Token be
Token ID307
Feature activation-3.24e-01

Pos logit contributions
 Vert+0.431
 depos+0.412
antam+0.407
 premiere+0.379
sterdam+0.367
Neg logit contributions
isine-0.608
tical-0.605
alty-0.604
vious-0.544
itiz-0.539
Token policy
Token ID2450
Feature activation-2.58e+00

Pos logit contributions
 Vert+0.297
 depos+0.286
antam+0.284
 premiere+0.265
sterdam+0.261
Neg logit contributions
isine-0.337
tical-0.337
alty-0.336
vious-0.299
itiz-0.296
Token for
Token ID329
Feature activation-5.41e-01

Pos logit contributions
tical+2.254
alty+2.238
isine+2.238
vious+1.995
itiz+1.988
Neg logit contributions
 Vert-1.829
antam-1.761
 depos-1.751
sterdam-1.621
 premiere-1.607
Token Candidate
Token ID40327
Feature activation-3.03e-01

Pos logit contributions
isine+0.484
tical+0.484
alty+0.483
vious+0.432
itiz+0.429
Neg logit contributions
 Vert-0.374
 depos-0.359
antam-0.357
 premiere-0.330
sterdam-0.326
Token Trump
Token ID1301
Feature activation-1.01e+00

Pos logit contributions
isine+0.235
tical+0.234
alty+0.234
vious+0.205
itiz+0.203
Neg logit contributions
 Vert-0.247
 depos-0.239
antam-0.237
 premiere-0.223
sterdam-0.219
Token than
Token ID621
Feature activation+5.54e-01

Pos logit contributions
isine+0.881
tical+0.880
alty+0.879
vious+0.783
itiz+0.777
Neg logit contributions
 Vert-0.723
 depos-0.694
antam-0.690
 premiere-0.642
sterdam-0.631
Token Clinton
Token ID2605
Feature activation-1.00e-01

Pos logit contributions
 Vert+0.398
 depos+0.382
antam+0.379
 premiere+0.353
sterdam+0.343
Neg logit contributions
isine-0.484
tical-0.482
alty-0.481
vious-0.429
itiz-0.426
Token.
Token ID13
Feature activation-1.74e-02

Pos logit contributions
isine+0.080
tical+0.080
alty+0.080
vious+0.071
itiz+0.070
Neg logit contributions
 Vert-0.078
 depos-0.076
antam-0.075
 premiere-0.070
sterdam-0.069
Token He
Token ID679
Feature activation-4.86e-01

Pos logit contributions
isine+0.014
alty+0.014
tical+0.014
vious+0.012
itiz+0.012
Neg logit contributions
 Vert-0.014
 depos-0.013
antam-0.013
 premiere-0.012
sterdam-0.012
Token isn
Token ID2125
Feature activation-3.99e-01

Pos logit contributions
isine+0.390
tical+0.389
alty+0.388
vious+0.342
itiz+0.340
Neg logit contributions
 Vert-0.382
 depos-0.368
antam-0.366
 premiere-0.343
sterdam-0.337
Token
Token ID447
Feature activation-7.67e-02

Pos logit contributions
isine+0.314
tical+0.312
alty+0.311
vious+0.273
itiz+0.271
Neg logit contributions
 Vert-0.321
 depos-0.309
antam-0.308
 premiere-0.289
sterdam-0.284
Token
Token ID247
Feature activation+1.04e-01

Pos logit contributions
tical+0.042
isine+0.042
alty+0.042
vious+0.035
itiz+0.034
Neg logit contributions
 Vert-0.079
 depos-0.077
antam-0.077
 premiere-0.073
sterdam-0.072
Token.
Token ID13
Feature activation-5.84e-01

Pos logit contributions
 Vert+0.204
 depos+0.197
antam+0.194
 premiere+0.181
sterdam+0.177
Neg logit contributions
isine-0.262
tical-0.261
alty-0.260
vious-0.232
itiz-0.231
Token
Token ID198
Feature activation-1.25e+00

Pos logit contributions
isine+0.478
tical+0.472
alty+0.471
itiz+0.416
vious+0.415
Neg logit contributions
 Vert-0.459
 depos-0.435
antam-0.433
 premiere-0.408
sterdam-0.395
Token
Token ID198
Feature activation-1.21e+00

Pos logit contributions
isine+0.966
tical+0.965
alty+0.963
vious+0.845
itiz+0.837
Neg logit contributions
 Vert-1.014
 depos-0.981
antam-0.974
 premiere-0.915
sterdam-0.902
Token"
Token ID1
Feature activation-2.28e-01

Pos logit contributions
isine+0.965
tical+0.964
alty+0.964
vious+0.850
itiz+0.839
Neg logit contributions
 Vert-0.964
 depos-0.933
antam-0.923
 premiere-0.868
sterdam-0.856
TokenI
Token ID40
Feature activation+3.98e-01

Pos logit contributions
isine+0.165
tical+0.163
alty+0.163
vious+0.141
itiz+0.140
Neg logit contributions
 Vert-0.198
 depos-0.190
antam-0.190
 premiere-0.179
sterdam-0.176
Token've
Token ID1053
Feature activation-2.58e+00

Pos logit contributions
 Vert+0.317
 depos+0.307
antam+0.303
 premiere+0.289
 deb+0.279
Neg logit contributions
isine-0.316
tical-0.314
alty-0.313
vious-0.274
itiz-0.274
Token had
Token ID550
Feature activation-2.28e-02

Pos logit contributions
alty+2.056
isine+2.055
tical+2.053
vious+1.813
itiz+1.793
Neg logit contributions
 Vert-2.028
 depos-1.953
antam-1.953
 premiere-1.815
sterdam-1.803
Token a
Token ID257
Feature activation-2.50e-01

Pos logit contributions
isine+0.021
tical+0.021
alty+0.021
vious+0.019
itiz+0.019
Neg logit contributions
 Vert-0.015
 depos-0.015
antam-0.014
 premiere-0.013
sterdam-0.013
Token lot
Token ID1256
Feature activation-1.35e+00

Pos logit contributions
isine+0.211
tical+0.211
alty+0.210
vious+0.186
itiz+0.184
Neg logit contributions
 Vert-0.188
 depos-0.181
antam-0.178
 premiere-0.168
sterdam-0.164
Token going
Token ID1016
Feature activation-1.13e+00

Pos logit contributions
isine+1.116
tical+1.114
alty+1.111
vious+0.983
itiz+0.974
Neg logit contributions
 Vert-1.032
 depos-0.996
antam-0.987
 premiere-0.926
sterdam-0.908
Token on
Token ID319
Feature activation-2.23e-01

Pos logit contributions
isine+0.977
tical+0.976
alty+0.973
vious+0.867
itiz+0.861
Neg logit contributions
 Vert-0.816
 depos-0.784
antam-0.779
 premiere-0.725
sterdam-0.713
Token D
Token ID360
Feature activation+1.22e+00

Pos logit contributions
isine+0.917
tical+0.915
alty+0.913
vious+0.818
itiz+0.810
Neg logit contributions
 Vert-0.709
 depos-0.684
antam-0.678
 premiere-0.627
sterdam-0.620
TokenY
Token ID56
Feature activation+2.25e+00

Pos logit contributions
 Vert+1.059
antam+1.012
 depos+1.007
 premiere+0.959
sterdam+0.933
Neg logit contributions
isine-0.885
tical-0.879
alty-0.879
vious-0.760
itiz-0.753
TokenAR
Token ID1503
Feature activation+7.18e-01

Pos logit contributions
 Vert+1.727
antam+1.629
 depos+1.627
 premiere+1.532
 deb+1.475
Neg logit contributions
isine-1.862
tical-1.851
alty-1.831
itiz-1.634
vious-1.629
Token (
Token ID357
Feature activation+4.24e-01

Pos logit contributions
 Vert+0.499
 depos+0.476
antam+0.472
 premiere+0.445
sterdam+0.430
Neg logit contributions
isine-0.641
tical-0.640
alty-0.637
vious-0.569
itiz-0.567
Tokentotal
Token ID23350
Feature activation-7.54e-01

Pos logit contributions
 Vert+0.354
 depos+0.342
antam+0.340
 premiere+0.321
sterdam+0.315
Neg logit contributions
isine-0.320
tical-0.318
alty-0.317
vious-0.276
itiz-0.274
Token value
Token ID1988
Feature activation-2.62e+00

Pos logit contributions
isine+0.635
tical+0.634
alty+0.633
vious+0.563
itiz+0.557
Neg logit contributions
 Vert-0.561
 depos-0.542
antam-0.538
 premiere-0.501
sterdam-0.494
Token at
Token ID379
Feature activation+5.13e-03

Pos logit contributions
tical+2.222
isine+2.221
alty+2.219
vious+1.978
itiz+1.953
Neg logit contributions
 Vert-1.925
 depos-1.861
antam-1.846
 premiere-1.715
sterdam-1.694
Token his
Token ID465
Feature activation-6.41e-02

Pos logit contributions
 Vert+0.004
 depos+0.004
antam+0.004
 premiere+0.003
sterdam+0.003
Neg logit contributions
isine-0.004
tical-0.004
alty-0.004
vious-0.004
itiz-0.004
Token position
Token ID2292
Feature activation+1.94e+00

Pos logit contributions
isine+0.064
alty+0.064
tical+0.064
vious+0.058
itiz+0.057
Neg logit contributions
 Vert-0.038
 depos-0.036
antam-0.036
 premiere-0.033
sterdam-0.032
Token),
Token ID828
Feature activation-4.20e-01

Pos logit contributions
 Vert+1.337
 depos+1.279
antam+1.261
 premiere+1.188
 deb+1.148
Neg logit contributions
isine-1.738
tical-1.733
alty-1.726
vious-1.539
atsuki-1.530
Token third
Token ID2368
Feature activation-6.74e-01

Pos logit contributions
isine+0.367
tical+0.366
alty+0.366
vious+0.326
itiz+0.324
Neg logit contributions
 Vert-0.299
 depos-0.288
antam-0.286
 premiere-0.266
sterdam-0.261
Token and
Token ID290
Feature activation+8.01e-01

Pos logit contributions
 Vert+0.749
 depos+0.721
antam+0.709
 premiere+0.663
sterdam+0.646
Neg logit contributions
isine-1.056
alty-1.049
tical-1.049
vious-0.940
itiz-0.932
Token reboot
Token ID20149
Feature activation+8.97e-01

Pos logit contributions
 Vert+0.497
 depos+0.475
antam+0.468
 premiere+0.434
sterdam+0.422
Neg logit contributions
isine-0.778
tical-0.775
alty-0.773
vious-0.698
itiz-0.693
Token endlessly
Token ID33903
Feature activation+3.52e-01

Pos logit contributions
 Vert+0.621
 depos+0.598
antam+0.587
 premiere+0.549
sterdam+0.537
Neg logit contributions
isine-0.809
tical-0.803
alty-0.802
vious-0.717
itiz-0.710
Token.
Token ID13
Feature activation-1.28e-01

Pos logit contributions
 Vert+0.241
 depos+0.232
antam+0.228
 premiere+0.213
sterdam+0.208
Neg logit contributions
isine-0.320
tical-0.318
alty-0.318
vious-0.284
itiz-0.283
Token That
Token ID1320
Feature activation-5.01e-01

Pos logit contributions
isine+0.103
tical+0.102
alty+0.102
vious+0.090
itiz+0.089
Neg logit contributions
 Vert-0.102
 depos-0.098
antam-0.097
 premiere-0.092
sterdam-0.090
Token means
Token ID1724
Feature activation-2.32e+00

Pos logit contributions
isine+0.414
tical+0.412
alty+0.411
vious+0.364
itiz+0.361
Neg logit contributions
 Vert-0.384
 depos-0.370
antam-0.366
 premiere-0.344
sterdam-0.337
Token that
Token ID326
Feature activation+5.84e-01

Pos logit contributions
tical+2.044
alty+2.029
isine+2.024
vious+1.822
itiz+1.803
Neg logit contributions
 Vert-1.621
antam-1.570
 depos-1.551
 premiere-1.443
sterdam-1.428
Token if
Token ID611
Feature activation+3.87e-01

Pos logit contributions
 Vert+0.419
 depos+0.403
antam+0.397
 premiere+0.372
sterdam+0.363
Neg logit contributions
isine-0.513
alty-0.509
tical-0.509
vious-0.453
itiz-0.450
Token Odin
Token ID19758
Feature activation+9.50e-01

Pos logit contributions
 Vert+0.284
 depos+0.273
antam+0.270
 premiere+0.253
sterdam+0.248
Neg logit contributions
isine-0.333
tical-0.331
alty-0.331
vious-0.294
itiz-0.292
Token fails
Token ID10143
Feature activation-2.25e-01

Pos logit contributions
 Vert+0.700
 depos+0.675
antam+0.668
 premiere+0.625
sterdam+0.613
Neg logit contributions
isine-0.811
tical-0.808
alty-0.804
vious-0.714
itiz-0.709
Token after
Token ID706
Feature activation+1.23e+00

Pos logit contributions
isine+0.208
tical+0.206
alty+0.206
vious+0.185
itiz+0.183
Neg logit contributions
 Vert-0.151
 depos-0.145
antam-0.143
 premiere-0.133
sterdam-0.130
Token friend
Token ID1545
Feature activation-2.66e+00

Pos logit contributions
isine+0.418
tical+0.417
alty+0.417
vious+0.371
itiz+0.368
Neg logit contributions
 Vert-0.349
 depos-0.335
antam-0.333
 premiere-0.310
sterdam-0.305
Token start
Token ID923
Feature activation-1.39e+00

Pos logit contributions
isine+2.448
alty+2.447
tical+2.439
vious+2.195
itiz+2.169
Neg logit contributions
 Vert-1.734
antam-1.683
 depos-1.663
sterdam-1.528
 premiere-1.528
Token running
Token ID2491
Feature activation-1.74e+00

Pos logit contributions
isine+1.216
tical+1.214
alty+1.211
vious+1.084
itiz+1.072
Neg logit contributions
 Vert-0.988
antam-0.946
 depos-0.944
 premiere-0.878
sterdam-0.864
Token again
Token ID757
Feature activation-9.33e-01

Pos logit contributions
tical+1.535
isine+1.530
alty+1.529
vious+1.367
itiz+1.351
Neg logit contributions
 Vert-1.222
antam-1.175
 depos-1.172
 premiere-1.084
sterdam-1.072
Token.
Token ID13
Feature activation-1.17e+00

Pos logit contributions
isine+0.843
tical+0.843
alty+0.840
vious+0.754
itiz+0.747
Neg logit contributions
 Vert-0.638
 depos-0.611
antam-0.608
 premiere-0.564
sterdam-0.553
Token Part
Token ID2142
Feature activation-3.03e+00

Pos logit contributions
isine+0.936
tical+0.934
alty+0.932
vious+0.822
itiz+0.814
Neg logit contributions
 Vert-0.924
 depos-0.892
antam-0.886
 premiere-0.831
sterdam-0.818
Token Four
Token ID6675
Feature activation+1.10e+00

Pos logit contributions
tical+2.503
isine+2.499
alty+2.477
vious+2.222
itiz+2.192
Neg logit contributions
 Vert-2.287
 depos-2.203
antam-2.193
 premiere-2.043
sterdam-2.023
Token General
Token ID3611
Feature activation+2.22e+00

Pos logit contributions
 Vert+0.782
 depos+0.748
antam+0.742
 premiere+0.694
sterdam+0.676
Neg logit contributions
isine-0.962
alty-0.959
tical-0.959
vious-0.853
itiz-0.850
Token Medical
Token ID8366
Feature activation-1.00e-01

Pos logit contributions
 Vert+1.664
 depos+1.589
antam+1.557
 premiere+1.476
 deb+1.436
Neg logit contributions
isine-1.857
tical-1.848
alty-1.846
vious-1.647
itiz-1.626
Token Station
Token ID9327
Feature activation-6.80e-01

Pos logit contributions
isine+0.086
tical+0.085
alty+0.085
vious+0.076
itiz+0.075
Neg logit contributions
 Vert-0.073
 depos-0.070
antam-0.070
 premiere-0.065
sterdam-0.064
Token,
Token ID11
Feature activation-1.55e+00

Pos logit contributions
isine+0.593
tical+0.592
alty+0.592
vious+0.527
itiz+0.523
Neg logit contributions
 Vert-0.486
 depos-0.467
antam-0.464
 premiere-0.432
sterdam-0.425
Token |
Token ID930
Feature activation-2.31e+00

Pos logit contributions
 Vert+0.925
 depos+0.887
antam+0.877
 premiere+0.824
sterdam+0.806
Neg logit contributions
isine-1.081
tical-1.076
alty-1.072
vious-0.950
itiz-0.949
Token [
Token ID685
Feature activation-1.72e+00

Pos logit contributions
alty+2.086
tical+2.082
isine+2.080
vious+1.871
itiz+1.845
Neg logit contributions
 Vert-1.567
antam-1.507
 depos-1.506
 premiere-1.390
sterdam-1.367
Tokenreturn
Token ID7783
Feature activation+2.30e-02

Pos logit contributions
alty+1.538
tical+1.536
isine+1.535
vious+1.383
itiz+1.356
Neg logit contributions
 Vert-1.189
 depos-1.142
antam-1.139
 premiere-1.055
sterdam-1.033
Token address
Token ID2209
Feature activation+6.50e-01

Pos logit contributions
 Vert+0.016
 depos+0.015
antam+0.015
 premiere+0.014
sterdam+0.014
Neg logit contributions
isine-0.021
tical-0.021
alty-0.020
vious-0.018
itiz-0.018
Token]
Token ID60
Feature activation-1.26e+00

Pos logit contributions
 Vert+0.508
 depos+0.488
antam+0.482
 premiere+0.454
sterdam+0.448
Neg logit contributions
isine-0.529
tical-0.526
alty-0.523
vious-0.462
itiz-0.460
Token |
Token ID930
Feature activation-2.67e+00

Pos logit contributions
isine+1.098
tical+1.097
alty+1.095
vious+0.977
itiz+0.967
Neg logit contributions
 Vert-0.905
 depos-0.871
antam-0.865
 premiere-0.804
sterdam-0.790
Token +
Token ID1343
Feature activation-1.17e-01

Pos logit contributions
alty+2.256
tical+2.253
isine+2.253
vious+2.012
itiz+1.976
Neg logit contributions
 Vert-1.949
antam-1.886
 depos-1.886
 premiere-1.744
sterdam-1.719
Token--------------------
Token ID19351
Feature activation+1.16e+00

Pos logit contributions
isine+0.137
alty+0.137
tical+0.136
vious+0.126
itiz+0.125
Neg logit contributions
 Vert-0.050
 depos-0.047
antam-0.046
 premiere-0.041
sterdam-0.039
Token--+
Token ID44785
Feature activation+1.22e+00

Pos logit contributions
 Vert+0.961
antam+0.930
 depos+0.930
 premiere+0.874
sterdam+0.850
Neg logit contributions
isine-0.884
tical-0.877
alty-0.873
itiz-0.763
vious-0.761
Token +
Token ID1343
Feature activation-2.88e-01

Pos logit contributions
 Vert+0.910
 depos+0.870
antam+0.861
 premiere+0.811
sterdam+0.792
Neg logit contributions
isine-1.041
tical-1.037
alty-1.034
itiz-0.915
vious-0.914
Token--------------------
Token ID19351
Feature activation+1.21e+00

Pos logit contributions
isine+0.334
alty+0.334
tical+0.334
vious+0.307
itiz+0.304
Neg logit contributions
 Vert-0.123
 depos-0.116
antam-0.113
 premiere-0.100
sterdam-0.097