TOP ACTIVATIONS
MAX = 1.547

perform pharmac ological and elect roph ys iological procedures . This
been made . On one hand , the film was turning
Guidelines . On the one hand , a generous tower separation
5 , 6 }, { 5 , 7 }} }, ...
2012 United States 5 667 Posts # 12 I 'm glad
MON TON Omar Kh adr has agreed to remain in
the Rab id Pupp ies slate . Essentially , the Rab
2011 United States 228 65 Posts # 13 On September 20
June 2009 Germany 247 34 Posts # 20 Nice , happy
moral decay of a des ens itized culture , he becomes
guys . You made your point . He s
he should be serving his sentence in Canada as a youth
agger ty consider setting a bail hearing based on these
Se venth Season : David vs . G oliath TBA TBA
make this compilation worthless , though , as the short missions
it makes it all toler able .
4 , 7 }, { 5 , 6 }, { 5
READ MORE : Omar Kh adr should be transferred to provincial
N PH : Dec ad ent . AV
2010 United States 6 83 Posts Last Edited : 2013 -

MIN ACTIVATIONS
MIN = -1.392

has been reluctant to take up progressive issues . Jones said
Stephen East on PA 1 hour ago I think a simple
ere f for Own ed < T > { type Target
f Mut for Own ed < T > { ... }
A respected think tank said in a report on
ulate D ensity Grid ( Uniform Grid < float > &
decide shortly whether to take up this judicial ethics ( and
some pilot who had taken off with his wings folded in
) told The Nat - ional that For cade ll
J AB arry Maryland 1 hour ago This election was not
T Pick Peter Syracuse 1 hour ago What the white working
year of ind ep - end ence or not will be
aire Sud h ir Ch oud h rie has been welcomed
, police Chief Frank Stra ub Jr . said .
> D ere f for Shared < ' a , T
him that the aircraft taking off had his wings folded .
should not fear the Bl oc Qué b é co is
set dir = c \ :\ tmp : */ This sets
last weekend . Michael Sch um acher 's Mercedes was third
Fasc is m of th e Potato 1

INTERVAL 0.812 - 1.547
CONTAINS 0.203%

is spending money there , though . It 's investing in
I fur row my eyebrows at the intruder . "
to save the Def erred Action for Childhood Arri vals (
hours before it makes it all toler able .
| 15 46 | | 6 | org . cl ojure

INTERVAL 0.078 - 0.812
CONTAINS 36.955%

atively sharing 1 , 024 times more content than they currently
is difficult . The last such event , in early 1996
this here . The guys are right . It all starts
uses a new hyper visor called Nit ro . Nit ro
series version using the radio buttons , entering a " w

INTERVAL -0.657 - 0.078
CONTAINS 62.073%

to the national conversation and ' stand up for our proud
s willingness to disregard Haiti s interests for its
Meg arian school : only the multiple is affirmative , where
Eve said in last week s episode , Ann
is les , this time to throw away the

INTERVAL -1.392 - -0.657
CONTAINS 0.769%

questions in the chat ( when I remembered to look up
but it could be a source of new technologies and industries
Google Scholar Park er , A . K .
creamy : For those of you who don
aps - Black President - Gay Intern Adam Pt 1 -
Token perform
Token ID1620
Feature activation-4.54e-01

Pos logit contributions
iren+0.706
erker+0.650
oter+0.650
 Miko+0.639
 carbohyd+0.637
Neg logit contributions
 Arbit-0.822
papers-0.708
gallery-0.708
OLOG-0.699
 Pret-0.689
Token pharmac
Token ID25702
Feature activation+3.79e-01

Pos logit contributions
iren+1.838
erker+1.712
oter+1.697
 carbohyd+1.687
 Miko+1.681
Neg logit contributions
 Arbit-1.819
gallery-1.543
papers-1.539
OLOG-1.521
 Pret-1.494
Tokenological
Token ID2770
Feature activation+1.58e-01

Pos logit contributions
 Arbit+1.052
OLOG+0.839
papers+0.830
gallery+0.810
 Pret+0.807
Neg logit contributions
iren-1.962
 carbohyd-1.890
erker-1.881
 Miko-1.873
oter-1.835
Token and
Token ID290
Feature activation-1.76e-01

Pos logit contributions
 Arbit+0.668
papers+0.567
gallery+0.565
 Pret+0.559
OLOG+0.559
Neg logit contributions
iren-0.608
erker-0.565
 carbohyd-0.559
oter-0.559
 Miko-0.553
Token elect
Token ID1742
Feature activation+4.60e-01

Pos logit contributions
iren+0.770
erker+0.718
oter+0.714
 carbohyd+0.711
 Miko+0.707
Neg logit contributions
 Arbit-0.654
papers-0.547
gallery-0.547
OLOG-0.535
 Pret-0.531
Tokenroph
Token ID10051
Feature activation+1.55e+00

Pos logit contributions
 Arbit+1.787
papers+1.515
OLOG+1.510
gallery+1.510
 Pret+1.488
Neg logit contributions
iren-1.874
 carbohyd-1.767
erker-1.757
 Miko-1.749
oter-1.737
Tokenys
Token ID893
Feature activation+1.11e+00

Pos logit contributions
 Arbit+5.670
OLOG+4.776
papers+4.736
 Pret+4.637
gallery+4.580
Neg logit contributions
iren-6.163
 carbohyd-6.046
 Miko-6.023
erker-5.865
 nodd-5.786
Tokeniological
Token ID15071
Feature activation+7.67e-01

Pos logit contributions
 Arbit+2.591
OLOG+1.989
papers+1.922
gallery+1.879
 Pret+1.872
Neg logit contributions
iren-5.988
 carbohyd-5.960
erker-5.787
urous-5.783
 Miko-5.781
Token procedures
Token ID9021
Feature activation-1.47e-02

Pos logit contributions
 Arbit+3.253
 Pret+2.745
papers+2.733
OLOG+2.688
gallery+2.683
Neg logit contributions
iren-2.962
erker-2.761
 carbohyd-2.740
oter-2.703
urous-2.694
Token.
Token ID13
Feature activation+3.74e-01

Pos logit contributions
iren+0.062
erker+0.058
oter+0.057
 carbohyd+0.057
 Miko+0.057
Neg logit contributions
 Arbit-0.057
papers-0.048
gallery-0.048
OLOG-0.047
 Pret-0.047
Token This
Token ID770
Feature activation+2.48e-01

Pos logit contributions
 Arbit+1.486
papers+1.248
gallery+1.243
 Pret+1.229
OLOG+1.229
Neg logit contributions
iren-1.541
erker-1.438
 carbohyd-1.429
oter-1.423
urous-1.406
Token been
Token ID587
Feature activation+4.95e-01

Pos logit contributions
 Arbit+1.882
papers+1.596
gallery+1.596
OLOG+1.588
 Pret+1.582
Neg logit contributions
iren-1.687
 carbohyd-1.577
erker-1.549
oter-1.530
urious-1.522
Token made
Token ID925
Feature activation+2.20e-01

Pos logit contributions
 Arbit+1.974
gallery+1.634
papers+1.625
 Pret+1.623
OLOG+1.606
Neg logit contributions
iren-2.048
 carbohyd-1.925
erker-1.896
oter-1.895
urious-1.873
Token.
Token ID13
Feature activation+1.21e-01

Pos logit contributions
 Arbit+0.856
papers+0.717
gallery+0.715
OLOG+0.705
 Pret+0.702
Neg logit contributions
iren-0.924
erker-0.863
oter-0.855
 carbohyd-0.855
 Miko-0.847
Token On
Token ID1550
Feature activation-1.88e-01

Pos logit contributions
 Arbit+0.489
papers+0.417
gallery+0.415
OLOG+0.410
 Pret+0.404
Neg logit contributions
iren-0.487
erker-0.453
 Miko-0.450
oter-0.449
ander-0.445
Token one
Token ID530
Feature activation+1.44e-01

Pos logit contributions
iren+0.827
erker+0.774
oter+0.769
 Miko+0.764
 carbohyd+0.763
Neg logit contributions
 Arbit-0.691
papers-0.573
gallery-0.572
OLOG-0.565
 Pret-0.560
Token hand
Token ID1021
Feature activation+1.46e+00

Pos logit contributions
 Arbit+0.620
papers+0.523
gallery+0.519
 Pret+0.518
OLOG+0.517
Neg logit contributions
iren-0.547
 carbohyd-0.508
erker-0.507
oter-0.500
 Miko-0.496
Token,
Token ID11
Feature activation+4.16e-01

Pos logit contributions
 Arbit+5.279
 Pret+4.170
papers+4.115
OLOG+4.103
 Halo+4.063
Neg logit contributions
iren-6.372
 carbohyd-6.191
erker-5.963
idi-5.787
urious-5.733
Token the
Token ID262
Feature activation+9.97e-02

Pos logit contributions
 Arbit+1.624
gallery+1.338
papers+1.333
 Pret+1.329
OLOG+1.317
Neg logit contributions
iren-1.762
 carbohyd-1.652
erker-1.643
oter-1.614
urous-1.597
Token film
Token ID2646
Feature activation-5.12e-01

Pos logit contributions
 Arbit+0.392
papers+0.328
gallery+0.326
 Pret+0.323
OLOG+0.322
Neg logit contributions
iren-0.416
erker-0.388
 carbohyd-0.387
oter-0.384
 Miko-0.381
Token was
Token ID373
Feature activation-2.29e-01

Pos logit contributions
iren+2.141
erker+2.010
oter+1.993
 Miko+1.975
 carbohyd+1.967
Neg logit contributions
 Arbit-1.984
papers-1.666
gallery-1.657
OLOG-1.639
 Pret-1.622
Token turning
Token ID6225
Feature activation+6.65e-02

Pos logit contributions
iren+0.904
erker+0.841
oter+0.833
 carbohyd+0.829
 Miko+0.827
Neg logit contributions
 Arbit-0.941
papers-0.800
gallery-0.798
OLOG-0.788
 Pret-0.783
Token Guidelines
Token ID31072
Feature activation+2.87e-01

Pos logit contributions
 Arbit+1.830
papers+1.505
 Pret+1.477
gallery+1.466
OLOG+1.449
Neg logit contributions
iren-2.228
erker-2.114
 carbohyd-2.110
oter-2.065
urious-2.052
Token.
Token ID13
Feature activation+4.01e-01

Pos logit contributions
 Arbit+1.125
papers+0.941
gallery+0.934
 Pret+0.921
OLOG+0.920
Neg logit contributions
iren-1.200
erker-1.128
 carbohyd-1.121
oter-1.112
urous-1.102
Token On
Token ID1550
Feature activation+1.94e-02

Pos logit contributions
 Arbit+1.566
gallery+1.298
papers+1.294
 Pret+1.291
OLOG+1.273
Neg logit contributions
iren-1.703
 carbohyd-1.611
erker-1.596
oter-1.573
urous-1.554
Token the
Token ID262
Feature activation+1.47e-01

Pos logit contributions
 Arbit+0.077
papers+0.065
gallery+0.064
 Pret+0.064
OLOG+0.063
Neg logit contributions
iren-0.080
erker-0.075
 carbohyd-0.075
oter-0.074
 Miko-0.073
Token one
Token ID530
Feature activation+4.21e-01

Pos logit contributions
 Arbit+0.584
gallery+0.490
papers+0.490
 Pret+0.483
OLOG+0.482
Neg logit contributions
iren-0.607
erker-0.566
 carbohyd-0.562
oter-0.560
 Miko-0.554
Token hand
Token ID1021
Feature activation+1.43e+00

Pos logit contributions
 Arbit+1.755
papers+1.456
 Pret+1.447
OLOG+1.438
gallery+1.429
Neg logit contributions
iren-1.658
erker-1.559
 carbohyd-1.548
 Miko-1.523
oter-1.517
Token,
Token ID11
Feature activation+4.25e-01

Pos logit contributions
 Arbit+4.787
 Pret+3.887
papers+3.775
gallery+3.727
OLOG+3.723
Neg logit contributions
iren-6.404
erker-5.987
 carbohyd-5.901
 Miko-5.817
idi-5.801
Token a
Token ID257
Feature activation+1.81e-01

Pos logit contributions
 Arbit+1.596
 Pret+1.321
gallery+1.318
papers+1.317
OLOG+1.288
Neg logit contributions
iren-1.845
erker-1.725
 carbohyd-1.719
oter-1.689
urous-1.678
Token generous
Token ID14431
Feature activation+1.07e-01

Pos logit contributions
 Arbit+0.730
gallery+0.615
papers+0.613
 Pret+0.607
OLOG+0.603
Neg logit contributions
iren-0.735
erker-0.687
 carbohyd-0.683
oter-0.679
 Miko-0.671
Token tower
Token ID10580
Feature activation-9.74e-02

Pos logit contributions
 Arbit+0.379
gallery+0.311
papers+0.311
 Pret+0.306
OLOG+0.304
Neg logit contributions
iren-0.486
erker-0.458
 carbohyd-0.455
oter-0.453
urous-0.448
Token separation
Token ID14139
Feature activation+1.79e-01

Pos logit contributions
iren+0.391
erker+0.363
oter+0.361
 Miko+0.359
 carbohyd+0.358
Neg logit contributions
 Arbit-0.395
papers-0.333
gallery-0.333
OLOG-0.331
 Pret-0.326
Token5
Token ID20
Feature activation+1.26e+00

Pos logit contributions
 Arbit+1.103
gallery+0.957
papers+0.947
 Pret+0.932
OLOG+0.928
Neg logit contributions
iren-0.928
 carbohyd-0.875
erker-0.864
 Miko-0.853
urous-0.845
Token,
Token ID11
Feature activation+1.39e-03

Pos logit contributions
 Arbit+4.921
gallery+4.131
papers+4.118
 Pret+4.030
OLOG+4.011
Neg logit contributions
iren-5.266
 carbohyd-5.219
 nodd-4.942
erker-4.929
oter-4.861
Token 6
Token ID718
Feature activation+4.94e-01

Pos logit contributions
 Arbit+0.005
gallery+0.004
papers+0.004
OLOG+0.003
 Pret+0.003
Neg logit contributions
iren-0.007
erker-0.006
 carbohyd-0.006
oter-0.006
urous-0.006
Token},
Token ID5512
Feature activation-2.13e-02

Pos logit contributions
 Arbit+1.802
papers+1.486
gallery+1.481
 Pret+1.464
OLOG+1.441
Neg logit contributions
iren-2.185
 carbohyd-2.071
erker-2.058
urous-2.021
oter-2.016
Token {
Token ID1391
Feature activation+3.23e-01

Pos logit contributions
iren+0.066
erker+0.061
 carbohyd+0.060
oter+0.060
urous+0.059
Neg logit contributions
 Arbit-0.107
papers-0.092
gallery-0.092
 Pret-0.092
OLOG-0.091
Token5
Token ID20
Feature activation+1.37e+00

Pos logit contributions
 Arbit+1.438
gallery+1.256
papers+1.241
 Pret+1.216
OLOG+1.215
Neg logit contributions
iren-1.161
 carbohyd-1.110
erker-1.088
 Miko-1.060
urous-1.056
Token,
Token ID11
Feature activation+1.17e-01

Pos logit contributions
 Arbit+5.250
gallery+4.408
papers+4.381
 Pret+4.289
OLOG+4.258
Neg logit contributions
 carbohyd-5.808
iren-5.765
 nodd-5.507
erker-5.426
oter-5.322
Token 7
Token ID767
Feature activation+3.77e-01

Pos logit contributions
 Arbit+0.371
gallery+0.292
papers+0.291
 Pret+0.287
OLOG+0.286
Neg logit contributions
iren-0.579
 carbohyd-0.555
erker-0.552
oter-0.543
urous-0.541
Token}}
Token ID11709
Feature activation+2.63e-01

Pos logit contributions
 Arbit+1.356
papers+1.120
gallery+1.102
 Pret+1.093
OLOG+1.088
Neg logit contributions
iren-1.695
erker-1.596
 carbohyd-1.591
oter-1.569
urous-1.565
Token},
Token ID5512
Feature activation+5.62e-02

Pos logit contributions
 Arbit+0.966
papers+0.789
OLOG+0.782
 Pret+0.781
gallery+0.778
Neg logit contributions
iren-1.163
erker-1.095
 carbohyd-1.090
urous-1.080
oter-1.075
Token...
Token ID2644
Feature activation+3.35e-02

Pos logit contributions
 Arbit+0.259
gallery+0.220
papers+0.219
 Pret+0.219
OLOG+0.217
Neg logit contributions
iren-0.199
erker-0.185
oter-0.181
urous-0.181
 carbohyd-0.180
Token 2012
Token ID2321
Feature activation+4.74e-01

Pos logit contributions
 Arbit+1.258
papers+1.058
gallery+1.050
OLOG+1.041
 Pret+1.016
Neg logit contributions
iren-1.553
erker-1.451
 Miko-1.445
oter-1.443
ander-1.429
Token United
Token ID1578
Feature activation+3.06e-01

Pos logit contributions
 Arbit+1.707
 Pret+1.386
gallery+1.367
papers+1.366
OLOG+1.344
Neg logit contributions
iren-2.161
 carbohyd-2.070
erker-2.024
oter-2.006
urious-1.988
Token States
Token ID1829
Feature activation+5.08e-01

Pos logit contributions
 Arbit+1.137
 Pret+0.922
papers+0.921
OLOG+0.899
gallery+0.898
Neg logit contributions
iren-1.371
erker-1.269
oter-1.267
 carbohyd-1.263
urious-1.262
Token 5
Token ID642
Feature activation+7.96e-01

Pos logit contributions
 Arbit+1.757
gallery+1.419
papers+1.417
 Pret+1.407
OLOG+1.394
Neg logit contributions
iren-2.365
 carbohyd-2.255
erker-2.228
oter-2.208
urous-2.186
Token667
Token ID28933
Feature activation-2.19e-01

Pos logit contributions
 Arbit+2.990
papers+2.473
gallery+2.456
 Pret+2.449
OLOG+2.415
Neg logit contributions
iren-3.450
 carbohyd-3.364
erker-3.251
oter-3.192
urious-3.151
Token Posts
Token ID12043
Feature activation+1.36e+00

Pos logit contributions
iren+0.770
 Miko+0.738
ander+0.717
oter+0.709
urous+0.704
Neg logit contributions
 Arbit-0.939
gallery-0.827
papers-0.827
OLOG-0.827
 Pret-0.783
Token #
Token ID1303
Feature activation+9.37e-01

Pos logit contributions
 Arbit+3.967
 Pret+3.043
papers+2.891
 Halo+2.873
gallery+2.835
Neg logit contributions
iren-6.908
 carbohyd-6.513
oter-6.457
erker-6.442
urous-6.351
Token12
Token ID1065
Feature activation+7.23e-01

Pos logit contributions
 Arbit+3.660
gallery+3.136
papers+3.085
 Pret+2.971
OLOG+2.947
Neg logit contributions
iren-3.914
 carbohyd-3.868
erker-3.691
 nodd-3.687
oter-3.603
Token I
Token ID314
Feature activation+3.93e-01

Pos logit contributions
 Arbit+2.882
 Pret+2.377
gallery+2.358
papers+2.344
 Cyan+2.296
Neg logit contributions
iren-2.992
 carbohyd-2.841
erker-2.798
oter-2.764
urious-2.711
Token'm
Token ID1101
Feature activation+1.67e-01

Pos logit contributions
 Arbit+1.557
gallery+1.296
papers+1.291
 Pret+1.280
OLOG+1.278
Neg logit contributions
iren-1.629
erker-1.524
 carbohyd-1.522
oter-1.497
urous-1.491
Token glad
Token ID9675
Feature activation+1.75e-02

Pos logit contributions
 Arbit+0.733
gallery+0.624
papers+0.623
 Pret+0.615
OLOG+0.614
Neg logit contributions
iren-0.623
erker-0.577
 carbohyd-0.573
oter-0.569
urous-0.562
TokenMON
Token ID27857
Feature activation+2.62e-01

Pos logit contributions
 Arbit+0.247
papers+0.203
gallery+0.202
OLOG+0.200
 Pret+0.198
Neg logit contributions
iren-0.322
erker-0.302
 carbohyd-0.300
oter-0.300
 Miko-0.297
TokenTON
Token ID11357
Feature activation+3.67e-01

Pos logit contributions
 Arbit+0.638
gallery+0.482
papers+0.481
OLOG+0.459
 Pret+0.456
Neg logit contributions
iren-1.472
erker-1.392
oter-1.391
 carbohyd-1.385
ander-1.379
Token
Token ID784
Feature activation+1.49e-01

Pos logit contributions
 Arbit+1.275
OLOG+1.028
gallery+1.026
papers+1.022
 Pret+1.014
Neg logit contributions
iren-1.694
erker-1.613
 carbohyd-1.611
oter-1.590
urous-1.574
Token Omar
Token ID24980
Feature activation-1.97e-01

Pos logit contributions
 Arbit+0.576
gallery+0.474
papers+0.473
 Pret+0.472
OLOG+0.469
Neg logit contributions
iren-0.636
 carbohyd-0.599
erker-0.596
oter-0.587
urous-0.581
Token Kh
Token ID5311
Feature activation+3.20e-01

Pos logit contributions
iren+0.879
erker+0.825
 carbohyd+0.819
oter+0.816
 Miko+0.806
Neg logit contributions
 Arbit-0.724
gallery-0.592
papers-0.590
 Pret-0.584
OLOG-0.581
Tokenadr
Token ID41909
Feature activation+1.35e+00

Pos logit contributions
 Arbit+0.894
gallery+0.691
papers+0.683
 Pret+0.662
OLOG+0.661
Neg logit contributions
iren-1.689
erker-1.612
 carbohyd-1.607
 Miko-1.588
oter-1.585
Token has
Token ID468
Feature activation+3.91e-01

Pos logit contributions
 Arbit+4.967
 Pret+4.023
papers+3.919
gallery+3.876
 ACC+3.794
Neg logit contributions
iren-5.843
 carbohyd-5.657
erker-5.583
oter-5.421
urious-5.325
Token agreed
Token ID4987
Feature activation+1.64e-01

Pos logit contributions
 Arbit+1.579
papers+1.321
gallery+1.314
 Pret+1.305
OLOG+1.297
Neg logit contributions
iren-1.585
erker-1.488
 carbohyd-1.483
oter-1.465
urious-1.448
Token to
Token ID284
Feature activation+4.92e-01

Pos logit contributions
 Arbit+0.584
papers+0.471
 Pret+0.467
OLOG+0.462
gallery+0.461
Neg logit contributions
iren-0.756
erker-0.715
 carbohyd-0.706
oter-0.700
 Miko-0.694
Token remain
Token ID3520
Feature activation+3.76e-01

Pos logit contributions
 Arbit+1.878
papers+1.545
gallery+1.540
 Pret+1.534
OLOG+1.520
Neg logit contributions
iren-2.112
erker-1.991
 carbohyd-1.973
oter-1.957
 Miko-1.942
Token in
Token ID287
Feature activation+2.14e-01

Pos logit contributions
 Arbit+1.365
papers+1.124
gallery+1.121
OLOG+1.102
 Pret+1.102
Neg logit contributions
iren-1.680
erker-1.577
 carbohyd-1.564
oter-1.561
 Miko-1.549
Token the
Token ID262
Feature activation+3.48e-01

Pos logit contributions
 Arbit+0.339
papers+0.280
 Pret+0.278
gallery+0.277
OLOG+0.274
Neg logit contributions
iren-0.377
erker-0.355
 carbohyd-0.353
urious-0.347
oter-0.347
Token Rab
Token ID28559
Feature activation-1.33e-02

Pos logit contributions
 Arbit+1.437
papers+1.207
 Pret+1.196
gallery+1.184
OLOG+1.176
Neg logit contributions
iren-1.391
erker-1.310
 carbohyd-1.298
urious-1.273
oter-1.265
Tokenid
Token ID312
Feature activation-2.71e-02

Pos logit contributions
iren+0.049
erker+0.046
 carbohyd+0.046
 Miko+0.045
urious+0.045
Neg logit contributions
 Arbit-0.058
papers-0.050
gallery-0.049
 Pret-0.049
OLOG-0.049
Token Pupp
Token ID20926
Feature activation-1.03e-02

Pos logit contributions
iren+0.147
erker+0.140
 carbohyd+0.139
oter+0.138
 Miko+0.137
Neg logit contributions
 Arbit-0.074
papers-0.055
gallery-0.054
 Pret-0.054
OLOG-0.054
Tokenies
Token ID444
Feature activation+8.76e-02

Pos logit contributions
iren+0.044
 carbohyd+0.041
erker+0.041
 Miko+0.041
oter+0.041
Neg logit contributions
 Arbit-0.039
papers-0.033
gallery-0.032
OLOG-0.032
 Pret-0.032
Token slate
Token ID27589
Feature activation+1.33e+00

Pos logit contributions
 Arbit+0.343
papers+0.286
gallery+0.283
 Pret+0.282
OLOG+0.280
Neg logit contributions
iren-0.367
erker-0.343
 carbohyd-0.342
oter-0.337
 Miko-0.337
Token.
Token ID13
Feature activation+1.91e-01

Pos logit contributions
 Arbit+4.885
papers+4.009
 Pret+3.990
gallery+3.891
OLOG+3.839
Neg logit contributions
iren-5.560
 carbohyd-5.392
erker-5.319
urious-5.251
urous-5.150
Token Essentially
Token ID34039
Feature activation-4.23e-02

Pos logit contributions
 Arbit+0.763
papers+0.636
gallery+0.635
 Pret+0.630
OLOG+0.627
Neg logit contributions
iren-0.788
 carbohyd-0.737
erker-0.737
oter-0.726
urious-0.719
Token,
Token ID11
Feature activation+2.29e-01

Pos logit contributions
iren+0.175
erker+0.164
 carbohyd+0.162
urious+0.160
oter+0.159
Neg logit contributions
 Arbit-0.170
papers-0.140
 Pret-0.140
gallery-0.140
OLOG-0.138
Token the
Token ID262
Feature activation+1.95e-01

Pos logit contributions
 Arbit+0.897
papers+0.738
 Pret+0.737
gallery+0.730
OLOG+0.722
Neg logit contributions
iren-0.972
erker-0.914
 carbohyd-0.907
urious-0.890
oter-0.888
Token Rab
Token ID28559
Feature activation+2.82e-01

Pos logit contributions
 Arbit+0.777
papers+0.647
 Pret+0.641
gallery+0.637
OLOG+0.629
Neg logit contributions
iren-0.809
erker-0.761
 carbohyd-0.754
oter-0.741
urious-0.741
Token 2011
Token ID2813
Feature activation+5.80e-01

Pos logit contributions
 Arbit+0.942
papers+0.788
gallery+0.782
OLOG+0.775
 Pret+0.759
Neg logit contributions
iren-1.172
erker-1.097
oter-1.092
 Miko-1.091
urous-1.080
Token United
Token ID1578
Feature activation+3.21e-01

Pos logit contributions
 Arbit+2.082
 Pret+1.686
gallery+1.654
papers+1.650
OLOG+1.625
Neg logit contributions
iren-2.657
 carbohyd-2.562
erker-2.490
oter-2.466
urious-2.445
Token States
Token ID1829
Feature activation+5.04e-01

Pos logit contributions
 Arbit+1.202
papers+0.976
 Pret+0.976
gallery+0.954
OLOG+0.951
Neg logit contributions
iren-1.429
oter-1.319
erker-1.319
 carbohyd-1.316
urious-1.312
Token 228
Token ID29041
Feature activation+1.00e-01

Pos logit contributions
 Arbit+1.750
gallery+1.416
papers+1.415
 Pret+1.402
OLOG+1.391
Neg logit contributions
iren-2.336
 carbohyd-2.222
erker-2.200
oter-2.179
urous-2.158
Token65
Token ID2996
Feature activation+1.07e-01

Pos logit contributions
 Arbit+0.413
papers+0.349
gallery+0.348
OLOG+0.344
 Pret+0.344
Neg logit contributions
iren-0.398
erker-0.370
 carbohyd-0.369
oter-0.366
urous-0.362
Token Posts
Token ID12043
Feature activation+1.32e+00

Pos logit contributions
 Arbit+0.456
gallery+0.398
papers+0.398
OLOG+0.396
 Pret+0.378
Neg logit contributions
iren-0.385
 Miko-0.368
ander-0.358
oter-0.355
erker-0.354
Token #
Token ID1303
Feature activation+9.45e-01

Pos logit contributions
 Arbit+3.893
 Pret+2.980
 Halo+2.820
papers+2.810
gallery+2.771
Neg logit contributions
iren-6.740
 carbohyd-6.336
oter-6.290
erker-6.281
urous-6.188
Token13
Token ID1485
Feature activation+8.65e-01

Pos logit contributions
 Arbit+3.553
gallery+3.011
papers+2.952
 Pret+2.876
OLOG+2.852
Neg logit contributions
iren-4.075
 carbohyd-4.004
 nodd-3.832
erker-3.830
oter-3.761
Token On
Token ID1550
Feature activation+4.71e-01

Pos logit contributions
 Arbit+3.448
 Pret+2.840
gallery+2.800
papers+2.785
 Cyan+2.748
Neg logit contributions
iren-3.582
 carbohyd-3.419
erker-3.357
oter-3.311
urious-3.244
Token September
Token ID2693
Feature activation+2.06e-02

Pos logit contributions
 Arbit+1.580
papers+1.265
gallery+1.264
 Pret+1.252
OLOG+1.233
Neg logit contributions
iren-2.243
 carbohyd-2.120
erker-2.118
oter-2.091
urous-2.070
Token 20
Token ID1160
Feature activation-1.32e-01

Pos logit contributions
 Arbit+0.064
papers+0.050
gallery+0.050
 Pret+0.050
OLOG+0.049
Neg logit contributions
iren-0.103
erker-0.097
 carbohyd-0.097
oter-0.097
urous-0.096
Token June
Token ID2795
Feature activation+4.97e-01

Pos logit contributions
 Arbit+0.676
papers+0.558
gallery+0.556
OLOG+0.550
 Pret+0.540
Neg logit contributions
iren-0.895
erker-0.839
oter-0.834
 Miko-0.832
urous-0.826
Token 2009
Token ID3717
Feature activation+3.43e-01

Pos logit contributions
 Arbit+1.741
papers+1.429
gallery+1.425
OLOG+1.403
 Pret+1.394
Neg logit contributions
iren-2.277
erker-2.137
oter-2.120
 carbohyd-2.116
 Miko-2.104
Token Germany
Token ID4486
Feature activation+1.78e-01

Pos logit contributions
 Arbit+1.198
 Pret+0.963
gallery+0.956
papers+0.954
OLOG+0.940
Neg logit contributions
iren-1.604
 carbohyd-1.524
erker-1.506
oter-1.490
urous-1.479
Token 247
Token ID30179
Feature activation+1.42e-01

Pos logit contributions
 Arbit+0.619
papers+0.509
gallery+0.507
OLOG+0.500
 Pret+0.495
Neg logit contributions
iren-0.816
erker-0.766
oter-0.760
 Miko-0.756
 carbohyd-0.755
Token34
Token ID2682
Feature activation-8.70e-02

Pos logit contributions
 Arbit+0.545
papers+0.454
gallery+0.453
OLOG+0.446
 Pret+0.446
Neg logit contributions
iren-0.606
erker-0.565
 carbohyd-0.564
oter-0.560
urous-0.554
Token Posts
Token ID12043
Feature activation+1.30e+00

Pos logit contributions
iren+0.303
 Miko+0.294
ander+0.284
oter+0.281
erker+0.279
Neg logit contributions
 Arbit-0.374
papers-0.331
gallery-0.329
OLOG-0.329
 Pret-0.310
Token #
Token ID1303
Feature activation+7.52e-01

Pos logit contributions
 Arbit+3.855
 Pret+2.975
papers+2.783
 Halo+2.778
gallery+2.751
Neg logit contributions
iren-6.629
 carbohyd-6.227
erker-6.206
oter-6.197
urous-6.085
Token20
Token ID1238
Feature activation+8.72e-01

Pos logit contributions
 Arbit+3.076
gallery+2.632
papers+2.614
OLOG+2.563
 Pret+2.552
Neg logit contributions
iren-3.000
 carbohyd-2.827
erker-2.802
oter-2.753
urous-2.735
Token Nice
Token ID18460
Feature activation+1.37e-01

Pos logit contributions
 Arbit+3.450
 Pret+2.817
gallery+2.802
papers+2.786
 Cyan+2.721
Neg logit contributions
iren-3.638
 carbohyd-3.459
erker-3.410
oter-3.363
urious-3.306
Token,
Token ID11
Feature activation-1.89e-02

Pos logit contributions
 Arbit+0.553
papers+0.463
gallery+0.462
 Pret+0.455
OLOG+0.453
Neg logit contributions
iren-0.558
erker-0.521
 carbohyd-0.519
oter-0.515
 Miko-0.510
Token happy
Token ID3772
Feature activation-1.22e-01

Pos logit contributions
iren+0.075
erker+0.069
 carbohyd+0.069
oter+0.069
 Miko+0.068
Neg logit contributions
 Arbit-0.079
papers-0.066
gallery-0.066
OLOG-0.065
 Pret-0.065
Token moral
Token ID6573
Feature activation+8.56e-02

Pos logit contributions
iren+0.410
erker+0.381
 carbohyd+0.378
oter+0.377
 Miko+0.374
Neg logit contributions
 Arbit-0.436
papers-0.370
gallery-0.369
OLOG-0.364
 Pret-0.364
Token decay
Token ID22119
Feature activation+7.74e-02

Pos logit contributions
 Arbit+0.357
papers+0.303
gallery+0.300
OLOG+0.299
 Pret+0.298
Neg logit contributions
iren-0.335
erker-0.315
 carbohyd-0.310
oter-0.310
 Miko-0.306
Token of
Token ID286
Feature activation-2.54e-01

Pos logit contributions
 Arbit+0.324
papers+0.275
gallery+0.273
 Pret+0.270
OLOG+0.270
Neg logit contributions
iren-0.303
erker-0.282
 carbohyd-0.281
oter-0.278
 Miko-0.274
Token a
Token ID257
Feature activation-5.06e-02

Pos logit contributions
iren+1.064
erker+0.994
 carbohyd+0.984
oter+0.984
 Miko+0.975
Neg logit contributions
 Arbit-0.988
papers-0.829
gallery-0.826
OLOG-0.815
 Pret-0.813
Token des
Token ID748
Feature activation-3.73e-02

Pos logit contributions
iren+0.209
erker+0.195
 carbohyd+0.194
oter+0.194
 Miko+0.192
Neg logit contributions
 Arbit-0.199
papers-0.167
gallery-0.167
OLOG-0.165
 Pret-0.165
Tokenens
Token ID641
Feature activation+1.29e+00

Pos logit contributions
iren+0.130
 carbohyd+0.122
 Miko+0.120
erker+0.120
oter+0.118
Neg logit contributions
 Arbit-0.170
gallery-0.147
papers-0.147
 Pret-0.145
OLOG-0.144
Tokenitized
Token ID36951
Feature activation+3.71e-01

Pos logit contributions
 Arbit+5.119
OLOG+4.377
papers+4.371
gallery+4.321
 Pret+4.224
Neg logit contributions
 carbohyd-4.790
iren-4.787
 Miko-4.466
erker-4.408
 nodd-4.396
Token culture
Token ID3968
Feature activation+4.28e-01

Pos logit contributions
 Arbit+1.519
gallery+1.280
 Pret+1.278
papers+1.267
OLOG+1.250
Neg logit contributions
iren-1.483
 carbohyd-1.390
erker-1.383
oter-1.360
urious-1.344
Token,
Token ID11
Feature activation+1.22e-02

Pos logit contributions
 Arbit+1.701
gallery+1.431
papers+1.430
 Pret+1.410
OLOG+1.400
Neg logit contributions
iren-1.757
 carbohyd-1.635
erker-1.633
oter-1.616
 Miko-1.599
Token he
Token ID339
Feature activation-2.94e-02

Pos logit contributions
 Arbit+0.050
gallery+0.042
papers+0.042
 Pret+0.041
OLOG+0.041
Neg logit contributions
iren-0.050
erker-0.046
 carbohyd-0.046
oter-0.045
urous-0.045
Token becomes
Token ID4329
Feature activation+3.33e-01

Pos logit contributions
iren+0.123
erker+0.115
 carbohyd+0.114
oter+0.113
 Miko+0.112
Neg logit contributions
 Arbit-0.115
papers-0.097
gallery-0.096
OLOG-0.095
 Pret-0.095
Token guys
Token ID3730
Feature activation-1.86e-01

Pos logit contributions
 Arbit+1.093
papers+0.915
gallery+0.913
 Pret+0.906
OLOG+0.901
Neg logit contributions
iren-1.094
erker-1.019
 carbohyd-1.014
oter-1.005
urous-0.994
Token.
Token ID13
Feature activation+3.51e-01

Pos logit contributions
iren+0.759
 carbohyd+0.711
erker+0.708
oter+0.704
 Miko+0.695
Neg logit contributions
 Arbit-0.747
papers-0.628
gallery-0.625
 Pret-0.618
OLOG-0.611
Token You
Token ID921
Feature activation+3.30e-01

Pos logit contributions
 Arbit+1.400
papers+1.176
gallery+1.174
 Pret+1.158
OLOG+1.157
Neg logit contributions
iren-1.444
erker-1.346
 carbohyd-1.340
oter-1.333
urous-1.317
Token made
Token ID925
Feature activation+6.96e-01

Pos logit contributions
 Arbit+1.261
gallery+1.048
papers+1.046
 Pret+1.039
OLOG+1.023
Neg logit contributions
iren-1.408
 carbohyd-1.323
erker-1.313
oter-1.297
urous-1.295
Token your
Token ID534
Feature activation+7.28e-01

Pos logit contributions
 Arbit+2.585
papers+2.132
 Pret+2.126
gallery+2.125
OLOG+2.091
Neg logit contributions
iren-3.053
 carbohyd-2.877
erker-2.870
oter-2.795
ander-2.772
Token point
Token ID966
Feature activation+1.29e+00

Pos logit contributions
 Arbit+3.033
papers+2.554
gallery+2.541
 Pret+2.531
OLOG+2.489
Neg logit contributions
iren-2.858
 carbohyd-2.685
erker-2.679
oter-2.634
urious-2.606
Token.
Token ID13
Feature activation+1.77e-01

Pos logit contributions
 Arbit+4.822
papers+3.946
gallery+3.912
 Pret+3.893
OLOG+3.835
Neg logit contributions
iren-5.454
 carbohyd-5.251
erker-5.112
oter-5.044
urous-4.989
Token He
Token ID679
Feature activation+1.10e-01

Pos logit contributions
 Arbit+0.710
papers+0.599
gallery+0.598
OLOG+0.590
 Pret+0.586
Neg logit contributions
iren-0.723
erker-0.672
oter-0.667
 carbohyd-0.663
 Miko-0.663
Token
Token ID447
Feature activation+1.15e-01

Pos logit contributions
 Arbit+0.432
gallery+0.364
papers+0.363
 Pret+0.357
OLOG+0.354
Neg logit contributions
iren-0.456
 carbohyd-0.431
erker-0.431
oter-0.422
urous-0.420
Token
Token ID247
Feature activation+4.10e-02

Pos logit contributions
 Arbit+0.352
gallery+0.283
papers+0.277
OLOG+0.269
 Pret+0.269
Neg logit contributions
iren-0.581
 carbohyd-0.551
oter-0.549
erker-0.546
urious-0.539
Tokens
Token ID82
Feature activation+3.54e-01

Pos logit contributions
 Arbit+0.132
gallery+0.108
papers+0.106
 Pret+0.105
OLOG+0.103
Neg logit contributions
iren-0.198
 carbohyd-0.190
erker-0.187
oter-0.187
 Miko-0.185
Token he
Token ID339
Feature activation+5.07e-01

Pos logit contributions
 Arbit+1.647
papers+1.335
 Pret+1.329
gallery+1.328
OLOG+1.314
Neg logit contributions
iren-1.934
erker-1.803
 carbohyd-1.798
oter-1.785
urous-1.765
Token should
Token ID815
Feature activation+4.34e-01

Pos logit contributions
 Arbit+1.892
papers+1.569
gallery+1.553
 Pret+1.535
OLOG+1.525
Neg logit contributions
iren-2.210
erker-2.071
 carbohyd-2.070
oter-2.039
 Miko-2.029
Token be
Token ID307
Feature activation+4.43e-01

Pos logit contributions
 Arbit+1.603
papers+1.318
gallery+1.315
 Pret+1.302
OLOG+1.285
Neg logit contributions
iren-1.893
 carbohyd-1.797
erker-1.790
oter-1.761
 Miko-1.754
Token serving
Token ID7351
Feature activation-4.15e-03

Pos logit contributions
 Arbit+1.723
papers+1.437
gallery+1.433
 Pret+1.417
OLOG+1.410
Neg logit contributions
iren-1.860
erker-1.739
 carbohyd-1.733
oter-1.718
urous-1.706
Token his
Token ID465
Feature activation+4.87e-01

Pos logit contributions
iren+0.018
erker+0.017
oter+0.016
 carbohyd+0.016
 Miko+0.016
Neg logit contributions
 Arbit-0.016
papers-0.013
gallery-0.013
OLOG-0.013
 Pret-0.013
Token sentence
Token ID6827
Feature activation+1.29e+00

Pos logit contributions
 Arbit+1.874
papers+1.548
gallery+1.538
 Pret+1.534
OLOG+1.515
Neg logit contributions
iren-2.077
erker-1.947
 carbohyd-1.941
oter-1.919
urious-1.906
Token in
Token ID287
Feature activation+4.71e-01

Pos logit contributions
 Arbit+4.708
papers+3.812
 Pret+3.800
gallery+3.735
OLOG+3.664
Neg logit contributions
iren-5.610
erker-5.377
 carbohyd-5.338
oter-5.166
urious-5.135
Token Canada
Token ID3340
Feature activation+8.68e-02

Pos logit contributions
 Arbit+1.718
gallery+1.404
 Pret+1.399
papers+1.386
OLOG+1.367
Neg logit contributions
iren-2.114
erker-1.980
 carbohyd-1.978
oter-1.962
urious-1.938
Token as
Token ID355
Feature activation+3.56e-01

Pos logit contributions
 Arbit+0.351
papers+0.298
gallery+0.297
OLOG+0.293
 Pret+0.291
Neg logit contributions
iren-0.350
erker-0.325
oter-0.323
 carbohyd-0.321
 Miko-0.320
Token a
Token ID257
Feature activation+3.74e-01

Pos logit contributions
 Arbit+1.459
papers+1.223
gallery+1.220
 Pret+1.211
OLOG+1.201
Neg logit contributions
iren-1.426
erker-1.331
 carbohyd-1.316
oter-1.314
 Miko-1.298
Token youth
Token ID6205
Feature activation-1.31e-01

Pos logit contributions
 Arbit+1.416
papers+1.170
gallery+1.165
 Pret+1.162
OLOG+1.148
Neg logit contributions
iren-1.615
erker-1.508
 carbohyd-1.500
oter-1.498
 Miko-1.478
Tokenagger
Token ID7928
Feature activation-4.87e-01

Pos logit contributions
iren+0.836
erker+0.772
 carbohyd+0.765
oter+0.764
 Miko+0.758
Neg logit contributions
 Arbit-1.045
papers-0.898
gallery-0.896
OLOG-0.886
 Pret-0.882
Tokenty
Token ID774
Feature activation+5.73e-02

Pos logit contributions
iren+2.038
erker+1.901
oter+1.884
 carbohyd+1.882
 Miko+1.868
Neg logit contributions
 Arbit-1.904
papers-1.597
gallery-1.593
OLOG-1.572
 Pret-1.564
Token consider
Token ID2074
Feature activation+1.04e-01

Pos logit contributions
 Arbit+0.231
papers+0.194
gallery+0.194
 Pret+0.191
OLOG+0.191
Neg logit contributions
iren-0.233
erker-0.217
 carbohyd-0.216
oter-0.215
 Miko-0.213
Token setting
Token ID4634
Feature activation+7.11e-02

Pos logit contributions
 Arbit+0.403
papers+0.338
gallery+0.337
OLOG+0.333
 Pret+0.330
Neg logit contributions
iren-0.435
erker-0.405
oter-0.402
 carbohyd-0.401
 Miko-0.400
Token a
Token ID257
Feature activation+2.40e-01

Pos logit contributions
 Arbit+0.246
papers+0.201
gallery+0.201
OLOG+0.198
 Pret+0.196
Neg logit contributions
iren-0.329
erker-0.309
oter-0.307
 carbohyd-0.307
 Miko-0.305
Token bail
Token ID12274
Feature activation+1.28e+00

Pos logit contributions
 Arbit+0.907
papers+0.756
gallery+0.754
OLOG+0.743
 Pret+0.739
Neg logit contributions
iren-1.038
erker-0.971
oter-0.963
 carbohyd-0.961
 Miko-0.955
Token hearing
Token ID4854
Feature activation+3.98e-01

Pos logit contributions
 Arbit+5.100
 Pret+4.135
papers+4.086
gallery+4.070
OLOG+3.991
Neg logit contributions
iren-5.126
 carbohyd-4.843
erker-4.814
 Miko-4.700
oter-4.700
Token based
Token ID1912
Feature activation+6.63e-02

Pos logit contributions
 Arbit+1.449
papers+1.195
gallery+1.186
 Pret+1.171
OLOG+1.170
Neg logit contributions
iren-1.774
erker-1.667
 carbohyd-1.653
oter-1.647
urous-1.633
Token on
Token ID319
Feature activation+5.73e-01

Pos logit contributions
 Arbit+0.254
papers+0.211
 Pret+0.207
OLOG+0.206
gallery+0.204
Neg logit contributions
iren-0.285
erker-0.269
oter-0.265
urous-0.262
 carbohyd-0.262
Token these
Token ID777
Feature activation-3.24e-03

Pos logit contributions
 Arbit+2.123
papers+1.751
 Pret+1.750
gallery+1.724
OLOG+1.711
Neg logit contributions
iren-2.516
erker-2.352
 carbohyd-2.352
oter-2.349
urous-2.314
Token
Token ID564
Feature activation-3.24e-03

Pos logit contributions
iren+0.014
erker+0.013
oter+0.013
 carbohyd+0.013
 Miko+0.013
Neg logit contributions
 Arbit-0.013
papers-0.010
gallery-0.010
OLOG-0.010
 Pret-0.010
TokenSe
Token ID4653
Feature activation-2.35e-01

Pos logit contributions
 Arbit+0.086
papers+0.070
gallery+0.070
OLOG+0.068
 Pret+0.068
Neg logit contributions
iren-0.115
erker-0.108
 carbohyd-0.108
oter-0.107
 Miko-0.107
Tokenventh
Token ID20987
Feature activation+1.86e-01

Pos logit contributions
iren+0.713
erker+0.658
 carbohyd+0.656
oter+0.645
 Miko+0.640
Neg logit contributions
 Arbit-1.179
gallery-1.033
papers-1.025
 Pret-1.018
OLOG-1.010
Token Season
Token ID7369
Feature activation+4.52e-02

Pos logit contributions
 Arbit+0.735
gallery+0.603
 Pret+0.603
papers+0.601
OLOG+0.590
Neg logit contributions
iren-0.781
 carbohyd-0.739
erker-0.729
oter-0.722
urious-0.717
Token:
Token ID25
Feature activation-2.49e-02

Pos logit contributions
 Arbit+0.183
papers+0.153
gallery+0.153
 Pret+0.153
OLOG+0.151
Neg logit contributions
iren-0.184
 carbohyd-0.173
erker-0.172
oter-0.169
urous-0.167
Token David
Token ID3271
Feature activation+4.05e-01

Pos logit contributions
iren+0.113
erker+0.106
 carbohyd+0.106
oter+0.105
urous+0.104
Neg logit contributions
 Arbit-0.089
papers-0.073
gallery-0.073
 Pret-0.072
OLOG-0.072
Token vs
Token ID3691
Feature activation+1.27e+00

Pos logit contributions
 Arbit+1.529
papers+1.273
 Pret+1.257
gallery+1.240
OLOG+1.228
Neg logit contributions
iren-1.751
 carbohyd-1.655
erker-1.646
oter-1.619
 Miko-1.612
Token.
Token ID13
Feature activation+1.90e-01

Pos logit contributions
 Arbit+4.689
 Pret+3.877
papers+3.653
 Halo+3.617
gallery+3.599
Neg logit contributions
iren-5.467
 carbohyd-5.412
urous-5.210
urious-5.138
erker-5.134
Token G
Token ID402
Feature activation-2.98e-01

Pos logit contributions
 Arbit+0.726
papers+0.601
gallery+0.601
 Pret+0.596
OLOG+0.593
Neg logit contributions
iren-0.814
erker-0.762
 carbohyd-0.759
oter-0.754
urous-0.747
Tokenoliath
Token ID43009
Feature activation+6.69e-01

Pos logit contributions
iren+1.230
erker+1.144
oter+1.134
 carbohyd+1.129
 Miko+1.123
Neg logit contributions
 Arbit-1.178
papers-0.992
gallery-0.990
OLOG-0.975
 Pret-0.971
Token TBA
Token ID48591
Feature activation+7.30e-01

Pos logit contributions
 Arbit+2.147
 Pret+1.718
papers+1.680
gallery+1.677
OLOG+1.631
Neg logit contributions
iren-3.253
 carbohyd-3.124
erker-3.084
oter-3.067
urious-3.027
Token TBA
Token ID48591
Feature activation+1.23e-01

Pos logit contributions
 Arbit+2.411
 Pret+1.938
gallery+1.893
papers+1.874
OLOG+1.859
Neg logit contributions
iren-3.514
 carbohyd-3.369
erker-3.311
oter-3.287
urious-3.258
Token make
Token ID787
Feature activation+4.66e-01

Pos logit contributions
 Arbit+0.981
papers+0.784
gallery+0.783
 Pret+0.775
OLOG+0.759
Neg logit contributions
iren-1.399
erker-1.320
 carbohyd-1.319
oter-1.308
 Miko-1.298
Token this
Token ID428
Feature activation+1.06e+00

Pos logit contributions
 Arbit+1.754
gallery+1.448
papers+1.439
 Pret+1.435
OLOG+1.407
Neg logit contributions
iren-2.029
erker-1.896
 carbohyd-1.893
oter-1.874
urious-1.857
Token compilation
Token ID23340
Feature activation+1.47e-02

Pos logit contributions
 Arbit+3.949
gallery+3.230
 Pret+3.218
papers+3.158
 Halo+3.112
Neg logit contributions
iren-4.609
 carbohyd-4.397
oter-4.269
erker-4.259
urious-4.255
Token worthless
Token ID28063
Feature activation+4.41e-01

Pos logit contributions
 Arbit+0.061
papers+0.051
gallery+0.051
 Pret+0.050
OLOG+0.050
Neg logit contributions
iren-0.059
erker-0.054
 carbohyd-0.054
oter-0.054
 Miko-0.054
Token,
Token ID11
Feature activation+4.97e-01

Pos logit contributions
 Arbit+1.712
papers+1.442
gallery+1.433
 Pret+1.402
OLOG+1.389
Neg logit contributions
iren-1.852
erker-1.725
 carbohyd-1.724
oter-1.715
 Miko-1.694
Token though
Token ID996
Feature activation+1.27e+00

Pos logit contributions
 Arbit+2.013
papers+1.677
gallery+1.672
 Pret+1.667
OLOG+1.642
Neg logit contributions
iren-2.030
 carbohyd-1.890
erker-1.885
oter-1.854
urious-1.842
Token,
Token ID11
Feature activation+6.15e-01

Pos logit contributions
 Arbit+4.498
 Pret+3.606
papers+3.599
gallery+3.562
 Halo+3.539
Neg logit contributions
iren-5.586
 carbohyd-5.418
erker-5.339
oter-5.211
urious-5.208
Token as
Token ID355
Feature activation+8.32e-01

Pos logit contributions
 Arbit+2.275
gallery+1.861
papers+1.861
 Pret+1.843
OLOG+1.821
Neg logit contributions
iren-2.698
 carbohyd-2.531
erker-2.530
oter-2.490
urious-2.479
Token the
Token ID262
Feature activation+2.04e-01

Pos logit contributions
 Arbit+3.148
gallery+2.577
 Pret+2.572
papers+2.557
OLOG+2.492
Neg logit contributions
iren-3.590
 carbohyd-3.369
erker-3.358
oter-3.297
urious-3.277
Token short
Token ID1790
Feature activation-3.30e-01

Pos logit contributions
 Arbit+0.793
papers+0.663
gallery+0.661
 Pret+0.651
OLOG+0.649
Neg logit contributions
iren-0.858
erker-0.803
 carbohyd-0.798
oter-0.795
 Miko-0.786
Token missions
Token ID10566
Feature activation-6.19e-01

Pos logit contributions
iren+1.362
erker+1.269
oter+1.258
 carbohyd+1.256
 Miko+1.247
Neg logit contributions
 Arbit-1.309
papers-1.101
gallery-1.098
OLOG-1.083
 Pret-1.078
Token
Token ID851
Feature activation-4.20e-01

Pos logit contributions
iren+1.975
erker+1.822
oter+1.811
 Miko+1.803
 carbohyd+1.799
Neg logit contributions
 Arbit-2.082
gallery-1.775
papers-1.774
OLOG-1.755
 Pret-1.726
Token it
Token ID340
Feature activation+1.76e-01

Pos logit contributions
iren+1.665
erker+1.544
oter+1.537
 Miko+1.530
 carbohyd+1.529
Neg logit contributions
 Arbit-1.716
papers-1.455
gallery-1.453
OLOG-1.439
 Pret-1.419
Token makes
Token ID1838
Feature activation+3.51e-01

Pos logit contributions
 Arbit+0.656
gallery+0.547
papers+0.543
 Pret+0.534
OLOG+0.534
Neg logit contributions
iren-0.764
erker-0.714
 carbohyd-0.712
oter-0.707
 Miko-0.702
Token it
Token ID340
Feature activation+8.37e-01

Pos logit contributions
 Arbit+1.453
gallery+1.228
papers+1.223
 Pret+1.214
OLOG+1.205
Neg logit contributions
iren-1.391
erker-1.295
 carbohyd-1.284
oter-1.271
urious-1.262
Token all
Token ID477
Feature activation+4.28e-01

Pos logit contributions
 Arbit+3.507
gallery+2.969
 Pret+2.923
papers+2.903
OLOG+2.900
Neg logit contributions
iren-3.236
 carbohyd-3.025
erker-2.961
oter-2.957
urious-2.930
Token toler
Token ID8214
Feature activation+1.27e+00

Pos logit contributions
 Arbit+1.696
gallery+1.420
papers+1.406
OLOG+1.400
 Pret+1.396
Neg logit contributions
iren-1.763
 carbohyd-1.640
erker-1.637
oter-1.617
 Miko-1.609
Tokenable
Token ID540
Feature activation+4.61e-01

Pos logit contributions
 Arbit+3.606
gallery+2.903
papers+2.829
OLOG+2.757
 Pret+2.669
Neg logit contributions
iren-6.218
 carbohyd-6.079
 Miko-5.895
erker-5.888
oter-5.787
Token.
Token ID13
Feature activation+7.11e-02

Pos logit contributions
 Arbit+1.797
gallery+1.503
papers+1.492
 Pret+1.477
OLOG+1.472
Neg logit contributions
iren-1.929
 carbohyd-1.798
erker-1.796
oter-1.778
urious-1.754
Token
Token ID198
Feature activation+2.00e-01

Pos logit contributions
 Arbit+0.291
papers+0.245
gallery+0.245
OLOG+0.242
 Pret+0.241
Neg logit contributions
iren-0.285
erker-0.265
 carbohyd-0.263
oter-0.263
 Miko-0.259
Token
Token ID198
Feature activation+1.22e-01

Pos logit contributions
 Arbit+0.888
papers+0.761
OLOG+0.758
gallery+0.756
 Pret+0.745
Neg logit contributions
iren-0.725
erker-0.664
oter-0.663
ander-0.661
 Miko-0.660
Token
Token ID447
Feature activation-2.31e-01

Pos logit contributions
 Arbit+0.492
gallery+0.418
papers+0.417
OLOG+0.411
 Pret+0.407
Neg logit contributions
iren-0.499
 carbohyd-0.467
erker-0.464
oter-0.458
 Miko-0.455
Token4
Token ID19
Feature activation+6.85e-01

Pos logit contributions
 Arbit+1.941
gallery+1.705
papers+1.683
 Pret+1.661
OLOG+1.656
Neg logit contributions
iren-1.465
 carbohyd-1.396
erker-1.361
 Miko-1.357
urous-1.333
Token,
Token ID11
Feature activation-6.74e-02

Pos logit contributions
 Arbit+2.850
papers+2.420
gallery+2.414
OLOG+2.384
 Pret+2.373
Neg logit contributions
iren-2.688
erker-2.496
oter-2.472
 carbohyd-2.467
 Miko-2.449
Token 7
Token ID767
Feature activation+4.24e-01

Pos logit contributions
iren+0.324
erker+0.306
 carbohyd+0.306
oter+0.302
urous+0.300
Neg logit contributions
 Arbit-0.223
gallery-0.179
papers-0.179
OLOG-0.175
 Pret-0.175
Token},
Token ID5512
Feature activation-8.28e-02

Pos logit contributions
 Arbit+1.514
papers+1.254
gallery+1.236
 Pret+1.220
OLOG+1.220
Neg logit contributions
iren-1.911
erker-1.796
 carbohyd-1.786
oter-1.769
urous-1.767
Token {
Token ID1391
Feature activation+2.52e-01

Pos logit contributions
iren+0.251
erker+0.232
oter+0.226
 carbohyd+0.226
urous+0.224
Neg logit contributions
 Arbit-0.421
papers-0.365
gallery-0.365
 Pret-0.363
OLOG-0.360
Token5
Token ID20
Feature activation+1.26e+00

Pos logit contributions
 Arbit+1.103
gallery+0.957
papers+0.947
 Pret+0.932
OLOG+0.928
Neg logit contributions
iren-0.928
 carbohyd-0.875
erker-0.864
 Miko-0.853
urous-0.845
Token,
Token ID11
Feature activation+1.39e-03

Pos logit contributions
 Arbit+4.921
gallery+4.131
papers+4.118
 Pret+4.030
OLOG+4.011
Neg logit contributions
iren-5.266
 carbohyd-5.219
 nodd-4.942
erker-4.929
oter-4.861
Token 6
Token ID718
Feature activation+4.94e-01

Pos logit contributions
 Arbit+0.005
gallery+0.004
papers+0.004
OLOG+0.003
 Pret+0.003
Neg logit contributions
iren-0.007
erker-0.006
 carbohyd-0.006
oter-0.006
urous-0.006
Token},
Token ID5512
Feature activation-2.13e-02

Pos logit contributions
 Arbit+1.802
papers+1.486
gallery+1.481
 Pret+1.464
OLOG+1.441
Neg logit contributions
iren-2.185
 carbohyd-2.071
erker-2.058
urous-2.021
oter-2.016
Token {
Token ID1391
Feature activation+3.23e-01

Pos logit contributions
iren+0.066
erker+0.061
 carbohyd+0.060
oter+0.060
urous+0.059
Neg logit contributions
 Arbit-0.107
papers-0.092
gallery-0.092
 Pret-0.092
OLOG-0.091
Token5
Token ID20
Feature activation+1.37e+00

Pos logit contributions
 Arbit+1.438
gallery+1.256
papers+1.241
 Pret+1.216
OLOG+1.215
Neg logit contributions
iren-1.161
 carbohyd-1.110
erker-1.088
 Miko-1.060
urous-1.056
TokenREAD
Token ID15675
Feature activation-5.23e-02

Pos logit contributions
 Arbit+0.208
papers+0.176
gallery+0.175
OLOG+0.173
 Pret+0.172
Neg logit contributions
iren-0.218
erker-0.203
 carbohyd-0.202
oter-0.201
 Miko-0.199
Token MORE
Token ID12011
Feature activation-7.52e-02

Pos logit contributions
iren+0.190
erker+0.174
 carbohyd+0.173
urous+0.171
oter+0.171
Neg logit contributions
 Arbit-0.236
gallery-0.202
papers-0.201
OLOG-0.200
 Pret-0.199
Token:
Token ID25
Feature activation-3.50e-01

Pos logit contributions
iren+0.302
erker+0.281
 carbohyd+0.279
oter+0.278
urous+0.276
Neg logit contributions
 Arbit-0.310
gallery-0.261
papers-0.259
OLOG-0.258
 Pret-0.257
Token Omar
Token ID24980
Feature activation+5.20e-01

Pos logit contributions
iren+1.566
erker+1.472
 Miko+1.470
oter+1.462
urous+1.450
Neg logit contributions
 Arbit-1.220
papers-1.033
gallery-1.022
OLOG-1.003
 Pret-0.984
Token Kh
Token ID5311
Feature activation+5.39e-01

Pos logit contributions
 Arbit+1.671
 Pret+1.270
gallery+1.261
papers+1.237
OLOG+1.223
Neg logit contributions
iren-2.602
erker-2.461
oter-2.425
 carbohyd-2.421
urous-2.389
Tokenadr
Token ID41909
Feature activation+1.24e+00

Pos logit contributions
 Arbit+1.625
papers+1.296
OLOG+1.276
gallery+1.276
 Pret+1.267
Neg logit contributions
iren-2.746
erker-2.588
oter-2.587
ander-2.556
urous-2.550
Token should
Token ID815
Feature activation+3.35e-01

Pos logit contributions
 Arbit+4.801
 Pret+3.933
papers+3.810
gallery+3.757
 ACC+3.724
Neg logit contributions
iren-5.252
 carbohyd-5.017
erker-4.936
oter-4.835
urous-4.784
Token be
Token ID307
Feature activation+4.48e-01

Pos logit contributions
 Arbit+1.297
papers+1.076
gallery+1.075
 Pret+1.067
OLOG+1.057
Neg logit contributions
iren-1.407
erker-1.323
 carbohyd-1.321
oter-1.305
 Miko-1.295
Token transferred
Token ID11172
Feature activation-8.73e-02

Pos logit contributions
 Arbit+1.722
papers+1.427
gallery+1.424
 Pret+1.411
OLOG+1.403
Neg logit contributions
iren-1.907
erker-1.783
 carbohyd-1.775
oter-1.763
urous-1.747
Token to
Token ID284
Feature activation+1.82e-01

Pos logit contributions
iren+0.371
erker+0.346
oter+0.345
 Miko+0.345
urous+0.342
Neg logit contributions
 Arbit-0.330
papers-0.279
gallery-0.278
OLOG-0.274
 Pret-0.269
Token provincial
Token ID15818
Feature activation+6.07e-01

Pos logit contributions
 Arbit+0.668
gallery+0.545
 Pret+0.543
papers+0.542
OLOG+0.537
Neg logit contributions
iren-0.812
erker-0.760
 carbohyd-0.758
oter-0.753
urious-0.745
Token
Token ID198
Feature activation-7.68e-01

Pos logit contributions
iren+2.122
ander+1.977
 Miko+1.951
erker+1.924
oter+1.914
Neg logit contributions
 Arbit-3.371
OLOG-2.944
papers-2.925
gallery-2.890
 Pret-2.827
TokenN
Token ID45
Feature activation-3.26e-01

Pos logit contributions
iren+2.395
erker+2.176
 carbohyd+2.157
oter+2.150
 Miko+2.130
Neg logit contributions
 Arbit-3.823
papers-3.347
gallery-3.345
OLOG-3.311
 Pret-3.291
TokenPH
Token ID11909
Feature activation-1.49e-01

Pos logit contributions
iren+1.205
erker+1.121
oter+1.111
ander+1.105
urious+1.102
Neg logit contributions
 Arbit-1.413
 Pret-1.195
papers-1.195
gallery-1.173
OLOG-1.159
Token:
Token ID25
Feature activation-2.94e-01

Pos logit contributions
iren+0.508
ander+0.471
 Miko+0.468
oter+0.468
erker+0.467
Neg logit contributions
 Arbit-0.675
papers-0.583
gallery-0.579
OLOG-0.578
 Pret-0.568
Token Dec
Token ID4280
Feature activation+3.37e-01

Pos logit contributions
iren+1.196
 Miko+1.132
erker+1.118
oter+1.113
urous+1.109
Neg logit contributions
 Arbit-1.131
papers-0.972
gallery-0.964
OLOG-0.947
 Pret-0.919
Tokenad
Token ID324
Feature activation+1.24e+00

Pos logit contributions
 Arbit+1.521
gallery+1.315
papers+1.315
 Pret+1.293
OLOG+1.292
Neg logit contributions
iren-1.182
 carbohyd-1.101
erker-1.090
 Miko-1.079
oter-1.054
Tokenent
Token ID298
Feature activation-1.47e-01

Pos logit contributions
 Arbit+4.434
papers+3.566
gallery+3.562
 Pret+3.545
OLOG+3.478
Neg logit contributions
iren-5.346
 carbohyd-5.130
erker-5.082
 Miko-4.903
idi-4.818
Token.
Token ID13
Feature activation+7.77e-02

Pos logit contributions
iren+0.588
erker+0.545
 carbohyd+0.543
oter+0.539
 Miko+0.533
Neg logit contributions
 Arbit-0.602
gallery-0.505
papers-0.504
 Pret-0.502
OLOG-0.499
Token
Token ID198
Feature activation-4.69e-01

Pos logit contributions
 Arbit+0.318
papers+0.268
gallery+0.267
OLOG+0.264
 Pret+0.264
Neg logit contributions
iren-0.312
erker-0.290
 carbohyd-0.288
oter-0.287
 Miko-0.284
Token
Token ID198
Feature activation-5.12e-01

Pos logit contributions
iren+1.504
ander+1.398
 Miko+1.382
erker+1.362
oter+1.358
Neg logit contributions
 Arbit-2.194
OLOG-1.910
papers-1.907
gallery-1.881
 Pret-1.847
TokenAV
Token ID10116
Feature activation+2.81e-01

Pos logit contributions
iren+1.921
 carbohyd+1.785
erker+1.772
oter+1.753
 Miko+1.752
Neg logit contributions
 Arbit-2.233
gallery-1.936
papers-1.918
OLOG-1.909
 Pret-1.877
Token 2010
Token ID3050
Feature activation+8.84e-01

Pos logit contributions
 Arbit+1.770
papers+1.455
gallery+1.449
OLOG+1.428
 Pret+1.416
Neg logit contributions
iren-2.328
erker-2.185
oter-2.169
 carbohyd-2.158
 Miko-2.155
Token United
Token ID1578
Feature activation+1.45e-01

Pos logit contributions
 Arbit+3.194
 Pret+2.609
gallery+2.517
papers+2.511
 Cheong+2.493
Neg logit contributions
iren-4.010
 carbohyd-3.915
erker-3.765
oter-3.718
urious-3.703
Token States
Token ID1829
Feature activation+4.25e-01

Pos logit contributions
 Arbit+0.574
papers+0.480
gallery+0.478
 Pret+0.473
OLOG+0.472
Neg logit contributions
iren-0.607
 carbohyd-0.566
erker-0.565
oter-0.561
urous-0.554
Token 6
Token ID718
Feature activation+6.82e-01

Pos logit contributions
 Arbit+1.485
papers+1.210
gallery+1.209
 Pret+1.190
OLOG+1.188
Neg logit contributions
iren-1.958
 carbohyd-1.844
erker-1.841
oter-1.825
urous-1.808
Token83
Token ID5999
Feature activation-1.43e-01

Pos logit contributions
 Arbit+2.535
gallery+2.088
papers+2.084
 Pret+2.076
OLOG+2.041
Neg logit contributions
iren-2.997
 carbohyd-2.895
erker-2.813
oter-2.775
urious-2.735
Token Posts
Token ID12043
Feature activation+1.23e+00

Pos logit contributions
iren+0.504
 Miko+0.490
ander+0.470
erker+0.466
oter+0.465
Neg logit contributions
 Arbit-0.614
papers-0.541
gallery-0.532
OLOG-0.529
 Pret-0.510
Token Last
Token ID4586
Feature activation+6.29e-01

Pos logit contributions
 Arbit+3.705
 Pret+2.861
papers+2.739
gallery+2.683
 Halo+2.677
Neg logit contributions
iren-6.231
 carbohyd-5.840
erker-5.817
oter-5.815
urous-5.686
Token Edited
Token ID34212
Feature activation+3.53e-01

Pos logit contributions
 Arbit+1.893
papers+1.503
gallery+1.493
OLOG+1.472
 Pret+1.454
Neg logit contributions
iren-3.192
erker-3.020
oter-2.996
 Miko-2.983
 carbohyd-2.972
Token:
Token ID25
Feature activation+3.61e-01

Pos logit contributions
 Arbit+1.534
papers+1.320
OLOG+1.312
gallery+1.307
 Pret+1.285
Neg logit contributions
iren-1.305
erker-1.205
oter-1.196
 Miko-1.191
ander-1.185
Token 2013
Token ID2211
Feature activation+1.89e-01

Pos logit contributions
 Arbit+1.456
papers+1.244
OLOG+1.233
gallery+1.228
 Pret+1.200
Neg logit contributions
iren-1.447
erker-1.340
oter-1.335
 Miko-1.335
ander-1.325
Token-
Token ID12
Feature activation+4.33e-01

Pos logit contributions
 Arbit+0.676
papers+0.575
OLOG+0.570
gallery+0.569
 Pret+0.542
Neg logit contributions
iren-0.827
 Miko-0.780
oter-0.769
ander-0.764
erker-0.762
Token has
Token ID468
Feature activation-2.71e-01

Pos logit contributions
iren+1.197
erker+1.120
oter+1.111
 carbohyd+1.109
 Miko+1.102
Neg logit contributions
 Arbit-1.024
papers-0.851
gallery-0.849
OLOG-0.837
 Pret-0.832
Token been
Token ID587
Feature activation+8.29e-02

Pos logit contributions
iren+1.027
erker+0.947
oter+0.943
 Miko+0.933
 carbohyd+0.931
Neg logit contributions
 Arbit-1.165
papers-0.995
gallery-0.994
OLOG-0.982
 Pret-0.974
Token reluctant
Token ID18416
Feature activation+1.97e-01

Pos logit contributions
 Arbit+0.350
papers+0.298
gallery+0.297
OLOG+0.293
 Pret+0.292
Neg logit contributions
iren-0.321
erker-0.298
 carbohyd-0.295
oter-0.295
 Miko-0.292
Token to
Token ID284
Feature activation-1.47e-01

Pos logit contributions
 Arbit+0.666
papers+0.539
gallery+0.537
OLOG+0.533
 Pret+0.522
Neg logit contributions
iren-0.931
erker-0.876
urous-0.858
oter-0.858
 carbohyd-0.857
Token take
Token ID1011
Feature activation-3.61e-01

Pos logit contributions
iren+0.550
erker+0.508
oter+0.507
 Miko+0.500
 carbohyd+0.498
Neg logit contributions
 Arbit-0.638
papers-0.548
gallery-0.547
OLOG-0.542
 Pret-0.535
Token up
Token ID510
Feature activation-1.39e+00

Pos logit contributions
iren+1.435
erker+1.332
oter+1.323
 Miko+1.315
 carbohyd+1.310
Neg logit contributions
 Arbit-1.478
papers-1.258
gallery-1.253
OLOG-1.237
 Pret-1.225
Token progressive
Token ID10393
Feature activation-2.32e-01

Pos logit contributions
iren+5.383
 Miko+5.051
oter+5.028
erker+4.999
ander+4.983
Neg logit contributions
 Arbit-5.504
gallery-4.811
papers-4.657
OLOG-4.597
 Pret-4.565
Token issues
Token ID2428
Feature activation-2.22e-01

Pos logit contributions
iren+1.057
erker+0.992
oter+0.985
 carbohyd+0.982
 Miko+0.977
Neg logit contributions
 Arbit-0.819
papers-0.673
gallery-0.672
OLOG-0.661
 Pret-0.657
Token.
Token ID13
Feature activation-1.97e-02

Pos logit contributions
iren+0.893
erker+0.831
oter+0.824
 carbohyd+0.820
 Miko+0.817
Neg logit contributions
 Arbit-0.898
papers-0.759
gallery-0.758
OLOG-0.748
 Pret-0.744
Token Jones
Token ID5437
Feature activation-3.60e-02

Pos logit contributions
iren+0.081
erker+0.076
 carbohyd+0.075
oter+0.075
urous+0.074
Neg logit contributions
 Arbit-0.079
gallery-0.066
papers-0.066
OLOG-0.065
 Pret-0.065
Token said
Token ID531
Feature activation+3.26e-01

Pos logit contributions
iren+0.153
erker+0.142
 carbohyd+0.142
oter+0.141
urous+0.139
Neg logit contributions
 Arbit-0.140
papers-0.117
gallery-0.116
 Pret-0.115
OLOG-0.114
Token Stephen
Token ID7970
Feature activation+1.31e-01

Pos logit contributions
iren+0.002
erker+0.002
 carbohyd+0.002
oter+0.002
urous+0.002
Neg logit contributions
 Arbit-0.002
papers-0.001
gallery-0.001
 Pret-0.001
OLOG-0.001
Token East
Token ID3687
Feature activation-2.24e-02

Pos logit contributions
 Arbit+0.503
papers+0.419
gallery+0.417
 Pret+0.413
OLOG+0.411
Neg logit contributions
iren-0.559
erker-0.524
 carbohyd-0.523
oter-0.519
urous-0.514
Tokenon
Token ID261
Feature activation-4.91e-01

Pos logit contributions
iren+0.092
 carbohyd+0.087
erker+0.087
oter+0.085
 Miko+0.085
Neg logit contributions
 Arbit-0.089
gallery-0.074
papers-0.074
 Pret-0.073
OLOG-0.073
Token PA
Token ID8147
Feature activation+2.64e-01

Pos logit contributions
iren+2.059
erker+1.919
oter+1.905
 carbohyd+1.894
 Miko+1.890
Neg logit contributions
 Arbit-1.904
papers-1.599
gallery-1.596
OLOG-1.573
 Pret-1.562
Token 1
Token ID352
Feature activation-4.14e-02

Pos logit contributions
 Arbit+0.933
OLOG+0.753
papers+0.752
gallery+0.752
 Pret+0.747
Neg logit contributions
iren-1.204
 carbohyd-1.137
erker-1.137
urous-1.119
oter-1.117
Token hour
Token ID1711
Feature activation-1.38e+00

Pos logit contributions
iren+0.188
oter+0.177
erker+0.177
 Miko+0.175
ander+0.175
Neg logit contributions
 Arbit-0.143
papers-0.122
OLOG-0.118
gallery-0.117
 Pret-0.117
Token ago
Token ID2084
Feature activation+1.10e-01

Pos logit contributions
iren+5.201
ander+4.949
oter+4.865
 Miko+4.745
idi+4.728
Neg logit contributions
 Arbit-5.504
 Cyan-4.699
OLOG-4.668
papers-4.665
 Pret-4.588
Token I
Token ID314
Feature activation+1.33e-01

Pos logit contributions
 Arbit+0.436
papers+0.366
gallery+0.366
OLOG+0.361
 Pret+0.359
Neg logit contributions
iren-0.455
erker-0.425
oter-0.421
 carbohyd-0.420
 Miko-0.417
Token think
Token ID892
Feature activation-2.86e-01

Pos logit contributions
 Arbit+0.528
papers+0.443
gallery+0.442
OLOG+0.437
 Pret+0.435
Neg logit contributions
iren-0.546
erker-0.509
 carbohyd-0.505
oter-0.504
 Miko-0.500
Token a
Token ID257
Feature activation-3.86e-01

Pos logit contributions
iren+1.156
erker+1.076
oter+1.069
 carbohyd+1.061
 Miko+1.061
Neg logit contributions
 Arbit-1.155
papers-0.977
gallery-0.977
OLOG-0.963
 Pret-0.955
Token simple
Token ID2829
Feature activation-1.91e-01

Pos logit contributions
iren+1.412
erker+1.299
oter+1.296
 Miko+1.282
urous+1.276
Neg logit contributions
 Arbit-1.701
papers-1.464
gallery-1.462
OLOG-1.444
 Pret-1.427
Tokenere
Token ID567
Feature activation-8.98e-02

Pos logit contributions
iren+1.314
erker+1.225
 carbohyd+1.216
 Miko+1.205
oter+1.200
Neg logit contributions
 Arbit-1.744
papers-1.503
gallery-1.494
OLOG-1.482
 Pret-1.477
Tokenf
Token ID69
Feature activation-2.80e-01

Pos logit contributions
iren+0.390
erker+0.365
 carbohyd+0.363
oter+0.362
urous+0.359
Neg logit contributions
 Arbit-0.336
papers-0.279
gallery-0.279
OLOG-0.275
 Pret-0.273
Token for
Token ID329
Feature activation-7.97e-01

Pos logit contributions
iren+0.859
erker+0.787
 carbohyd+0.782
oter+0.774
 Miko+0.767
Neg logit contributions
 Arbit-1.405
papers-1.219
gallery-1.218
 Pret-1.209
OLOG-1.209
Token Own
Token ID11744
Feature activation-7.72e-01

Pos logit contributions
iren+3.318
erker+3.105
 Miko+3.080
oter+3.068
urous+3.036
Neg logit contributions
 Arbit-3.021
papers-2.613
gallery-2.600
OLOG-2.561
 Pret-2.484
Tokened
Token ID276
Feature activation-7.40e-01

Pos logit contributions
iren+2.672
erker+2.457
oter+2.443
ander+2.442
urious+2.390
Neg logit contributions
 Arbit-3.518
papers-3.055
gallery-3.029
OLOG-3.020
 Pret-2.970
Token <
Token ID1279
Feature activation-1.36e+00

Pos logit contributions
iren+2.031
erker+1.824
 carbohyd+1.800
oter+1.796
 Miko+1.773
Neg logit contributions
 Arbit-3.967
papers-3.491
gallery-3.481
OLOG-3.454
 Pret-3.449
Token T
Token ID309
Feature activation-7.29e-01

Pos logit contributions
iren+5.143
erker+4.825
oter+4.751
 Miko+4.720
ander+4.669
Neg logit contributions
 Arbit-5.498
papers-4.900
gallery-4.857
OLOG-4.728
 Pret-4.597
Token >
Token ID1875
Feature activation-4.27e-01

Pos logit contributions
iren+3.078
erker+2.870
oter+2.848
 carbohyd+2.847
 Miko+2.824
Neg logit contributions
 Arbit-2.824
papers-2.362
gallery-2.357
OLOG-2.324
 Pret-2.315
Token {
Token ID1391
Feature activation-3.25e-01

Pos logit contributions
iren+1.229
erker+1.107
 carbohyd+1.106
oter+1.093
 Miko+1.081
Neg logit contributions
 Arbit-2.238
papers-1.951
gallery-1.949
 Pret-1.936
OLOG-1.934
Token type
Token ID2099
Feature activation-4.31e-01

Pos logit contributions
iren+1.363
erker+1.271
 carbohyd+1.259
oter+1.256
urous+1.251
Neg logit contributions
 Arbit-1.281
papers-1.065
gallery-1.058
 Pret-1.053
OLOG-1.048
Token Target
Token ID12744
Feature activation-2.88e-01

Pos logit contributions
iren+1.723
erker+1.606
 carbohyd+1.592
oter+1.587
 Miko+1.572
Neg logit contributions
 Arbit-1.766
papers-1.489
gallery-1.486
OLOG-1.467
 Pret-1.464
Tokenf
Token ID69
Feature activation-3.60e-01

Pos logit contributions
iren+0.580
oter+0.538
erker+0.536
 Miko+0.526
ander+0.526
Neg logit contributions
 Arbit-0.562
papers-0.474
OLOG-0.473
gallery-0.469
 Pret-0.461
TokenMut
Token ID41603
Feature activation-7.63e-01

Pos logit contributions
iren+1.559
erker+1.461
 carbohyd+1.454
oter+1.444
urous+1.434
Neg logit contributions
 Arbit-1.363
papers-1.126
gallery-1.121
 Pret-1.110
OLOG-1.109
Token for
Token ID329
Feature activation-7.16e-01

Pos logit contributions
iren+3.474
erker+3.260
oter+3.233
 carbohyd+3.231
 Miko+3.208
Neg logit contributions
 Arbit-2.699
papers-2.217
gallery-2.211
OLOG-2.177
 Pret-2.165
Token Own
Token ID11744
Feature activation-9.62e-01

Pos logit contributions
iren+2.859
erker+2.659
oter+2.633
 carbohyd+2.623
 Miko+2.615
Neg logit contributions
 Arbit-2.918
papers-2.483
gallery-2.475
OLOG-2.443
 Pret-2.420
Tokened
Token ID276
Feature activation-8.14e-01

Pos logit contributions
iren+3.050
ander+2.840
erker+2.808
oter+2.784
urious+2.781
Neg logit contributions
 Arbit-4.588
OLOG-4.003
papers-3.959
 Pret-3.917
gallery-3.879
Token <
Token ID1279
Feature activation-1.35e+00

Pos logit contributions
iren+1.678
 Miko+1.433
oter+1.431
erker+1.429
ander+1.403
Neg logit contributions
 Arbit-4.688
papers-4.348
gallery-4.274
OLOG-4.255
 Cheong-4.152
Token T
Token ID309
Feature activation-6.91e-01

Pos logit contributions
iren+4.270
 Miko+4.125
erker+3.991
oter+3.983
ander+3.945
Neg logit contributions
 Arbit-5.745
papers-5.578
gallery-5.421
OLOG-5.307
 Cheong-5.069
Token >
Token ID1875
Feature activation-3.79e-01

Pos logit contributions
iren+2.515
erker+2.352
 Miko+2.324
oter+2.316
ander+2.315
Neg logit contributions
 Arbit-2.922
papers-2.597
OLOG-2.519
gallery-2.519
 Cheong-2.434
Token {
Token ID1391
Feature activation-4.38e-01

Pos logit contributions
iren+0.878
erker+0.778
oter+0.772
 Miko+0.768
ander+0.750
Neg logit contributions
 Arbit-2.135
papers-1.951
gallery-1.924
OLOG-1.917
 Pret-1.870
Token...
Token ID2644
Feature activation+7.43e-02

Pos logit contributions
iren+2.057
erker+1.926
 carbohyd+1.913
oter+1.909
urous+1.901
Neg logit contributions
 Arbit-1.508
papers-1.212
gallery-1.211
 Pret-1.196
OLOG-1.193
Token }
Token ID1782
Feature activation+1.74e-01

Pos logit contributions
 Arbit+0.265
papers+0.219
gallery+0.218
OLOG+0.216
 Pret+0.213
Neg logit contributions
iren-0.335
erker-0.314
oter-0.312
 carbohyd-0.310
 Miko-0.310
Token
Token ID198
Feature activation-2.40e-01

Pos logit contributions
iren+1.139
 carbohyd+1.076
erker+1.063
oter+1.050
urous+1.034
Neg logit contributions
 Arbit-1.129
papers-0.942
 Pret-0.938
gallery-0.937
OLOG-0.929
Token
Token ID198
Feature activation-1.97e-01

Pos logit contributions
iren+0.815
ander+0.749
oter+0.742
 Miko+0.740
erker+0.740
Neg logit contributions
 Arbit-1.099
OLOG-0.951
papers-0.947
gallery-0.940
 Pret-0.925
TokenA
Token ID32
Feature activation-1.58e-01

Pos logit contributions
iren+0.802
 carbohyd+0.751
erker+0.747
oter+0.739
 Miko+0.735
Neg logit contributions
 Arbit-0.789
papers-0.670
gallery-0.669
OLOG-0.660
 Pret-0.653
Token respected
Token ID14462
Feature activation-3.81e-01

Pos logit contributions
iren+0.647
erker+0.603
oter+0.597
 carbohyd+0.596
 Miko+0.592
Neg logit contributions
 Arbit-0.633
papers-0.533
gallery-0.532
OLOG-0.525
 Pret-0.522
Token think
Token ID892
Feature activation-3.42e-01

Pos logit contributions
iren+1.427
erker+1.315
oter+1.305
 Miko+1.299
urous+1.285
Neg logit contributions
 Arbit-1.638
gallery-1.416
papers-1.406
OLOG-1.390
 Pret-1.371
Token tank
Token ID6873
Feature activation-1.31e+00

Pos logit contributions
iren+1.337
erker+1.244
oter+1.231
 carbohyd+1.223
 Miko+1.220
Neg logit contributions
 Arbit-1.429
gallery-1.214
papers-1.213
OLOG-1.196
 Pret-1.192
Token said
Token ID531
Feature activation+5.19e-03

Pos logit contributions
iren+4.976
erker+4.676
oter+4.606
 Miko+4.566
urous+4.533
Neg logit contributions
 Arbit-5.341
gallery-4.679
papers-4.497
OLOG-4.481
 Pret-4.460
Token in
Token ID287
Feature activation-3.68e-02

Pos logit contributions
 Arbit+0.019
papers+0.016
gallery+0.016
 Pret+0.015
OLOG+0.015
Neg logit contributions
iren-0.023
erker-0.022
 carbohyd-0.022
oter-0.021
urous-0.021
Token a
Token ID257
Feature activation-8.69e-02

Pos logit contributions
iren+0.162
erker+0.152
 carbohyd+0.152
oter+0.151
 Miko+0.149
Neg logit contributions
 Arbit-0.136
papers-0.113
gallery-0.112
 Pret-0.111
OLOG-0.110
Token report
Token ID989
Feature activation-5.11e-01

Pos logit contributions
iren+0.407
erker+0.383
 carbohyd+0.380
oter+0.380
 Miko+0.377
Neg logit contributions
 Arbit-0.295
papers-0.241
gallery-0.240
OLOG-0.236
 Pret-0.235
Token on
Token ID319
Feature activation+9.89e-03

Pos logit contributions
iren+2.293
erker+2.147
oter+2.135
 carbohyd+2.119
 Miko+2.119
Neg logit contributions
 Arbit-1.834
gallery-1.514
papers-1.513
OLOG-1.488
 Pret-1.479
Tokenulate
Token ID5039
Feature activation-6.80e-01

Pos logit contributions
 Arbit+1.529
papers+1.325
gallery+1.320
OLOG+1.315
 Pret+1.308
Neg logit contributions
iren-1.001
erker-0.908
oter-0.906
urous-0.887
urious-0.885
TokenD
Token ID35
Feature activation-3.45e-01

Pos logit contributions
iren+3.492
erker+3.286
oter+3.265
 carbohyd+3.249
urious+3.242
Neg logit contributions
 Arbit-1.965
papers-1.562
gallery-1.534
OLOG-1.517
 Pret-1.496
Tokenensity
Token ID6377
Feature activation-1.59e-01

Pos logit contributions
iren+1.390
oter+1.280
erker+1.265
ander+1.252
urious+1.252
Neg logit contributions
 Arbit-1.445
OLOG-1.199
 Pret-1.194
papers-1.188
gallery-1.182
TokenGrid
Token ID41339
Feature activation-5.02e-02

Pos logit contributions
iren+0.693
erker+0.654
 carbohyd+0.652
oter+0.647
 Miko+0.641
Neg logit contributions
 Arbit-0.593
gallery-0.494
papers-0.492
OLOG-0.484
 Pret-0.480
Token(
Token ID7
Feature activation-3.12e-01

Pos logit contributions
iren+0.232
erker+0.219
 carbohyd+0.217
oter+0.216
urous+0.215
Neg logit contributions
 Arbit-0.175
papers-0.143
gallery-0.142
OLOG-0.140
 Pret-0.140
Token Uniform
Token ID35712
Feature activation-1.29e+00

Pos logit contributions
iren+1.348
erker+1.258
oter+1.248
 carbohyd+1.244
 Miko+1.236
Neg logit contributions
 Arbit-1.174
papers-0.983
gallery-0.978
OLOG-0.967
 Pret-0.959
TokenGrid
Token ID41339
Feature activation-3.98e-01

Pos logit contributions
iren+5.107
erker+4.698
oter+4.681
 Miko+4.668
 carbohyd+4.645
Neg logit contributions
 Arbit-5.104
papers-4.414
gallery-4.360
OLOG-4.355
 Pret-4.280
Token<
Token ID27
Feature activation-4.36e-01

Pos logit contributions
iren+1.570
erker+1.455
oter+1.445
 carbohyd+1.438
 Miko+1.432
Neg logit contributions
 Arbit-1.635
papers-1.394
gallery-1.389
OLOG-1.375
 Pret-1.362
Token float
Token ID12178
Feature activation-9.91e-01

Pos logit contributions
iren+1.868
erker+1.740
oter+1.723
 carbohyd+1.711
ander+1.703
Neg logit contributions
 Arbit-1.640
papers-1.384
gallery-1.372
OLOG-1.362
 Pret-1.348
Token >
Token ID1875
Feature activation+2.83e-02

Pos logit contributions
iren+3.909
erker+3.640
 Miko+3.600
oter+3.573
ander+3.543
Neg logit contributions
 Arbit-3.990
papers-3.438
OLOG-3.407
gallery-3.402
 Pret-3.333
Token &
Token ID1222
Feature activation-4.60e-01

Pos logit contributions
 Arbit+0.117
papers+0.099
gallery+0.098
OLOG+0.097
 Pret+0.097
Neg logit contributions
iren-0.112
erker-0.105
oter-0.104
 carbohyd-0.104
 Miko-0.103
Token decide
Token ID5409
Feature activation+3.46e-01

Pos logit contributions
iren+1.393
erker+1.281
oter+1.271
 Miko+1.259
urous+1.251
Neg logit contributions
 Arbit-1.581
gallery-1.368
papers-1.362
OLOG-1.350
 Pret-1.330
Token shortly
Token ID8972
Feature activation-3.88e-01

Pos logit contributions
 Arbit+1.237
papers+1.003
 Pret+0.986
OLOG+0.975
gallery+0.975
Neg logit contributions
iren-1.573
 carbohyd-1.497
erker-1.492
oter-1.480
urous-1.466
Token whether
Token ID1771
Feature activation+1.24e-01

Pos logit contributions
iren+1.717
erker+1.608
oter+1.595
 carbohyd+1.592
 Miko+1.583
Neg logit contributions
 Arbit-1.422
papers-1.178
gallery-1.175
OLOG-1.157
 Pret-1.151
Token to
Token ID284
Feature activation+1.35e-01

Pos logit contributions
 Arbit+0.455
papers+0.371
 Pret+0.367
OLOG+0.364
gallery+0.362
Neg logit contributions
iren-0.559
erker-0.525
 carbohyd-0.522
oter-0.517
urous-0.514
Token take
Token ID1011
Feature activation-1.72e-02

Pos logit contributions
 Arbit+0.560
papers+0.470
gallery+0.468
 Pret+0.464
OLOG+0.461
Neg logit contributions
iren-0.532
 carbohyd-0.497
erker-0.496
oter-0.489
urous-0.485
Token up
Token ID510
Feature activation-1.28e+00

Pos logit contributions
iren+0.080
erker+0.075
 carbohyd+0.075
oter+0.075
urious+0.074
Neg logit contributions
 Arbit-0.059
papers-0.048
gallery-0.048
 Pret-0.047
OLOG-0.047
Token this
Token ID428
Feature activation-1.99e-01

Pos logit contributions
iren+5.089
erker+4.742
 Miko+4.701
oter+4.694
urous+4.648
Neg logit contributions
 Arbit-5.066
gallery-4.415
papers-4.325
OLOG-4.286
 Pret-4.203
Token judicial
Token ID13657
Feature activation-3.75e-01

Pos logit contributions
iren+0.894
erker+0.839
oter+0.832
 carbohyd+0.829
 Miko+0.826
Neg logit contributions
 Arbit-0.712
papers-0.588
gallery-0.587
OLOG-0.578
 Pret-0.574
Token ethics
Token ID14458
Feature activation+9.94e-02

Pos logit contributions
iren+1.505
erker+1.396
oter+1.382
 Miko+1.377
 carbohyd+1.366
Neg logit contributions
 Arbit-1.512
gallery-1.295
papers-1.292
OLOG-1.276
 Pret-1.254
Token (
Token ID357
Feature activation-2.79e-02

Pos logit contributions
 Arbit+0.381
papers+0.316
gallery+0.315
OLOG+0.311
 Pret+0.311
Neg logit contributions
iren-0.424
erker-0.397
 carbohyd-0.397
oter-0.394
 Miko-0.390
Tokenand
Token ID392
Feature activation-2.35e-01

Pos logit contributions
iren+0.109
erker+0.101
 carbohyd+0.101
oter+0.100
 Miko+0.100
Neg logit contributions
 Arbit-0.117
papers-0.100
gallery-0.099
OLOG-0.097
 Pret-0.097
Token some
Token ID617
Feature activation-4.95e-02

Pos logit contributions
 Arbit+0.740
gallery+0.608
papers+0.608
 Pret+0.602
OLOG+0.599
Neg logit contributions
iren-0.869
erker-0.815
 carbohyd-0.811
oter-0.806
urous-0.798
Token pilot
Token ID8022
Feature activation-2.21e-01

Pos logit contributions
iren+0.212
erker+0.199
 carbohyd+0.197
oter+0.197
urous+0.194
Neg logit contributions
 Arbit-0.190
papers-0.158
gallery-0.158
OLOG-0.155
 Pret-0.155
Token who
Token ID508
Feature activation+2.62e-01

Pos logit contributions
iren+0.914
erker+0.852
oter+0.844
 carbohyd+0.843
 Miko+0.836
Neg logit contributions
 Arbit-0.870
papers-0.732
gallery-0.730
OLOG-0.720
 Pret-0.717
Token had
Token ID550
Feature activation-5.59e-02

Pos logit contributions
 Arbit+1.067
papers+0.899
gallery+0.894
 Pret+0.885
OLOG+0.883
Neg logit contributions
iren-1.051
erker-0.983
 carbohyd-0.983
oter-0.968
urous-0.961
Token taken
Token ID2077
Feature activation-1.92e-01

Pos logit contributions
iren+0.218
erker+0.203
oter+0.201
 carbohyd+0.200
 Miko+0.199
Neg logit contributions
 Arbit-0.234
papers-0.199
gallery-0.198
OLOG-0.196
 Pret-0.195
Token off
Token ID572
Feature activation-1.28e+00

Pos logit contributions
iren+0.823
erker+0.769
oter+0.763
 carbohyd+0.760
 Miko+0.757
Neg logit contributions
 Arbit-0.727
papers-0.607
gallery-0.605
OLOG-0.597
 Pret-0.593
Token with
Token ID351
Feature activation-4.26e-01

Pos logit contributions
iren+5.005
 Miko+4.634
urious+4.591
oter+4.584
ander+4.561
Neg logit contributions
 Arbit-5.111
gallery-4.375
papers-4.367
OLOG-4.284
 Pret-4.172
Token his
Token ID465
Feature activation-4.42e-01

Pos logit contributions
iren+1.795
erker+1.671
oter+1.659
 carbohyd+1.654
 Miko+1.649
Neg logit contributions
 Arbit-1.644
papers-1.380
gallery-1.375
OLOG-1.356
 Pret-1.346
Token wings
Token ID12098
Feature activation-2.27e-01

Pos logit contributions
iren+1.801
erker+1.666
oter+1.656
 Miko+1.652
 carbohyd+1.643
Neg logit contributions
 Arbit-1.759
papers-1.496
gallery-1.486
OLOG-1.469
 Pret-1.452
Token folded
Token ID24650
Feature activation+1.17e-01

Pos logit contributions
iren+0.834
erker+0.768
oter+0.762
 carbohyd+0.759
 Miko+0.754
Neg logit contributions
 Arbit-1.002
papers-0.859
gallery-0.859
OLOG-0.850
 Pret-0.843
Token in
Token ID287
Feature activation-1.51e-01

Pos logit contributions
 Arbit+0.467
papers+0.392
gallery+0.390
 Pret+0.386
OLOG+0.384
Neg logit contributions
iren-0.483
erker-0.454
 carbohyd-0.450
oter-0.447
 Miko-0.442
Token)
Token ID8
Feature activation+1.44e-01

Pos logit contributions
iren+1.811
erker+1.680
oter+1.667
 carbohyd+1.662
 Miko+1.651
Neg logit contributions
 Arbit-1.891
papers-1.606
gallery-1.602
OLOG-1.580
 Pret-1.573
Token told
Token ID1297
Feature activation+3.56e-01

Pos logit contributions
 Arbit+0.582
papers+0.487
gallery+0.485
 Pret+0.481
OLOG+0.480
Neg logit contributions
iren-0.590
erker-0.552
 carbohyd-0.547
oter-0.543
 Miko-0.539
Token The
Token ID383
Feature activation-1.59e-01

Pos logit contributions
 Arbit+1.319
papers+1.078
gallery+1.072
 Pret+1.067
OLOG+1.056
Neg logit contributions
iren-1.573
erker-1.485
 carbohyd-1.471
oter-1.457
urious-1.446
Token Nat
Token ID14393
Feature activation-2.45e-01

Pos logit contributions
iren+0.727
erker+0.684
 carbohyd+0.682
oter+0.677
urous+0.671
Neg logit contributions
 Arbit-0.564
papers-0.461
gallery-0.460
OLOG-0.455
 Pret-0.454
Token-
Token ID12
Feature activation-1.87e-01

Pos logit contributions
iren+0.930
erker+0.866
 carbohyd+0.865
 Miko+0.855
oter+0.854
Neg logit contributions
 Arbit-1.055
papers-0.899
gallery-0.893
OLOG-0.884
 Pret-0.879
Token
Token ID220
Feature activation-1.27e+00

Pos logit contributions
iren+0.768
erker+0.716
 carbohyd+0.710
oter+0.707
 Miko+0.702
Neg logit contributions
 Arbit-0.746
papers-0.627
gallery-0.627
OLOG-0.615
 Pret-0.614
Tokenional
Token ID1538
Feature activation-1.17e-01

Pos logit contributions
iren+4.489
oter+4.068
erker+4.065
urous+4.008
ander+3.986
Neg logit contributions
 Arbit-5.679
gallery-4.882
OLOG-4.864
papers-4.863
 Pret-4.835
Token that
Token ID326
Feature activation-9.42e-02

Pos logit contributions
iren+0.496
erker+0.465
 carbohyd+0.461
oter+0.460
 Miko+0.456
Neg logit contributions
 Arbit-0.448
papers-0.374
gallery-0.373
OLOG-0.368
 Pret-0.367
Token For
Token ID1114
Feature activation+8.02e-04

Pos logit contributions
iren+0.398
erker+0.372
oter+0.368
 carbohyd+0.368
 Miko+0.365
Neg logit contributions
 Arbit-0.363
papers-0.304
gallery-0.304
OLOG-0.299
 Pret-0.298
Tokencade
Token ID46395
Feature activation+6.61e-02

Pos logit contributions
 Arbit+0.002
papers+0.002
 Pret+0.002
OLOG+0.002
gallery+0.002
Neg logit contributions
iren-0.004
erker-0.004
oter-0.004
ander-0.004
 Miko-0.004
Tokenll
Token ID297
Feature activation+9.41e-02

Pos logit contributions
 Arbit+0.314
papers+0.272
OLOG+0.270
 Pret+0.268
gallery+0.268
Neg logit contributions
iren-0.224
erker-0.202
oter-0.201
 Miko-0.198
urious-0.198
Token J
Token ID449
Feature activation-5.19e-01

Pos logit contributions
iren+1.330
erker+1.241
oter+1.231
 carbohyd+1.227
 Miko+1.222
Neg logit contributions
 Arbit-1.211
papers-1.014
gallery-1.012
OLOG-0.998
 Pret-0.992
TokenAB
Token ID6242
Feature activation+2.79e-01

Pos logit contributions
iren+2.054
erker+1.907
oter+1.891
 carbohyd+1.881
 Miko+1.871
Neg logit contributions
 Arbit-2.144
papers-1.819
gallery-1.816
OLOG-1.792
 Pret-1.782
Tokenarry
Token ID6532
Feature activation-4.70e-02

Pos logit contributions
 Arbit+1.004
papers+0.822
gallery+0.820
OLOG+0.814
 Pret+0.812
Neg logit contributions
iren-1.254
erker-1.174
 carbohyd-1.173
oter-1.159
urous-1.156
Token Maryland
Token ID10769
Feature activation-3.13e-01

Pos logit contributions
iren+0.202
erker+0.189
 carbohyd+0.188
oter+0.187
urous+0.185
Neg logit contributions
 Arbit-0.179
papers-0.149
gallery-0.148
OLOG-0.146
 Pret-0.146
Token 1
Token ID352
Feature activation+1.34e-02

Pos logit contributions
iren+1.420
erker+1.329
oter+1.326
 Miko+1.318
ander+1.310
Neg logit contributions
 Arbit-1.093
papers-0.907
gallery-0.905
OLOG-0.892
 Pret-0.876
Token hour
Token ID1711
Feature activation-1.27e+00

Pos logit contributions
 Arbit+0.044
papers+0.036
gallery+0.035
OLOG+0.035
 Pret+0.035
Neg logit contributions
iren-0.064
erker-0.060
oter-0.060
 carbohyd-0.060
 Miko-0.059
Token ago
Token ID2084
Feature activation+3.62e-01

Pos logit contributions
iren+5.371
ander+5.010
 Miko+4.928
erker+4.913
idi+4.908
Neg logit contributions
 Arbit-4.620
gallery-3.978
papers-3.974
OLOG-3.941
 Pret-3.802
Token This
Token ID770
Feature activation-2.65e-02

Pos logit contributions
 Arbit+1.423
papers+1.177
gallery+1.176
 Pret+1.174
OLOG+1.160
Neg logit contributions
iren-1.521
 carbohyd-1.428
erker-1.422
oter-1.400
urous-1.391
Token election
Token ID3071
Feature activation-1.51e-01

Pos logit contributions
iren+0.119
erker+0.112
oter+0.111
 carbohyd+0.110
 Miko+0.110
Neg logit contributions
 Arbit-0.095
papers-0.078
gallery-0.078
OLOG-0.077
 Pret-0.076
Token was
Token ID373
Feature activation-2.19e-01

Pos logit contributions
iren+0.632
erker+0.589
oter+0.585
 carbohyd+0.582
 Miko+0.579
Neg logit contributions
 Arbit-0.587
papers-0.493
gallery-0.492
OLOG-0.485
 Pret-0.482
Token not
Token ID407
Feature activation-8.08e-02

Pos logit contributions
iren+0.860
erker+0.799
oter+0.791
 carbohyd+0.789
 Miko+0.784
Neg logit contributions
 Arbit-0.914
papers-0.776
gallery-0.775
OLOG-0.765
 Pret-0.761
TokenT
Token ID51
Feature activation-3.74e-02

Pos logit contributions
 Arbit+0.343
papers+0.297
gallery+0.294
OLOG+0.291
 Pret+0.289
Neg logit contributions
iren-0.255
oter-0.236
erker-0.235
 Miko-0.233
ander-0.233
Token Pick
Token ID12346
Feature activation-4.69e-02

Pos logit contributions
iren+0.118
oter+0.109
ander+0.108
 Miko+0.108
erker+0.108
Neg logit contributions
 Arbit-0.181
papers-0.162
OLOG-0.160
gallery-0.160
 Cheong-0.153
Token Peter
Token ID5613
Feature activation-2.78e-03

Pos logit contributions
iren+0.198
erker+0.185
 carbohyd+0.184
oter+0.183
urous+0.182
Neg logit contributions
 Arbit-0.183
papers-0.152
gallery-0.151
 Pret-0.150
OLOG-0.149
Token Syracuse
Token ID29141
Feature activation+1.04e-02

Pos logit contributions
iren+0.012
erker+0.011
 carbohyd+0.011
oter+0.011
urous+0.011
Neg logit contributions
 Arbit-0.011
papers-0.009
gallery-0.009
 Pret-0.009
OLOG-0.009
Token 1
Token ID352
Feature activation+8.34e-02

Pos logit contributions
 Arbit+0.038
gallery+0.031
papers+0.031
 Pret+0.031
OLOG+0.031
Neg logit contributions
iren-0.047
erker-0.044
 carbohyd-0.044
oter-0.043
urous-0.043
Token hour
Token ID1711
Feature activation-1.27e+00

Pos logit contributions
 Arbit+0.288
papers+0.246
OLOG+0.239
gallery+0.237
 Pret+0.236
Neg logit contributions
iren-0.379
oter-0.357
erker-0.356
 Miko-0.354
ander-0.352
Token ago
Token ID2084
Feature activation+1.71e-01

Pos logit contributions
iren+4.747
ander+4.522
oter+4.431
 Miko+4.371
idi+4.349
Neg logit contributions
 Arbit-5.076
 Cyan-4.344
OLOG-4.342
papers-4.336
gallery-4.251
Token What
Token ID1867
Feature activation+3.95e-01

Pos logit contributions
 Arbit+0.676
papers+0.567
gallery+0.566
OLOG+0.558
 Pret+0.558
Neg logit contributions
iren-0.707
erker-0.660
 carbohyd-0.655
oter-0.653
urous-0.646
Token the
Token ID262
Feature activation+1.96e-01

Pos logit contributions
 Arbit+1.540
papers+1.285
gallery+1.281
 Pret+1.270
OLOG+1.264
Neg logit contributions
iren-1.653
erker-1.546
 carbohyd-1.540
oter-1.523
urous-1.514
Token white
Token ID2330
Feature activation-3.87e-01

Pos logit contributions
 Arbit+0.765
papers+0.640
gallery+0.637
 Pret+0.630
OLOG+0.628
Neg logit contributions
iren-0.821
erker-0.768
 carbohyd-0.765
oter-0.760
urous-0.752
Token working
Token ID1762
Feature activation+1.23e-01

Pos logit contributions
iren+1.472
erker+1.364
oter+1.350
 carbohyd+1.350
 Miko+1.337
Neg logit contributions
 Arbit-1.657
papers-1.414
gallery-1.408
OLOG-1.392
 Pret-1.388
Token year
Token ID614
Feature activation-1.36e-01

Pos logit contributions
iren+0.081
erker+0.076
 carbohyd+0.075
oter+0.075
 Miko+0.074
Neg logit contributions
 Arbit-0.068
papers-0.056
gallery-0.056
OLOG-0.055
 Pret-0.055
Token of
Token ID286
Feature activation+1.29e-01

Pos logit contributions
iren+0.514
erker+0.479
 carbohyd+0.474
oter+0.469
 Miko+0.466
Neg logit contributions
 Arbit-0.587
papers-0.499
gallery-0.495
 Pret-0.492
OLOG-0.492
Token ind
Token ID773
Feature activation-1.06e-01

Pos logit contributions
 Arbit+0.493
papers+0.406
 Pret+0.403
gallery+0.401
OLOG+0.398
Neg logit contributions
iren-0.560
erker-0.526
 carbohyd-0.523
oter-0.517
 Miko-0.513
Tokenep
Token ID538
Feature activation+9.46e-01

Pos logit contributions
iren+0.379
erker+0.351
 carbohyd+0.351
 Miko+0.347
oter+0.345
Neg logit contributions
 Arbit-0.480
papers-0.412
gallery-0.410
OLOG-0.407
 Pret-0.403
Token-
Token ID12
Feature activation+4.95e-02

Pos logit contributions
 Arbit+3.858
papers+3.338
gallery+3.281
 Pret+3.239
OLOG+3.216
Neg logit contributions
iren-3.555
 carbohyd-3.475
erker-3.421
urous-3.318
 Miko-3.318
Token end
Token ID886
Feature activation-1.26e+00

Pos logit contributions
 Arbit+0.208
papers+0.177
gallery+0.175
 Pret+0.175
OLOG+0.173
Neg logit contributions
iren-0.193
erker-0.181
 carbohyd-0.177
oter-0.176
 Miko-0.176
Tokenence
Token ID594
Feature activation-1.70e-01

Pos logit contributions
iren+5.027
urous+4.683
oter+4.668
urious+4.637
erker+4.616
Neg logit contributions
 Arbit-5.035
gallery-4.309
OLOG-4.286
papers-4.254
 Pret-4.209
Token or
Token ID393
Feature activation-9.90e-02

Pos logit contributions
iren+0.685
erker+0.637
oter+0.632
 carbohyd+0.630
 Miko+0.626
Neg logit contributions
 Arbit-0.690
papers-0.584
gallery-0.583
OLOG-0.575
 Pret-0.572
Token not
Token ID407
Feature activation+3.60e-01

Pos logit contributions
iren+0.391
erker+0.364
 carbohyd+0.360
oter+0.360
 Miko+0.356
Neg logit contributions
 Arbit-0.411
papers-0.347
gallery-0.346
OLOG-0.342
 Pret-0.342
Token will
Token ID481
Feature activation-1.39e-01

Pos logit contributions
 Arbit+1.388
papers+1.154
gallery+1.150
 Pret+1.136
OLOG+1.136
Neg logit contributions
iren-1.518
erker-1.429
 carbohyd-1.417
oter-1.394
urous-1.387
Token be
Token ID307
Feature activation-2.79e-01

Pos logit contributions
iren+0.509
erker+0.476
 carbohyd+0.471
oter+0.466
 Miko+0.464
Neg logit contributions
 Arbit-0.614
papers-0.526
gallery-0.522
OLOG-0.520
 Pret-0.516
Tokenaire
Token ID7626
Feature activation-3.63e-01

Pos logit contributions
iren+3.874
oter+3.596
erker+3.589
urious+3.571
 Miko+3.556
Neg logit contributions
 Arbit-3.534
papers-2.961
gallery-2.949
OLOG-2.919
 Pret-2.880
Token Sud
Token ID14818
Feature activation+2.78e-02

Pos logit contributions
iren+1.461
erker+1.351
 Miko+1.344
oter+1.341
urous+1.332
Neg logit contributions
 Arbit-1.459
papers-1.240
gallery-1.240
OLOG-1.223
 Pret-1.201
Tokenh
Token ID71
Feature activation-3.38e-01

Pos logit contributions
 Arbit+0.122
papers+0.104
gallery+0.103
 Pret+0.103
OLOG+0.101
Neg logit contributions
iren-0.103
 carbohyd-0.096
erker-0.095
 Miko-0.094
oter-0.094
Tokenir
Token ID343
Feature activation-3.59e-01

Pos logit contributions
iren+0.654
 carbohyd+0.582
erker+0.580
 Miko+0.559
oter+0.555
Neg logit contributions
 Arbit-2.066
papers-1.848
gallery-1.848
 Pret-1.831
OLOG-1.828
Token Ch
Token ID609
Feature activation-5.42e-02

Pos logit contributions
iren+1.513
erker+1.422
 carbohyd+1.414
oter+1.400
 Miko+1.389
Neg logit contributions
 Arbit-1.395
papers-1.162
gallery-1.158
 Pret-1.147
OLOG-1.140
Tokenoud
Token ID2778
Feature activation-1.26e+00

Pos logit contributions
iren+0.188
 carbohyd+0.180
 Miko+0.175
erker+0.175
oter+0.172
Neg logit contributions
 Arbit-0.245
papers-0.212
gallery-0.210
OLOG-0.207
 Pret-0.207
Tokenh
Token ID71
Feature activation-2.25e-01

Pos logit contributions
iren+4.644
erker+4.256
urous+4.234
oter+4.223
idi+4.194
Neg logit contributions
 Arbit-5.472
papers-4.713
OLOG-4.694
gallery-4.679
 Pret-4.615
Tokenrie
Token ID5034
Feature activation-1.36e-01

Pos logit contributions
iren+0.592
erker+0.533
 carbohyd+0.527
oter+0.523
 Miko+0.517
Neg logit contributions
 Arbit-1.226
papers-1.084
gallery-1.083
OLOG-1.071
 Pret-1.070
Token has
Token ID468
Feature activation-7.07e-02

Pos logit contributions
iren+0.569
erker+0.534
 carbohyd+0.531
oter+0.527
 Miko+0.523
Neg logit contributions
 Arbit-0.529
papers-0.440
gallery-0.440
 Pret-0.436
OLOG-0.434
Token been
Token ID587
Feature activation+1.34e-01

Pos logit contributions
iren+0.279
erker+0.258
oter+0.256
 carbohyd+0.255
 Miko+0.254
Neg logit contributions
 Arbit-0.294
papers-0.249
gallery-0.249
OLOG-0.246
 Pret-0.244
Token welcomed
Token ID15846
Feature activation+1.29e-01

Pos logit contributions
 Arbit+0.560
papers+0.474
gallery+0.473
 Pret+0.467
OLOG+0.466
Neg logit contributions
iren-0.527
erker-0.490
 carbohyd-0.486
oter-0.484
urous-0.479
Token,
Token ID11
Feature activation-6.44e-02

Pos logit contributions
iren+0.255
erker+0.240
 carbohyd+0.237
oter+0.237
 Miko+0.234
Neg logit contributions
 Arbit-0.244
papers-0.205
gallery-0.205
OLOG-0.202
 Pret-0.202
Token police
Token ID1644
Feature activation+1.80e-02

Pos logit contributions
iren+0.272
erker+0.254
 carbohyd+0.251
oter+0.251
 Miko+0.249
Neg logit contributions
 Arbit-0.250
papers-0.209
gallery-0.208
OLOG-0.205
 Pret-0.205
Token Chief
Token ID5953
Feature activation-2.82e-01

Pos logit contributions
 Arbit+0.065
papers+0.053
 Pret+0.053
gallery+0.053
OLOG+0.053
Neg logit contributions
iren-0.080
 carbohyd-0.076
erker-0.075
oter-0.075
urous-0.074
Token Frank
Token ID5278
Feature activation-3.64e-01

Pos logit contributions
iren+1.195
erker+1.113
oter+1.105
 Miko+1.102
urous+1.093
Neg logit contributions
 Arbit-1.083
papers-0.911
gallery-0.909
OLOG-0.897
 Pret-0.884
Token Stra
Token ID15195
Feature activation-1.15e-01

Pos logit contributions
iren+1.563
erker+1.455
oter+1.444
 Miko+1.442
urous+1.431
Neg logit contributions
 Arbit-1.368
papers-1.148
gallery-1.146
OLOG-1.132
 Pret-1.110
Tokenub
Token ID549
Feature activation-1.25e+00

Pos logit contributions
iren+0.446
 carbohyd+0.427
erker+0.419
 Miko+0.416
oter+0.415
Neg logit contributions
 Arbit-0.469
gallery-0.402
papers-0.401
 Pret-0.394
OLOG-0.390
Token Jr
Token ID7504
Feature activation+1.97e-01

Pos logit contributions
iren+5.103
erker+4.736
oter+4.709
 carbohyd+4.664
 Miko+4.652
Neg logit contributions
 Arbit-4.962
gallery-4.176
papers-4.172
OLOG-4.121
 Pret-4.082
Token.
Token ID13
Feature activation+1.25e-01

Pos logit contributions
 Arbit+0.745
papers+0.619
gallery+0.614
 Pret+0.610
OLOG+0.608
Neg logit contributions
iren-0.823
erker-0.795
 carbohyd-0.787
oter-0.776
 Miko-0.772
Token said
Token ID531
Feature activation-1.62e-01

Pos logit contributions
 Arbit+0.443
 Pret+0.360
papers+0.360
gallery+0.359
OLOG+0.352
Neg logit contributions
iren-0.560
erker-0.537
 carbohyd-0.528
oter-0.526
urious-0.520
Token.
Token ID13
Feature activation-9.16e-02

Pos logit contributions
iren+0.704
erker+0.666
 carbohyd+0.662
oter+0.658
urous+0.652
Neg logit contributions
 Arbit-0.609
papers-0.505
gallery-0.501
 Pret-0.498
OLOG-0.496
Token
Token ID198
Feature activation-5.87e-02

Pos logit contributions
iren+0.379
 carbohyd+0.357
erker+0.357
oter+0.352
 Miko+0.345
Neg logit contributions
 Arbit-0.367
papers-0.307
 Pret-0.307
gallery-0.306
OLOG-0.300
Token >
Token ID1875
Feature activation-5.69e-02

Pos logit contributions
iren+1.331
erker+1.241
 carbohyd+1.234
oter+1.231
 Miko+1.222
Neg logit contributions
 Arbit-1.210
papers-1.010
gallery-1.009
OLOG-0.994
 Pret-0.991
Token D
Token ID360
Feature activation+2.33e-02

Pos logit contributions
iren+0.245
erker+0.229
 carbohyd+0.229
oter+0.227
urous+0.224
Neg logit contributions
 Arbit-0.218
papers-0.179
gallery-0.179
 Pret-0.178
OLOG-0.177
Tokenere
Token ID567
Feature activation+2.68e-02

Pos logit contributions
 Arbit+0.105
papers+0.090
gallery+0.089
 Pret+0.088
OLOG+0.088
Neg logit contributions
iren-0.081
 carbohyd-0.077
erker-0.077
 Miko-0.077
urous-0.075
Tokenf
Token ID69
Feature activation-2.89e-01

Pos logit contributions
 Arbit+0.106
papers+0.090
OLOG+0.089
gallery+0.089
 Pret+0.087
Neg logit contributions
iren-0.111
erker-0.103
oter-0.103
 Miko-0.101
ander-0.101
Token for
Token ID329
Feature activation-5.12e-01

Pos logit contributions
iren+1.251
erker+1.172
 carbohyd+1.166
oter+1.158
 Miko+1.151
Neg logit contributions
 Arbit-1.094
papers-0.900
gallery-0.897
 Pret-0.890
OLOG-0.888
Token Shared
Token ID39403
Feature activation-1.24e+00

Pos logit contributions
iren+2.086
 Miko+1.947
erker+1.928
oter+1.926
ander+1.915
Neg logit contributions
 Arbit-1.956
papers-1.727
gallery-1.706
OLOG-1.689
 Pret-1.608
Token <
Token ID1279
Feature activation-1.20e+00

Pos logit contributions
iren+2.165
 Miko+1.882
oter+1.833
ander+1.820
erker+1.817
Neg logit contributions
 Arbit-7.285
papers-6.792
OLOG-6.654
gallery-6.648
 Pret-6.465
Token '
Token ID705
Feature activation-7.42e-01

Pos logit contributions
iren+3.733
ander+3.551
 Miko+3.516
oter+3.492
erker+3.419
Neg logit contributions
 Arbit-5.204
papers-4.861
OLOG-4.791
gallery-4.776
 Cheong-4.557
Tokena
Token ID64
Feature activation-1.68e-01

Pos logit contributions
iren+3.003
oter+2.817
ander+2.809
idi+2.808
urous+2.777
Neg logit contributions
 Arbit-2.912
OLOG-2.467
 Pret-2.463
papers-2.377
 Cyan-2.344
Token,
Token ID837
Feature activation-7.98e-01

Pos logit contributions
iren+0.623
erker+0.578
 Miko+0.575
oter+0.570
ander+0.566
Neg logit contributions
 Arbit-0.721
papers-0.630
OLOG-0.621
gallery-0.620
 Pret-0.605
Token T
Token ID309
Feature activation-2.45e-01

Pos logit contributions
iren+2.757
 Miko+2.633
oter+2.579
erker+2.554
ander+2.542
Neg logit contributions
 Arbit-3.379
papers-3.126
gallery-3.059
OLOG-3.027
 Cheong-2.871
Token him
Token ID683
Feature activation-2.37e-01

Pos logit contributions
iren+0.892
erker+0.840
 carbohyd+0.833
oter+0.832
 Miko+0.823
Neg logit contributions
 Arbit-0.676
papers-0.552
gallery-0.550
OLOG-0.543
 Pret-0.540
Token that
Token ID326
Feature activation-2.30e-01

Pos logit contributions
iren+0.970
erker+0.908
 carbohyd+0.901
oter+0.897
urous+0.887
Neg logit contributions
 Arbit-0.950
papers-0.796
gallery-0.792
OLOG-0.785
 Pret-0.784
Token the
Token ID262
Feature activation+8.45e-03

Pos logit contributions
iren+0.930
erker+0.866
oter+0.858
 carbohyd+0.857
 Miko+0.850
Neg logit contributions
 Arbit-0.930
papers-0.786
gallery-0.784
OLOG-0.774
 Pret-0.770
Token aircraft
Token ID6215
Feature activation-2.48e-01

Pos logit contributions
 Arbit+0.033
papers+0.028
gallery+0.028
OLOG+0.027
 Pret+0.027
Neg logit contributions
iren-0.035
erker-0.033
 carbohyd-0.033
oter-0.033
urous-0.032
Token taking
Token ID2263
Feature activation+3.16e-01

Pos logit contributions
iren+1.041
erker+0.970
oter+0.962
 carbohyd+0.956
 Miko+0.956
Neg logit contributions
 Arbit-0.962
papers-0.807
gallery-0.806
OLOG-0.795
 Pret-0.789
Token off
Token ID572
Feature activation-1.24e+00

Pos logit contributions
 Arbit+1.125
papers+0.922
gallery+0.920
 Pret+0.910
OLOG+0.906
Neg logit contributions
iren-1.427
erker-1.350
 carbohyd-1.342
oter-1.330
urous-1.319
Token had
Token ID550
Feature activation-1.96e-01

Pos logit contributions
iren+4.817
 Miko+4.531
ander+4.391
oter+4.380
erker+4.334
Neg logit contributions
 Arbit-4.897
gallery-4.267
papers-4.224
OLOG-4.157
 Pret-3.994
Token his
Token ID465
Feature activation+1.31e-01

Pos logit contributions
iren+0.767
erker+0.712
oter+0.705
 carbohyd+0.704
 Miko+0.699
Neg logit contributions
 Arbit-0.815
papers-0.692
gallery-0.691
OLOG-0.682
 Pret-0.679
Token wings
Token ID12098
Feature activation-6.17e-02

Pos logit contributions
 Arbit+0.546
papers+0.462
gallery+0.459
 Pret+0.456
OLOG+0.455
Neg logit contributions
iren-0.515
erker-0.484
 carbohyd-0.482
oter-0.477
urous-0.473
Token folded
Token ID24650
Feature activation+4.91e-01

Pos logit contributions
iren+0.220
erker+0.204
 carbohyd+0.202
oter+0.201
 Miko+0.199
Neg logit contributions
 Arbit-0.279
papers-0.240
gallery-0.239
 Pret-0.236
OLOG-0.235
Token.
Token ID13
Feature activation-2.48e-01

Pos logit contributions
 Arbit+1.907
papers+1.596
gallery+1.578
 Pret+1.564
OLOG+1.548
Neg logit contributions
iren-2.049
erker-1.939
 carbohyd-1.928
oter-1.895
 Miko-1.876
Token should
Token ID815
Feature activation+9.99e-03

Pos logit contributions
iren+0.724
erker+0.675
 carbohyd+0.673
oter+0.668
 Miko+0.663
Neg logit contributions
 Arbit-0.664
papers-0.554
gallery-0.553
 Pret-0.544
OLOG-0.543
Token not
Token ID407
Feature activation+1.24e-01

Pos logit contributions
 Arbit+0.042
papers+0.035
gallery+0.035
 Pret+0.035
OLOG+0.034
Neg logit contributions
iren-0.039
erker-0.037
 carbohyd-0.036
oter-0.036
 Miko-0.036
Token fear
Token ID3252
Feature activation-2.97e-01

Pos logit contributions
 Arbit+0.496
papers+0.417
gallery+0.416
 Pret+0.410
OLOG+0.408
Neg logit contributions
iren-0.506
erker-0.473
 carbohyd-0.472
oter-0.465
 Miko-0.463
Token the
Token ID262
Feature activation-2.44e-01

Pos logit contributions
iren+1.212
erker+1.128
oter+1.121
 carbohyd+1.114
 Miko+1.111
Neg logit contributions
 Arbit-1.184
papers-0.999
gallery-0.998
OLOG-0.985
 Pret-0.977
Token Bl
Token ID1086
Feature activation-5.03e-01

Pos logit contributions
iren+0.988
erker+0.917
oter+0.911
 carbohyd+0.905
 Miko+0.903
Neg logit contributions
 Arbit-0.987
gallery-0.834
papers-0.834
OLOG-0.823
 Pret-0.816
Tokenoc
Token ID420
Feature activation-1.24e+00

Pos logit contributions
iren+1.052
erker+0.907
oter+0.894
 carbohyd+0.882
 Miko+0.870
Neg logit contributions
 Arbit-3.022
papers-2.704
gallery-2.702
OLOG-2.678
 Pret-2.672
Token Qué
Token ID46345
Feature activation+1.78e-01

Pos logit contributions
iren+4.760
erker+4.421
oter+4.404
urious+4.372
urous+4.370
Neg logit contributions
 Arbit-5.088
gallery-4.366
OLOG-4.303
papers-4.295
 Pret-4.209
Tokenb
Token ID65
Feature activation-3.42e-01

Pos logit contributions
 Arbit+0.436
papers+0.322
gallery+0.318
 Pret+0.310
OLOG+0.306
Neg logit contributions
iren-1.001
erker-0.960
 carbohyd-0.958
 Miko-0.952
urous-0.944
Tokené
Token ID2634
Feature activation-5.45e-01

Pos logit contributions
iren+1.270
ander+1.152
oter+1.150
erker+1.134
urous+1.132
Neg logit contributions
 Arbit-1.498
gallery-1.309
OLOG-1.303
papers-1.301
 Pret-1.269
Tokenco
Token ID1073
Feature activation-2.29e-01

Pos logit contributions
iren+2.311
oter+2.158
erker+2.135
ander+2.123
urious+2.116
Neg logit contributions
 Arbit-2.045
papers-1.733
gallery-1.724
OLOG-1.712
 Pret-1.700
Tokenis
Token ID271
Feature activation-2.70e-01

Pos logit contributions
iren+1.134
erker+1.068
 carbohyd+1.067
 Miko+1.061
oter+1.060
Neg logit contributions
 Arbit-0.717
papers-0.568
gallery-0.567
OLOG-0.557
 Pret-0.557
Tokenset
Token ID2617
Feature activation-3.24e-01

Pos logit contributions
iren+0.245
erker+0.230
 carbohyd+0.228
oter+0.227
 Miko+0.227
Neg logit contributions
 Arbit-0.205
papers-0.172
gallery-0.171
 Pret-0.168
OLOG-0.167
Token dir
Token ID26672
Feature activation-9.69e-01

Pos logit contributions
iren+1.181
erker+1.089
oter+1.079
 carbohyd+1.074
 Miko+1.068
Neg logit contributions
 Arbit-1.441
papers-1.238
gallery-1.234
OLOG-1.223
 Pret-1.213
Token=
Token ID28
Feature activation-3.20e-01

Pos logit contributions
iren+3.261
erker+2.970
oter+2.954
ander+2.927
 Miko+2.901
Neg logit contributions
 Arbit-4.521
gallery-3.889
papers-3.887
OLOG-3.882
 Pret-3.833
Tokenc
Token ID66
Feature activation-3.17e-01

Pos logit contributions
iren+1.194
erker+1.105
 carbohyd+1.097
oter+1.093
 Miko+1.086
Neg logit contributions
 Arbit-1.396
papers-1.197
gallery-1.195
OLOG-1.176
 Pret-1.173
Token\
Token ID59
Feature activation-1.42e-01

Pos logit contributions
iren+1.190
erker+1.102
 carbohyd+1.094
oter+1.087
 Miko+1.081
Neg logit contributions
 Arbit-1.374
papers-1.176
gallery-1.174
OLOG-1.157
 Pret-1.156
Token:\
Token ID7479
Feature activation-1.22e+00

Pos logit contributions
iren+0.559
erker+0.521
 carbohyd+0.518
oter+0.514
 Miko+0.511
Neg logit contributions
 Arbit-0.592
papers-0.504
gallery-0.502
 Pret-0.494
OLOG-0.494
Tokentmp
Token ID22065
Feature activation-1.77e-01

Pos logit contributions
iren+4.716
oter+4.350
erker+4.338
ander+4.289
urious+4.288
Neg logit contributions
 Arbit-4.994
OLOG-4.233
papers-4.203
gallery-4.200
 Pret-4.126
Token:
Token ID25
Feature activation-4.38e-01

Pos logit contributions
iren+0.665
erker+0.616
 carbohyd+0.612
oter+0.609
 Miko+0.605
Neg logit contributions
 Arbit-0.765
papers-0.654
gallery-0.653
OLOG-0.643
 Pret-0.642
Token */
Token ID9466
Feature activation+3.86e-03

Pos logit contributions
iren+1.515
erker+1.392
oter+1.377
 carbohyd+1.373
 Miko+1.362
Neg logit contributions
 Arbit-2.023
papers-1.748
gallery-1.744
OLOG-1.725
 Pret-1.717
Token This
Token ID770
Feature activation+1.75e-01

Pos logit contributions
 Arbit+0.015
papers+0.013
gallery+0.013
OLOG+0.012
 Pret+0.012
Neg logit contributions
iren-0.016
erker-0.015
 carbohyd-0.015
oter-0.015
 Miko-0.015
Token sets
Token ID5621
Feature activation+1.24e-01

Pos logit contributions
 Arbit+0.690
gallery+0.569
papers+0.569
 Pret+0.567
OLOG+0.562
Neg logit contributions
iren-0.732
erker-0.685
 carbohyd-0.684
oter-0.676
urous-0.671
Token last
Token ID938
Feature activation-2.66e-01

Pos logit contributions
iren+1.443
erker+1.339
oter+1.335
 Miko+1.327
urous+1.318
Neg logit contributions
 Arbit-1.304
papers-1.099
gallery-1.098
OLOG-1.083
 Pret-1.066
Token weekend
Token ID5041
Feature activation+1.50e-01

Pos logit contributions
iren+1.217
erker+1.139
oter+1.132
 Miko+1.124
 carbohyd+1.123
Neg logit contributions
 Arbit-0.934
papers-0.772
gallery-0.768
OLOG-0.759
 Pret-0.744
Token.
Token ID13
Feature activation-2.57e-01

Pos logit contributions
 Arbit+0.591
papers+0.493
gallery+0.487
 Pret+0.486
OLOG+0.481
Neg logit contributions
iren-0.625
erker-0.591
 carbohyd-0.590
oter-0.578
urous-0.577
Token Michael
Token ID3899
Feature activation-1.61e-01

Pos logit contributions
iren+1.012
erker+0.939
oter+0.931
 carbohyd+0.926
 Miko+0.924
Neg logit contributions
 Arbit-1.062
papers-0.903
gallery-0.899
OLOG-0.888
 Pret-0.883
Token Sch
Token ID3059
Feature activation+6.30e-02

Pos logit contributions
iren+0.720
erker+0.677
 carbohyd+0.674
oter+0.670
 Miko+0.663
Neg logit contributions
 Arbit-0.582
gallery-0.478
papers-0.478
 Pret-0.474
OLOG-0.471
Tokenum
Token ID388
Feature activation-1.22e+00

Pos logit contributions
 Arbit+0.256
gallery+0.221
papers+0.219
 Pret+0.214
OLOG+0.213
Neg logit contributions
iren-0.246
 carbohyd-0.237
 Miko-0.231
erker-0.231
oter-0.228
Tokenacher
Token ID3493
Feature activation-2.74e-01

Pos logit contributions
iren+2.026
oter+1.760
erker+1.661
ander+1.587
urous+1.507
Neg logit contributions
 Arbit-7.792
OLOG-7.108
papers-7.087
gallery-7.031
 Pret-6.890
Token's
Token ID338
Feature activation-2.60e-01

Pos logit contributions
iren+1.117
erker+1.037
oter+1.031
 carbohyd+1.023
 Miko+1.021
Neg logit contributions
 Arbit-1.095
papers-0.923
gallery-0.922
OLOG-0.911
 Pret-0.903
Token Mercedes
Token ID21279
Feature activation-5.11e-01

Pos logit contributions
iren+1.061
erker+0.985
oter+0.978
 carbohyd+0.974
 Miko+0.971
Neg logit contributions
 Arbit-1.036
papers-0.876
gallery-0.873
OLOG-0.862
 Pret-0.853
Token was
Token ID373
Feature activation-2.23e-02

Pos logit contributions
iren+2.132
erker+1.987
oter+1.970
 Miko+1.956
 carbohyd+1.947
Neg logit contributions
 Arbit-1.985
papers-1.679
gallery-1.671
OLOG-1.658
 Pret-1.627
Token third
Token ID2368
Feature activation-3.93e-01

Pos logit contributions
iren+0.088
erker+0.082
 carbohyd+0.081
oter+0.081
urous+0.080
Neg logit contributions
 Arbit-0.093
papers-0.079
gallery-0.079
 Pret-0.078
OLOG-0.078
Token Fasc
Token ID41467
Feature activation-3.94e-02

Pos logit contributions
 Arbit+0.677
papers+0.564
 Pret+0.559
OLOG+0.558
gallery+0.558
Neg logit contributions
iren-0.709
erker-0.667
 carbohyd-0.663
oter-0.655
 Miko-0.649
Token is
Token ID318
Feature activation-4.48e-01

Pos logit contributions
iren+0.126
 carbohyd+0.118
erker+0.117
 Miko+0.116
oter+0.114
Neg logit contributions
 Arbit-0.190
papers-0.166
gallery-0.165
OLOG-0.164
 Pret-0.162
Tokenm
Token ID76
Feature activation-3.31e-01

Pos logit contributions
iren+1.832
erker+1.705
oter+1.691
 carbohyd+1.686
 Miko+1.676
Neg logit contributions
 Arbit-1.784
papers-1.504
gallery-1.502
OLOG-1.481
 Pret-1.472
Token of
Token ID286
Feature activation-4.45e-01

Pos logit contributions
iren+1.354
erker+1.263
 carbohyd+1.251
oter+1.249
 Miko+1.239
Neg logit contributions
 Arbit-1.331
papers-1.118
gallery-1.115
OLOG-1.101
 Pret-1.099
Token th
Token ID294
Feature activation-2.81e-01

Pos logit contributions
iren+1.869
erker+1.744
oter+1.729
 carbohyd+1.726
 Miko+1.714
Neg logit contributions
 Arbit-1.728
papers-1.448
gallery-1.445
OLOG-1.425
 Pret-1.418
Token e
Token ID304
Feature activation-1.21e+00

Pos logit contributions
iren+1.064
erker+0.986
 carbohyd+0.980
oter+0.972
 Miko+0.969
Neg logit contributions
 Arbit-1.211
papers-1.032
gallery-1.029
OLOG-1.018
 Pret-1.013
Token Potato
Token ID43876
Feature activation+6.33e-02

Pos logit contributions
iren+5.143
oter+4.757
erker+4.749
urous+4.722
 Miko+4.687
Neg logit contributions
 Arbit-4.483
papers-3.795
gallery-3.788
OLOG-3.728
 Pret-3.657
Token
Token ID198
Feature activation-2.47e-01

Pos logit contributions
 Arbit+0.242
papers+0.201
gallery+0.200
 Pret+0.198
OLOG+0.197
Neg logit contributions
iren-0.270
erker-0.254
 carbohyd-0.253
oter-0.250
urous-0.249
Token
Token ID198
Feature activation-1.62e-01

Pos logit contributions
iren+1.002
erker+0.937
 carbohyd+0.930
oter+0.923
 Miko+0.918
Neg logit contributions
 Arbit-1.002
papers-0.849
gallery-0.849
OLOG-0.836
 Pret-0.832
Token1
Token ID16
Feature activation+5.64e-02

Pos logit contributions
iren+0.667
erker+0.623
 carbohyd+0.619
oter+0.615
 Miko+0.613
Neg logit contributions
 Arbit-0.642
papers-0.543
gallery-0.542
OLOG-0.533
 Pret-0.529
Token
Token ID198
Feature activation-4.70e-01

Pos logit contributions
 Arbit+0.224
gallery+0.187
papers+0.187
 Pret+0.185
OLOG+0.183
Neg logit contributions
iren-0.235
erker-0.220
 carbohyd-0.217
oter-0.216
urous-0.214
Token is
Token ID318
Feature activation-1.32e-01

Pos logit contributions
 Arbit+0.818
papers+0.681
gallery+0.678
 Pret+0.669
OLOG+0.666
Neg logit contributions
iren-0.902
 carbohyd-0.843
erker-0.842
oter-0.833
 Miko-0.826
Token spending
Token ID4581
Feature activation-5.42e-01

Pos logit contributions
iren+0.485
erker+0.448
oter+0.445
 Miko+0.442
 carbohyd+0.440
Neg logit contributions
 Arbit-0.581
papers-0.500
gallery-0.497
OLOG-0.495
 Pret-0.489
Token money
Token ID1637
Feature activation+1.32e-01

Pos logit contributions
iren+2.098
erker+1.942
oter+1.929
 Miko+1.918
urous+1.911
Neg logit contributions
 Arbit-2.250
papers-1.922
gallery-1.916
OLOG-1.908
 Pret-1.872
Token there
Token ID612
Feature activation+1.10e-01

Pos logit contributions
 Arbit+0.507
papers+0.423
gallery+0.421
 Pret+0.415
OLOG+0.415
Neg logit contributions
iren-0.562
erker-0.525
 carbohyd-0.522
oter-0.519
 Miko-0.515
Token,
Token ID11
Feature activation+2.24e-01

Pos logit contributions
 Arbit+0.447
papers+0.378
gallery+0.377
OLOG+0.371
 Pret+0.370
Neg logit contributions
iren-0.442
erker-0.411
 carbohyd-0.410
oter-0.406
 Miko-0.403
Token though
Token ID996
Feature activation+8.31e-01

Pos logit contributions
 Arbit+1.097
papers+0.950
gallery+0.950
 Pret+0.940
OLOG+0.935
Neg logit contributions
iren-0.722
erker-0.659
 carbohyd-0.656
oter-0.649
urous-0.640
Token.
Token ID13
Feature activation+3.50e-01

Pos logit contributions
 Arbit+3.053
 Pret+2.489
papers+2.481
gallery+2.463
 Cyan+2.423
Neg logit contributions
iren-3.577
 carbohyd-3.484
erker-3.442
oter-3.329
urous-3.323
Token It
Token ID632
Feature activation+7.18e-02

Pos logit contributions
 Arbit+1.354
gallery+1.120
papers+1.119
 Pret+1.108
OLOG+1.100
Neg logit contributions
iren-1.494
 carbohyd-1.405
erker-1.398
oter-1.381
urious-1.366
Token's
Token ID338
Feature activation-1.91e-01

Pos logit contributions
 Arbit+0.292
papers+0.247
gallery+0.247
OLOG+0.244
 Pret+0.242
Neg logit contributions
iren-0.288
erker-0.268
oter-0.266
 carbohyd-0.264
 Miko-0.263
Token investing
Token ID14771
Feature activation-6.31e-01

Pos logit contributions
iren+0.689
erker+0.636
oter+0.634
 Miko+0.627
ander+0.622
Neg logit contributions
 Arbit-0.846
papers-0.735
gallery-0.730
OLOG-0.730
 Pret-0.714
Token in
Token ID287
Feature activation-3.56e-02

Pos logit contributions
iren+2.540
erker+2.347
oter+2.342
 Miko+2.332
ander+2.320
Neg logit contributions
 Arbit-2.521
gallery-2.139
papers-2.134
OLOG-2.116
 Pret-2.078
Token
Token ID198
Feature activation-1.22e-01

Pos logit contributions
iren+0.826
ander+0.763
 Miko+0.758
erker+0.753
oter+0.750
Neg logit contributions
 Arbit-1.155
OLOG-1.004
papers-1.001
gallery-0.995
 Pret-0.973
TokenI
Token ID40
Feature activation+3.87e-01

Pos logit contributions
iren+0.460
erker+0.425
 carbohyd+0.425
oter+0.422
 Miko+0.417
Neg logit contributions
 Arbit-0.527
papers-0.451
gallery-0.451
OLOG-0.445
 Pret-0.442
Token fur
Token ID9230
Feature activation+7.50e-01

Pos logit contributions
 Arbit+1.569
papers+1.322
gallery+1.320
OLOG+1.303
 Pret+1.300
Neg logit contributions
iren-1.559
erker-1.449
 carbohyd-1.443
oter-1.436
 Miko-1.424
Tokenrow
Token ID808
Feature activation+9.64e-01

Pos logit contributions
 Arbit+2.630
papers+2.116
 Pret+2.097
OLOG+2.095
gallery+2.068
Neg logit contributions
iren-3.357
 carbohyd-3.310
erker-3.234
 Miko-3.182
oter-3.173
Token my
Token ID616
Feature activation+6.83e-01

Pos logit contributions
 Arbit+4.140
 Pret+3.520
papers+3.515
OLOG+3.453
gallery+3.446
Neg logit contributions
iren-3.491
 carbohyd-3.369
erker-3.300
oter-3.280
 Miko-3.211
Token eyebrows
Token ID26928
Feature activation+1.00e+00

Pos logit contributions
 Arbit+2.114
 Pret+1.653
papers+1.651
OLOG+1.645
gallery+1.624
Neg logit contributions
iren-3.394
 carbohyd-3.218
erker-3.175
oter-3.152
 Miko-3.135
Token at
Token ID379
Feature activation+3.74e-01

Pos logit contributions
 Arbit+3.675
papers+3.020
 Pret+2.993
gallery+2.972
OLOG+2.910
Neg logit contributions
iren-4.315
 carbohyd-4.159
erker-4.041
oter-3.998
urous-3.986
Token the
Token ID262
Feature activation+4.53e-01

Pos logit contributions
 Arbit+1.423
 Pret+1.165
papers+1.154
gallery+1.149
OLOG+1.144
Neg logit contributions
iren-1.613
 carbohyd-1.534
erker-1.510
oter-1.489
urious-1.477
Token intruder
Token ID48927
Feature activation+4.19e-01

Pos logit contributions
 Arbit+1.862
papers+1.551
gallery+1.546
 Pret+1.540
OLOG+1.534
Neg logit contributions
iren-1.807
 carbohyd-1.696
erker-1.686
oter-1.667
ander-1.644
Token.
Token ID13
Feature activation+4.31e-01

Pos logit contributions
 Arbit+1.611
 Pret+1.332
papers+1.329
gallery+1.313
OLOG+1.305
Neg logit contributions
iren-1.752
 carbohyd-1.680
erker-1.653
oter-1.635
ander-1.618
Token "
Token ID366
Feature activation+4.32e-01

Pos logit contributions
 Arbit+1.688
 Pret+1.404
papers+1.383
gallery+1.380
OLOG+1.364
Neg logit contributions
iren-1.836
 carbohyd-1.776
erker-1.718
oter-1.704
urious-1.671
Token to
Token ID284
Feature activation-5.94e-02

Pos logit contributions
 Arbit+1.064
papers+0.882
 Pret+0.871
gallery+0.867
OLOG+0.865
Neg logit contributions
iren-1.152
erker-1.073
 carbohyd-1.071
oter-1.052
urous-1.047
Token save
Token ID3613
Feature activation-3.71e-02

Pos logit contributions
iren+0.224
erker+0.208
 carbohyd+0.206
oter+0.205
 Miko+0.203
Neg logit contributions
 Arbit-0.257
papers-0.219
gallery-0.218
 Pret-0.216
OLOG-0.216
Token the
Token ID262
Feature activation+2.21e-02

Pos logit contributions
iren+0.156
erker+0.145
 carbohyd+0.144
oter+0.144
 Miko+0.142
Neg logit contributions
 Arbit-0.145
papers-0.122
gallery-0.120
OLOG-0.119
 Pret-0.119
Token Def
Token ID2896
Feature activation-1.17e-01

Pos logit contributions
 Arbit+0.085
papers+0.072
gallery+0.071
OLOG+0.070
 Pret+0.070
Neg logit contributions
iren-0.093
erker-0.087
oter-0.086
 carbohyd-0.086
 Miko-0.085
Tokenerred
Token ID17436
Feature activation+3.21e-01

Pos logit contributions
iren+0.553
erker+0.518
oter+0.515
urious+0.511
ander+0.509
Neg logit contributions
 Arbit-0.399
papers-0.323
gallery-0.323
OLOG-0.320
 Pret-0.318
Token Action
Token ID7561
Feature activation+8.13e-01

Pos logit contributions
 Arbit+1.220
papers+1.000
gallery+0.995
 Pret+0.993
OLOG+0.980
Neg logit contributions
iren-1.389
erker-1.309
 carbohyd-1.305
oter-1.280
urous-1.277
Token for
Token ID329
Feature activation+1.52e-01

Pos logit contributions
 Arbit+2.586
papers+1.990
 Pret+1.984
gallery+1.962
OLOG+1.950
Neg logit contributions
iren-4.042
 carbohyd-3.842
erker-3.824
urious-3.712
oter-3.709
Token Childhood
Token ID40992
Feature activation+5.06e-01

Pos logit contributions
 Arbit+0.565
papers+0.464
 Pret+0.457
gallery+0.457
OLOG+0.455
Neg logit contributions
iren-0.668
erker-0.627
 carbohyd-0.623
oter-0.618
 Miko-0.613
Token Arri
Token ID27350
Feature activation+4.30e-01

Pos logit contributions
 Arbit+1.708
 Pret+1.340
papers+1.338
gallery+1.315
OLOG+1.313
Neg logit contributions
iren-2.404
 carbohyd-2.312
erker-2.300
oter-2.253
 Miko-2.228
Tokenvals
Token ID12786
Feature activation+3.39e-01

Pos logit contributions
 Arbit+1.872
papers+1.602
gallery+1.598
OLOG+1.576
 Pret+1.571
Neg logit contributions
iren-1.606
erker-1.485
 carbohyd-1.474
oter-1.468
 Miko-1.456
Token (
Token ID357
Feature activation+1.15e-01

Pos logit contributions
 Arbit+1.438
papers+1.210
OLOG+1.193
 Pret+1.193
gallery+1.184
Neg logit contributions
iren-1.318
 carbohyd-1.230
erker-1.227
oter-1.203
 Miko-1.197
Token hours
Token ID2250
Feature activation-3.09e-01

Pos logit contributions
iren+1.398
erker+1.294
oter+1.289
 Miko+1.283
ander+1.280
Neg logit contributions
 Arbit-1.434
papers-1.223
gallery-1.221
OLOG-1.208
 Pret-1.180
Token before
Token ID878
Feature activation-5.03e-01

Pos logit contributions
iren+1.418
erker+1.329
oter+1.320
 Miko+1.314
 carbohyd+1.314
Neg logit contributions
 Arbit-1.082
papers-0.890
gallery-0.884
OLOG-0.871
 Pret-0.865
Token
Token ID851
Feature activation-4.20e-01

Pos logit contributions
iren+1.975
erker+1.822
oter+1.811
 Miko+1.803
 carbohyd+1.799
Neg logit contributions
 Arbit-2.082
gallery-1.775
papers-1.774
OLOG-1.755
 Pret-1.726
Token it
Token ID340
Feature activation+1.76e-01

Pos logit contributions
iren+1.665
erker+1.544
oter+1.537
 Miko+1.530
 carbohyd+1.529
Neg logit contributions
 Arbit-1.716
papers-1.455
gallery-1.453
OLOG-1.439
 Pret-1.419
Token makes
Token ID1838
Feature activation+3.51e-01

Pos logit contributions
 Arbit+0.656
gallery+0.547
papers+0.543
 Pret+0.534
OLOG+0.534
Neg logit contributions
iren-0.764
erker-0.714
 carbohyd-0.712
oter-0.707
 Miko-0.702
Token it
Token ID340
Feature activation+8.37e-01

Pos logit contributions
 Arbit+1.453
gallery+1.228
papers+1.223
 Pret+1.214
OLOG+1.205
Neg logit contributions
iren-1.391
erker-1.295
 carbohyd-1.284
oter-1.271
urious-1.262
Token all
Token ID477
Feature activation+4.28e-01

Pos logit contributions
 Arbit+3.507
gallery+2.969
 Pret+2.923
papers+2.903
OLOG+2.900
Neg logit contributions
iren-3.236
 carbohyd-3.025
erker-2.961
oter-2.957
urious-2.930
Token toler
Token ID8214
Feature activation+1.27e+00

Pos logit contributions
 Arbit+1.696
gallery+1.420
papers+1.406
OLOG+1.400
 Pret+1.396
Neg logit contributions
iren-1.763
 carbohyd-1.640
erker-1.637
oter-1.617
 Miko-1.609
Tokenable
Token ID540
Feature activation+4.61e-01

Pos logit contributions
 Arbit+3.606
gallery+2.903
papers+2.829
OLOG+2.757
 Pret+2.669
Neg logit contributions
iren-6.218
 carbohyd-6.079
 Miko-5.895
erker-5.888
oter-5.787
Token.
Token ID13
Feature activation+7.11e-02

Pos logit contributions
 Arbit+1.797
gallery+1.503
papers+1.492
 Pret+1.477
OLOG+1.472
Neg logit contributions
iren-1.929
 carbohyd-1.798
erker-1.796
oter-1.778
urious-1.754
Token
Token ID198
Feature activation+2.00e-01

Pos logit contributions
 Arbit+0.291
papers+0.245
gallery+0.245
OLOG+0.242
 Pret+0.241
Neg logit contributions
iren-0.285
erker-0.265
 carbohyd-0.263
oter-0.263
 Miko-0.259
Token |
Token ID930
Feature activation-1.99e-01

Pos logit contributions
iren+0.441
erker+0.410
 carbohyd+0.407
oter+0.405
 Miko+0.402
Neg logit contributions
 Arbit-0.453
gallery-0.384
papers-0.383
OLOG-0.377
 Pret-0.375
Token 15
Token ID1315
Feature activation+1.44e-01

Pos logit contributions
iren+0.929
 Miko+0.869
erker+0.867
oter+0.863
ander+0.858
Neg logit contributions
 Arbit-0.665
papers-0.548
gallery-0.541
OLOG-0.537
 Pret-0.524
Token46
Token ID3510
Feature activation-5.22e-02

Pos logit contributions
 Arbit+0.574
papers+0.483
gallery+0.482
OLOG+0.476
 Pret+0.473
Neg logit contributions
iren-0.590
erker-0.550
oter-0.545
 carbohyd-0.543
 Miko-0.540
Token |
Token ID930
Feature activation+4.54e-02

Pos logit contributions
iren+0.180
 Miko+0.166
ander+0.166
oter+0.164
erker+0.164
Neg logit contributions
 Arbit-0.237
papers-0.207
OLOG-0.202
gallery-0.201
 Pret-0.200
Token |
Token ID930
Feature activation-1.95e-01

Pos logit contributions
 Arbit+0.182
gallery+0.154
papers+0.152
OLOG+0.151
 Pret+0.150
Neg logit contributions
iren-0.187
erker-0.176
oter-0.173
urous-0.172
 carbohyd-0.172
Token 6
Token ID718
Feature activation+1.18e+00

Pos logit contributions
iren+0.864
erker+0.817
 carbohyd+0.805
oter+0.801
 Miko+0.798
Neg logit contributions
 Arbit-0.725
papers-0.595
gallery-0.594
OLOG-0.591
 Pret-0.585
Token |
Token ID930
Feature activation+1.67e-01

Pos logit contributions
 Arbit+4.683
gallery+3.979
papers+3.944
 Pret+3.877
OLOG+3.864
Neg logit contributions
iren-4.807
 carbohyd-4.713
erker-4.509
 nodd-4.447
oter-4.432
Token org
Token ID8745
Feature activation+1.17e-01

Pos logit contributions
 Arbit+0.731
gallery+0.623
papers+0.614
OLOG+0.611
 Pret+0.609
Neg logit contributions
iren-0.624
erker-0.579
urous-0.571
oter-0.571
 carbohyd-0.570
Token.
Token ID764
Feature activation+1.91e-01

Pos logit contributions
 Arbit+0.423
papers+0.352
OLOG+0.351
gallery+0.346
 Pret+0.346
Neg logit contributions
iren-0.521
erker-0.485
ander-0.485
oter-0.484
 Miko-0.480
Token cl
Token ID537
Feature activation+2.15e-01

Pos logit contributions
 Arbit+0.788
papers+0.671
gallery+0.666
OLOG+0.666
 Pret+0.656
Neg logit contributions
iren-0.755
erker-0.701
oter-0.698
 Miko-0.690
urous-0.684
Tokenojure
Token ID32511
Feature activation-4.55e-01

Pos logit contributions
 Arbit+1.190
papers+1.055
gallery+1.053
OLOG+1.044
 Pret+1.040
Neg logit contributions
iren-0.549
erker-0.489
oter-0.481
 carbohyd-0.480
 Miko-0.474
Tokenatively
Token ID9404
Feature activation-6.50e-01

Pos logit contributions
 Arbit+2.222
gallery+1.967
papers+1.931
OLOG+1.909
 Pret+1.876
Neg logit contributions
iren-1.534
 carbohyd-1.445
erker-1.431
 Miko-1.401
urous-1.353
Token sharing
Token ID7373
Feature activation-5.09e-01

Pos logit contributions
iren+2.362
erker+2.158
oter+2.158
ander+2.146
 Miko+2.142
Neg logit contributions
 Arbit-2.833
OLOG-2.448
papers-2.443
gallery-2.434
 Pret-2.395
Token 1
Token ID352
Feature activation-3.02e-02

Pos logit contributions
iren+1.973
erker+1.828
oter+1.825
 Miko+1.805
urious+1.797
Neg logit contributions
 Arbit-2.112
gallery-1.802
papers-1.797
OLOG-1.785
 Pret-1.763
Token,
Token ID11
Feature activation-3.71e-01

Pos logit contributions
iren+0.124
erker+0.116
 carbohyd+0.115
oter+0.114
urous+0.113
Neg logit contributions
 Arbit-0.121
papers-0.101
gallery-0.101
OLOG-0.099
 Pret-0.099
Token024
Token ID40839
Feature activation-3.95e-01

Pos logit contributions
iren+1.397
erker+1.291
oter+1.280
 carbohyd+1.273
 Miko+1.267
Neg logit contributions
 Arbit-1.598
papers-1.366
gallery-1.364
OLOG-1.347
 Pret-1.340
Token times
Token ID1661
Feature activation+2.73e-01

Pos logit contributions
iren+1.586
erker+1.477
oter+1.465
 carbohyd+1.458
 Miko+1.454
Neg logit contributions
 Arbit-1.593
papers-1.345
gallery-1.343
OLOG-1.330
 Pret-1.321
Token more
Token ID517
Feature activation-1.12e-01

Pos logit contributions
 Arbit+1.064
papers+0.888
gallery+0.888
 Pret+0.873
OLOG+0.867
Neg logit contributions
iren-1.140
erker-1.070
 carbohyd-1.068
oter-1.048
urous-1.047
Token content
Token ID2695
Feature activation-3.12e-02

Pos logit contributions
iren+0.454
erker+0.422
 carbohyd+0.418
oter+0.418
 Miko+0.414
Neg logit contributions
 Arbit-0.452
papers-0.382
gallery-0.380
OLOG-0.374
 Pret-0.374
Token than
Token ID621
Feature activation+1.12e-01

Pos logit contributions
iren+0.131
erker+0.122
oter+0.121
 carbohyd+0.121
 Miko+0.120
Neg logit contributions
 Arbit-0.122
papers-0.102
gallery-0.102
OLOG-0.100
 Pret-0.100
Token they
Token ID484
Feature activation-2.23e-02

Pos logit contributions
 Arbit+0.473
papers+0.402
gallery+0.401
OLOG+0.396
 Pret+0.395
Neg logit contributions
iren-0.434
erker-0.403
 carbohyd-0.399
oter-0.399
 Miko-0.395
Token currently
Token ID3058
Feature activation+2.04e-01

Pos logit contributions
iren+0.088
erker+0.082
oter+0.082
 carbohyd+0.081
 Miko+0.081
Neg logit contributions
 Arbit-0.092
papers-0.078
gallery-0.078
OLOG-0.077
 Pret-0.076
Token is
Token ID318
Feature activation-2.17e-01

Pos logit contributions
iren+1.319
erker+1.228
oter+1.223
 carbohyd+1.215
 Miko+1.212
Neg logit contributions
 Arbit-1.160
gallery-0.967
papers-0.965
OLOG-0.954
 Pret-0.945
Token difficult
Token ID2408
Feature activation+4.71e-03

Pos logit contributions
iren+0.829
erker+0.771
 carbohyd+0.763
oter+0.759
urous+0.752
Neg logit contributions
 Arbit-0.925
papers-0.787
gallery-0.784
OLOG-0.775
 Pret-0.773
Token.
Token ID13
Feature activation+4.48e-01

Pos logit contributions
 Arbit+0.019
papers+0.016
gallery+0.016
OLOG+0.016
 Pret+0.015
Neg logit contributions
iren-0.019
erker-0.018
 carbohyd-0.018
oter-0.018
 Miko-0.018
Token The
Token ID383
Feature activation+1.52e-01

Pos logit contributions
 Arbit+1.772
 Pret+1.463
gallery+1.461
papers+1.461
OLOG+1.448
Neg logit contributions
iren-1.880
 carbohyd-1.786
erker-1.762
oter-1.733
urious-1.721
Token last
Token ID938
Feature activation+4.96e-01

Pos logit contributions
 Arbit+0.610
papers+0.512
gallery+0.511
OLOG+0.505
 Pret+0.504
Neg logit contributions
iren-0.622
erker-0.581
 carbohyd-0.578
oter-0.574
 Miko-0.568
Token such
Token ID884
Feature activation+5.73e-01

Pos logit contributions
 Arbit+1.958
papers+1.633
gallery+1.625
 Pret+1.622
OLOG+1.595
Neg logit contributions
iren-2.051
 carbohyd-1.943
erker-1.921
oter-1.902
urious-1.890
Token event
Token ID1785
Feature activation+3.19e-01

Pos logit contributions
 Arbit+2.272
papers+1.888
gallery+1.882
 Pret+1.876
OLOG+1.860
Neg logit contributions
iren-2.346
 carbohyd-2.230
erker-2.211
oter-2.184
urous-2.172
Token,
Token ID11
Feature activation+7.43e-02

Pos logit contributions
 Arbit+1.235
papers+1.028
gallery+1.024
OLOG+1.017
 Pret+1.011
Neg logit contributions
iren-1.341
erker-1.259
 carbohyd-1.253
oter-1.241
urous-1.230
Token in
Token ID287
Feature activation+2.67e-01

Pos logit contributions
 Arbit+0.281
papers+0.237
gallery+0.236
OLOG+0.232
 Pret+0.230
Neg logit contributions
iren-0.318
erker-0.296
oter-0.296
 Miko-0.294
 carbohyd-0.292
Token early
Token ID1903
Feature activation+3.71e-01

Pos logit contributions
 Arbit+1.083
papers+0.913
gallery+0.911
 Pret+0.899
OLOG+0.898
Neg logit contributions
iren-1.080
erker-1.007
 carbohyd-0.999
oter-0.995
 Miko-0.985
Token 1996
Token ID8235
Feature activation+3.24e-02

Pos logit contributions
 Arbit+1.371
papers+1.137
gallery+1.134
OLOG+1.117
 Pret+1.112
Neg logit contributions
iren-1.634
erker-1.531
oter-1.517
 carbohyd-1.517
 Miko-1.504
Token this
Token ID428
Feature activation+2.37e-01

Pos logit contributions
iren+1.548
erker+1.446
oter+1.432
 Miko+1.417
 carbohyd+1.414
Neg logit contributions
 Arbit-1.609
papers-1.366
gallery-1.361
OLOG-1.348
 Pret-1.335
Token here
Token ID994
Feature activation+7.25e-02

Pos logit contributions
 Arbit+0.955
papers+0.803
gallery+0.802
 Pret+0.790
OLOG+0.789
Neg logit contributions
iren-0.967
erker-0.898
 carbohyd-0.893
oter-0.890
 Miko-0.881
Token.
Token ID13
Feature activation+2.14e-01

Pos logit contributions
 Arbit+0.286
papers+0.240
gallery+0.240
OLOG+0.236
 Pret+0.236
Neg logit contributions
iren-0.301
erker-0.280
 carbohyd-0.280
oter-0.278
urous-0.275
Token The
Token ID383
Feature activation+2.80e-01

Pos logit contributions
 Arbit+0.855
papers+0.728
gallery+0.723
OLOG+0.715
 Pret+0.705
Neg logit contributions
iren-0.866
erker-0.806
 Miko-0.800
oter-0.800
urous-0.792
Token guys
Token ID3730
Feature activation-1.41e-01

Pos logit contributions
 Arbit+1.133
gallery+0.952
papers+0.950
 Pret+0.936
OLOG+0.935
Neg logit contributions
iren-1.136
erker-1.057
 carbohyd-1.054
oter-1.043
 Miko-1.031
Token are
Token ID389
Feature activation+1.73e-01

Pos logit contributions
iren+0.564
erker+0.524
 carbohyd+0.520
oter+0.519
 Miko+0.514
Neg logit contributions
 Arbit-0.574
papers-0.485
gallery-0.484
OLOG-0.477
 Pret-0.476
Token right
Token ID826
Feature activation+4.55e-01

Pos logit contributions
 Arbit+0.742
papers+0.633
gallery+0.632
OLOG+0.624
 Pret+0.622
Neg logit contributions
iren-0.659
erker-0.610
oter-0.604
 carbohyd-0.603
 Miko-0.598
Token.
Token ID13
Feature activation+3.07e-01

Pos logit contributions
 Arbit+1.728
papers+1.434
gallery+1.420
 Pret+1.398
OLOG+1.387
Neg logit contributions
iren-1.951
 carbohyd-1.832
erker-1.822
oter-1.806
urous-1.783
Token It
Token ID632
Feature activation+3.04e-01

Pos logit contributions
 Arbit+1.231
papers+1.037
gallery+1.035
OLOG+1.021
 Pret+1.018
Neg logit contributions
iren-1.252
erker-1.165
 carbohyd-1.155
oter-1.155
 Miko-1.143
Token all
Token ID477
Feature activation-1.63e-03

Pos logit contributions
 Arbit+1.090
gallery+0.894
papers+0.890
 Pret+0.875
OLOG+0.871
Neg logit contributions
iren-1.372
erker-1.279
 carbohyd-1.277
oter-1.259
 Miko-1.255
Token starts
Token ID4940
Feature activation+3.93e-01

Pos logit contributions
iren+0.006
erker+0.006
 carbohyd+0.006
oter+0.006
 Miko+0.006
Neg logit contributions
 Arbit-0.007
papers-0.006
gallery-0.006
OLOG-0.006
 Pret-0.006
Token uses
Token ID3544
Feature activation-3.52e-01

Pos logit contributions
iren+1.179
erker+1.096
oter+1.088
 carbohyd+1.081
 Miko+1.079
Neg logit contributions
 Arbit-1.111
papers-0.934
gallery-0.934
OLOG-0.922
 Pret-0.914
Token a
Token ID257
Feature activation+2.95e-02

Pos logit contributions
iren+1.492
erker+1.392
oter+1.379
 carbohyd+1.378
 Miko+1.368
Neg logit contributions
 Arbit-1.360
papers-1.135
gallery-1.130
OLOG-1.116
 Pret-1.114
Token new
Token ID649
Feature activation+2.48e-02

Pos logit contributions
 Arbit+0.119
papers+0.100
gallery+0.100
 Pret+0.099
OLOG+0.099
Neg logit contributions
iren-0.120
erker-0.111
 carbohyd-0.110
oter-0.110
 Miko-0.109
Token hyper
Token ID8718
Feature activation+2.24e-01

Pos logit contributions
 Arbit+0.098
papers+0.082
gallery+0.081
 Pret+0.081
OLOG+0.080
Neg logit contributions
iren-0.103
erker-0.096
 carbohyd-0.095
oter-0.095
 Miko-0.094
Tokenvisor
Token ID13131
Feature activation+2.20e-01

Pos logit contributions
 Arbit+1.159
papers+1.028
gallery+1.020
OLOG+1.004
 Pret+1.001
Neg logit contributions
iren-0.656
erker-0.590
 carbohyd-0.590
 Miko-0.575
oter-0.574
Token called
Token ID1444
Feature activation+7.84e-02

Pos logit contributions
 Arbit+0.923
papers+0.778
 Pret+0.771
gallery+0.771
OLOG+0.767
Neg logit contributions
iren-0.866
erker-0.803
 carbohyd-0.801
oter-0.791
 Miko-0.784
Token Nit
Token ID24282
Feature activation+1.91e-01

Pos logit contributions
 Arbit+0.322
papers+0.266
 Pret+0.266
gallery+0.264
OLOG+0.262
Neg logit contributions
iren-0.319
erker-0.297
 carbohyd-0.294
oter-0.292
 Miko-0.290
Tokenro
Token ID305
Feature activation+1.51e-01

Pos logit contributions
 Arbit+0.834
gallery+0.717
papers+0.717
OLOG+0.706
 Pret+0.701
Neg logit contributions
iren-0.708
 carbohyd-0.660
erker-0.653
 Miko-0.646
oter-0.645
Token.
Token ID13
Feature activation-2.52e-02

Pos logit contributions
 Arbit+0.587
papers+0.486
gallery+0.483
 Pret+0.482
OLOG+0.481
Neg logit contributions
iren-0.638
erker-0.595
 carbohyd-0.593
oter-0.586
 Miko-0.585
Token Nit
Token ID24282
Feature activation+9.46e-02

Pos logit contributions
iren+0.100
erker+0.093
 carbohyd+0.092
oter+0.092
 Miko+0.091
Neg logit contributions
 Arbit-0.105
papers-0.088
gallery-0.088
 Pret-0.087
OLOG-0.087
Tokenro
Token ID305
Feature activation+1.73e-01

Pos logit contributions
 Arbit+0.441
papers+0.379
gallery+0.377
 Pret+0.375
OLOG+0.375
Neg logit contributions
iren-0.326
erker-0.301
oter-0.300
urious-0.295
urous-0.295
Token series
Token ID2168
Feature activation+5.91e-02

Pos logit contributions
 Arbit+2.183
papers+1.816
gallery+1.813
 Pret+1.806
OLOG+1.794
Neg logit contributions
iren-2.165
erker-2.018
 carbohyd-2.009
oter-1.986
urous-1.974
Token version
Token ID2196
Feature activation+6.99e-02

Pos logit contributions
 Arbit+0.253
papers+0.213
 Pret+0.213
gallery+0.213
OLOG+0.211
Neg logit contributions
iren-0.227
erker-0.211
 carbohyd-0.211
oter-0.208
urous-0.207
Token using
Token ID1262
Feature activation+3.91e-02

Pos logit contributions
 Arbit+0.287
papers+0.241
gallery+0.241
 Pret+0.238
OLOG+0.238
Neg logit contributions
iren-0.280
erker-0.261
 carbohyd-0.260
oter-0.257
urous-0.255
Token the
Token ID262
Feature activation+8.83e-02

Pos logit contributions
 Arbit+0.149
gallery+0.123
papers+0.123
 Pret+0.122
OLOG+0.121
Neg logit contributions
iren-0.169
erker-0.158
 carbohyd-0.157
oter-0.156
 Miko-0.155
Token radio
Token ID5243
Feature activation-4.01e-02

Pos logit contributions
 Arbit+0.346
gallery+0.289
papers+0.289
OLOG+0.284
 Pret+0.284
Neg logit contributions
iren-0.370
erker-0.346
 carbohyd-0.343
oter-0.342
 Miko-0.339
Token buttons
Token ID12163
Feature activation+1.93e-01

Pos logit contributions
iren+0.175
erker+0.165
 carbohyd+0.163
oter+0.163
urous+0.162
Neg logit contributions
 Arbit-0.149
papers-0.124
gallery-0.123
OLOG-0.122
 Pret-0.121
Token,
Token ID11
Feature activation+1.98e-01

Pos logit contributions
 Arbit+0.747
papers+0.620
gallery+0.619
 Pret+0.611
OLOG+0.610
Neg logit contributions
iren-0.809
erker-0.763
 carbohyd-0.761
oter-0.751
urous-0.750
Token entering
Token ID8218
Feature activation-9.87e-02

Pos logit contributions
 Arbit+0.783
gallery+0.653
papers+0.652
 Pret+0.644
OLOG+0.643
Neg logit contributions
iren-0.822
erker-0.771
 carbohyd-0.762
oter-0.759
urous-0.752
Token a
Token ID257
Feature activation-5.75e-02

Pos logit contributions
iren+0.410
erker+0.381
oter+0.379
 carbohyd+0.377
 Miko+0.376
Neg logit contributions
 Arbit-0.386
papers-0.326
gallery-0.325
OLOG-0.320
 Pret-0.318
Token "
Token ID366
Feature activation+1.42e-01

Pos logit contributions
iren+0.245
erker+0.228
oter+0.226
 carbohyd+0.225
 Miko+0.225
Neg logit contributions
 Arbit-0.220
papers-0.184
gallery-0.184
OLOG-0.181
 Pret-0.180
Tokenw
Token ID86
Feature activation+4.69e-01

Pos logit contributions
 Arbit+0.566
papers+0.482
gallery+0.481
OLOG+0.471
 Pret+0.470
Neg logit contributions
iren-0.581
 carbohyd-0.543
erker-0.543
oter-0.537
 Miko-0.534
Token to
Token ID284
Feature activation-2.83e-02

Pos logit contributions
iren+0.396
erker+0.372
 carbohyd+0.370
oter+0.367
 Miko+0.365
Neg logit contributions
 Arbit-0.327
papers-0.271
gallery-0.270
OLOG-0.265
 Pret-0.264
Token the
Token ID262
Feature activation-1.65e-02

Pos logit contributions
iren+0.123
erker+0.115
 carbohyd+0.115
oter+0.113
 Miko+0.113
Neg logit contributions
 Arbit-0.107
papers-0.089
gallery-0.088
OLOG-0.088
 Pret-0.087
Token national
Token ID2260
Feature activation-1.13e-02

Pos logit contributions
iren+0.069
erker+0.064
 carbohyd+0.064
oter+0.064
 Miko+0.063
Neg logit contributions
 Arbit-0.064
papers-0.054
gallery-0.054
OLOG-0.053
 Pret-0.053
Token conversation
Token ID5273
Feature activation+5.77e-02

Pos logit contributions
iren+0.044
erker+0.041
oter+0.040
 carbohyd+0.040
 Miko+0.040
Neg logit contributions
 Arbit-0.048
papers-0.041
gallery-0.041
OLOG-0.040
 Pret-0.040
Token and
Token ID290
Feature activation-2.77e-01

Pos logit contributions
 Arbit+0.233
papers+0.196
gallery+0.195
OLOG+0.193
 Pret+0.192
Neg logit contributions
iren-0.234
erker-0.219
 carbohyd-0.218
oter-0.216
 Miko-0.214
Token '
Token ID705
Feature activation-8.65e-02

Pos logit contributions
iren+1.104
erker+1.025
oter+1.020
 Miko+1.010
urous+1.006
Neg logit contributions
 Arbit-1.133
papers-0.961
gallery-0.958
OLOG-0.947
 Pret-0.940
Tokenstand
Token ID1481
Feature activation-8.50e-02

Pos logit contributions
iren+0.348
erker+0.324
 carbohyd+0.321
oter+0.321
 Miko+0.318
Neg logit contributions
 Arbit-0.351
papers-0.298
gallery-0.297
OLOG-0.292
 Pret-0.291
Token up
Token ID510
Feature activation-3.73e-01

Pos logit contributions
iren+0.375
erker+0.352
oter+0.349
 carbohyd+0.348
 Miko+0.346
Neg logit contributions
 Arbit-0.312
papers-0.259
gallery-0.258
OLOG-0.255
 Pret-0.253
Token for
Token ID329
Feature activation-4.12e-01

Pos logit contributions
iren+1.633
erker+1.529
oter+1.520
 carbohyd+1.509
 Miko+1.508
Neg logit contributions
 Arbit-1.376
papers-1.143
gallery-1.143
OLOG-1.123
 Pret-1.117
Token our
Token ID674
Feature activation-1.86e-01

Pos logit contributions
iren+1.631
erker+1.511
oter+1.505
 Miko+1.494
ander+1.485
Neg logit contributions
 Arbit-1.687
gallery-1.440
papers-1.434
OLOG-1.415
 Pret-1.401
Token proud
Token ID6613
Feature activation-4.75e-01

Pos logit contributions
iren+0.757
erker+0.703
oter+0.699
 carbohyd+0.692
 Miko+0.692
Neg logit contributions
 Arbit-0.745
gallery-0.629
papers-0.629
OLOG-0.620
 Pret-0.615
Tokens
Token ID82
Feature activation-4.98e-02

Pos logit contributions
 Arbit+0.151
papers+0.120
gallery+0.119
OLOG+0.117
 Pret+0.116
Neg logit contributions
iren-0.251
erker-0.237
 carbohyd-0.235
oter-0.235
 Miko-0.233
Token willingness
Token ID16826
Feature activation+2.03e-01

Pos logit contributions
iren+0.184
erker+0.170
 carbohyd+0.168
oter+0.168
 Miko+0.167
Neg logit contributions
 Arbit-0.219
papers-0.188
gallery-0.187
OLOG-0.185
 Pret-0.184
Token to
Token ID284
Feature activation+5.84e-02

Pos logit contributions
 Arbit+0.693
papers+0.563
gallery+0.555
OLOG+0.550
 Pret+0.546
Neg logit contributions
iren-0.949
erker-0.902
 carbohyd-0.886
 Miko-0.880
oter-0.880
Token disregard
Token ID25070
Feature activation+2.76e-02

Pos logit contributions
 Arbit+0.253
papers+0.215
gallery+0.215
OLOG+0.212
 Pret+0.212
Neg logit contributions
iren-0.220
erker-0.204
 carbohyd-0.202
oter-0.201
 Miko-0.200
Token Haiti
Token ID25051
Feature activation-3.67e-01

Pos logit contributions
 Arbit+0.107
papers+0.087
 Pret+0.087
gallery+0.087
OLOG+0.086
Neg logit contributions
iren-0.118
erker-0.112
 carbohyd-0.110
oter-0.109
urious-0.108
Token
Token ID447
Feature activation-2.90e-01

Pos logit contributions
iren+1.605
erker+1.507
 carbohyd+1.490
oter+1.487
 Miko+1.477
Neg logit contributions
 Arbit-1.369
papers-1.134
gallery-1.131
OLOG-1.118
 Pret-1.112
Token
Token ID247
Feature activation-1.56e-01

Pos logit contributions
iren+1.364
erker+1.290
 Miko+1.273
oter+1.267
ander+1.259
Neg logit contributions
 Arbit-0.976
papers-0.796
OLOG-0.790
gallery-0.789
 Pret-0.784
Tokens
Token ID82
Feature activation-2.30e-01

Pos logit contributions
iren+0.803
erker+0.764
 carbohyd+0.759
oter+0.754
 Miko+0.751
Neg logit contributions
 Arbit-0.458
papers-0.360
gallery-0.358
 Pret-0.350
OLOG-0.349
Token interests
Token ID5353
Feature activation+2.54e-01

Pos logit contributions
iren+0.947
erker+0.881
oter+0.875
 carbohyd+0.872
 Miko+0.867
Neg logit contributions
 Arbit-0.914
papers-0.770
gallery-0.768
OLOG-0.758
 Pret-0.753
Token for
Token ID329
Feature activation-3.06e-01

Pos logit contributions
 Arbit+1.001
papers+0.838
gallery+0.834
 Pret+0.822
OLOG+0.820
Neg logit contributions
iren-1.058
erker-0.992
 carbohyd-0.987
oter-0.977
 Miko-0.968
Token its
Token ID663
Feature activation-4.28e-01

Pos logit contributions
iren+1.303
erker+1.216
oter+1.206
 carbohyd+1.204
 Miko+1.196
Neg logit contributions
 Arbit-1.174
papers-0.982
gallery-0.979
OLOG-0.965
 Pret-0.960
Token Meg
Token ID8336
Feature activation+2.23e-01

Pos logit contributions
 Arbit+1.351
papers+1.138
gallery+1.137
 Pret+1.133
OLOG+1.129
Neg logit contributions
iren-1.275
erker-1.193
 carbohyd-1.188
oter-1.165
urous-1.159
Tokenarian
Token ID3699
Feature activation+3.89e-01

Pos logit contributions
 Arbit+1.005
gallery+0.875
papers+0.867
OLOG+0.849
 Pret+0.846
Neg logit contributions
iren-0.777
 carbohyd-0.737
erker-0.724
 Miko-0.711
urous-0.710
Token school
Token ID1524
Feature activation+1.91e-01

Pos logit contributions
 Arbit+1.602
papers+1.346
gallery+1.334
 Pret+1.333
OLOG+1.327
Neg logit contributions
iren-1.543
erker-1.451
 carbohyd-1.449
oter-1.418
urous-1.413
Token:
Token ID25
Feature activation+2.05e-01

Pos logit contributions
 Arbit+0.774
papers+0.662
gallery+0.655
OLOG+0.647
 Pret+0.645
Neg logit contributions
iren-0.760
erker-0.720
 carbohyd-0.716
oter-0.704
 Miko-0.701
Tokenonly
Token ID8807
Feature activation-6.00e-02

Pos logit contributions
 Arbit+0.823
papers+0.693
gallery+0.690
 Pret+0.682
OLOG+0.682
Neg logit contributions
iren-0.836
erker-0.786
 carbohyd-0.779
oter-0.767
 Miko-0.766
Token the
Token ID262
Feature activation+2.99e-03

Pos logit contributions
iren+0.253
erker+0.237
 carbohyd+0.234
oter+0.234
 Miko+0.232
Neg logit contributions
 Arbit-0.233
papers-0.195
gallery-0.194
OLOG-0.192
 Pret-0.191
Token multiple
Token ID3294
Feature activation-3.13e-01

Pos logit contributions
 Arbit+0.012
papers+0.010
gallery+0.010
OLOG+0.010
 Pret+0.010
Neg logit contributions
iren-0.012
erker-0.011
 carbohyd-0.011
oter-0.011
 Miko-0.011
Token is
Token ID318
Feature activation-3.95e-01

Pos logit contributions
iren+1.272
erker+1.184
oter+1.173
 carbohyd+1.172
 Miko+1.163
Neg logit contributions
 Arbit-1.263
papers-1.066
gallery-1.063
OLOG-1.049
 Pret-1.044
Token affirmative
Token ID27990
Feature activation-3.07e-01

Pos logit contributions
iren+1.569
erker+1.457
oter+1.445
 carbohyd+1.441
 Miko+1.431
Neg logit contributions
 Arbit-1.624
papers-1.376
gallery-1.373
OLOG-1.355
 Pret-1.349
Token,
Token ID11
Feature activation+1.80e-01

Pos logit contributions
iren+1.237
erker+1.151
oter+1.140
 carbohyd+1.139
 Miko+1.130
Neg logit contributions
 Arbit-1.248
papers-1.054
gallery-1.051
OLOG-1.038
 Pret-1.033
Tokenwhere
Token ID3003
Feature activation-4.68e-02

Pos logit contributions
 Arbit+0.739
papers+0.626
gallery+0.622
OLOG+0.615
 Pret+0.614
Neg logit contributions
iren-0.712
erker-0.668
 carbohyd-0.664
 Miko-0.654
oter-0.652
Token Eve
Token ID12882
Feature activation-1.23e-01

Pos logit contributions
iren+0.127
erker+0.118
 carbohyd+0.117
oter+0.117
 Miko+0.116
Neg logit contributions
 Arbit-0.134
gallery-0.113
papers-0.113
OLOG-0.111
 Pret-0.111
Token said
Token ID531
Feature activation+1.38e-02

Pos logit contributions
iren+0.467
erker+0.433
 carbohyd+0.431
oter+0.427
 Miko+0.422
Neg logit contributions
 Arbit-0.527
gallery-0.449
papers-0.446
 Pret-0.442
OLOG-0.441
Token in
Token ID287
Feature activation-1.97e-01

Pos logit contributions
 Arbit+0.055
papers+0.046
gallery+0.046
OLOG+0.045
 Pret+0.045
Neg logit contributions
iren-0.057
erker-0.053
 carbohyd-0.053
oter-0.053
urous-0.052
Token last
Token ID938
Feature activation-7.51e-02

Pos logit contributions
iren+0.829
erker+0.774
 carbohyd+0.768
oter+0.766
 Miko+0.759
Neg logit contributions
 Arbit-0.765
papers-0.638
gallery-0.638
OLOG-0.629
 Pret-0.629
Token week
Token ID1285
Feature activation+5.22e-03

Pos logit contributions
iren+0.348
erker+0.326
 carbohyd+0.324
oter+0.322
 Miko+0.320
Neg logit contributions
 Arbit-0.262
gallery-0.215
papers-0.215
OLOG-0.210
 Pret-0.210
Token
Token ID447
Feature activation+4.96e-02

Pos logit contributions
 Arbit+0.019
papers+0.015
gallery+0.015
OLOG+0.015
 Pret+0.015
Neg logit contributions
iren-0.024
 carbohyd-0.022
erker-0.022
oter-0.022
urious-0.022
Token
Token ID247
Feature activation+9.68e-02

Pos logit contributions
 Arbit+0.160
papers+0.129
gallery+0.128
OLOG+0.127
 Pret+0.126
Neg logit contributions
iren-0.241
erker-0.228
oter-0.225
 Miko-0.225
urous-0.224
Tokens
Token ID82
Feature activation+3.57e-02

Pos logit contributions
 Arbit+0.282
gallery+0.222
papers+0.220
 Pret+0.214
OLOG+0.213
Neg logit contributions
iren-0.501
 carbohyd-0.481
erker-0.473
oter-0.470
 Miko-0.466
Token episode
Token ID4471
Feature activation+1.09e-02

Pos logit contributions
 Arbit+0.139
papers+0.116
gallery+0.116
 Pret+0.114
OLOG+0.114
Neg logit contributions
iren-0.150
 carbohyd-0.140
erker-0.140
oter-0.139
 Miko-0.137
Token,
Token ID11
Feature activation-1.20e-01

Pos logit contributions
 Arbit+0.043
papers+0.037
gallery+0.036
OLOG+0.036
 Pret+0.036
Neg logit contributions
iren-0.045
erker-0.041
 carbohyd-0.041
oter-0.041
urious-0.041
Token Ann
Token ID5506
Feature activation+1.79e-01

Pos logit contributions
iren+0.488
erker+0.454
oter+0.450
 carbohyd+0.449
 Miko+0.447
Neg logit contributions
 Arbit-0.484
papers-0.409
gallery-0.408
OLOG-0.402
 Pret-0.400
Tokenis
Token ID271
Feature activation-2.65e-01

Pos logit contributions
iren+1.688
ander+1.550
erker+1.549
oter+1.541
urous+1.540
Neg logit contributions
 Arbit-1.353
OLOG-1.115
papers-1.096
 Pret-1.084
gallery-1.074
Tokenles
Token ID829
Feature activation+2.36e-01

Pos logit contributions
iren+0.889
erker+0.800
ander+0.791
urious+0.787
oter+0.786
Neg logit contributions
 Arbit-1.275
OLOG-1.100
papers-1.096
 Pret-1.094
gallery-1.078
Token,
Token ID11
Feature activation-4.27e-02

Pos logit contributions
 Arbit+0.874
papers+0.725
gallery+0.722
 Pret+0.710
OLOG+0.708
Neg logit contributions
iren-1.036
 carbohyd-0.977
erker-0.976
oter-0.961
 Miko-0.953
Token this
Token ID428
Feature activation-6.33e-02

Pos logit contributions
iren+0.172
erker+0.160
 carbohyd+0.158
oter+0.158
 Miko+0.156
Neg logit contributions
 Arbit-0.175
papers-0.147
gallery-0.147
 Pret-0.145
OLOG-0.145
Token time
Token ID640
Feature activation-5.36e-01

Pos logit contributions
iren+0.257
erker+0.239
 carbohyd+0.238
oter+0.236
 Miko+0.234
Neg logit contributions
 Arbit-0.255
papers-0.215
gallery-0.214
OLOG-0.211
 Pret-0.211
Token to
Token ID284
Feature activation+1.74e-02

Pos logit contributions
iren+2.182
erker+2.030
oter+2.027
 Miko+2.015
urous+1.999
Neg logit contributions
 Arbit-2.110
gallery-1.791
papers-1.788
OLOG-1.765
 Pret-1.739
Token throw
Token ID3714
Feature activation+1.26e-01

Pos logit contributions
 Arbit+0.068
papers+0.057
gallery+0.057
 Pret+0.056
OLOG+0.056
Neg logit contributions
iren-0.073
erker-0.068
 carbohyd-0.068
oter-0.067
 Miko-0.067
Token away
Token ID1497
Feature activation-9.86e-02

Pos logit contributions
 Arbit+0.487
papers+0.408
gallery+0.404
OLOG+0.401
 Pret+0.401
Neg logit contributions
iren-0.531
erker-0.500
 carbohyd-0.495
oter-0.491
 Miko-0.487
Token the
Token ID262
Feature activation-9.84e-02

Pos logit contributions
iren+0.400
erker+0.373
 carbohyd+0.370
oter+0.367
 Miko+0.365
Neg logit contributions
 Arbit-0.399
papers-0.337
gallery-0.334
 Pret-0.331
OLOG-0.331
Token
Token ID564
Feature activation-1.12e-01

Pos logit contributions
iren+0.408
erker+0.380
 carbohyd+0.376
oter+0.376
 Miko+0.373
Neg logit contributions
 Arbit-0.389
papers-0.327
gallery-0.326
OLOG-0.322
 Pret-0.320
Token
Token ID250
Feature activation-6.91e-02

Pos logit contributions
iren+0.530
erker+0.499
 carbohyd+0.495
oter+0.495
 Miko+0.491
Neg logit contributions
 Arbit-0.373
papers-0.302
gallery-0.301
OLOG-0.296
 Pret-0.295
Token questions
Token ID2683
Feature activation+1.19e-01

Pos logit contributions
 Arbit+0.425
papers+0.362
gallery+0.358
 Pret+0.357
OLOG+0.354
Neg logit contributions
iren-0.363
 carbohyd-0.338
erker-0.336
oter-0.331
urous-0.326
Token in
Token ID287
Feature activation-2.29e-01

Pos logit contributions
 Arbit+0.485
papers+0.406
gallery+0.405
OLOG+0.400
 Pret+0.399
Neg logit contributions
iren-0.485
 carbohyd-0.453
erker-0.452
oter-0.446
urous-0.442
Token the
Token ID262
Feature activation-1.65e-01

Pos logit contributions
iren+0.958
erker+0.893
 carbohyd+0.887
oter+0.881
 Miko+0.875
Neg logit contributions
 Arbit-0.904
papers-0.755
gallery-0.751
 Pret-0.744
OLOG-0.739
Token chat
Token ID8537
Feature activation-2.89e-01

Pos logit contributions
iren+0.703
erker+0.656
 carbohyd+0.654
oter+0.649
 Miko+0.641
Neg logit contributions
 Arbit-0.639
papers-0.532
gallery-0.531
 Pret-0.522
OLOG-0.521
Token (
Token ID357
Feature activation+5.23e-03

Pos logit contributions
iren+1.177
erker+1.094
oter+1.086
 carbohyd+1.080
 Miko+1.076
Neg logit contributions
 Arbit-1.161
papers-0.979
gallery-0.976
OLOG-0.965
 Pret-0.961
Tokenwhen
Token ID12518
Feature activation-6.63e-01

Pos logit contributions
 Arbit+0.022
papers+0.019
gallery+0.019
OLOG+0.018
 Pret+0.018
Neg logit contributions
iren-0.020
erker-0.019
 carbohyd-0.019
oter-0.019
 Miko-0.018
Token I
Token ID314
Feature activation-1.34e-01

Pos logit contributions
iren+2.401
erker+2.211
oter+2.201
 Miko+2.187
 carbohyd+2.169
Neg logit contributions
 Arbit-2.931
papers-2.537
gallery-2.528
OLOG-2.503
 Pret-2.476
Token remembered
Token ID12086
Feature activation+3.08e-01

Pos logit contributions
iren+0.539
erker+0.500
oter+0.498
 Miko+0.493
 carbohyd+0.492
Neg logit contributions
 Arbit-0.543
papers-0.461
gallery-0.460
OLOG-0.454
 Pret-0.451
Token to
Token ID284
Feature activation-4.42e-02

Pos logit contributions
 Arbit+1.226
papers+1.010
 Pret+1.008
gallery+1.004
OLOG+0.988
Neg logit contributions
iren-1.293
 carbohyd-1.208
erker-1.204
oter-1.177
urous-1.176
Token look
Token ID804
Feature activation-1.29e-01

Pos logit contributions
iren+0.178
erker+0.166
oter+0.165
 Miko+0.163
 carbohyd+0.163
Neg logit contributions
 Arbit-0.178
papers-0.151
gallery-0.151
OLOG-0.149
 Pret-0.147
Token up
Token ID510
Feature activation-2.29e-01

Pos logit contributions
iren+0.564
erker+0.527
oter+0.523
 carbohyd+0.522
 Miko+0.519
Neg logit contributions
 Arbit-0.478
papers-0.397
gallery-0.396
OLOG-0.391
 Pret-0.389
Token but
Token ID475
Feature activation+4.11e-01

Pos logit contributions
 Arbit+0.395
papers+0.333
gallery+0.332
 Pret+0.329
OLOG+0.326
Neg logit contributions
iren-0.386
erker-0.361
 carbohyd-0.356
oter-0.354
urous-0.350
Token it
Token ID340
Feature activation+1.39e-02

Pos logit contributions
 Arbit+1.654
papers+1.389
gallery+1.381
 Pret+1.379
OLOG+1.363
Neg logit contributions
iren-1.676
erker-1.570
 carbohyd-1.562
oter-1.543
urious-1.524
Token could
Token ID714
Feature activation-1.95e-01

Pos logit contributions
 Arbit+0.054
papers+0.045
gallery+0.045
OLOG+0.044
 Pret+0.044
Neg logit contributions
iren-0.059
erker-0.055
oter-0.054
 carbohyd-0.054
 Miko-0.054
Token be
Token ID307
Feature activation+4.19e-02

Pos logit contributions
iren+0.740
erker+0.685
oter+0.679
 carbohyd+0.677
 Miko+0.672
Neg logit contributions
 Arbit-0.838
papers-0.715
gallery-0.714
OLOG-0.705
 Pret-0.702
Token a
Token ID257
Feature activation-1.23e-01

Pos logit contributions
 Arbit+0.173
papers+0.147
gallery+0.147
OLOG+0.145
 Pret+0.144
Neg logit contributions
iren-0.166
erker-0.154
oter-0.152
 carbohyd-0.152
 Miko-0.151
Token source
Token ID2723
Feature activation-7.37e-01

Pos logit contributions
iren+0.459
erker+0.424
oter+0.420
 carbohyd+0.417
 Miko+0.416
Neg logit contributions
 Arbit-0.538
papers-0.461
gallery-0.460
OLOG-0.454
 Pret-0.452
Token of
Token ID286
Feature activation-6.41e-01

Pos logit contributions
iren+2.621
erker+2.421
oter+2.388
 carbohyd+2.387
 Miko+2.365
Neg logit contributions
 Arbit-3.353
papers-2.889
gallery-2.883
OLOG-2.851
 Pret-2.836
Token new
Token ID649
Feature activation-3.33e-01

Pos logit contributions
iren+2.245
erker+2.041
oter+2.028
 Miko+2.017
ander+2.005
Neg logit contributions
 Arbit-2.924
papers-2.530
gallery-2.528
OLOG-2.504
 Pret-2.469
Token technologies
Token ID8514
Feature activation-1.33e-01

Pos logit contributions
iren+1.206
erker+1.102
oter+1.099
 Miko+1.090
urious+1.084
Neg logit contributions
 Arbit-1.489
gallery-1.282
papers-1.276
OLOG-1.268
 Pret-1.253
Token and
Token ID290
Feature activation-1.24e-01

Pos logit contributions
iren+0.552
erker+0.515
 carbohyd+0.510
oter+0.510
 Miko+0.505
Neg logit contributions
 Arbit-0.526
papers-0.442
gallery-0.441
OLOG-0.435
 Pret-0.433
Token industries
Token ID11798
Feature activation+1.63e-01

Pos logit contributions
iren+0.455
erker+0.419
oter+0.416
 carbohyd+0.413
 Miko+0.412
Neg logit contributions
 Arbit-0.544
papers-0.467
gallery-0.466
OLOG-0.461
 Pret-0.458
TokenGoogle
Token ID11708
Feature activation-1.02e-01

Pos logit contributions
iren+0.124
erker+0.116
oter+0.116
ander+0.115
 Miko+0.114
Neg logit contributions
 Arbit-0.100
papers-0.081
gallery-0.081
 Pret-0.080
OLOG-0.080
Token Scholar
Token ID11713
Feature activation+2.99e-01

Pos logit contributions
iren+0.397
erker+0.372
oter+0.372
 Miko+0.371
ander+0.368
Neg logit contributions
 Arbit-0.405
papers-0.354
gallery-0.350
OLOG-0.347
 Pret-0.340
Token
Token ID198
Feature activation-2.22e-01

Pos logit contributions
 Arbit+1.182
OLOG+0.988
gallery+0.987
papers+0.983
 Pret+0.962
Neg logit contributions
iren-1.241
erker-1.154
 carbohyd-1.150
oter-1.146
urous-1.141
Token
Token ID198
Feature activation-2.06e-01

Pos logit contributions
iren+0.747
ander+0.686
oter+0.683
 Miko+0.683
erker+0.674
Neg logit contributions
 Arbit-1.029
OLOG-0.893
gallery-0.888
papers-0.888
 Pret-0.859
TokenPark
Token ID25478
Feature activation-3.02e-01

Pos logit contributions
iren+0.913
 carbohyd+0.856
erker+0.856
oter+0.845
 Miko+0.843
Neg logit contributions
 Arbit-0.751
papers-0.627
gallery-0.624
OLOG-0.616
 Pret-0.611
Tokener
Token ID263
Feature activation-6.78e-01

Pos logit contributions
iren+1.149
erker+1.065
 carbohyd+1.062
oter+1.055
 Miko+1.043
Neg logit contributions
 Arbit-1.296
papers-1.111
gallery-1.103
OLOG-1.088
 Pret-1.088
Token,
Token ID11
Feature activation+1.56e-01

Pos logit contributions
iren+2.704
erker+2.515
 carbohyd+2.491
oter+2.490
 Miko+2.468
Neg logit contributions
 Arbit-2.785
papers-2.359
gallery-2.349
OLOG-2.320
 Pret-2.313
Token A
Token ID317
Feature activation+1.29e-01

Pos logit contributions
 Arbit+0.615
papers+0.524
gallery+0.521
OLOG+0.514
 Pret+0.501
Neg logit contributions
iren-0.640
 Miko-0.598
erker-0.595
oter-0.589
ander-0.586
Token.
Token ID13
Feature activation+1.30e-01

Pos logit contributions
 Arbit+0.531
papers+0.452
gallery+0.443
OLOG+0.443
 Pret+0.441
Neg logit contributions
iren-0.507
erker-0.476
 carbohyd-0.474
oter-0.469
 Miko-0.469
Token K
Token ID509
Feature activation+8.86e-02

Pos logit contributions
 Arbit+0.499
papers+0.419
gallery+0.418
OLOG+0.412
 Pret+0.409
Neg logit contributions
iren-0.547
erker-0.510
oter-0.506
 Miko-0.503
 carbohyd-0.502
Token.
Token ID13
Feature activation+1.45e-01

Pos logit contributions
 Arbit+0.381
papers+0.326
OLOG+0.321
gallery+0.320
 Pret+0.318
Neg logit contributions
iren-0.331
erker-0.312
 carbohyd-0.310
 Miko-0.307
oter-0.305
Token creamy
Token ID27892
Feature activation-1.48e-01

Pos logit contributions
iren+1.008
erker+0.924
oter+0.913
 carbohyd+0.912
 Miko+0.903
Neg logit contributions
 Arbit-1.420
papers-1.231
gallery-1.228
OLOG-1.215
 Pret-1.211
Token:
Token ID25
Feature activation-1.73e-01

Pos logit contributions
iren+0.601
erker+0.560
 carbohyd+0.556
oter+0.553
 Miko+0.549
Neg logit contributions
 Arbit-0.594
papers-0.499
gallery-0.499
 Pret-0.493
OLOG-0.492
Token
Token ID198
Feature activation-2.92e-01

Pos logit contributions
iren+0.713
erker+0.667
oter+0.663
 Miko+0.655
 carbohyd+0.655
Neg logit contributions
 Arbit-0.688
papers-0.578
 Pret-0.575
gallery-0.575
OLOG-0.569
Token
Token ID198
Feature activation-2.43e-01

Pos logit contributions
iren+0.973
ander+0.897
 Miko+0.886
oter+0.885
erker+0.883
Neg logit contributions
 Arbit-1.355
OLOG-1.174
papers-1.170
gallery-1.156
 Pret-1.140
TokenFor
Token ID1890
Feature activation-1.72e-01

Pos logit contributions
iren+0.949
erker+0.880
oter+0.872
 carbohyd+0.871
 Miko+0.864
Neg logit contributions
 Arbit-1.017
papers-0.865
gallery-0.863
OLOG-0.852
 Pret-0.848
Token those
Token ID883
Feature activation-8.03e-01

Pos logit contributions
iren+0.725
erker+0.677
oter+0.671
 carbohyd+0.670
 Miko+0.663
Neg logit contributions
 Arbit-0.670
papers-0.560
gallery-0.559
 Pret-0.553
OLOG-0.552
Token of
Token ID286
Feature activation-1.95e-01

Pos logit contributions
iren+2.799
erker+2.576
 carbohyd+2.539
oter+2.538
 Miko+2.522
Neg logit contributions
 Arbit-3.681
gallery-3.177
papers-3.177
OLOG-3.140
 Pret-3.110
Token you
Token ID345
Feature activation-5.36e-02

Pos logit contributions
iren+0.748
erker+0.689
 carbohyd+0.685
oter+0.684
 Miko+0.675
Neg logit contributions
 Arbit-0.831
gallery-0.709
papers-0.704
 Pret-0.700
OLOG-0.695
Token who
Token ID508
Feature activation+2.56e-02

Pos logit contributions
iren+0.193
 carbohyd+0.178
erker+0.178
oter+0.177
urous+0.174
Neg logit contributions
 Arbit-0.241
 Pret-0.206
gallery-0.206
papers-0.205
OLOG-0.202
Token don
Token ID836
Feature activation-2.66e-01

Pos logit contributions
 Arbit+0.100
papers+0.083
gallery+0.083
 Pret+0.082
OLOG+0.082
Neg logit contributions
iren-0.107
erker-0.100
 carbohyd-0.100
oter-0.099
 Miko-0.099
Token
Token ID447
Feature activation-2.42e-01

Pos logit contributions
iren+0.941
ander+0.860
oter+0.859
erker+0.858
 Miko+0.858
Neg logit contributions
 Arbit-1.202
papers-1.029
OLOG-1.019
gallery-1.016
 Pret-1.013
Tokenaps
Token ID1686
Feature activation+9.41e-02

Pos logit contributions
 Arbit+2.152
papers+1.854
 Pret+1.827
gallery+1.817
OLOG+1.809
Neg logit contributions
iren-1.775
 carbohyd-1.668
erker-1.622
 Miko-1.609
urous-1.577
Token-
Token ID12
Feature activation+1.56e-01

Pos logit contributions
 Arbit+0.363
papers+0.300
 Pret+0.298
gallery+0.296
OLOG+0.293
Neg logit contributions
iren-0.405
 carbohyd-0.383
erker-0.377
oter-0.373
urous-0.369
TokenBlack
Token ID9915
Feature activation-2.64e-01

Pos logit contributions
 Arbit+0.607
gallery+0.512
papers+0.510
OLOG+0.502
 Pret+0.502
Neg logit contributions
iren-0.660
 carbohyd-0.626
erker-0.615
oter-0.606
urous-0.603
Token President
Token ID1992
Feature activation+2.76e-01

Pos logit contributions
iren+1.102
erker+1.026
 carbohyd+1.024
oter+1.014
urous+1.006
Neg logit contributions
 Arbit-1.045
papers-0.876
gallery-0.869
 Pret-0.862
OLOG-0.858
Token-
Token ID12
Feature activation+2.43e-01

Pos logit contributions
 Arbit+0.987
papers+0.812
 Pret+0.801
gallery+0.788
OLOG+0.776
Neg logit contributions
iren-1.260
 carbohyd-1.196
erker-1.184
oter-1.171
urous-1.168
TokenGay
Token ID41787
Feature activation-7.32e-01

Pos logit contributions
 Arbit+0.946
gallery+0.799
papers+0.796
OLOG+0.784
 Pret+0.783
Neg logit contributions
iren-1.026
 carbohyd-0.976
erker-0.957
oter-0.943
urous-0.938
Token Intern
Token ID2445
Feature activation-1.90e-02

Pos logit contributions
iren+3.108
oter+2.897
erker+2.896
 Miko+2.880
ander+2.870
Neg logit contributions
 Arbit-2.733
gallery-2.316
OLOG-2.292
papers-2.291
 Pret-2.219
Token Adam
Token ID7244
Feature activation-9.81e-02

Pos logit contributions
iren+0.091
erker+0.086
 carbohyd+0.086
oter+0.085
urous+0.085
Neg logit contributions
 Arbit-0.063
papers-0.051
gallery-0.051
 Pret-0.050
OLOG-0.050
Token Pt
Token ID34352
Feature activation+4.90e-01

Pos logit contributions
iren+0.431
erker+0.404
 carbohyd+0.403
oter+0.399
 Miko+0.395
Neg logit contributions
 Arbit-0.366
papers-0.302
gallery-0.300
 Pret-0.298
OLOG-0.295
Token1
Token ID16
Feature activation+3.70e-01

Pos logit contributions
 Arbit+1.798
papers+1.473
 Pret+1.472
gallery+1.465
OLOG+1.429
Neg logit contributions
iren-2.139
 carbohyd-2.066
erker-2.023
oter-1.991
 Miko-1.977
Token-
Token ID12
Feature activation-3.53e-02

Pos logit contributions
 Arbit+1.223
papers+0.980
 Pret+0.967
gallery+0.958
OLOG+0.936
Neg logit contributions
iren-1.784
 carbohyd-1.696
erker-1.687
oter-1.671
urous-1.667