Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    mentions of interception and related concepts regarding surveillance or military actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.04
    2:0.17
    3:0.06
    4:0.09
    5:0.09
    6:0.03
    7:0.03
    8:0.14
    9:0.16
    10:0.06
    11:0.03
    Negative Logits
    ══
    -1.41
     oats
    -1.31
    idia
    -1.25
    isted
    -1.23
     shoulders
    -1.17
    cill
    -1.15
     endors
    -1.12
    izons
    -1.10
    Í
    -1.09
     ornament
    -1.07
    POSITIVE LOGITS
     transmissions
    1.39
    Dispatch
    1.34
     intercepted
    1.30
     reconnaissance
    1.30
     HMS
    1.25
     GSL
    1.24
     RHP
    1.24
     helicop
    1.23
     UFOs
    1.21
     downed
    1.17
    Act Density 0.005%

    No Known Activations