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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns indicating personal relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.09
    1:0.06
    2:0.12
    3:0.07
    4:0.07
    5:0.08
    6:0.08
    7:0.07
    8:0.10
    9:0.09
    10:0.06
    11:0.06
    Negative Logits
    asus
    -3.28
    hran
    -3.01
    SpaceEngineers
    -2.77
    versions
    -2.71
    urations
    -2.63
     Domin
    -2.59
    arine
    -2.55
    acs
    -2.54
     substrate
    -2.52
     Lucifer
    -2.43
    POSITIVE LOGITS
     platoon
    3.48
     snipers
    3.46
     inval
    3.25
     Cameroon
    2.96
     condol
    2.91
     Villa
    2.85
     sniper
    2.85
    Score
    2.83
     anecd
    2.74
     unemploy
    2.65
    Act Density 0.000%

    No Known Activations