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

    Neuronpedia

    INDEX
    Explanations

    strings or sequences that represent identifiers or codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Мексичка
    -0.79
    EFIAPI
    -0.72
    ReusableCell
    -0.69
     kaarangay
    -0.67
    msgTypes
    -0.65
     ModelExpression
    -0.65
    parsedMessage
    -0.65
    Hauptartikel
    -0.64
     дописавши
    -0.63
    sulf
    -0.62
    POSITIVE LOGITS
    c
    0.85
    l
    0.69
    f
    0.68
    b
    0.64
    in
    0.60
    v
    0.58
     ejus
    0.58
    p
    0.57
    Step
    0.53
    g
    0.53
    Act Density 0.136%

    No Known Activations