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

    Neuronpedia

    INDEX
    Explanations

    colloquial expressions and informal language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     But
    -0.51
    giarism
    -0.50
     ProtoMessage
    -0.49
     Im
    -0.49
    HostException
    -0.49
     Ouverture
    -0.48
     clearColor
    -0.46
     invokevirtual
    -0.45
     Drapeau
    -0.45
     صوتيه
    -0.45
    POSITIVE LOGITS
     Saltar
    0.62
    y
    0.62
    arriver
    0.62
    étant
    0.60
    appré
    0.56
    aurait
    0.56
    expandindo
    0.56
     rentrée
    0.55
    accepte
    0.54
    explique
    0.54
    Act Density 0.117%

    No Known Activations