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

    Neuronpedia

    INDEX
    Explanations

    expressions of affection and personal interactions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    الدراسه
    -0.63
    GraphicsUnit
    -0.63
     Cæsar
    -0.62
     Monfieur
    -0.62
    urium
    -0.61
     Maximus
    -0.60
    jmniej
    -0.60
     downvotes
    -0.57
    مصادر
    -0.57
     purpoſe
    -0.56
    POSITIVE LOGITS
     estimés
    0.48
    NameInMap
    0.47
     فريبيس
    0.46
    CloseOperation
    0.44
    FieldNumber
    0.43
     pernyataan
    0.42
    acional
    0.42
    曖昧さ回避
    0.41
    opener
    0.41
    andaan
    0.41
    Act Density 0.006%

    No Known Activations