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

    Neuronpedia

    INDEX
    Explanations

    legal or official actions and recommendations

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Réponses
    -0.68
     beginnetje
    -0.62
    Derbyniad
    -0.58
    BeginInit
    -0.57
    Portail
    -0.56
    -0.53
    Kjelder
    -0.52
    hogy
    -0.51
    expandindo
    -0.51
    setVerticalGroup
    -0.51
    POSITIVE LOGITS
    agno
    0.56
    \|_{\
    0.55
    esistenza
    0.55
    enumi
    0.53
    DoubleQuotes
    0.53
     обращения
    0.51
    БЕ
    0.51
    alom
    0.50
    artin
    0.50
     yuan
    0.49
    Act Density 0.260%

    No Known Activations