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

    Neuronpedia

    INDEX
    Explanations

    references to illegal substances or chemical components

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.56
    setVerticalGroup
    -0.52
     Foer
    -0.51
     ffilm
    -0.50
    通り
    -0.49
    etzung
    -0.48
     Badge
    -0.48
    حياته
    -0.48
     للمعارف
    -0.47
     communautés
    -0.47
    POSITIVE LOGITS
     called
    0.64
     unidentified
    0.63
     poffe
    0.59
     termed
    0.57
     purpoſe
    0.57
     referred
    0.57
     sessionFactory
    0.56
     inconnu
    0.56
    称为
    0.55
     myſelf
    0.55
    Act Density 0.234%

    No Known Activations