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

    Neuronpedia

    INDEX
    Explanations

    mathematical relations and properties involving variables and constants in expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    putExtra
    -0.56
     Lightboxes
    -0.54
     ProtoMessage
    -0.53
    RequestParam
    -0.53
    wards
    -0.52
    Bronnen
    -0.51
    /*:
    -0.51
    Grado
    -0.51
    embe
    -0.50
     Grado
    -0.48
    POSITIVE LOGITS
     denominator
    0.73
    denominator
    0.59
    StructEnd
    0.57
     vyd
    0.54
    rungsseite
    0.54
    aarrggbb
    0.53
    __":
    0.52
    expandindo
    0.52
     оригіналу
    0.51
     Vanden
    0.49
    Act Density 1.034%

    No Known Activations