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

    Neuronpedia

    INDEX
    Explanations

    the presence of names and personal identifiers in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ########.
    -0.60
    RTDA
    -0.58
    LookAnd
    -0.56
    RenderAtEndOf
    -0.55
    `,
    -0.53
    totalSupply
    -0.53
    '],$
    -0.52
    المناصب
    -0.51
    RectangleBorder
    -0.50
    CONSIN
    -0.50
    POSITIVE LOGITS
    SerializedSize
    0.56
    ViewImports
    0.55
    Author
    0.52
     Автор
    0.50
     автор
    0.50
     author
    0.50
     Author
    0.50
     Ropa
    0.50
    pau
    0.49
     ujednoznacz
    0.49
    Act Density 0.298%

    No Known Activations