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

    Neuronpedia

    INDEX
    Explanations

    terms associated with classification and categorization processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enders
    -0.15
     McGu
    -0.15
    dera
    -0.15
    रत
    -0.14
    Thrown
    -0.14
    ToLeft
    -0.13
     Hearth
    -0.13
     teg
    -0.13
     chimney
    -0.13
     spo
    -0.13
    POSITIVE LOGITS
    ABS
    0.15
    unya
    0.14
    ixer
    0.14
     è¯
    0.14
    itan
    0.14
    [sizeof
    0.14
     Gros
    0.14
    ä¹
    0.13
    PLAIN
    0.13
     Schro
    0.13
    Act Density 0.006%

    No Known Activations