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

    Neuronpedia

    INDEX
    Explanations

    numerical references or citations in academic literature

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ढ
    -0.17
    ienia
    -0.15
    andan
    -0.14
    ırak
    -0.14
    ibbon
    -0.14
    uta
    -0.14
    ë¨
    -0.14
     Stranger
    -0.14
    -END
    -0.14
    ilon
    -0.14
    POSITIVE LOGITS
    IGNAL
    0.16
    holm
    0.16
    jmp
    0.15
    906
    0.15
    phans
    0.14
    686
    0.14
    endo
    0.14
    Æ°Æ¡i
    0.14
    oro
    0.13
     hol
    0.13
    Act Density 0.030%

    No Known Activations