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

    Neuronpedia

    INDEX
    Explanations

    references to anonymity and confidentiality in discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ansen
    -0.16
    _residual
    -0.15
    iag
    -0.15
    گاÙĨÛĮ
    -0.14
     Yue
    -0.14
     ç
    -0.14
    askan
    -0.14
    ãi
    -0.14
    oulos
    -0.14
    rum
    -0.14
    POSITIVE LOGITS
    achen
    0.15
    manuel
    0.15
    ña
    0.15
     há»ĵi
    0.14
     Todo
    0.14
    Ĭ
    0.14
    ìĶ
    0.14
    人çī©
    0.14
    889
    0.14
    Todo
    0.14
    Act Density 0.002%

    No Known Activations