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

    Neuronpedia

    INDEX
    Explanations

    questions and phrases that challenge societal norms and expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alis
    -0.17
    ÑģÑĤи
    -0.16
    /wiki
    -0.15
    ÙıÙĪÙĨ
    -0.15
    etu
    -0.15
     Macros
    -0.15
    webs
    -0.14
    _FA
    -0.14
    oup
    -0.14
    puted
    -0.14
    POSITIVE LOGITS
    aket
    0.16
    ArrayOf
    0.15
    erk
    0.15
    aye
    0.14
    NOP
    0.14
    pak
    0.14
    ransition
    0.14
    Ú©ÙĦ
    0.13
    åĨ
    0.13
     separ
    0.13
    Act Density 0.103%

    No Known Activations