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

    Neuronpedia

    INDEX
    Explanations

    documents and information related to guidelines, procedures, and updates on various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    LATED
    -0.17
    538
    -0.16
     Illustrated
    -0.16
    VIC
    -0.15
     Fauc
    -0.15
    ãĥ³ãĤº
    -0.14
    Illustr
    -0.14
    ::*
    -0.14
    UpInside
    -0.14
    utzer
    -0.14
    POSITIVE LOGITS
     can
    0.48
    can
    0.34
     можно
    0.30
     można
    0.29
     appears
    0.29
    åı¯ä»¥
    0.28
     follows
    0.27
    ï¼Įåı¯ä»¥
    0.25
     appear
    0.25
     можна
    0.25
    Act Density 0.170%

    No Known Activations