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

    Neuronpedia

    INDEX
    Explanations

    punctuated speech and quotations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ，
    -0.99
    。
    -0.97
    （
    -0.73
    」
    -0.69
    principalColumn
    -0.64
    modelBuilder
    -0.64
    ).
    -0.62
    　
    -0.58
    nical
    -0.58
    ،
    -0.58
    POSITIVE LOGITS
     يتيمه
    0.60
     فريبيس
    0.60
    انيف
    0.53
     مرئيه
    0.53
     TextAlign
    0.47
     onCancelled
    0.46
    )).
    0.44
    haël
    0.43
    Aholisi
    0.43
    TheReal
    0.42
    Act Density 0.426%

    No Known Activations