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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and specific syntactic structures within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .
    -0.65
    。
    -0.61
    ।
    -0.59
    ).
    -0.59
    ].
    -0.57
    >().
    -0.56
    %.
    -0.53
    SharedCtor
    -0.53
     ।
    -0.52
    点此举报
    -0.51
    POSITIVE LOGITS
     समीक्षाओं
    0.70
     meanwhile
    0.67
     kasarigan
    0.67
     however
    0.66
     estekak
    0.65
    AnimationsModule
    0.64
    AddHtmlAttribute
    0.63
    edly
    0.63
     incidentally
    0.62
     infatti
    0.59
    Act Density 0.310%

    No Known Activations