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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and their variations in usage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     فريبيس
    -0.75
     CreateTagHelper
    -0.71
    ftagPool
    -0.66
    tagHelperRunner
    -0.59
    ंदीखरीदारी
    -0.55
    setVerticalGroup
    -0.54
    المناصب
    -0.54
    ########.
    -0.53
    ьаж
    -0.52
     ModelExpression
    -0.52
    POSITIVE LOGITS
    lower
    0.60
    citation
    0.56
     citation
    0.54
    clar
    0.52
    needs
    0.50
    dub
    0.49
     unreliable
    0.49
    Needs
    0.49
     footnote
    0.47
    Notes
    0.47
    Act Density 0.426%

    No Known Activations