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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "punct" and variations related to punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PRES
    -0.80
    GROUND
    -0.76
    isSpecialOrderable
    -0.75
    CTV
    -0.74
    SAY
    -0.74
    CVE
    -0.72
    geist
    -0.71
    HEAD
    -0.70
    OHN
    -0.69
    Sham
    -0.69
    POSITIVE LOGITS
    uated
    1.27
    uation
    1.16
    uates
    1.10
    ured
    1.05
    uating
    1.04
    uality
    1.01
    ures
    0.97
    etr
    0.95
    uate
    0.94
    inct
    0.92
    Act Density 0.012%

    No Known Activations