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

    Neuronpedia

    INDEX
    Explanations

    specific strings of characters (possibly codes or identifiers) surrounded by special characters 'Ċ'

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and their frequency in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plet
    -0.66
     shorthand
    -0.62
    ĸļ
    -0.60
     horrend
    -0.60
    ĪĴ
    -0.59
    lamm
    -0.59
     equival
    -0.59
    ò
    -0.58
     simulac
    -0.57
    ñ
    -0.55
    POSITIVE LOGITS
    Finally
    0.95
    However
    0.93
    Another
    0.89
    Overall
    0.88
    According
    0.87
    Lastly
    0.85
    Since
    0.84
    Still
    0.84
    Although
    0.83
    Also
    0.82
    Act Density 0.933%

    No Known Activations