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

    Neuronpedia

    INDEX
    Explanations

    occurrences of quotation marks or apostrophes indicating speech or contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atott
    -0.69
     immemorial
    -0.69
    mentos
    -0.66
     ThemeData
    -0.66
    homonymie
    -0.66
     pinulongan
    -0.65
    offsetof
    -0.64
    umesc
    -0.63
     Sahara
    -0.63
    Abitanti
    -0.63
    POSITIVE LOGITS
    s
    1.22
    ’
    0.97
    )’
    0.91
    !’
    0.90
    %'
    0.90
    +'
    0.89
    €™
    0.88
    }'
    0.87
    >'
    0.86
    ’,
    0.86
    Act Density 0.137%

    No Known Activations