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

    Neuronpedia

    INDEX
    Explanations

    phrases or sentences that end abruptly with a specific punctuation or word

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically quotation marks and periods, indicating dialogue or sentence endings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     contrace
    -0.87
     challeng
    -0.83
     experien
    -0.79
     financially
    -0.69
     confir
    -0.68
     advoc
    -0.67
     exha
    -0.64
     sugg
    -0.64
     cryst
    -0.63
    gaard
    -0.63
    POSITIVE LOGITS
    soType
    0.85
     ["
    0.82
    english
    0.79
    thumbnails
    0.77
    isSpecialOrderable
    0.69
    arte
    0.67
     âĢķ
    0.66
     href
    0.66
    Written
    0.65
    >>\
    0.64
    Act Density 0.060%

    No Known Activations