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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, particularly commas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.21
    '
    -0.93
    ’
    -0.82
    “
    -0.77
    2
    -0.74
    <h2>
    -0.74
    <h1>
    -0.70
    "
    -0.70
    (
    -0.69
    1
    -0.67
    POSITIVE LOGITS
     myſelf
    0.80
    verständlich
    0.80
    oredCriteria
    0.78
    BibitemShut
    0.78
     היתה
    0.75
     Roskov
    0.74
    bibinfo
    0.72
    σθαι
    0.72
    uttavia
    0.72
    bibfield
    0.70
    Act Density 0.429%

    No Known Activations