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

    Neuronpedia

    INDEX
    Explanations

    significant punctuation marks and their usage in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cokinetics
    -0.79
    migrationBuilder
    -0.78
    DockStyle
    -0.78
    NameInMap
    -0.76
     vuitton
    -0.75
     demurrer
    -0.73
    $_['
    -0.73
    .*")]
    -0.69
    <bos>
    -0.68
    icordia
    -0.67
    POSITIVE LOGITS
    Související
    0.49
    oredCriteria
    0.49
     […]
    0.43
     ")[
    0.42
    nante
    0.42
    chiede
    0.41
    polis
    0.40
     explained
    0.40
    ssan
    0.39
    Firstly
    0.39
    Act Density 0.386%

    No Known Activations