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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    EndContext
    -1.39
    parsedMessage
    -1.06
    ArrowToggle
    -1.03
    EDEFAULT
    -1.03
    ItemBackground
    -1.03
    featureID
    -1.02
    +#+#
    -1.02
    LookAnd
    -1.00
     ModelExpression
    -0.99
    setVerticalGroup
    -0.99
    POSITIVE LOGITS
    .
    0.62
    import
    0.59
    n
    0.54
    m
    0.53
     
    0.53
    '
    0.53
    ma
    0.53
    ff
    0.53
    c
    0.52
    f
    0.52
    Act Density 0.016%

    No Known Activations