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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating relationships or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -1.64
    IsMutable
    -1.36
    parsedMessage
    -1.33
     propOrder
    -1.30
    oredCriteria
    -1.23
    DeleteBehavior
    -1.22
    AutoScaleMode
    -1.14
     Paglinawan
    -1.12
    StoreMessageInfo
    -1.12
     betweenstory
    -1.05
    POSITIVE LOGITS
    '
    0.94
    “
    0.89
    ’
    0.87
    \
    0.83
    "
    0.83
    (
    0.82
    2
    0.80
    1
    0.79
    ↵
    0.78
    <b>
    0.78
    Act Density 1.379%

    No Known Activations