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

    Neuronpedia

    INDEX
    Explanations

    occurrences of numerical values and their context in various sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.72
    ↵↵
    -0.58
    '
    -0.56
    0
    -0.55
    1
    -0.55
    The
    -0.54
    ’
    -0.54
    .
    -0.51
    T
    -0.51
    2
    -0.51
    POSITIVE LOGITS
     Roskov
    1.03
    IsMutable
    0.88
     myſelf
    0.86
    parsedMessage
    0.83
    StoreMessageInfo
    0.79
    oredCriteria
    0.78
    windowFixed
    0.75
     againſt
    0.73
    WriteTagHelper
    0.71
    queryInterface
    0.71
    Act Density 0.400%

    No Known Activations