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

    Neuronpedia

    INDEX
    Explanations

    occurrences of underscores and their variations in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    baugh
    -0.16
    anny
    -0.15
    onto
    -0.15
    ensis
    -0.15
    ril
    -0.15
    ól
    -0.15
    Ç
    -0.15
    ersh
    -0.15
    erm
    -0.14
    geries
    -0.14
    POSITIVE LOGITS
    init
    0.30
     str
    0.26
     init
    0.24
    repr
    0.23
    /init
    0.22
    unicode
    0.22
    -init
    0.22
    len
    0.20
     len
    0.20
    ________________________________________________________________
    0.19
    Act Density 0.003%

    No Known Activations