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

    Neuronpedia

    INDEX
    Explanations

    programming and technical programming language constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    <bos>
    -1.62
    "
    -0.83
    (
    -0.82
    “
    -0.82
    ↵
    -0.80
     
    -0.80
    ",
    -0.80
    )
    -0.79
    ).
    -0.77
    .
    -0.77
    POSITIVE LOGITS
     дописавши
    0.95
     Roskov
    0.89
     myſelf
    0.84
    FTFY
    0.83
    NUMX
    0.83
     EconPapers
    0.82
     nahilalakip
    0.82
    parsedMessage
    0.82
    adaptiveStyles
    0.80
    Suerte
    0.80
    Act Density 9.476%

    No Known Activations