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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and operations within a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eczy
    -0.16
    Äģn
    -0.16
    ?,?,?,?,
    -0.15
    fony
    -0.14
     Fifth
    -0.14
    ĥ½
    -0.13
    iciente
    -0.13
    uron
    -0.13
     Mata
    -0.13
    .Serve
    -0.13
    POSITIVE LOGITS
    3
    0.48
     third
    0.35
     three
    0.35
    -three
    0.31
    ï¼ĵ
    0.31
    Û³
    0.31
    third
    0.31
     Third
    0.31
    ä¸ī
    0.30
     Three
    0.30
    Act Density 0.082%

    No Known Activations