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

    Neuronpedia

    INDEX
    Explanations

    code-related elements and variables in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    esseract
    -0.16
    _mE
    -0.16
    @nate
    -0.16
    reu
    -0.15
    ardon
    -0.15
    _mC
    -0.15
    HandlerContext
    -0.14
    ierrez
    -0.14
    _tA
    -0.14
    ilden
    -0.14
    POSITIVE LOGITS
    castle
    0.18
    NF
    0.15
    allen
    0.15
    quisition
    0.15
    NG
    0.15
    _checkpoint
    0.15
    ì
    0.15
    Su
    0.14
    su
    0.14
    -su
    0.14
    Act Density 0.011%

    No Known Activations