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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to software compatibility and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    (disposing
    -0.15
    ICO
    -0.15
    _flutter
    -0.14
    ras
    -0.14
    illon
    -0.14
    anford
    -0.14
    eldorf
    -0.14
    amera
    -0.13
    enstein
    -0.13
    elenium
    -0.13
    POSITIVE LOGITS
     compatibility
    0.75
     Compatibility
    0.66
     compatible
    0.65
     compat
    0.64
    compat
    0.63
    Compatibility
    0.62
     Compatible
    0.57
    compatible
    0.56
     incompatible
    0.56
    -compatible
    0.54
    Act Density 0.143%

    No Known Activations