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

    Neuronpedia

    INDEX
    Explanations

    words related to software bug fixes or improvements

    oai_token-act-pair · gpt-3.5-turbo

    references to bug fixes and maintenance updates in software

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uron
    -0.83
    educ
    -0.81
    isine
    -0.76
    aden
    -0.72
    aughtered
    -0.70
    oths
    -0.69
    weeney
    -0.68
    isted
    -0.67
    irl
    -0.67
    igion
    -0.67
    POSITIVE LOGITS
    fixes
    1.18
     workaround
    1.03
    fix
    0.94
     fixes
    0.92
     Fixes
    0.89
    FIX
    0.88
    CVE
    0.85
     CVE
    0.84
     typo
    0.83
     patched
    0.81
    Act Density 0.058%

    No Known Activations