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

    Neuronpedia

    INDEX
    Explanations

    mentions of software updates or improvements

    oai_token-act-pair · gpt-3.5-turbo

    references to software patches

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.83
    yss
    -0.75
    emouth
    -0.69
    minist
    -0.68
    ccording
    -0.67
    amic
    -0.65
    Demand
    -0.65
    ¬
    -0.65
    emy
    -0.64
     Heller
    -0.63
    POSITIVE LOGITS
     patch
    1.07
     Patch
    0.99
     patches
    0.91
     patched
    0.89
    work
    0.85
    ioned
    0.80
    patch
    0.80
    ogue
    0.78
    Patch
    0.75
    ions
    0.73
    Act Density 0.011%

    No Known Activations