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

    Neuronpedia

    INDEX
    Explanations

    issues or references to bugs within a software or system context

    oai_token-act-pair · gpt-3.5-turbo

    references to software bugs and issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ACP
    -0.73
    arnaev
    -0.73
     sclerosis
    -0.73
    ointed
    -0.70
    perty
    -0.70
     VIDEOS
    -0.70
    uania
    -0.69
     Pradesh
    -0.68
    ã
    -0.66
    tsky
    -0.65
    POSITIVE LOGITS
    bear
    1.03
    fixes
    0.96
    zilla
    0.95
     Bunny
    0.95
    fix
    0.95
    gered
    0.91
    bug
    0.88
    atti
    0.83
    bugs
    0.82
     bounty
    0.79
    Act Density 0.013%

    No Known Activations