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

    Neuronpedia

    INDEX
    Explanations

    issues or problems that need fixing within systems or projects

    oai_token-act-pair · gpt-3.5-turbo

    mentions of software bugs and their fixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arnaev
    -0.75
    ACP
    -0.73
    inav
    -0.69
    ophers
    -0.69
    kus
    -0.68
    rontal
    -0.66
    agher
    -0.66
    weeney
    -0.65
     CHO
    -0.65
    ointed
    -0.64
    POSITIVE LOGITS
    fixes
    0.97
    bugs
    0.95
    gered
    0.94
    bug
    0.94
    Bug
    0.91
    bear
    0.91
    fix
    0.89
     bugs
    0.87
     bug
    0.86
     Bunny
    0.83
    Act Density 0.012%

    No Known Activations