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

    Neuronpedia

    INDEX
    Explanations

    words related to identifying and reporting software defects or glitches

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "bug."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ACP
    -0.77
     sclerosis
    -0.74
    perty
    -0.74
    uania
    -0.71
    xit
    -0.70
    tsky
    -0.70
     Pradesh
    -0.68
    apist
    -0.67
     VIDEOS
    -0.66
    agher
    -0.66
    POSITIVE LOGITS
    bear
    1.12
    gered
    1.01
    fixes
    0.93
     Bunny
    0.91
    fix
    0.90
    zilla
    0.90
    bug
    0.84
    atti
    0.84
     bounty
    0.83
    iously
    0.81
    Act Density 0.016%

    No Known Activations