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

    Neuronpedia

    INDEX
    Explanations

    software bugs and fixes in a code context

    oai_token-act-pair · gpt-3.5-turbo

    technical issues or bugs related to software functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ÂŃ
    -0.77
    adies
    -0.74
    —-
    -0.74
     duly
    -0.71
     passions
    -0.68
    "—
    -0.68
     boldly
    -0.68
    aciously
    -0.67
    ë
    -0.66
     reasoned
    -0.64
    POSITIVE LOGITS
     incorrectly
    1.09
     tooltip
    1.04
     respawn
    1.00
     incorrect
    0.98
     popup
    0.97
     GUI
    0.93
     improperly
    0.89
     teleport
    0.86
     errone
    0.85
     overwrite
    0.83
    Act Density 0.339%

    No Known Activations