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

    Neuronpedia

    INDEX
    Explanations

    words related to overriding decisions or commands

    oai_token-act-pair · gpt-3.5-turbo

    terms related to overriding or vetoing authority or decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    istics
    -0.78
    Torrent
    -0.74
     Knot
    -0.74
     Bomber
    -0.72
    atform
    -0.70
    iatrics
    -0.70
    estones
    -0.67
    rug
    -0.66
    cture
    -0.66
    ECD
    -0.66
    POSITIVE LOGITS
     overr
    1.14
     override
    1.11
    idden
    0.91
    xual
    0.86
     overriding
    0.83
     defaults
    0.78
    ride
    0.78
    ragon
    0.75
     scramble
    0.72
     default
    0.71
    Act Density 0.016%

    No Known Activations