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

    Neuronpedia

    INDEX
    Explanations

    keywords related to supremacy or importance

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases that signify ultimate authority or superiority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ppo
    -0.86
    TPS
    -0.77
    OUT
    -0.76
     Lup
    -0.70
    zl
    -0.68
    Ey
    -0.68
     Cro
    -0.65
     Doct
    -0.65
     Cheong
    -0.65
     Hoffman
    -0.64
    POSITIVE LOGITS
    ly
    0.84
     referen
    0.83
    iour
    0.79
     supreme
    0.78
    rament
    0.76
     pinnacle
    0.74
     vigilance
    0.73
     decree
    0.73
    reme
    0.73
    essential
    0.72
    Act Density 0.006%

    No Known Activations