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

    Neuronpedia

    INDEX
    Explanations

    words related to superiority or exceptionalism

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "super" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reloaded
    -0.73
     Seym
    -0.72
    aughs
    -0.72
     Lauder
    -0.70
    edIn
    -0.68
    Downloadha
    -0.65
     Frie
    -0.64
    ynski
    -0.63
     Qiao
    -0.63
     Anat
    -0.63
    POSITIVE LOGITS
    imposed
    1.20
    visor
    1.17
    nova
    1.04
    cedes
    1.03
    charged
    1.03
    visory
    1.00
    charg
    0.95
    computer
    0.95
    powers
    0.93
    visors
    0.90
    Act Density 0.013%

    No Known Activations