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

    Neuronpedia

    INDEX
    Explanations

    words related to dominance, influence, or control

    oai_token-act-pair · gpt-3.5-turbo

    the concept of dominance or persistence in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bor
    -0.71
     wells
    -0.69
    clamation
    -0.67
     Bravo
    -0.67
    forestation
    -0.65
    por
    -0.64
    uddy
    -0.63
    carbon
    -0.62
    pled
    -0.62
    ciples
    -0.60
    POSITIVE LOGITS
     prevail
    1.01
     prevailed
    0.95
    enance
    0.90
    acebook
    0.83
    PDATE
    0.79
     against
    0.79
    rences
    0.78
    SHIP
    0.74
    theless
    0.72
    igent
    0.71
    Act Density 0.043%

    No Known Activations