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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to competency

    oai_token-act-pair · gpt-3.5-turbo

    words related to competence and incompetence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pause
    -0.74
    forest
    -0.72
    ORN
    -0.71
    den
    -0.70
    1950
    -0.69
    stead
    -0.69
    patch
    -0.69
    Raid
    -0.67
    Pear
    -0.65
    Closure
    -0.64
    POSITIVE LOGITS
     competence
    0.97
    umbn
    0.90
     incompetent
    0.85
    abama
    0.84
     competent
    0.82
    uracy
    0.80
    acies
    0.79
     incompetence
    0.79
     incompet
    0.78
    ascript
    0.75
    Act Density 0.023%

    No Known Activations