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

    Neuronpedia

    INDEX
    Explanations

    words related to competence and competency

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to competence and incompetence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    1950
    -0.75
    bed
    -0.71
    fare
    -0.71
    zman
    -0.70
    patch
    -0.68
    planes
    -0.66
    romeda
    -0.66
     slit
    -0.66
    quad
    -0.65
    plane
    -0.65
    POSITIVE LOGITS
     competence
    0.96
    umbn
    0.95
    uracy
    0.90
    ascript
    0.90
     incompetent
    0.89
     competent
    0.83
     incompet
    0.83
     compet
    0.82
    acies
    0.81
    iencies
    0.81
    Act Density 0.035%

    No Known Activations