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

    Neuronpedia

    INDEX
    Explanations

    occupations and professions

    oai_token-act-pair · gpt-3.5-turbo

    job titles and professions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ceilings
    -0.80
     conclusions
    -0.77
     chests
    -0.75
     judgments
    -0.72
     assumptions
    -0.72
     notions
    -0.71
     timelines
    -0.69
    ouls
    -0.69
     explanations
    -0.68
     attackers
    -0.68
    POSITIVE LOGITS
    digy
    0.92
     specializing
    0.86
    ess
    0.80
    alyst
    0.78
    igmatic
    0.77
    ective
    0.75
    enary
    0.73
    naissance
    0.73
    forcer
    0.72
    ploma
    0.71
    Act Density 0.182%

    No Known Activations