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

    Neuronpedia

    INDEX
    Explanations

    words related to professions ending with 'ist' or 'er'

    oai_token-act-pair · gpt-3.5-turbo

    words related to various professional roles or occupations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Territories
    -0.68
     regeneration
    -0.66
    headers
    -0.63
     numerical
    -0.63
    ãĥ¼ãĥ³
    -0.62
     Warden
    -0.61
    SIZE
    -0.61
     woodland
    -0.61
     dissolution
    -0.61
    SpaceEngineers
    -0.60
    POSITIVE LOGITS
     extraord
    0.99
     specializing
    0.95
    hip
    0.92
    hire
    0.89
    hips
    0.85
    haw
    0.84
    ucker
    0.81
    afety
    0.78
     hired
    0.77
    ynthesis
    0.76
    Act Density 0.143%

    No Known Activations