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

    Neuronpedia

    INDEX
    Explanations

    terms related to hierarchical classification levels or types

    oai_token-act-pair · gpt-3.5-turbo

    classifications of legal offenses or classes of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OPLE
    -0.73
     stump
    -0.69
     wit
    -0.68
     Bakr
    -0.66
     ende
    -0.62
    issance
    -0.61
    ternity
    -0.58
     Senegal
    -0.58
     Scotia
    -0.58
     Sussex
    -0.58
    POSITIVE LOGITS
    ifications
    1.33
    ifiers
    1.09
    ifying
    1.07
    ifies
    1.05
    ifier
    1.04
    mates
    1.00
    ifiable
    0.97
    mate
    0.96
    ribing
    0.92
    ification
    0.90
    Act Density 0.021%

    No Known Activations