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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to famous individuals

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pees
    -0.81
    ETS
    -0.79
    oks
    -0.78
    acci
    -0.78
    ayers
    -0.75
    mas
    -0.74
    ciating
    -0.74
    ittens
    -0.71
    limits
    -0.71
    issions
    -0.71
    POSITIVE LOGITS
     educator
    1.18
     politician
    1.10
     activist
    1.05
     philosopher
    1.04
     longtime
    1.04
     entrepreneur
    1.03
     translator
    1.00
     thinker
    1.00
     former
    0.97
     theorist
    0.97
    Act Density 0.106%

    No Known Activations