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

    Neuronpedia

    INDEX
    Explanations

    website programming syntax elements

    oai_token-act-pair · gpt-3.5-turbo

    technical jargon and coding syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.80
    omorphic
    -0.78
     upside
    -0.68
     antagon
    -0.64
     Eugene
    -0.63
     frog
    -0.62
     antit
    -0.62
    rupal
    -0.61
    phalt
    -0.61
    onyms
    -0.61
    POSITIVE LOGITS
     Funds
    0.70
     Mortgage
    0.67
    antage
    0.66
     Reserve
    0.66
    ?????-
    0.64
     Females
    0.63
    MENTS
    0.63
    uncle
    0.62
    arr
    0.61
    schild
    0.61
    Act Density 0.044%

    No Known Activations