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

    Neuronpedia

    INDEX
    Explanations

    geographic locations or areas

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations and areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aughs
    -0.75
    oulos
    -0.75
    stice
    -0.71
    ÄŁ
    -0.67
    sonian
    -0.65
    alion
    -0.65
    sts
    -0.64
     Makes
    -0.63
    amation
    -0.63
    jac
    -0.62
    POSITIVE LOGITS
     plagued
    1.21
     ravaged
    1.20
     where
    1.19
     frequ
    1.14
     prone
    1.09
     inaccessible
    1.08
     dominated
    1.07
     governed
    1.05
     devastated
    1.03
     afflicted
    1.03
    Act Density 0.134%

    No Known Activations