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

    Neuronpedia

    INDEX
    Explanations

    the name "Humboldt"

    oai_token-act-pair · gpt-3.5-turbo

    words related to locations and their details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    atile
    -0.74
    uese
    -0.71
    minus
    -0.70
    aign
    -0.70
    going
    -0.69
     Osw
    -0.69
    anwhile
    -0.68
    nels
    -0.68
    employment
    -0.67
    isSpecialOrderable
    -0.67
    POSITIVE LOGITS
     Field
    0.70
    erers
    0.63
     Sutherland
    0.60
     Roberts
    0.60
     Franch
    0.58
    WARE
    0.58
    oulos
    0.58
     astronomers
    0.58
     Bus
    0.57
    eger
    0.57
    Act Density 0.274%

    No Known Activations