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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to a specific fictional or geographical context

    oai_token-act-pair · gpt-3.5-turbo

    references to video game characters and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    meal
    -0.78
    fam
    -0.66
     round
    -0.64
     expr
    -0.61
     FT
    -0.61
    reply
    -0.61
     entitle
    -0.60
    egg
    -0.58
     ministerial
    -0.58
     brood
    -0.58
    POSITIVE LOGITS
    olin
    2.72
    cca
    2.40
    olis
    1.79
    uana
    1.54
    acca
    1.44
    onna
    1.39
    otta
    1.29
    enez
    1.22
    ocket
    1.04
    fecture
    0.99
    Act Density 0.033%

    No Known Activations