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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically those relating to various names and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to notable individuals and organizations in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ONSORED
    -0.53
    IBLE
    -0.47
    ãĤ¢ãĥ«
    -0.45
    depending
    -0.43
     Canaver
    -0.41
     ¯
    -0.40
     WRITE
    -0.40
    abus
    -0.40
    FontSize
    -0.39
    ?????-
    -0.39
    POSITIVE LOGITS
     and
    1.08
     etc
    0.95
     or
    0.93
    ®,
    0.77
     &
    0.75
     AND
    0.70
     versus
    0.68
    -,
    0.68
     et
    0.66
    ,
    0.66
    Act Density 2.262%

    No Known Activations