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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks, especially periods, that may signify the end of statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ampus
    -0.16
    kuk
    -0.14
    ,'#
    -0.14
    akat
    -0.13
    iams
    -0.13
    ayer
    -0.13
    ilogy
    -0.13
    .RunWith
    -0.13
    foon
    -0.13
    lk
    -0.13
    POSITIVE LOGITS
     напÑĢимеÑĢ
    0.17
     napÅĻÃŃklad
    0.17
     napÅĻ
    0.17
    bsp
    0.16
     first
    0.16
     ÙħØ«ÙĦا
    0.16
    èŃ
    0.16
     For
    0.15
     Lodge
    0.15
    :↵
    0.15
    Act Density 0.066%

    No Known Activations