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

    Neuronpedia

    INDEX
    Explanations

    dichotomies or distinctions between two or more options or categories

    oai_token-act-pair · gpt-3.5-turbo

    references to categorizations and divisions within topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Beast
    -0.76
    DERR
    -0.74
     Andromeda
    -0.74
    uddin
    -0.69
    bats
    -0.67
    ebook
    -0.66
    ocaust
    -0.65
    ãĤ¼ãĤ¦ãĤ¹
    -0.63
    UNE
    -0.63
    Downloadha
    -0.63
    POSITIVE LOGITS
    :-
    0.93
    %:
    0.88
     viz
    0.88
     simultaneously
    0.77
     distinct
    0.73
    :(
    0.70
    :
    0.69
    ):
    0.69
     concurrently
    0.68
    :'
    0.68
    Act Density 0.169%

    No Known Activations