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

    Neuronpedia

    INDEX
    Explanations

    Volume numbers and titles

    oai_token-act-pair · gpt-3.5-turbo

    references to specific publications or volumes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    20439
    -0.69
    kl
    -0.67
     DH
    -0.62
    hon
    -0.61
    DH
    -0.60
    ÄŁ
    -0.59
    ellen
    -0.59
    Serv
    -0.59
     cle
    -0.57
     Anat
    -0.56
    POSITIVE LOGITS
    ifer
    0.73
    ÙĨ
    0.71
    wise
    0.68
    acters
    0.67
    estic
    0.66
    uine
    0.65
    ŀ
    0.63
    ulse
    0.63
    querade
    0.62
    icut
    0.62
    Act Density 0.141%

    No Known Activations