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

    Neuronpedia

    INDEX
    Explanations

    phrases related to copyright information

    oai_token-act-pair · gpt-3.5-turbo

    references to news organizations and their associated details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dos
    -0.72
     Takeru
    -0.67
    laus
    -0.67
    osaurus
    -0.63
    bourg
    -0.62
    stown
    -0.61
     Gust
    -0.60
    izable
    -0.59
     behav
    -0.58
     dock
    -0.58
    POSITIVE LOGITS
    iphate
    0.84
    ocument
    0.68
    istries
    0.68
    foundation
    0.64
    claimer
    0.63
    iesel
    0.63
    ternity
    0.62
    ippery
    0.61
    ritis
    0.61
    itbart
    0.60
    Act Density 0.104%

    No Known Activations