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

    Neuronpedia

    INDEX
    Explanations

    references to previous or past studies, research, surveys, or operations

    oai_token-act-pair · gpt-3.5-turbo

    references to previous studies and research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sung
    -0.69
    Pri
    -0.64
    $$$$
    -0.62
     ILCS
    -0.60
    onics
    -0.58
    ãĤª
    -0.57
     Appropri
    -0.57
    Station
    -0.57
    ueller
    -0.56
    ioxide
    -0.55
    POSITIVE LOGITS
     administrations
    0.74
    bernatorial
    0.73
     generations
    0.72
     installments
    0.71
    iations
    0.70
     iterations
    0.67
    inctions
    0.65
    quit
    0.64
     eras
    0.63
     unsuccessfully
    0.62
    Act Density 0.242%

    No Known Activations