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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific names, particularly those that seem to be associated with political or military figures

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals, particularly those with the name "Naw" or "Daw."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Prism
    -0.67
     Juno
    -0.67
     Gabriel
    -0.64
     Purg
    -0.62
     grape
    -0.60
     ANGEL
    -0.60
    ¯¯¯¯¯¯¯¯
    -0.60
     Pope
    -0.59
     Kaiser
    -0.59
     Sacrament
    -0.59
    POSITIVE LOGITS
    lins
    1.05
    lat
    1.03
    dat
    1.01
    da
    0.98
    ez
    0.96
    ees
    0.95
    trak
    0.94
    dh
    0.94
    die
    0.93
    awi
    0.93
    Act Density 0.052%

    No Known Activations