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

    Neuronpedia

    INDEX
    Explanations

    references or descriptions of things being possible

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bane
    -0.91
    bey
    -0.83
    masters
    -0.80
    men
    -0.78
    court
    -0.75
    waters
    -0.74
    ĪĴ
    -0.74
    mens
    -0.74
    gar
    -0.72
    maid
    -0.71
    POSITIVE LOGITS
    alities
    0.82
    cffffcc
    0.81
     combinations
    0.77
    ities
    0.77
     embodiments
    0.76
     exception
    0.71
     (%)
    0.68
     scenarios
    0.67
     universes
    0.67
    iary
    0.66
    Act Density 0.050%

    No Known Activations