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

    Neuronpedia

    INDEX
    Explanations

    the word "some" followed by other descriptors or circumstances

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditional or varying levels of certainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CARD
    -0.67
    APTER
    -0.67
    iola
    -0.66
    urden
    -0.63
    rup
    -0.62
    rollers
    -0.61
    gon
    -0.61
    tis
    -0.61
    iano
    -0.60
    andon
    -0.59
    POSITIVE LOGITS
     unspecified
    0.97
    ones
    0.89
     inexplicable
    0.87
     undefined
    0.87
    how
    0.86
     embodiments
    0.86
     semblance
    0.84
     extent
    0.83
    place
    0.81
     unforeseen
    0.77
    Act Density 0.050%

    No Known Activations