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

    Neuronpedia

    INDEX
    Explanations

    mentions of absence or lack of something

    oai_token-act-pair · gpt-3.5-turbo

    a repeated emphasis on the word "any."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    plex
    -0.79
    rex
    -0.72
    rox
    -0.71
    ip
    -0.68
    gypt
    -0.68
    gal
    -0.67
    wered
    -0.66
    hap
    -0.65
    rea
    -0.64
    stadt
    -0.64
    POSITIVE LOGITS
    THING
    1.24
    WHERE
    1.03
     meaningful
    0.98
     particular
    0.97
     significant
    0.95
    place
    0.94
    ones
    0.86
     substantive
    0.85
    ONE
    0.85
     credible
    0.83
    Act Density 0.084%

    No Known Activations