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

    Neuronpedia

    INDEX
    Explanations

    information related to people and their actions reported by other people, typically involving statements about them attributed to sources

    oai_token-act-pair · gpt-3.5-turbo

    references to people or sources providing information or insights

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mascot
    -0.82
     Gutenberg
    -0.74
    tumblr
    -0.70
     landfall
    -0.69
    ãĥĺ
    -0.66
     Mechdragon
    -0.66
    osate
    -0.65
    odor
    -0.62
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.61
     manifesto
    -0.61
    POSITIVE LOGITS
     briefed
    1.25
    dozen
    0.98
     knowledgeable
    0.89
     anonymity
    0.84
     familiar
    0.83
    amiliar
    0.82
     UNCLASSIFIED
    0.80
     reviewed
    0.80
    Asked
    0.80
     interviewed
    0.80
    Act Density 0.302%

    No Known Activations