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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or specific terms

    oai_token-act-pair · gpt-3.5-turbo

    the verb "is" and variations of being in statements about definitions or identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    usercontent
    -0.79
    */
    -0.73
     traged
    -0.71
    inventoryQuantity
    -0.71
    "},"
    -0.67
    edin
    -0.66
    Tes
    -0.63
    Others
    -0.63
    Footnote
    -0.62
    udeau
    -0.61
    POSITIVE LOGITS
     comprised
    1.10
     basically
    1.02
     essentially
    1.00
     an
    0.96
     composed
    0.91
     supposed
    0.91
     located
    0.91
     a
    0.90
     defined
    0.90
     another
    0.89
    Act Density 0.186%

    No Known Activations