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

    Neuronpedia

    INDEX
    Explanations

    proper nouns

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual with the name "De"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CPC
    -0.71
     exhibits
    -0.66
     task
    -0.66
     idle
    -0.60
     "$:/
    -0.60
     OPS
    -0.58
     activity
    -0.58
     850
    -0.58
     dispens
    -0.57
     Wage
    -0.57
    POSITIVE LOGITS
    utsch
    1.25
    legate
    1.25
    arest
    1.25
    legates
    1.24
    eper
    1.15
    ception
    1.13
    acon
    1.11
    leted
    1.10
    Marco
    1.10
    bris
    1.09
    Act Density 0.019%

    No Known Activations