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

    Neuronpedia

    INDEX
    Explanations

    proper names

    oai_token-act-pair · gpt-3.5-turbo

    proper names and specific identifiers related to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Skydragon
    -0.83
     ACTION
    -0.77
     acceleration
    -0.71
     simulator
    -0.70
     dictators
    -0.70
     Communists
    -0.69
     deflation
    -0.69
     downgrade
    -0.68
     sidx
    -0.68
     technical
    -0.67
    POSITIVE LOGITS
    ilyn
    1.59
    annah
    1.49
    helle
    1.45
    andra
    1.44
    yna
    1.43
    abeth
    1.42
    lene
    1.42
    annie
    1.41
    ricia
    1.41
    ilee
    1.41
    Act Density 0.263%

    No Known Activations