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

    Neuronpedia

    INDEX
    Explanations

    names of individuals, especially in the context of politics, cinema, and journalism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     eternity
    -0.59
     Palest
    -0.59
    $.
    -0.58
     Kafka
    -0.57
     Gods
    -0.55
    Els
    -0.53
     Pieces
    -0.53
     Pengu
    -0.53
    Quantity
    -0.53
    +.
    -0.52
    POSITIVE LOGITS
     reacted
    1.24
     took
    1.15
     went
    1.13
     has
    1.13
     gave
    1.10
     prevailed
    1.09
     weighed
    1.08
     appeared
    1.08
     welcomed
    1.07
     showed
    1.07
    Act Density 2.961%

    No Known Activations