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

    Neuronpedia

    INDEX
    Explanations

    phrases related to specific locations or academic fields

    oai_token-act-pair · gpt-3.5-turbo

    references to specific regions or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arious
    -0.96
    perature
    -0.81
    utor
    -0.79
    iannopoulos
    -0.77
    uador
    -0.77
    orned
    -0.76
    iculty
    -0.76
    FAULT
    -0.75
    orthy
    -0.75
    oths
    -0.75
    POSITIVE LOGITS
     Dealer
    0.81
     Products
    0.79
     Tribe
    0.79
     Blaze
    0.79
     Pure
    0.77
     Streaming
    0.77
     Mix
    0.76
     Freeze
    0.76
     Shooting
    0.74
     Deal
    0.74
    Act Density 0.017%

    No Known Activations