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

    Neuronpedia

    INDEX
    Explanations

    fan-related terms or mentions

    oai_token-act-pair · gpt-3.5-turbo

    references to fans and their experiences or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Morning
    -0.64
    tein
    -0.61
    abus
    -0.61
     Lie
    -0.59
     Morph
    -0.59
     MacArthur
    -0.59
    iban
    -0.57
     Lich
    -0.57
     Osc
    -0.57
    innon
    -0.57
    POSITIVE LOGITS
    erv
    1.29
    haw
    1.19
    hip
    1.17
    atical
    1.15
    atics
    1.06
    ubs
    1.05
    hips
    1.03
    boys
    1.01
    atically
    0.96
    fare
    0.94
    Act Density 0.046%

    No Known Activations