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

    Neuronpedia

    INDEX
    Explanations

    words related to vocal abilities or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to vocal expressions or vocalists

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uden
    -0.91
     Reincarn
    -0.91
    agher
    -0.83
    awaru
    -0.78
    roxy
    -0.73
    romeda
    -0.72
     Carbuncle
    -0.69
    ionage
    -0.69
    ģĸ
    -0.68
     Journals
    -0.67
    POSITIVE LOGITS
    izations
    1.26
     cords
    1.20
    isations
    1.17
     chords
    1.06
    izes
    1.00
    izers
    0.99
    izing
    0.98
     fry
    0.95
    ized
    0.94
    izer
    0.92
    Act Density 0.025%

    No Known Activations