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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "vo" accompanied by a specific number

    oai_token-act-pair · gpt-3.5-turbo

    references to vocal performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    taker
    -0.73
    papers
    -0.65
     foundations
    -0.64
    Else
    -0.64
    owship
    -0.63
     CTR
    -0.63
     abiding
    -0.63
    matically
    -0.63
    riad
    -0.62
     Kurd
    -0.62
    POSITIVE LOGITS
    orde
    0.96
    oice
    0.92
    ile
    0.87
    apor
    0.86
    ices
    0.86
    VO
    0.84
    iture
    0.83
    pload
    0.83
    irus
    0.83
    iced
    0.82
    Act Density 0.010%

    No Known Activations