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

    Neuronpedia

    INDEX
    Explanations

    references to human voices

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "voice" in various contexts, indicating its significance in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Barbar
    -0.70
    deals
    -0.68
     Dates
    -0.66
    NRS
    -0.65
    é¾į
    -0.64
    BALL
    -0.64
    ammad
    -0.64
    ival
    -0.63
     Related
    -0.62
     econom
    -0.62
    POSITIVE LOGITS
     voice
    3.90
    voice
    2.73
     voices
    2.70
     Voice
    2.45
    Voice
    2.31
     voicing
    1.76
     voiced
    1.69
     Voices
    1.62
     voic
    1.58
     VO
    1.56
    Act Density 0.017%

    No Known Activations