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

    Neuronpedia

    INDEX
    Explanations

    phrases related to voice-overs or narrations

    oai_token-act-pair · gpt-3.5-turbo

    references to voices and the concept of speaking or narration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    é¾
    -0.86
    antine
    -0.73
    ा
    -0.71
     nets
    -0.67
     bis
    -0.67
    iston
    -0.66
    adelphia
    -0.64
     mishand
    -0.63
    NF
    -0.63
    olicy
    -0.62
    POSITIVE LOGITS
     louder
    0.81
     voices
    0.78
     Voices
    0.78
     VO
    0.78
     chorus
    0.74
    voice
    0.73
    Song
    0.71
     recorder
    0.69
    PRES
    0.68
    choes
    0.68
    Act Density 0.158%

    No Known Activations