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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the start of audio content

    oai_token-act-pair · gpt-3.5-turbo

    instances of the imperative "listen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Expend
    -0.68
    EStreamFrame
    -0.66
     Reincarn
    -0.66
     Scotia
    -0.65
     graft
    -0.62
     revenge
    -0.61
     Kag
    -0.60
    irie
    -0.58
    \/\/
    -0.58
    vae
    -0.57
    POSITIVE LOGITS
    ership
    1.06
     listen
    0.91
     attent
    0.90
    ers
    0.87
    Listen
    0.86
    quartered
    0.84
    ings
    0.81
     Listen
    0.80
     listened
    0.78
    ificantly
    0.78
    Act Density 0.018%

    No Known Activations