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

    Neuronpedia

    INDEX
    Explanations

    mentions of speakers in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to speakers in a context of events or conferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ster
    -0.66
     Moss
    -0.63
    rises
    -0.63
    YP
    -0.63
     Reporting
    -0.63
    laus
    -0.62
    ENA
    -0.62
    imes
    -0.59
    jac
    -0.59
    hens
    -0.59
    POSITIVE LOGITS
     speakers
    1.30
     speaker
    1.23
    mith
    0.88
     voices
    0.85
    phone
    0.84
     louder
    0.80
    speech
    0.79
    voice
    0.78
     headphones
    0.77
    hip
    0.75
    Act Density 0.013%

    No Known Activations