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

    Neuronpedia

    INDEX
    Explanations

    instances of speech and descriptions of tones or accents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uce
    -0.15
     activity
    -0.14
     Salmon
    -0.14
    tab
    -0.14
    allon
    -0.14
     trib
    -0.13
     silent
    -0.13
    ientos
    -0.13
    ilar
    -0.13
    ophy
    -0.13
    POSITIVE LOGITS
     accent
    0.35
     voice
    0.34
     accents
    0.32
    accent
    0.32
     voices
    0.27
    voice
    0.27
     Voice
    0.27
     nasal
    0.27
    Voice
    0.26
     tone
    0.26
    Act Density 0.174%

    No Known Activations