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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a person speaking or giving a speech

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "spoke" indicating reported speech or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assi
    -0.71
    gradation
    -0.68
    mental
    -0.66
    \/\/
    -0.66
    vernment
    -0.66
    =~
    -0.65
    inner
    -0.65
    engeance
    -0.65
    rypt
    -0.65
    ======
    -0.65
    POSITIVE LOGITS
     aloud
    0.93
    ophone
    0.85
     artic
    0.83
     volumes
    0.82
     voices
    0.80
     spoken
    0.78
     fluent
    0.77
     Cosponsors
    0.77
     Mandarin
    0.76
    voice
    0.76
    Act Density 0.024%

    No Known Activations