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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "speak" is used in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    references to the act of speaking or discussing topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aredevil
    -0.79
    \/\/
    -0.78
    ======
    -0.70
    gart
    -0.69
    ritional
    -0.65
    ikhail
    -0.64
    agara
    -0.64
    gradation
    -0.64
    etheless
    -0.63
    abwe
    -0.63
    POSITIVE LOGITS
     aloud
    0.93
    voice
    0.88
     louder
    0.84
     volumes
    0.83
     english
    0.82
     fluent
    0.79
     spoken
    0.77
    bone
    0.75
    Frameworks
    0.74
     English
    0.73
    Act Density 0.034%

    No Known Activations