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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey speech or spoken dialogue, particularly with emotional or impactful content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    and phrases

    np_acts-logits-general · gemini-2.0-flash

    words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ISupport
    -0.48
     Identified
    -0.37
    PickerController
    -0.34
    Identified
    -0.34
     Aut
    -0.33
     Harlequin
    -0.33
    Життєпис
    -0.32
    rtype
    -0.31
     Draws
    -0.31
    aktor
    -0.31
    POSITIVE LOGITS
     phrases
    0.90
     words
    0.90
     utterance
    0.88
     phrase
    0.80
     صوتيه
    0.80
     speech
    0.78
    phrases
    0.77
     Worte
    0.77
     frases
    0.76
     verbal
    0.75
    Act Density 0.520%

    No Known Activations