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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue and speech-related actions

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

    Follows speech verbs (said, muttered)

    np_acts-logits-general · gemini-2.0-flash

    utterance with qualification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -0.63
     فريبيس
    -0.63
    MigrationBuilder
    -0.60
     EClass
    -0.59
    bootstrapcdn
    -0.57
    rungsseite
    -0.55
    principalTable
    -0.54
    CJK
    -0.54
    arXiv
    -0.53
    saying
    -0.53
    POSITIVE LOGITS
     aloud
    0.78
     while
    0.70
     softly
    0.67
     sarcas
    0.67
     referring
    0.64
    complexContent
    0.63
     looking
    0.61
     sambil
    0.60
     casually
    0.59
     innocently
    0.58
    Act Density 0.093%

    No Known Activations