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

    Neuronpedia

    INDEX
    Explanations

    dialogue markers and emotional expressions in conversations

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

    Follows quotation marks or questions

    np_acts-logits-general · gemini-2.0-flash

    dialogue markers and responses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     שוליים
    -0.56
     Chwiliwch
    -0.55
    tvguidetime
    -0.50
    DataAnnotations
    -0.47
    endous
    -0.47
    ̈́
    -0.46
    omeness
    -0.46
    IsUnicode
    -0.45
    tiérrez
    -0.45
    bootstrapcdn
    -0.45
    POSITIVE LOGITS
     replied
    0.56
    ตอบ
    0.51
     nahilalakip
    0.49
     responded
    0.44
     replies
    0.44
     answered
    0.44
     responding
    0.43
     retorted
    0.43
     responds
    0.42
     respondeu
    0.42
    Act Density 0.098%

    No Known Activations