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

    Neuronpedia

    INDEX
    Explanations

    polite closing phrases in correspondence

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

    Saludos, thanks, regards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personensuche
    -0.62
    InputBorder
    -0.60
    Tembelea
    -0.60
    RectangleBorder
    -0.59
     PeEnEo
    -0.56
    LookAnd
    -0.55
    الحياه
    -0.54
     resourceCulture
    -0.53
     Chwiliwch
    -0.52
    AddTagHelper
    -0.52
    POSITIVE LOGITS
    keti
    0.46
     Thank
    0.45
     thank
    0.43
    Thanks
    0.43
     Thanks
    0.42
    Thank
    0.42
    Iné
    0.41
     Sonn
    0.41
    Rourke
    0.40
     Duarte
    0.40
    Act Density 0.010%

    No Known Activations