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

    Neuronpedia

    INDEX
    Explanations

    references to silence or silence-related concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    OGND
    -0.90
     חיצוניים
    -0.82
     estekak
    -0.81
     Coz
    -0.80
    dată
    -0.73
     للاسماء
    -0.72
    WireFormatLite
    -0.72
    ViewBag
    -0.71
     Schalke
    -0.70
    ="@+
    -0.70
    POSITIVE LOGITS
     silent
    1.45
     Silent
    1.34
    Silent
    1.33
    silent
    1.30
     Sil
    1.27
     Silence
    1.23
     sil
    1.19
     silence
    1.19
     silently
    1.16
     Quiet
    1.13
    Act Density 0.014%

    No Known Activations