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

    Neuronpedia

    INDEX
    Explanations

    expressions of satisfaction and contentment

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

    "satisfaction" or "satisfied"

    np_acts-logits-general · gemini-2.0-flash

    satisfied with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⁠
    -0.40
    Parcelize
    -0.40
     dangers
    -0.40
     lupus
    -0.39
     مرئيه
    -0.38
     sheaf
    -0.38
     germs
    -0.38
     ⁠
    -0.38
     rude
    -0.37
     foolishness
    -0.37
    POSITIVE LOGITS
     satisfaction
    1.10
     Satisfaction
    1.09
    satisfaction
    0.96
    Satisfaction
    0.94
     Satisfied
    0.93
     satisfied
    0.90
     satisf
    0.87
    atisfactory
    0.85
     satisfecho
    0.84
     Satis
    0.83
    Act Density 0.119%

    No Known Activations