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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise and shock

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

    "surprise" or "surprised"

    np_acts-logits-general · gemini-2.0-flash

    surprise and shock

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    mmate
    -0.61
     prédé
    -0.58
    QtCore
    -0.56
     Geb
    -0.55
     CURLOPT
    -0.55
    erobe
    -0.53
    brecht
    -0.52
     feuille
    -0.51
    QUADS
    -0.51
    PhysRevD
    -0.51
    POSITIVE LOGITS
     surprise
    0.88
     Surprise
    0.88
     surpris
    0.85
     Jefus
    0.84
    ingly
    0.78
    Surprise
    0.77
    surprise
    0.77
     itſelf
    0.76
     SHOCK
    0.75
     myſelf
    0.75
    Act Density 0.101%

    No Known Activations