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

    Neuronpedia

    INDEX
    Explanations

    expressions of surprise or shock

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    QtCore
    -0.66
    ⓧ
    -0.60
    CopyWith
    -0.58
    rawDesc
    -0.56
    =$((
    -0.56
    erobe
    -0.55
    bestand
    -0.54
     Kane
    -0.53
     onto
    -0.53
    CPP
    -0.52
    POSITIVE LOGITS
     surprise
    1.56
     surprised
    1.50
     Surprise
    1.47
     surprises
    1.37
     shocked
    1.35
    surprise
    1.35
     overras
    1.34
     surpresa
    1.33
    Surprise
    1.31
     surpris
    1.31
    Act Density 0.091%

    No Known Activations