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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "surprise" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Drapeau
    -0.73
    ArgsConstructor
    -0.73
     CoreData
    -0.68
    بوابة
    -0.67
    Personendaten
    -0.65
    ngdoc
    -0.65
     actionMode
    -0.64
    Datuak
    -0.63
    Carcinogenicity
    -0.62
    ViewChild
    -0.61
    POSITIVE LOGITS
     surprise
    1.86
     surprised
    1.74
     Surprise
    1.67
    surprise
    1.61
    Surprise
    1.44
    surprised
    1.44
     surprising
    1.36
     surprises
    1.34
     surpris
    1.32
     Überras
    1.26
    Act Density 0.073%

    No Known Activations