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

    Neuronpedia

    INDEX
    Explanations

    references to unexpected or surprising events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NavController
    -0.71
     Kat
    -0.69
    Kat
    -0.65
    fifths
    -0.62
    jerc
    -0.62
    orianCalendar
    -0.61
    IMDG
    -0.60
     fær
    -0.60
     I
    -0.59
    خاذ
    -0.59
    POSITIVE LOGITS
     Surprise
    1.23
     surprise
    1.11
     surpris
    1.05
    Surprise
    0.97
     surprised
    0.96
     reaſon
    0.93
    surprise
    0.92
     surprises
    0.89
     pleaſure
    0.86
     itſelf
    0.84
    Act Density 0.006%

    No Known Activations