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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "surprise" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    schirm
    -0.72
    salle
    -0.71
    )_{
    -0.66
    bucket
    -0.65
    futbolista
    -0.64
    ArrowToggle
    -0.63
    helial
    -0.62
    iverr
    -0.61
     Polk
    -0.61
     Laub
    -0.61
    POSITIVE LOGITS
     Surprise
    1.20
     surprise
    1.13
    surprise
    0.99
    Surprise
    0.99
     surprises
    0.94
     surprising
    0.93
     surpris
    0.93
     surprised
    0.92
    sterious
    0.84
     sympy
    0.82
    Act Density 0.052%

    No Known Activations