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

    Neuronpedia

    INDEX
    Explanations

    phrases that express feelings of surprise or anticipation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ewire
    -0.15
    enderror
    -0.15
    _sensitive
    -0.14
    ableViewController
    -0.14
    اتÙĩ
    -0.14
     incons
    -0.14
    ืà¸Ńà¸Ĥ
    -0.13
    XR
    -0.13
    esen
    -0.13
    gd
    -0.13
    POSITIVE LOGITS
     surprise
    1.02
     surprises
    0.88
     Surprise
    0.88
     surprised
    0.79
     surpr
    0.77
     surprising
    0.71
     unexpected
    0.66
    sur
    0.64
     Sur
    0.62
    Sur
    0.61
    Act Density 0.404%

    No Known Activations