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

    Neuronpedia

    INDEX
    Explanations

    instances where someone is surprised or amazed by a particular event or revelation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or disbelief

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hemor
    -0.69
    interstitial
    -0.60
     bona
    -0.60
    osi
    -0.59
     Annotations
    -0.58
    bern
    -0.58
    accompan
    -0.58
     assum
    -0.58
    ilon
    -0.58
    winner
    -0.57
    POSITIVE LOGITS
     how
    0.95
     by
    0.75
     surprised
    0.74
     seeing
    0.74
     when
    0.67
    how
    0.67
     aback
    0.67
     discover
    0.65
     amaz
    0.64
     HOW
    0.64
    Act Density 0.061%

    No Known Activations