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

    Neuronpedia

    INDEX
    Explanations

    emotional reactions and expressions of surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Majefty
    -0.44
     itſelf
    -0.42
    aragua
    -0.40
    nEnter
    -0.40
    Datagram
    -0.39
     prefent
    -0.38
     inför
    -0.38
    Parent
    -0.38
     ioe
    -0.38
     audi
    -0.37
    POSITIVE LOGITS
     disappointed
    0.57
     okaza
    0.56
     surprised
    0.54
     ternyata
    0.53
    surprised
    0.52
     disambiguazione
    0.52
     disappointment
    0.51
    發現
    0.51
    UnusedPrivate
    0.51
     обнаружи
    0.50
    Act Density 0.258%

    No Known Activations