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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that indicate communication and expressions of emotions or sentiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     onCancelled
    -0.58
    lapsingToolbar
    -0.57
    createServer
    -0.56
     transfieras
    -0.50
    økt
    -0.48
     vPvB
    -0.47
     conquête
    -0.46
     juger
    -0.45
    cerpt
    -0.45
    poran
    -0.45
    POSITIVE LOGITS
     surprise
    1.17
     shock
    1.13
     amazement
    1.11
     astonishment
    1.09
     disappointment
    1.08
     annoyance
    1.08
     disgust
    1.08
     frustration
    1.07
     dismay
    1.04
     concern
    1.03
    Act Density 0.348%

    No Known Activations