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

    Neuronpedia

    INDEX
    Explanations

    expressions of negativity or disappointment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    كذا
    -0.57
    たびに
    -0.52
     piele
    -0.52
    верх
    -0.51
     mosso
    -0.49
    איך
    -0.49
     lienzo
    -0.48
    êmios
    -0.48
     culoare
    -0.48
     stets
    -0.48
    POSITIVE LOGITS
     unfortunately
    4.20
    Unfortunately
    3.69
    unfortunately
    3.68
     Unfortunately
    3.65
     sadly
    3.52
     malheureusement
    3.35
    Sadly
    3.22
     Sadly
    3.18
     purtroppo
    3.17
     leider
    2.91
    Act Density 0.069%

    No Known Activations