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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal feelings and emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    feeling
    -0.49
    waitKey
    -0.45
     виправивши
    -0.45
     Dostupné
    -0.42
     feeling
    -0.42
    存于互联网档案馆
    -0.40
     useAppContext
    -0.40
    ❉
    -0.39
     WebDriverWait
    -0.38
    Tembelea
    -0.38
    POSITIVE LOGITS
     obligated
    0.84
     compelled
    0.84
     obliged
    0.80
     comfortable
    0.77
     confident
    0.74
     guilty
    0.73
     empowered
    0.67
     sorry
    0.66
     safe
    0.64
     safer
    0.64
    Act Density 0.108%

    No Known Activations