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

    Neuronpedia

    INDEX
    Explanations

    emotions and descriptive adjectives related to discomfort, aggression, or negative feelings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UpInside
    -0.85
     doGet
    -0.71
    stateProvider
    -0.71
     gynhyrchwyd
    -0.70
    帖最后由
    -0.66
    DockStyle
    -0.65
    setcounter
    -0.64
    TimerTask
    -0.62
     समीक्षाएं
    -0.62
    VIAF
    -0.62
    POSITIVE LOGITS
     infuriating
    0.95
     frustrating
    0.88
     annoying
    0.87
    istible
    0.82
     unpleasant
    0.82
     itſelf
    0.80
     irritating
    0.80
     attractive
    0.79
    Прият
    0.79
     sickening
    0.78
    Act Density 0.235%

    No Known Activations