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

    Neuronpedia

    INDEX
    Explanations

    expressions of anger and frustration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    associated with anger

    np_acts-logits-general · gemini-2.0-flash

    anger, rage, complaining

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NSCoder
    -0.67
     föruts
    -0.61
     wonders
    -0.59
     referenties
    -0.58
     velkommen
    -0.57
    TemporalType
    -0.57
     Paglinawan
    -0.55
    Opportunities
    -0.55
    ondis
    -0.55
     Waray
    -0.55
    POSITIVE LOGITS
     Anger
    0.93
     anger
    0.93
     angry
    0.92
    Anger
    0.90
     Angry
    0.85
    Angry
    0.82
     protes
    0.81
     rage
    0.76
     protesting
    0.76
     complaining
    0.76
    Act Density 0.235%

    No Known Activations