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

    Neuronpedia

    INDEX
    Explanations

    instances of emotional conflict or controversy in relationships

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

    allegations and lawsuits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cies
    -0.55
     entusias
    -0.48
     merve
    -0.46
     rado
    -0.43
     delightful
    -0.42
     excellence
    -0.42
    乐观
    -0.42
     engineering
    -0.41
     enthousi
    -0.41
     joyful
    -0.41
    POSITIVE LOGITS
     accusations
    0.89
     allegations
    0.79
     accusing
    0.75
     accusation
    0.71
     alleged
    0.70
     ویکی‌پدی
    0.68
     allegedly
    0.68
     hurtful
    0.64
     allegation
    0.63
     controversial
    0.62
    Act Density 0.028%

    No Known Activations