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

    Neuronpedia

    INDEX
    Explanations

    narratives involving characters facing challenges and making deals related to supernatural elements

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

    female pronouns

    np_acts-logits-general · gemini-2.0-flash

    female pronouns and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yourselves
    -0.71
     dets
    -0.62
     яке
    -0.62
     koji
    -0.62
    quels
    -0.59
     Оно
    -0.59
    老婆
    -0.57
     sportowe
    -0.56
     οποίο
    -0.56
    WebVitals
    -0.56
    POSITIVE LOGITS
     herself
    3.34
     her
    3.31
     she
    2.54
    herself
    2.43
    她的
    1.98
     suaminya
    1.87
     그녀
    1.87
     hennes
    1.85
    her
    1.79
    她
    1.78
    Act Density 1.465%

    No Known Activations