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

    Neuronpedia

    INDEX
    Explanations

    references to familial relationships and interactions, particularly involving husbands and wives

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

    Follows names or pronouns

    np_acts-logits-general · gemini-2.0-flash

    her or she in relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    看着他
    -0.51
    setVerticalGroup
    -0.50
    被他
    -0.49
     he
    -0.47
    ньому
    -0.47
    StateList
    -0.43
    CodeAttribute
    -0.42
     uLocal
    -0.41
    pperware
    -0.41
    对他
    -0.41
    POSITIVE LOGITS
     she
    1.04
    对她
    0.91
     hers
    0.85
     her
    0.81
    在她
    0.81
     그녀
    0.80
    给她
    0.79
    让她
    0.78
     ей
    0.77
    是她
    0.77
    Act Density 0.575%

    No Known Activations