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

    Neuronpedia

    INDEX
    Explanations

    references to family dynamics and parental roles

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

    Followed by possessive adjectives ("her," "his")

    np_acts-logits-general · gemini-2.0-flash

    possessive pronouns and family members

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -1.09
     parents
    -1.01
     Parents
    -1.00
    Family
    -0.96
    family
    -0.95
    Parents
    -0.94
    Families
    -0.93
     family
    -0.92
     Family
    -0.90
     Families
    -0.89
    POSITIVE LOGITS
     ligiloj
    0.68
     通販
    0.67
    //
    0.63
     linkovi
    0.61
    ArrowToggle
    0.55
     Italijanski
    0.54
     оригіналу
    0.51
    RTEE
    0.51
     समीक्षक
    0.51
     godfather
    0.49
    Act Density 0.140%

    No Known Activations