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

    Neuronpedia

    INDEX
    Explanations

    references to female characters or pronouns

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

    "her"

    np_acts-logits-general · gemini-2.0-flash

    possessive pronoun her

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Normdatei
    -0.84
     itſelf
    -0.78
     Efq
    -0.70
    DockStyle
    -0.69
    InjectAttribute
    -0.69
     mahdol
    -0.69
    seamnă
    -0.67
    TagMode
    -0.67
     themſelves
    -0.64
    ContentAsync
    -0.63
    POSITIVE LOGITS
     own
    1.19
     her
    0.87
     Her
    0.87
     sendiri
    0.85
    alds
    0.84
     Majesty
    0.82
    zelf
    0.80
    eabouts
    0.79
    เอง
    0.74
     she
    0.73
    Act Density 0.068%

    No Known Activations