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

    Neuronpedia

    INDEX
    Explanations

    references to gender-specific pronouns, particularly "she" and "her"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Joy
    -0.77
     Rusty
    -0.71
     CLR
    -0.70
     Vil
    -0.69
     Vaugh
    -0.66
     Airl
    -0.65
     Vive
    -0.64
     COUR
    -0.64
     Orders
    -0.63
     Settlement
    -0.63
    POSITIVE LOGITS
    self
    1.04
    selves
    0.80
     own
    0.72
    athed
    0.71
     selves
    0.70
    acht
    0.70
    elf
    0.69
     needs
    0.69
    affer
    0.67
    itage
    0.66
    Act Density 0.018%

    No Known Activations