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

    Neuronpedia

    INDEX
    Explanations

    speakers in a conversation based on the use of words like "he" and "she" before a statement

    oai_token-act-pair · gpt-3.5-turbo

    pronouns, particularly personal pronouns referring to male and female subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Credit
    -0.69
     Outside
    -0.59
     Allied
    -0.59
     Chamber
    -0.58
     Tours
    -0.58
     National
    -0.58
     Partnership
    -0.57
     Draft
    -0.57
     Cur
    -0.56
     nationally
    -0.55
    POSITIVE LOGITS
    ngth
    0.87
    mos
    0.83
     didnt
    0.83
    rael
    0.82
    bsite
    0.81
    hov
    0.78
    gemony
    0.77
    xual
    0.77
    tics
    0.75
    areth
    0.75
    Act Density 0.082%

    No Known Activations