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

    Neuronpedia

    INDEX
    Explanations

    mentions of political figures' spouses, particularly the term "First Lady"

    oai_token-act-pair · gpt-3.5-turbo

    references to the roles and titles associated with female figures in leadership positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dynamo
    -0.69
    adr
    -0.68
    amaz
    -0.66
    STD
    -0.66
    Hour
    -0.65
    anton
    -0.64
    sen
    -0.63
    Region
    -0.62
    ETH
    -0.62
    DAY
    -0.61
    POSITIVE LOGITS
     âī¡
    0.66
    ©¶æ
    0.65
    eve
    0.63
     Misty
    0.61
    rences
    0.60
    cil
    0.59
     collision
    0.59
    rency
    0.59
    ÃŃs
    0.59
     nomine
    0.58
    Act Density 0.079%

    No Known Activations