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

    Neuronpedia

    INDEX
    Explanations

    female names

    oai_token-act-pair · gpt-3.5-turbo

    names or titles of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anyl
    -0.80
    ¥ŀ
    -0.77
     sleeper
    -0.74
    igmatic
    -0.73
    irlf
    -0.71
    cffff
    -0.70
     gearing
    -0.68
    ounding
    -0.68
     circulating
    -0.66
    aucus
    -0.65
    POSITIVE LOGITS
     Moore
    0.94
     Carter
    0.92
     Rodgers
    0.91
     Anders
    0.90
     Elliott
    0.89
    abeth
    0.89
     Hansen
    0.88
    hyde
    0.88
     Kelley
    0.87
     Hardy
    0.85
    Act Density 0.211%

    No Known Activations