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

    Neuronpedia

    INDEX
    Explanations

    proper names, particularly those of women or female figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.71
    tagHelperRunner
    -0.70
     handsome
    -0.68
     Himself
    -0.66
     himself
    -0.64
    indicato
    -0.64
     điển
    -0.63
    xtick
    -0.61
     Gentleman
    -0.61
    HasColumnType
    -0.60
    POSITIVE LOGITS
     actress
    1.00
     herself
    0.90
     actresses
    0.88
     goddess
    0.87
     Elizabeth
    0.86
     businesswoman
    0.83
     Elisabeth
    0.82
    Elizabeth
    0.80
     Nancy
    0.79
     Therese
    0.79
    Act Density 1.179%

    No Known Activations