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

    Neuronpedia

    INDEX
    Explanations

    phrases related to an individual person, specifically referring to them as "guy"

    oai_token-act-pair · gpt-3.5-turbo

    references to a male character or individual

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.76
    illus
    -0.71
    èª
    -0.71
    rawdownloadcloneembedreportprint
    -0.68
     Parables
    -0.67
    tnc
    -0.67
    isans
    -0.66
    ories
    -0.66
     Supplement
    -0.66
    yrus
    -0.65
    POSITIVE LOGITS
    abase
    0.86
     who
    0.84
    holes
    0.83
    bags
    0.73
     jeans
    0.73
     else
    0.73
    hole
    0.73
     banging
    0.72
     pissed
    0.69
    bag
    0.69
    Act Density 0.046%

    No Known Activations