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

    Neuronpedia

    INDEX
    Explanations

    terms and phrases related to the LGBT community and identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.04
    1:0.04
    2:0.08
    3:0.32
    4:0.02
    5:0.12
    6:0.02
    7:0.08
    8:0.04
    9:0.02
    10:0.12
    11:0.05
    Negative Logits
     warehouses
    -2.00
     receipts
    -1.96
     defenses
    -1.92
     coffers
    -1.84
     treasures
    -1.80
     kitchens
    -1.79
     greatness
    -1.74
     ceilings
    -1.73
    ngth
    -1.72
     marqu
    -1.71
    POSITIVE LOGITS
    Female
    2.23
    female
    2.20
     lesbian
    2.09
    emale
    2.06
    binary
    1.97
    cycle
    1.94
    ouple
    1.93
    omen
    1.92
    itizen
    1.91
    Male
    1.88
    Act Density 0.002%

    No Known Activations