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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dressing up or wearing costumes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.01
    1:0.01
    2:0.05
    3:0.06
    4:0.10
    5:0.02
    6:0.04
    7:0.45
    8:0.02
    9:0.03
    10:0.09
    11:0.06
    Negative Logits
    owners
    -1.64
    Effects
    -1.62
    holding
    -1.59
    affected
    -1.58
    otten
    -1.57
     unanswered
    -1.53
     dissatisf
    -1.52
    occupied
    -1.50
    marks
    -1.49
    asta
    -1.47
    POSITIVE LOGITS
     Bride
    1.73
     Jacket
    1.67
     Shirt
    1.63
     robes
    1.60
     Masquerade
    1.57
     underwear
    1.53
     costume
    1.51
     clothing
    1.48
     attire
    1.48
     dresses
    1.48
    Act Density 0.024%

    No Known Activations