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

    Neuronpedia

    INDEX
    Explanations

    phrases related to acts of disrespect or disdainful behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.03
    1:0.01
    2:0.06
    3:0.05
    4:0.13
    5:0.03
    6:0.08
    7:0.29
    8:0.04
    9:0.03
    10:0.11
    11:0.10
    Negative Logits
     Moderate
    -1.63
    quickShipAvailable
    -1.63
    ORTS
    -1.52
    externalActionCode
    -1.51
    CVE
    -1.51
    FLAG
    -1.48
     Mathemat
    -1.45
    soDeliveryDate
    -1.42
    sym
    -1.39
    ItemThumbnailImage
    -1.38
    POSITIVE LOGITS
     grate
    1.78
    opol
    1.59
     vengeance
    1.52
     Brus
    1.52
     beet
    1.48
     scraps
    1.47
     gore
    1.45
    ilk
    1.43
     hairs
    1.43
     BS
    1.39
    Act Density 0.002%

    No Known Activations