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

    Neuronpedia

    INDEX
    Explanations

    phrases related to injury and bleeding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.08
    3:0.05
    4:0.12
    5:0.02
    6:0.08
    7:0.34
    8:0.02
    9:0.04
    10:0.10
    11:0.06
    Negative Logits
    soDeliveryDate
    -2.08
    ominated
    -1.64
    CLASS
    -1.62
    committee
    -1.59
     directors
    -1.50
    Default
    -1.50
    authorized
    -1.48
    approved
    -1.48
    gg
    -1.48
    ────
    -1.48
    POSITIVE LOGITS
     wounds
    2.05
     bruises
    1.98
     regenerate
    1.72
     scalp
    1.65
     membranes
    1.62
     untreated
    1.58
     scars
    1.58
     flesh
    1.56
     slices
    1.54
     shrink
    1.54
    Act Density 0.001%

    No Known Activations