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

    Neuronpedia

    INDEX
    Explanations

    temporal expressions related to time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.24
    3:0.08
    4:0.12
    5:0.03
    6:0.11
    7:0.09
    8:0.05
    9:0.03
    10:0.10
    11:0.06
    Negative Logits
    inventoryQuantity
    -1.82
    ression
    -1.61
    ISION
    -1.60
    amera
    -1.56
    ORY
    -1.43
     bullshit
    -1.43
     theater
    -1.36
     architecture
    -1.35
    circle
    -1.34
     boutique
    -1.33
    POSITIVE LOGITS
    oğ
    1.64
    laughter
    1.53
     Prelude
    1.46
    pecially
    1.40
     externalToEVAOnly
    1.39
    seys
    1.37
    eday
    1.36
     compared
    1.36
     Passenger
    1.34
     averaging
    1.34
    Act Density 0.008%

    No Known Activations