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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names related to individuals or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.08
    2:0.02
    3:0.14
    4:0.02
    5:0.05
    6:0.17
    7:0.04
    8:0.04
    9:0.01
    10:0.13
    11:0.20
    Negative Logits
     Boat
    -2.92
     Bucket
    -2.56
     Sister
    -2.48
     Cruise
    -2.41
    BuyableInstoreAndOnline
    -2.38
     Spoon
    -2.35
     Shuttle
    -2.34
     Sisters
    -2.30
     cruise
    -2.30
    PIN
    -2.28
    POSITIVE LOGITS
    .,
    4.00
    :,
    3.40
    .,"
    3.38
    ..
    3.23
    ,,
    3.07
    .:
    3.04
    .),
    3.03
    -,
    2.84
    ./
    2.77
    .-
    2.75
    Act Density 0.000%

    No Known Activations