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

    Neuronpedia

    INDEX
    Explanations

    references to military installations and their locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.07
    3:0.04
    4:0.06
    5:0.03
    6:0.08
    7:0.18
    8:0.03
    9:0.04
    10:0.27
    11:0.12
    Negative Logits
    alis
    -1.54
    lus
    -1.49
     vibr
    -1.47
     "$:/
    -1.45
    テ
    -1.44
    ハ
    -1.42
    20439
    -1.37
    mode
    -1.36
     remix
    -1.36
    vous
    -1.35
    POSITIVE LOGITS
     Prepar
    1.57
     barracks
    1.45
    rition
    1.41
    efe
    1.41
     Sioux
    1.35
    gregation
    1.35
     Harbor
    1.34
     Normandy
    1.32
    arnaev
    1.30
    ospital
    1.29
    Act Density 0.003%

    No Known Activations