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

    Neuronpedia

    INDEX
    Explanations

    references to location names and streets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.05
    1:0.04
    2:0.27
    3:0.04
    4:0.23
    5:0.04
    6:0.02
    7:0.03
    8:0.06
    9:0.10
    10:0.06
    11:0.02
    Negative Logits
    ザ
    -1.78
    ァ
    -1.46
    ibo
    -1.40
     contrace
    -1.39
    ��
    -1.37
    aline
    -1.37
    gyn
    -1.36
     Cosponsors
    -1.34
    ranged
    -1.33
    覚醒
    -1.29
    POSITIVE LOGITS
    erer
    1.44
     CTR
    1.43
    nings
    1.38
    monary
    1.35
    edge
    1.33
    rier
    1.25
    akings
    1.22
     Wall
    1.20
    warts
    1.19
    margin
    1.18
    Act Density 0.009%

    No Known Activations