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

    Neuronpedia

    INDEX
    Explanations

    numerical data, particularly statistics or averages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.16
    1:0.03
    2:0.09
    3:0.10
    4:0.10
    5:0.04
    6:0.07
    7:0.02
    8:0.11
    9:0.05
    10:0.06
    11:0.10
    Negative Logits
    STDOUT
    -1.43
    Contribut
    -1.37
    Assembly
    -1.34
    NetMessage
    -1.28
    ModLoader
    -1.28
    dozen
    -1.27
    LAB
    -1.25
     Cosponsors
    -1.22
     quir
    -1.19
    Ball
    -1.18
    POSITIVE LOGITS
    nosis
    1.49
     408
    1.36
     XVI
    1.32
     501
    1.30
     601
    1.25
     384
    1.25
     3
    1.22
     320
    1.21
     2
    1.21
     2100
    1.20
    Act Density 0.011%

    No Known Activations