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

    Neuronpedia

    INDEX
    Explanations

    special characters or symbols used in written documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.06
    1:0.03
    2:0.09
    3:0.07
    4:0.05
    5:0.05
    6:0.32
    7:0.10
    8:0.05
    9:0.04
    10:0.04
    11:0.06
    Negative Logits
    DERR
    -1.38
     サーティワン
    -1.34
     batted
    -1.33
     Suz
    -1.31
     transpired
    -1.30
     Muss
    -1.24
     fever
    -1.24
     IOC
    -1.21
     concussion
    -1.20
     inval
    -1.20
    POSITIVE LOGITS
    ote
    1.57
    ️
    1.49
    olor
    1.37
    utive
    1.36
    nder
    1.33
    acion
    1.31
    olate
    1.30
    roups
    1.29
    anny
    1.28
    doi
    1.27
    Act Density 0.003%

    No Known Activations