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

    Neuronpedia

    INDEX
    Explanations

    attends to links or references marked by slashes from arbitrary tokens

    oai_attention-head · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Head Attr Weights
    0:0.07
    1:0.09
    2:0.18
    3:0.13
    4:0.08
    5:0.04
    6:0.17
    7:0.20
    Negative Logits
    modelBuilder
    -0.29
    AutoresizingMask
    -0.29
    Bioaccumulative
    -0.28
    IntoConstraints
    -0.28
     Wikispecies
    -0.28
    Referanser
    -0.27
    layui
    -0.27
    jsonwebtoken
    -0.26
    Hentet
    -0.26
     насељу
    -0.26
    POSITIVE LOGITS
     Italijani
    0.27
     لينك
    0.24
     correctes
    0.24
    ~=
    0.23
    kai
    0.23
     gynhyrchwyd
    0.23
    Datuak
    0.23
     Tabor
    0.23
     Paar
    0.22
    gent
    0.22
    Act Density 0.061%

    No Known Activations