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

    Neuronpedia

    INDEX
    Explanations

    sections of code and programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     etc
    -0.26
     hence
    -0.26
     also
    -0.25
    respectively
    -0.23
     the
    -0.20
     sacerdotes
    -0.19
     iż
    -0.18
     '{@
    -0.18
     étoit
    -0.17
     therefore
    -0.17
    POSITIVE LOGITS
    begin
    0.97
    OGND
    0.96
     stiefe
    0.89
     fashiola
    0.88
     ddelwed
    0.88
     zwiſchen
    0.87
     geſch
    0.87
     يتيمه
    0.85
    mathrm
    0.85
    wiliwch
    0.85
    Act Density 0.611%

    No Known Activations