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

    Neuronpedia

    INDEX
    Explanations

    specialized programming language symbols and syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.85
    ,
    -0.80
    .
    -0.74
     is
    -0.70
     of
    -0.68
      
    -0.66
    ↵
    -0.66
     in
    -0.65
     and
    -0.65
     also
    -0.63
    POSITIVE LOGITS
     Paglinawan
    1.37
     propOrder
    1.36
    ArrowToggle
    1.36
    ьаж
    1.34
     ainfi
    1.30
    Autoritní
    1.29
    windowFixed
    1.22
    __':
    1.19
    хьтан
    1.19
    1.18
    Act Density 3.351%

    No Known Activations