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

    Neuronpedia

    INDEX
    Explanations

    punctuation and formatting symbols in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     McCart
    -0.15
    ti
    -0.14
     Decomp
    -0.14
    brit
    -0.14
    adb
    -0.13
    itori
    -0.13
    kehr
    -0.13
    chwitz
    -0.13
    /tiny
    -0.13
    ä¸Ī
    -0.13
    POSITIVE LOGITS
    arias
    0.17
     Leone
    0.16
     Legion
    0.15
    à¹Ģลย
    0.15
    åĤĻ
    0.15
    inium
    0.14
    afi
    0.14
     legion
    0.14
     Griffin
    0.14
    .datatables
    0.14
    Act Density 0.010%

    No Known Activations