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

    Neuronpedia

    INDEX
    Explanations

    special comments or non-code elements within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UserScript
    -0.56
    
    -0.55
    romes
    -0.52
     âmes
    -0.52
    RUPT
    -0.52
     méri
    -0.51
    achel
    -0.50
     NDEBUG
    -0.50
    //
    -0.50
    فحة
    -0.49
    POSITIVE LOGITS
     مشين
    0.89
     utafitiHapana
    0.74
    <eos>
    0.71
    enderror
    0.66
    ьаж
    0.65
     kasarigan
    0.60
     архивлан
    0.59
    !*\
    0.58
    ↵
    0.58
    ↵↵↵
    0.58
    Act Density 0.216%

    No Known Activations