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

    Neuronpedia

    INDEX
    Explanations

    end-of-turn markers in a conversation or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    C/C++ macro definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.85
    httphttps
    -0.82
     CreateTagHelper
    -0.82
    Билгалдахарш
    -0.81
     ujednoznacz
    -0.81
    setVerticalGroup
    -0.81
    <unused52>
    -0.81
    <unused43>
    -0.81
    <unused14>
    -0.81
    <unused8>
    -0.81
    POSITIVE LOGITS
     is
    0.29
     
    0.29
     louer
    0.28
     ourselves
    0.28
     existi
    0.27
     orgullo
    0.27
     approximately
    0.26
    en
    0.26
     Mund
    0.26
     मिल
    0.26
    Act Density 0.382%

    No Known Activations