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

    Neuronpedia

    INDEX
    Explanations

    references to quotes or cited phrases within the text

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

    quoted word definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     NUKAT
    -0.42
     betweenstory
    -0.35
     encargado
    -0.35
    Xna
    -0.33
    aimana
    -0.33
     encargada
    -0.32
    ByVersion
    -0.31
     shewn
    -0.31
     permitan
    -0.31
    DMETHOD
    -0.31
    POSITIVE LOGITS
    ########.
    0.77
    httphttps
    0.63
    脚注の使い方
    0.56
    quatch
    0.56
    signol
    0.55
    ſelben
    0.52
    coroutines
    0.51
    ParallelGroup
    0.51
    WaitGroup
    0.51
    0.50
    Act Density 0.033%

    No Known Activations