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

    Neuronpedia

    INDEX
    Explanations

    references to Markov processes and concepts related to them

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

    Markov kernel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Purpose
    -0.43
    ilat
    -0.43
     Dzi
    -0.42
     Pani
    -0.42
     Bedi
    -0.42
    Attention
    -0.42
    luigi
    -0.41
     Yee
    -0.40
     Spes
    -0.40
     Boden
    -0.39
    POSITIVE LOGITS
     Markov
    2.69
    Markov
    2.31
     Marko
    1.13
    Marko
    1.07
     MARK
    0.83
     Mark
    0.77
     Markle
    0.71
    MARK
    0.70
    byshev
    0.69
     mark
    0.69
    Act Density 0.015%

    No Known Activations