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

    Neuronpedia

    INDEX
    Explanations

    terms related to Markov models and their equivalence assumptions

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

    Markov equivalence class, minimality, entailed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Everyone
    -0.33
     everyone
    -0.31
     Everyone
    -0.30
     venu
    -0.29
    everyone
    -0.29
     EVERYONE
    -0.29
    ngx
    -0.28
     again
    -0.27
     لم
    -0.27
     devrez
    -0.27
    POSITIVE LOGITS
    GEBURTSDATUM
    0.67
    parsedMessage
    0.64
     المعيارى
    0.59
    <unused41>
    0.59
    <unused21>
    0.58
    <unused20>
    0.58
    <unused23>
    0.58
    <unused39>
    0.58
    <unused6>
    0.58
    <unused8>
    0.58
    Act Density 0.143%

    No Known Activations