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

    Neuronpedia

    INDEX
    Explanations

    concepts related to graph theory and Markov equivalence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    — 
    -0.86
    antMatchers
    -0.81
    rawtypes
    -0.77
    extAlignment
    -0.75
    icoot
    -0.75
    öhnt
    -0.72
    siapkan
    -0.70
    jillo
    -0.69
    rmızı
    -0.69
     nahilalakip
    -0.67
    POSITIVE LOGITS
     Pele
    0.84
     MEC
    0.83
     Beren
    0.83
    eb
    0.82
    Pele
    0.80
    et
    0.80
    ere
    0.80
    es
    0.78
    eche
    0.77
    eba
    0.77
    Act Density 4.873%

    No Known Activations