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

    Neuronpedia

    INDEX
    Explanations

    the concept of understanding in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     demais
    -0.58
    isbol
    -0.58
    caux
    -0.56
    ьаж
    -0.56
    saraba
    -0.56
    ferous
    -0.56
    aratus
    -0.55
    rinfo
    -0.54
    GHG
    -0.54
     arbej
    -0.53
    POSITIVE LOGITS
     understanding
    1.63
     Understanding
    1.45
    understanding
    1.41
     knowing
    1.33
    Understanding
    1.29
     Knowing
    1.26
    knowing
    1.23
    Knowing
    1.16
     misunder
    0.88
     understandings
    0.84
    Act Density 0.083%

    No Known Activations