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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "know."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Datuak
    -0.58
     Tef
    -0.57
     виправивши
    -0.57
    (":");
    -0.57
     referenties
    -0.57
     Efq
    -0.56
    ✨:
    -0.56
     utafitiHapana
    -0.56
    μως
    -0.55
     disponibilités
    -0.53
    POSITIVE LOGITS
     know
    1.05
    我知道
    0.81
    ContentAsync
    0.73
     wiem
    0.71
     knows
    0.69
    Certainly
    0.68
     understand
    0.67
    know
    0.66
     obviously
    0.66
     conozco
    0.66
    Act Density 0.095%

    No Known Activations