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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "thought."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    xically
    -0.73
     sạn
    -0.67
    kloped
    -0.60
    muk
    -0.58
    ing
    -0.57
     Bezirk
    -0.56
    Mek
    -0.56
     nạn
    -0.56
    ছে
    -0.55
    queles
    -0.55
    POSITIVE LOGITS
     thought
    3.73
     Thought
    3.48
    Thought
    3.44
    thought
    3.42
     THOUGHT
    3.18
    thoughts
    1.69
     thoughts
    1.67
     believed
    1.62
     pensé
    1.47
     Thoughts
    1.47
    Act Density 0.067%

    No Known Activations