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

    Neuronpedia

    INDEX
    Explanations

    expressions of thoughtfulness and contemplation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    o
    -0.85
    ing
    -0.85
    er
    -0.78
    ed
    -0.76
    k
    -0.75
    ers
    -0.74
    )][
    -0.69
     Mek
    -0.69
    oon
    -0.67
    acirc
    -0.66
    POSITIVE LOGITS
     Thought
    1.19
    thought
    1.16
     THOUGHT
    1.12
    Thought
    1.10
     thought
    0.98
    thoughts
    0.90
    Manbalar
    0.88
     thoughts
    0.87
     Thoughts
    0.85
     SOT
    0.83
    Act Density 0.081%

    No Known Activations