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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "noted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns mentioned in a context of noting or commenting in texts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    heed
    -0.82
    quer
    -0.78
    ctors
    -0.75
    SE
    -0.73
    vernment
    -0.72
     dope
    -0.64
    agan
    -0.64
    fecture
    -0.63
    cum
    -0.63
     ROCK
    -0.63
    POSITIVE LOGITS
     noted
    0.94
     noting
    0.80
     notes
    0.80
    WER
    0.75
     discrepancies
    0.72
    eele
    0.71
    unct
    0.70
    Notes
    0.67
     Notes
    0.67
     deductions
    0.67
    Act Density 0.017%

    No Known Activations