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

    Neuronpedia

    INDEX
    Explanations

    phrases beginning with 'that' and embedded within sentences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     guessing
    -0.63
     Thoughts
    -0.63
     Doctrine
    -0.61
     boarding
    -0.59
     Gallery
    -0.59
     Anyway
    -0.58
     Cards
    -0.58
    ONE
    -0.57
    hat
    -0.57
    aq
    -0.56
    POSITIVE LOGITS
     accompanies
    1.11
     resembles
    1.03
     arose
    1.01
     encompasses
    0.99
     enables
    0.98
     extends
    0.97
     includes
    0.97
     promotes
    0.96
     spans
    0.96
     satisfies
    0.94
    Act Density 1.106%

    No Known Activations