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

    Neuronpedia

    INDEX
    Explanations

    phrases related to stepping over boundaries or limits

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    iann
    -0.81
    boards
    -0.79
    uries
    -0.75
    imon
    -0.74
    uesday
    -0.72
    ributes
    -0.70
    ackle
    -0.69
    urrencies
    -0.69
    tions
    -0.68
    sequent
    -0.67
    POSITIVE LOGITS
     misunderstood
    1.18
     miscon
    1.16
     wrong
    1.14
     mistaken
    1.09
     misunderstanding
    1.09
     underest
    1.08
     misunderstand
    1.08
     exagger
    1.01
     overest
    1.01
     misinterpret
    0.99
    Act Density 0.617%

    No Known Activations