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

    Neuronpedia

    INDEX
    Explanations

    questions or topics related to learning or being curious about a specific subject

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rising
    -0.76
     Kinnikuman
    -0.68
    soDeliveryDate
    -0.66
    soever
    -0.66
     Lag
    -0.64
     Stru
    -0.62
     Rising
    -0.61
    packing
    -0.61
    ById
    -0.60
     Returning
    -0.60
    POSITIVE LOGITS
     emulate
    1.32
     hear
    1.21
     maximize
    1.16
     keep
    1.09
     recreate
    1.08
     avoid
    1.08
     know
    1.08
     replicate
    1.07
     see
    1.07
     pursue
    1.05
    Act Density 0.174%

    No Known Activations