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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "to" followed by a verb

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    rising
    -0.75
    soever
    -0.71
    soDeliveryDate
    -0.68
    guards
    -0.65
    quickShipAvailable
    -0.64
     Kinnikuman
    -0.63
    ById
    -0.62
     Compass
    -0.60
     Returning
    -0.60
     Ely
    -0.60
    POSITIVE LOGITS
     emulate
    1.28
     maximize
    1.22
     hear
    1.18
     keep
    1.15
     know
    1.09
     recreate
    1.09
     capitalize
    1.08
     avoid
    1.07
     reassure
    1.07
     explore
    1.07
    Act Density 0.117%

    No Known Activations