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

    Neuronpedia

    INDEX
    Explanations

    the word "to", particularly when used in a future context or to express purpose

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    quickShipAvailable
    -0.73
    EStream
    -0.72
    starting
    -0.68
     Binding
    -0.66
    Sure
    -0.65
    OTAL
    -0.64
    soDeliveryDate
    -0.64
     Ac
    -0.63
    anooga
    -0.61
    MAT
    -0.61
    POSITIVE LOGITS
     accumulate
    1.07
     refine
    1.06
     operate
    1.05
     strive
    1.03
     pursue
    1.01
     pour
    1.00
     wrestle
    1.00
     rely
    0.99
     enjoy
    0.98
     evolve
    0.98
    Act Density 0.073%

    No Known Activations