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

    Neuronpedia

    INDEX
    Explanations

    instances where future plans are mentioned

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    quickShipAvailable
    -0.81
     Explan
    -0.80
     Primordial
    -0.71
     Picks
    -0.66
    ritical
    -0.66
     Problem
    -0.65
     Logic
    -0.64
     Lac
    -0.61
    listed
    -0.61
    problem
    -0.60
    POSITIVE LOGITS
     meet
    1.01
     stay
    1.00
     spend
    0.96
     pursue
    0.96
     explore
    0.94
     continue
    0.93
     visit
    0.93
     retire
    0.93
     utilize
    0.93
     move
    0.92
    Act Density 0.111%

    No Known Activations