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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progress or change over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progress or development over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Later
    -0.68
    emate
    -0.68
    uesday
    -0.64
    article
    -0.63
     THEN
    -0.62
    umbn
    -0.62
    MJ
    -0.62
    ideos
    -0.61
    uez
    -0.60
    APE
    -0.57
    POSITIVE LOGITS
     lately
    1.21
     remarkably
    1.12
     tremendously
    1.02
     leaps
    1.02
     since
    1.01
     accustomed
    0.99
     steadily
    0.99
     considerably
    0.98
     quite
    0.93
     awfully
    0.92
    Act Density 0.267%

    No Known Activations