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

    Neuronpedia

    INDEX
    Explanations

    temporal references related to time durations and intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Subsequent
    -0.71
     Subsequently
    -0.63
     subsequent
    -0.59
    Afterwards
    -0.55
    最後は
    -0.54
    sequent
    -0.53
     subsequently
    -0.53
     Thereafter
    -0.52
     Afterwards
    -0.51
     Afterward
    -0.48
    POSITIVE LOGITS
     later
    1.18
    later
    0.75
     Later
    0.73
    Later
    0.71
     LATER
    0.68
     senare
    0.67
     layer
    0.63
     letter
    0.60
     später
    0.60
     lat
    0.59
    Act Density 0.223%

    No Known Activations