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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the timing or sequence of events

    oai_token-act-pair · gpt-3.5-turbo

    references to time, particularly focusing on the concept of "last" moments or instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥİ
    -0.91
    styles
    -0.80
    apons
    -0.72
    exclusive
    -0.71
    mes
    -0.70
    models
    -0.70
    ux
    -0.70
    arters
    -0.70
    wr
    -0.68
    raltar
    -0.68
    POSITIVE LOGITS
     minute
    1.02
     hurdle
    0.96
     occurrence
    0.96
     whiff
    0.95
     gasp
    0.90
     occupant
    0.90
     thing
    0.89
     heartbeat
    0.87
     breath
    0.85
     day
    0.84
    Act Density 0.139%

    No Known Activations