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

    Neuronpedia

    INDEX
    Explanations

    words related to chronological sequence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Then" suggesting a chronological sequence in narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    md
    -0.76
    tein
    -0.74
    urally
    -0.62
     Pwr
    -0.62
    orum
    -0.59
    ":"/
    -0.59
    ciples
    -0.59
    osi
    -0.59
    CF
    -0.59
    scribe
    -0.59
    POSITIVE LOGITS
     came
    1.00
     suddenly
    0.89
     arose
    0.82
     abruptly
    0.80
     happened
    0.77
     bombshell
    0.77
     sprang
    0.75
    uddenly
    0.74
     tragedy
    0.73
     yesterday
    0.71
    Act Density 0.195%

    No Known Activations