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

    Neuronpedia

    INDEX
    Explanations

    the word "then" in a sequence of events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "then."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Doctrine
    -0.69
    VID
    -0.63
     behavi
    -0.61
     belief
    -0.61
     Presence
    -0.60
     Federation
    -0.58
    ICLE
    -0.58
    BAT
    -0.57
    caps
    -0.57
    channelAvailability
    -0.57
    POSITIVE LOGITS
     proceeded
    1.44
     proceed
    0.97
     proceeds
    0.95
     transitioned
    0.95
     promptly
    0.92
     marched
    0.86
     embarked
    0.85
     moved
    0.83
     migrated
    0.81
     went
    0.80
    Act Density 0.054%

    No Known Activations