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

    Neuronpedia

    INDEX
    Explanations

    instances where events occur in a sequence, particularly focusing on the event happening later in that sequence

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "later."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ble
    -0.76
    mad
    -0.71
    tick
    -0.69
    chest
    -0.68
    cking
    -0.65
    emen
    -0.63
    ickle
    -0.61
    rod
    -0.61
    Torrent
    -0.61
     Cause
    -0.60
    POSITIVE LOGITS
    etheless
    0.85
     iterations
    0.82
    noon
    0.76
     succumbed
    0.75
    aneously
    0.74
     generations
    0.74
     satell
    0.74
     succumb
    0.73
    theless
    0.73
     regretted
    0.72
    Act Density 0.032%

    No Known Activations