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

    Neuronpedia

    INDEX
    Explanations

    updates within text

    oai_token-act-pair · gpt-3.5-turbo

    instances of "Update" notifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aden
    -0.95
    enic
    -0.80
    ffiti
    -0.77
    vous
    -0.75
    athered
    -0.73
    aez
    -0.73
    verning
    -0.73
    ecause
    -0.72
    egu
    -0.72
    anship
    -0.71
    POSITIVE LOGITS
     Update
    0.95
    Update
    0.85
     Timeline
    0.84
     Deadline
    0.83
    :]
    0.78
    UPDATE
    0.77
     timeline
    0.74
    endum
    0.73
     Correction
    0.73
     update
    0.72
    Act Density 0.016%

    No Known Activations