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

    Neuronpedia

    INDEX
    Explanations

    phrases related to software or system updates

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Update."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pract
    -0.75
     favoured
    -0.75
     subconscious
    -0.74
     persona
    -0.71
     sed
    -0.70
     leading
    -0.70
     gul
    -0.70
     mentally
    -0.69
    mouth
    -0.68
     king
    -0.68
    POSITIVE LOGITS
    Update
    3.74
    UPDATE
    2.58
    update
    2.26
     Update
    2.20
     UPDATE
    2.17
    Updated
    2.00
    Edit
    1.73
     update
    1.70
    Correction
    1.59
    updated
    1.52
    Act Density 0.011%

    No Known Activations