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

    Neuronpedia

    INDEX
    Explanations

    updates and news-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to updates or notifications about content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aden
    -0.90
    uana
    -0.78
    enic
    -0.76
    rongh
    -0.74
    orney
    -0.73
    nered
    -0.72
    otten
    -0.71
    bered
    -0.71
    fruit
    -0.70
     inh
    -0.69
    POSITIVE LOGITS
    Update
    1.12
     Update
    1.09
    UPDATE
    1.05
     UPDATE
    0.92
    CLAIM
    0.82
     EDIT
    0.82
     Timeline
    0.81
     Deadline
    0.81
    Edit
    0.80
     update
    0.78
    Act Density 0.012%

    No Known Activations