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

    Neuronpedia

    INDEX
    Explanations

    words related to breaking events or news

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "breaking" associated with news or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aceae
    -0.78
    folios
    -0.70
    urs
    -0.70
    oir
    -0.69
     Pref
    -0.68
     Marketable
    -0.67
    uments
    -0.67
    pathy
    -0.66
     Beaut
    -0.66
    naire
    -0.66
    POSITIVE LOGITS
     breaking
    3.57
    breaking
    2.36
     shattering
    2.00
    Breaking
    1.90
     Breaking
    1.85
     break
    1.83
     breaching
    1.70
     broke
    1.62
     breaks
    1.60
     fracturing
    1.58
    Act Density 0.022%

    No Known Activations