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

    Neuronpedia

    INDEX
    Explanations

    Breaking news-related phrases.

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to breaking news updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inating
    -0.74
    haps
    -0.73
    wagen
    -0.71
    eva
    -0.70
    izing
    -0.68
    ifference
    -0.67
    itatively
    -0.67
    iless
    -0.67
    ung
    -0.66
    ogical
    -0.66
    POSITIVE LOGITS
    fast
    1.05
    neck
    0.78
    AKING
    0.77
    down
    0.76
    Berry
    0.75
     Lives
    0.70
     Bad
    0.69
     News
    0.68
     Breaking
    0.68
    tons
    0.68
    Act Density 0.022%

    No Known Activations