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

    Neuronpedia

    INDEX
    Explanations

    references to specific dates and events in news articles

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and temporal indicators in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orno
    -0.68
    ̶
    -0.67
    just
    -0.64
    ollar
    -0.62
     honestly
    -0.62
    76561
    -0.62
    '"
    -0.61
    ander
    -0.61
    mini
    -0.61
    escape
    -0.60
    POSITIVE LOGITS
     HuffPost
    1.14
     NEWS
    0.79
     POLITICO
    0.78
     Dangerous
    0.72
    gov
    0.70
     Forbes
    0.69
     guiActiveUnfocused
    0.67
    active
    0.67
     Trend
    0.67
    orthy
    0.67
    Act Density 0.070%

    No Known Activations