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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating duration or time periods

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating duration or ongoing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inki
    -0.78
    bart
    -0.68
    ansk
    -0.64
    ioned
    -0.63
    ))))
    -0.63
    illin
    -0.62
    Empty
    -0.61
    vana
    -0.60
    OFF
    -0.60
    ãĥĩ
    -0.57
    POSITIVE LOGITS
     awhile
    1.57
     decades
    1.45
     millennia
    1.35
     centuries
    1.34
     years
    1.31
     months
    1.14
     generations
    1.13
     YEAR
    1.10
     ages
    1.04
     weeks
    1.00
    Act Density 0.129%

    No Known Activations