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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progression or development over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Seconds
    -0.15
     vyh
    -0.15
    ovah
    -0.15
    timeofday
    -0.15
    ÑĶм
    -0.14
    olid
    -0.14
    utoff
    -0.14
    OVE
    -0.14
    Hits
    -0.14
    ัวà¸Ńย
    -0.13
    POSITIVE LOGITS
     miles
    0.28
     long
    0.27
     Miles
    0.27
     distance
    0.26
     distances
    0.23
     mile
    0.22
    mile
    0.21
    distance
    0.21
     Distance
    0.21
     mileage
    0.20
    Act Density 0.016%

    No Known Activations