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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating progress or development over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olid
    -0.17
    akov
    -0.17
    OVE
    -0.15
    timeofday
    -0.15
    áno
    -0.15
    ovah
    -0.15
    icode
    -0.15
    аков
    -0.14
    ahan
    -0.14
     سÛĮÙħ
    -0.14
    POSITIVE LOGITS
     miles
    0.31
     Miles
    0.29
     long
    0.29
     mile
    0.27
     distance
    0.26
    mile
    0.25
     distances
    0.24
    distance
    0.22
    Âłmiles
    0.22
     mileage
    0.21
    Act Density 0.029%

    No Known Activations