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

    Neuronpedia

    INDEX
    Explanations

    geographical locations and references to cities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ока
    -0.17
     Giang
    -0.16
    oden
    -0.15
    .vm
    -0.15
    ัà¸Ĺ
    -0.15
    ilateral
    -0.15
    abcdefghijkl
    -0.15
    perty
    -0.15
    imir
    -0.14
     elevator
    -0.14
    POSITIVE LOGITS
     Nice
    0.34
     Nancy
    0.33
     Tours
    0.31
     Antib
    0.30
    Nice
    0.29
     Chart
    0.27
     Gap
    0.27
     Dunk
    0.27
     Cler
    0.27
     Vers
    0.26
    Act Density 0.080%

    No Known Activations