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

    Neuronpedia

    INDEX
    Explanations

    instances of exclusivity or uniqueness in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olis
    -0.18
     Fried
    -0.15
    iler
    -0.15
    okud
    -0.15
    nom
    -0.15
    olon
    -0.14
    eneg
    -0.14
    lev
    -0.14
     Haram
    -0.14
     uv
    -0.14
    POSITIVE LOGITS
    azer
    0.18
     ÙħÛĮÙĦ
    0.17
     Pod
    0.15
    erli
    0.15
     è¡
    0.15
    locker
    0.15
    Hum
    0.14
     POD
    0.14
     addCriterion
    0.14
     Òij
    0.14
    Act Density 0.186%

    No Known Activations