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

    Neuronpedia

    INDEX
    Explanations

    references to hierarchical categorizations or classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    704
    -0.16
    sert
    -0.15
    ÙĪÙĦÙĩ
    -0.14
    çIJ´
    -0.14
    ýt
    -0.13
     Beste
    -0.13
    ipers
    -0.13
     elekt
    -0.13
    inally
    -0.13
    ient
    -0.13
    POSITIVE LOGITS
    istrovstvÃŃ
    0.21
    doch
    0.19
    dog
    0.19
     Armour
    0.18
    lings
    0.18
    graduate
    0.17
    ivatel
    0.17
    whelming
    0.16
    dogs
    0.16
    ground
    0.16
    Act Density 0.021%

    No Known Activations