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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating lack or absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     somew
    -0.15
    enz
    -0.14
    ottle
    -0.14
    auen
    -0.14
    utas
    -0.13
    mt
    -0.13
    åķĨ
    -0.13
    topl
    -0.13
    eny
    -0.13
    ÑĤеÑĢи
    -0.13
    POSITIVE LOGITS
     nor
    0.28
    nor
    0.23
     anymore
    0.22
     Nor
    0.18
    Nor
    0.18
     sondern
    0.17
    epad
    0.17
     بÙĦÚ©Ùĩ
    0.16
    atest
    0.15
    ele
    0.15
    Act Density 0.200%

    No Known Activations