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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to names of institutions, locations, or notable entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æĢ§çļĦ
    -0.15
    arium
    -0.15
    _allocate
    -0.14
    ature
    -0.14
    ãĥĺ
    -0.14
    æĢ§
    -0.13
    hpp
    -0.13
    ifest
    -0.13
    .PERMISSION
    -0.13
     kali
    -0.13
    POSITIVE LOGITS
    ensus
    0.16
    Calibri
    0.16
    .Guna
    0.15
    EndElement
    0.15
    ront
    0.15
    illage
    0.15
    ought
    0.15
    ÅĤo
    0.14
    isode
    0.14
    -wide
    0.14
    Act Density 0.317%

    No Known Activations