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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     yiy
    -0.15
     Král
    -0.15
    ابÙĦ
    -0.15
     رÛĮ
    -0.15
    ähr
    -0.14
    avig
    -0.14
    ãĥ³ãĤ¯
    -0.14
    .safe
    -0.14
    ä¸ĺ
    -0.14
    기íĥĢ
    -0.14
    POSITIVE LOGITS
    urette
    0.17
    ature
    0.16
    ollen
    0.15
    warf
    0.15
     transfer
    0.15
     Transfer
    0.14
     ac
    0.14
    -w
    0.14
     Lock
    0.14
    Transfer
    0.14
    Act Density 0.045%

    No Known Activations