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

    Neuronpedia

    INDEX
    Explanations

    references to geography and locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aign
    -0.15
    deen
    -0.14
     McK
    -0.14
     DÄĽ
    -0.14
    Facade
    -0.13
     Bail
    -0.13
     داÙĨ
    -0.13
     Dann
    -0.13
    antis
    -0.13
    andle
    -0.13
    POSITIVE LOGITS
     Ly
    0.19
     Troll
    0.19
     Modal
    0.18
     Saud
    0.18
    vat
    0.18
     Sass
    0.17
     Lang
    0.17
    ACS
    0.17
     Rein
    0.17
     Aust
    0.16
    Act Density 0.003%

    No Known Activations