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

    Neuronpedia

    INDEX
    Explanations

    references to geographical locations and their significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .rar
    -0.16
     Ariel
    -0.15
    amics
    -0.15
     mies
    -0.14
     verd
    -0.14
     maks
    -0.14
    baugh
    -0.14
    Ñīе
    -0.14
    andr
    -0.14
    etur
    -0.13
    POSITIVE LOGITS
    linky
    0.16
    lez
    0.15
    Aw
    0.14
    lands
    0.14
    jas
    0.14
     Kho
    0.14
    .gb
    0.13
     ìĤ°
    0.13
    GRA
    0.13
    çł
    0.13
    Act Density 0.152%

    No Known Activations