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

    Neuronpedia

    INDEX
    Explanations

    references to specific places or geographical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lero
    -0.17
    erdale
    -0.16
    од
    -0.15
    ayne
    -0.15
    ADER
    -0.15
    chin
    -0.14
    enheim
    -0.14
    iene
    -0.14
     dziew
    -0.14
    tm
    -0.14
    POSITIVE LOGITS
    nya
    0.25
     yang
    0.23
    itas
    0.23
     dengan
    0.21
     dan
    0.21
     tersebut
    0.21
     untuk
    0.20
     dil
    0.20
     dari
    0.19
     dalam
    0.19
    Act Density 0.006%

    No Known Activations