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

    Neuronpedia

    INDEX
    Explanations

    common conjunctions and pronouns in multiple languages, indicating integration of multicultural elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ists
    -0.16
    Į
    -0.15
    bud
    -0.15
    eden
    -0.14
     noss
    -0.14
    esis
    -0.14
    Ñĸли
    -0.14
    ecute
    -0.13
    ìļ±
    -0.13
    ìĨ
    -0.13
    POSITIVE LOGITS
     je
    0.57
    Âłje
    0.41
     se
    0.36
     Ñ
    0.32
     Je
    0.30
     ga
    0.29
    je
    0.29
    Je
    0.28
     JE
    0.24
     jest
    0.23
    Act Density 0.006%

    No Known Activations