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

    Neuronpedia

    INDEX
    Explanations

    references to political beliefs and ideologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibo
    -0.16
    jem
    -0.15
    ibe
    -0.15
    idor
    -0.15
    ç¿Ĵ
    -0.15
    GBK
    -0.14
    ÑĨÑİ
    -0.14
    unde
    -0.14
    áž
    -0.14
    ãĥŃãĥ¼
    -0.14
    POSITIVE LOGITS
     sop
    0.15
    946
    0.15
    omorphic
    0.15
    ARA
    0.14
    ara
    0.14
     Order
    0.13
    088
    0.13
    太éĥİ
    0.13
     Ary
    0.13
     Marketable
    0.13
    Act Density 0.366%

    No Known Activations