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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raith
    -0.21
    ONY
    -0.16
    abb
    -0.16
    ucc
    -0.16
    lei
    -0.15
    udd
    -0.14
    verige
    -0.14
    æIJŃ
    -0.14
    pons
    -0.14
    opard
    -0.14
    POSITIVE LOGITS
    bast
    0.16
    ëĭµ
    0.16
    ạng
    0.15
    碼
    0.14
     pedig
    0.14
    WER
    0.14
    iard
    0.14
    ìĿ¸ìĿĢ
    0.13
    LBL
    0.13
    idon
    0.13
    Act Density 0.059%

    No Known Activations