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

    Neuronpedia

    INDEX
    Explanations

    historical figures, particularly rulers and their reigns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ê°¤
    -0.15
     idi
    -0.14
    ISE
    -0.14
     ìĶ¨
    -0.14
    rlen
    -0.14
    417
    -0.14
    adele
    -0.13
    оÑĢаÑı
    -0.13
    alice
    -0.13
    sam
    -0.13
    POSITIVE LOGITS
     King
    0.28
     king
    0.23
     Queen
    0.21
    King
    0.20
     Baldwin
    0.19
     Emperor
    0.19
     بÛĮر
    0.18
     Charles
    0.18
     Sig
    0.18
     Frederick
    0.18
    Act Density 0.121%

    No Known Activations