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

    Neuronpedia

    INDEX
    Explanations

    pronouns and references to personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Jahres
    -0.14
    otec
    -0.14
     mạch
    -0.14
    erville
    -0.13
    ÐIJÑĢÑħÑĸв
    -0.13
    heimer
    -0.13
    eceÄŁini
    -0.13
     ÐĿав
    -0.13
     Pavel
    -0.13
    еÑĢÑĮ
    -0.13
    POSITIVE LOGITS
     can
    0.54
    can
    0.44
     could
    0.43
     ca
    0.43
    .can
    0.39
     cab
    0.38
     cand
    0.38
     cane
    0.37
     cans
    0.37
     CAN
    0.37
    Act Density 0.196%

    No Known Activations