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

    Neuronpedia

    INDEX
    Explanations

    references to the name "John."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    //=
    -0.75
     ſche
    -0.75
    Portail
    -0.75
    zzle
    -0.74
     ADE
    -0.73
     Carrasco
    -0.73
     Soro
    -0.71
     下午
    -0.71
     Rache
    -0.70
     ſind
    -0.69
    POSITIVE LOGITS
     John
    2.07
    John
    1.81
     john
    1.70
     JOHN
    1.66
    JOHN
    1.63
    john
    1.52
     Джон
    1.26
     Johns
    1.23
    johns
    1.15
    Johns
    1.11
    Act Density 0.035%

    No Known Activations