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

    Neuronpedia

    INDEX
    Explanations

    references to the name "William" and its impact on various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Geiſt
    -1.04
     ſeinen
    -1.03
     beſch
    -0.97
     queſta
    -0.96
     المعيارى
    -0.95
     verſch
    -0.95
     dieſer
    -0.94
     laſſen
    -0.93
     Geſch
    -0.93
    <unused41>
    -0.93
    POSITIVE LOGITS
     The
    0.72
     
    0.69
     A
    0.66
     (
    0.65
     William
    0.64
    ,
    0.64
     N
    0.62
     I
    0.62
     "
    0.60
     S
    0.60
    Act Density 0.289%

    No Known Activations