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

    Neuronpedia

    INDEX
    Explanations

    titles or formal titles referencing individuals, particularly those with the honorific "Sir."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -1.02
     Efq
    -0.92
     houſe
    -0.90
     pleaſure
    -0.88
    Искәрмәләр
    -0.87
     purpoſe
    -0.86
     whoſe
    -0.82
     myſelf
    -0.81
     ſche
    -0.81
    Mako
    -0.81
    POSITIVE LOGITS
     Sir
    1.39
     SIR
    1.32
    SIR
    1.22
    Sir
    1.17
     Sirs
    0.98
     Sira
    0.94
     sir
    0.86
    CORBA
    0.72
     Siro
    0.68
     Laird
    0.67
    Act Density 0.004%

    No Known Activations