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

    Neuronpedia

    INDEX
    Explanations

    titles of nobility or honorifics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reaſon
    -0.77
     itſelf
    -0.73
     gainera
    -0.70
     purpoſe
    -0.68
     Houſe
    -0.67
     domo
    -0.65
     houſe
    -0.61
     uſed
    -0.61
    anyahu
    -0.61
     perſon
    -0.61
    POSITIVE LOGITS
     Sir
    1.57
    Sir
    1.43
     sir
    1.30
    SIR
    1.30
     SIR
    1.26
    sir
    1.10
     Tim
    0.91
    Tim
    0.77
    TypedDataSet
    0.70
     Pek
    0.69
    Act Density 0.041%

    No Known Activations