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

    Neuronpedia

    INDEX
    Explanations

    references to saints and related religious figures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Roskov
    -0.98
     itſelf
    -0.91
     pleaſure
    -0.90
     poffe
    -0.88
     ſever
    -0.87
     uſed
    -0.85
    minecraftforge
    -0.84
     myſelf
    -0.84
    adaptiveStyles
    -0.84
     ſhe
    -0.83
    POSITIVE LOGITS
     Saint
    1.37
    Saint
    1.23
     SAINT
    1.19
     saint
    1.06
     Saints
    1.06
    SAINT
    0.96
     saints
    0.84
    saint
    0.83
    Saints
    0.82
     Sankt
    0.75
    Act Density 0.022%

    No Known Activations