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

    Neuronpedia

    INDEX
    Explanations

    references to carbonized or charred materials

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -0.91
     PNP
    -0.86
     pleaſure
    -0.86
     Istri
    -0.85
     Hirst
    -0.85
     Majefty
    -0.84
     betweenstory
    -0.84
     Togo
    -0.83
     Jove
    -0.83
     leaſt
    -0.83
    POSITIVE LOGITS
     Char
    1.24
     CHAR
    1.03
    Char
    1.02
    CHAR
    0.99
     char
    0.94
     Schar
    0.89
     Charlie
    0.79
    chars
    0.78
     Charlene
    0.77
     chars
    0.77
    Act Density 0.016%

    No Known Activations