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

    Neuronpedia

    INDEX
    Explanations

    references to specific character types and their related attributes or elements

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    awtextra
    -0.85
     Alvarado
    -0.84
     Isk
    -0.82
    FloatField
    -0.80
     Sterling
    -0.79
     Plin
    -0.79
    flatMap
    -0.79
    Sterling
    -0.79
    AndEndTag
    -0.78
     FormBuilder
    -0.77
    POSITIVE LOGITS
     ker
    1.32
     Ker
    1.24
     KER
    1.13
    Ker
    1.09
     keratin
    0.98
    ker
    0.92
     Kerr
    0.85
     Kerk
    0.78
    KER
    0.77
    يكب
    0.76
    Act Density 0.011%

    No Known Activations