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

    Neuronpedia

    INDEX
    Explanations

    numeric representations, particularly decimal and point values

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ist
    -0.58
    ess
    -0.50
     ind
    -0.48
    ists
    -0.46
     (
    -0.46
     so
    -0.45
    y
    -0.44
    ark
    -0.44
    ds
    -0.44
    F
    -0.44
    POSITIVE LOGITS
     تانيه
    0.83
     Monfieur
    0.81
     Efq
    0.78
    вгений
    0.77
    ThroughAttribute
    0.77
     Majefty
    0.77
     Савезне
    0.73
     fevere
    0.72
     CreateTagHelper
    0.72
     ſever
    0.71
    Act Density 0.004%

    No Known Activations