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

    Neuronpedia

    INDEX
    Explanations

    references to scientific or technical processes, particularly those involving extraction or analysis of data

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     itſelf
    -0.90
     myſelf
    -0.87
     Monfieur
    -0.86
    EDEFAULT
    -0.85
     ſeveral
    -0.85
     Efq
    -0.83
     Majefty
    -0.81
     Reſ
    -0.81
     Conſ
    -0.80
     leſs
    -0.79
    POSITIVE LOGITS
     comment
    0.58
    comment
    0.52
     detailed
    0.52
     comments
    0.51
     below
    0.48
     comentario
    0.48
     paragraph
    0.46
     note
    0.45
     description
    0.44
     brief
    0.44
    Act Density 1.015%

    No Known Activations