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

    Neuronpedia

    INDEX
    Explanations

    numerical data and measurements in a scientific context

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     in
    -0.60
     an
    -0.54
    .
    -0.51
     over
    -0.50
     to
    -0.47
    <eos>
    -0.46
    en
    -0.45
     a
    -0.45
     
    -0.44
    and
    -0.43
    POSITIVE LOGITS
     Jefus
    1.43
     Efq
    1.38
     Monfieur
    1.30
     Majefty
    1.27
     myſelf
    1.26
     itſelf
    1.23
     Chriftian
    1.20
     Theſe
    1.18
     ſeveral
    1.16
     poffible
    1.15
    Act Density 0.034%

    No Known Activations