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

    Neuronpedia

    INDEX
    Explanations

    numerical values and mathematical operations

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and formatting related to statistics or financial figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mayo
    -0.70
     cod
    -0.67
     conflic
    -0.64
     Frey
    -0.64
     Dare
    -0.63
     Jed
    -0.63
     nos
    -0.62
     v
    -0.61
     Keller
    -0.61
     anomal
    -0.61
    POSITIVE LOGITS
    50
    1.32
    150
    1.23
    60
    1.23
    30
    1.21
    100
    1.20
    90
    1.19
    180
    1.17
    40
    1.17
    70
    1.15
    120
    1.14
    Act Density 0.160%

    No Known Activations