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

    Neuronpedia

    INDEX
    Explanations

    numerical ranges and units of measurement

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and their ranges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.70
     Bugs
    -0.63
     corpor
    -0.61
    birds
    -0.59
     Baird
    -0.59
    itch
    -0.58
     Clifford
    -0.58
     Grimes
    -0.57
    achev
    -0.57
     robotic
    -0.57
    POSITIVE LOGITS
     800
    1.35
    600
    1.34
    800
    1.33
     900
    1.30
    1200
    1.30
    1500
    1.29
     600
    1.28
    700
    1.28
     700
    1.26
     1200
    1.25
    Act Density 0.091%

    No Known Activations