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

    Neuronpedia

    INDEX
    Explanations

    high-frequency numerical references and formatting elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     level
    -0.18
     Aub
    -0.15
    inger
    -0.15
     spread
    -0.14
     ud
    -0.14
     cart
    -0.14
    ingers
    -0.14
    ud
    -0.14
     set
    -0.14
     skin
    -0.14
    POSITIVE LOGITS
     Contrast
    0.18
    orte
    0.15
    romo
    0.15
    istrov
    0.14
     Garner
    0.14
     excer
    0.14
     kabil
    0.14
     Hag
    0.14
    hlen
    0.14
     Wahl
    0.14
    Act Density 0.000%

    No Known Activations