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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and expressions, particularly those associated with equations and constants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    paralleled
    -0.17
    ej
    -0.16
    eft
    -0.15
    (?
    -0.15
    ings
    -0.14
    inger
    -0.14
    Âł
    -0.14
     everything
    -0.14
    ãĤ¥
    -0.14
     Everything
    -0.14
    POSITIVE LOGITS
    zelf
    0.17
    pent
    0.16
    -inverse
    0.15
    zee
    0.15
    rok
    0.14
    /qu
    0.14
    rompt
    0.14
    836
    0.13
    ordan
    0.13
    icana
    0.13
    Act Density 0.047%

    No Known Activations