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

    Neuronpedia

    INDEX
    Explanations

    comparative phrases related to health risks and differences in populations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    alin
    -0.16
    ¤ij
    -0.16
    623
    -0.16
    ãĥ³ãĥĹ
    -0.15
    ensem
    -0.15
    908
    -0.15
    arak
    -0.15
    anes
    -0.15
    icks
    -0.14
    ersh
    -0.14
    POSITIVE LOGITS
     ActionTypes
    0.15
     SIGN
    0.15
    397
    0.14
    Sign
    0.14
     Sign
    0.14
     Dice
    0.14
     ÙĨسبت
    0.14
    -sign
    0.13
    kk
    0.13
    áº
    0.13
    Act Density 0.073%

    No Known Activations