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

    Neuronpedia

    INDEX
    Explanations

    significant numerical values and indicators of decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    çuk
    -0.17
    OKIE
    -0.15
     chiếu
    -0.14
    izzo
    -0.14
    REDIT
    -0.14
    è¾
    -0.14
    068
    -0.13
    iosa
    -0.13
    uppe
    -0.13
    uess
    -0.13
    POSITIVE LOGITS
    yst
    0.15
    ixture
    0.15
    yn
    0.14
     ÙĨص
    0.14
    urette
    0.14
     coz
    0.14
     cach
    0.13
     Shawn
    0.13
     SON
    0.13
    íijľ
    0.13
    Act Density 0.032%

    No Known Activations