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

    Neuronpedia

    INDEX
    Explanations

    statements about mathematical properties and assertions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Integral
    -0.17
     above
    -0.16
     intuit
    -0.16
    olla
    -0.15
    est
    -0.15
     integral
    -0.15
    ixed
    -0.15
    że
    -0.14
     Haut
    -0.14
     analogous
    -0.14
    POSITIVE LOGITS
    tempt
    0.19
     math
    0.16
    ills
    0.15
    기ëıĦ
    0.14
     valide
    0.14
     tract
    0.14
     ÐĿеÑĤ
    0.14
    ìĹĨìĿĮ
    0.14
    士
    0.14
    ¥¿
    0.14
    Act Density 0.103%

    No Known Activations