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

    Neuronpedia

    INDEX
    Explanations

    expressions indicating superiority or high quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     infinit
    -0.17
    enville
    -0.16
    wu
    -0.16
    /releases
    -0.15
    è¾¼ãģ¿
    -0.15
     Yol
    -0.14
    lassian
    -0.14
     equ
    -0.14
    jourd
    -0.14
     Wine
    -0.14
    POSITIVE LOGITS
    hiba
    0.16
     Westbrook
    0.15
    ensa
    0.15
     Waters
    0.14
    uhan
    0.14
     carr
    0.14
    ican
    0.14
     forg
    0.14
    vers
    0.13
     tires
    0.13
    Act Density 0.301%

    No Known Activations