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

    Neuronpedia

    INDEX
    Explanations

    references to various categories and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ase
    -0.17
    iversit
    -0.17
    leigh
    -0.16
    ryo
    -0.16
    agers
    -0.16
    coming
    -0.16
    enberg
    -0.15
    fully
    -0.15
    ors
    -0.15
    ÑģÑı
    -0.15
    POSITIVE LOGITS
    åĪ¥
    0.21
    égorie
    0.20
    apult
    0.19
    /sub
    0.19
    wide
    0.19
    åĪ«
    0.18
    -specific
    0.18
    etting
    0.18
     بÙĨدÛĮ
    0.17
    /class
    0.17
    Act Density 0.016%

    No Known Activations