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

    Neuronpedia

    INDEX
    Explanations

    references to scholarly research and articles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iaux
    -0.16
    YK
    -0.15
    649
    -0.15
    antu
    -0.14
    amo
    -0.14
     Hat
    -0.14
    uler
    -0.14
    arih
    -0.14
    565
    -0.14
    alytics
    -0.14
    POSITIVE LOGITS
     wiki
    0.23
    wiki
    0.21
    -pocket
    0.17
     based
    0.16
     Smarty
    0.15
    anger
    0.15
    ÅĻes
    0.15
    inear
    0.14
     Based
    0.14
     quam
    0.14
    Act Density 0.036%

    No Known Activations