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

    Neuronpedia

    INDEX
    Explanations

    references to consultations and public feedback processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anza
    -0.17
    uff
    -0.17
    -modules
    -0.16
    è½
    -0.15
    ikal
    -0.15
    emes
    -0.15
    ki
    -0.14
     purs
    -0.14
     Holden
    -0.14
    lemn
    -0.14
    POSITIVE LOGITS
     Cure
    0.16
    ãĥ¼ãĥĭ
    0.16
    Äĩi
    0.15
    æĪ
    0.15
    é³´
    0.14
    κηÏĤ
    0.14
    tright
    0.14
    0.14
    .Layer
    0.14
     Gul
    0.14
    Act Density 0.020%

    No Known Activations