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

    Neuronpedia

    INDEX
    Explanations

    references to formal decision-making processes and legislative actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    æ±
    -0.16
    اشت
    -0.15
     racket
    -0.15
    ãĥĵãĥ¼
    -0.15
    zo
    -0.14
     Bain
    -0.14
    ãĤ¿ãĥ¼
    -0.14
    ä»ģ
    -0.14
    že
    -0.14
    je
    -0.14
    POSITIVE LOGITS
    erez
    0.18
     requ
    0.15
    polator
    0.15
     certif
    0.14
    ollect
    0.14
    oble
    0.14
    ilent
    0.14
     Wars
    0.14
    женÑĮ
    0.14
    /fw
    0.13
    Act Density 0.181%

    No Known Activations