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

    Neuronpedia

    INDEX
    Explanations

    references to health-related studies or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ricks
    -0.17
     Duty
    -0.17
    pcf
    -0.16
    ikal
    -0.15
    illac
    -0.15
    akt
    -0.15
    ziej
    -0.15
    ÅĦ
    -0.15
    pop
    -0.15
    æķ·
    -0.15
    POSITIVE LOGITS
    irate
    0.17
    arem
    0.16
    xAF
    0.15
     Magnet
    0.15
    inja
    0.15
    eft
    0.15
    éı¡
    0.14
     rec
    0.14
     Zero
    0.14
    ãĤ¼
    0.14
    Act Density 0.003%

    No Known Activations