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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of pills and their related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iliz
    -0.15
    SYS
    -0.15
    celed
    -0.15
    yms
    -0.15
    abo
    -0.14
    twig
    -0.14
    SystemService
    -0.14
    ousel
    -0.14
    yor
    -0.14
    iji
    -0.13
    POSITIVE LOGITS
    pill
    0.23
    -pill
    0.22
     Pill
    0.19
    ault
    0.19
     pill
    0.19
    owy
    0.19
     pil
    0.18
    nger
    0.17
    ings
    0.16
    ars
    0.16
    Act Density 0.011%

    No Known Activations