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

    Neuronpedia

    INDEX
    Explanations

    phrases related to detailed descriptions and contextual elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ollar
    -0.18
     Laur
    -0.15
    kees
    -0.15
    illion
    -0.14
    á»Ļ
    -0.14
    ortal
    -0.14
     Chance
    -0.14
    ved
    -0.14
    oup
    -0.13
    yped
    -0.13
    POSITIVE LOGITS
    à¸Ńà¸Ķ
    0.15
    tuk
    0.15
     jer
    0.14
    jer
    0.14
    916
    0.14
    leftright
    0.14
    Newton
    0.13
    ares
    0.13
     bang
    0.13
    egan
    0.13
    Act Density 0.106%

    No Known Activations