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

    Neuronpedia

    INDEX
    Explanations

    references to standards and frameworks in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     zen
    -0.14
     convin
    -0.14
    247
    -0.13
    oral
    -0.13
    ìļķ
    -0.13
     Hampton
    -0.13
    Zen
    -0.13
    ç¼ĺ
    -0.13
    edis
    -0.13
    lil
    -0.13
    POSITIVE LOGITS
     standard
    0.24
    -standard
    0.21
     usual
    0.21
    usual
    0.21
     normal
    0.20
    alty
    0.19
     NORMAL
    0.19
     standart
    0.19
     fare
    0.19
    standard
    0.18
    Act Density 0.228%

    No Known Activations