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

    Neuronpedia

    INDEX
    Explanations

    numerical references and codes related to specific rules or guidelines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urette
    -0.16
    innacle
    -0.16
    abbit
    -0.15
    alama
    -0.15
    ihn
    -0.15
    otas
    -0.15
    Insensitive
    -0.14
    aban
    -0.14
    upos
    -0.14
    ادت
    -0.14
    POSITIVE LOGITS
    ãĥĩãĥ«
    0.17
     Farms
    0.15
     bi
    0.15
     paras
    0.15
    1
    0.15
    onna
    0.14
     Futures
    0.14
    eren
    0.14
     Neal
    0.13
     point
    0.13
    Act Density 0.041%

    No Known Activations