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

    Neuronpedia

    INDEX
    Explanations

    references to tradition or traditional practices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aq
    -0.15
    manship
    -0.14
    es
    -0.14
    erra
    -0.14
    idel
    -0.14
    Descriptors
    -0.14
    ãģ¹ãģį
    -0.14
     roughly
    -0.14
    opc
    -0.14
    /he
    -0.14
    POSITIVE LOGITS
    ists
    0.21
    ized
    0.20
    itionally
    0.19
    izing
    0.17
    ization
    0.17
    /original
    0.17
    izes
    0.17
    ize
    0.16
    ised
    0.16
    zie
    0.16
    Act Density 0.033%

    No Known Activations