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

    Neuronpedia

    INDEX
    Explanations

    terms related to tax brackets and classifications in financial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pairs
    -0.15
    decess
    -0.14
    lena
    -0.14
    awner
    -0.14
     Harr
    -0.14
    issy
    -0.14
    æŃ©
    -0.14
    oldt
    -0.14
    .Dependency
    -0.13
    olg
    -0.13
    POSITIVE LOGITS
     category
    0.43
     Category
    0.34
    category
    0.34
    -category
    0.32
     categories
    0.31
    Category
    0.30
     каÑĤегоÑĢ
    0.29
     CATEGORY
    0.28
     group
    0.28
    _category
    0.28
    Act Density 0.174%

    No Known Activations