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

    Neuronpedia

    INDEX
    Explanations

    references to tax-related policies and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ader
    -0.15
    adero
    -0.15
    ninger
    -0.14
    ULO
    -0.14
    ador
    -0.14
    _confirmation
    -0.14
    _ctl
    -0.14
    ères
    -0.14
    utz
    -0.14
    quist
    -0.13
    POSITIVE LOGITS
     terms
    0.18
     President
    0.16
     president
    0.15
     House
    0.15
     new
    0.15
    ALIGN
    0.14
     draft
    0.14
    ä¾į
    0.14
    timing
    0.14
     February
    0.14
    Act Density 0.161%

    No Known Activations