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

    Neuronpedia

    INDEX
    Explanations

    phrases related to financial deductions or deductions in general

    oai_token-act-pair · gpt-3.5-turbo

    references to tax deductions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hell
    -0.78
     Nieto
    -0.77
    cock
    -0.70
     Rebell
    -0.70
    ña
    -0.70
    wave
    -0.67
    anco
    -0.66
    NK
    -0.63
    builders
    -0.63
    Factory
    -0.62
    POSITIVE LOGITS
     deducted
    0.87
     deductions
    0.87
     allowable
    0.87
    edu
    0.85
    roit
    0.84
    aneous
    0.81
     deductible
    0.79
     allowance
    0.78
    payer
    0.77
     deduct
    0.77
    Act Density 0.034%

    No Known Activations