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

    Neuronpedia

    INDEX
    Explanations

    numerical values and financial terms related to deductions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to tax deductions and financial calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anco
    -0.72
     Rebell
    -0.72
     Shake
    -0.66
    wave
    -0.65
    cock
    -0.65
    fram
    -0.64
     Surge
    -0.63
    istas
    -0.63
    borough
    -0.63
    ambo
    -0.63
    POSITIVE LOGITS
    uced
    0.87
    ications
    0.84
    roit
    0.82
    iciary
    0.78
    edu
    0.77
    plet
    0.75
     deduct
    0.75
     deducted
    0.75
     deduction
    0.74
    uction
    0.74
    Act Density 0.057%

    No Known Activations