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

    Neuronpedia

    INDEX
    Explanations

    mentions of the word "taxes"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "taxes"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lihood
    -0.74
    Else
    -0.73
     Sie
    -0.72
     Hundred
    -0.71
     Condition
    -0.69
     Crescent
    -0.67
     Sadd
    -0.67
    Found
    -0.67
     Dur
    -0.67
    "]=>
    -0.66
    POSITIVE LOGITS
     taxes
    1.27
     levied
    1.11
     collectors
    1.08
     Taxes
    1.07
    payer
    1.03
     tax
    0.99
     taxed
    0.95
     owed
    0.92
     collector
    0.91
     taxation
    0.87
    Act Density 0.010%

    No Known Activations