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

    Neuronpedia

    INDEX
    Explanations

    specific terms related to tax laws and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Reſ
    -0.84
     Inſ
    -0.80
     Efq
    -0.79
     ſeveral
    -0.78
     faſt
    -0.78
     houſe
    -0.77
     leaſt
    -0.76
     ſtate
    -0.76
     purpoſe
    -0.76
     myſelf
    -0.75
    POSITIVE LOGITS
     will
    0.65
     needs
    0.54
     has
    0.52
     is
    0.49
    ibouti
    0.48
     won
    0.47
     may
    0.47
     might
    0.46
     can
    0.46
     pylori
    0.45
    Act Density 1.129%

    No Known Activations