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

    Neuronpedia

    INDEX
    Explanations

    dates, numbers, and technical specifications

    oai_token-act-pair · gpt-3.5-turbo

    numerical data or references to specific items, particularly involving dates and statistical figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    achus
    -0.92
    cle
    -0.69
    houses
    -0.69
    ktop
    -0.68
    gart
    -0.67
     reluct
    -0.64
     separat
    -0.63
     millenn
    -0.62
     cavity
    -0.62
    ensing
    -0.62
    POSITIVE LOGITS
    rd
    1.03
    00
    0.88
    017
    0.80
    iets
    0.78
    æĹ
    0.78
    ese
    0.77
    awks
    0.74
    ity
    0.73
    jamin
    0.73
    ior
    0.72
    Act Density 0.106%

    No Known Activations