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

    Neuronpedia

    INDEX
    Explanations

    sentences starting with the word "But"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    obyl
    -0.67
    ãģ®
    -0.64
    pointer
    -0.64
    kie
    -0.62
    built
    -0.62
    irms
    -0.61
    ãģĨ
    -0.61
    ãĤµ
    -0.61
    edu
    -0.60
    è¦ļéĨĴ
    -0.59
    POSITIVE LOGITS
    tons
    1.38
     alas
    1.29
     beware
    1.01
    chers
    1.00
     hey
    0.93
     unlike
    0.92
    chery
    0.91
     luckily
    0.90
     fortunately
    0.90
    tery
    0.88
    Act Density 0.467%

    No Known Activations