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

    Neuronpedia

    INDEX
    Explanations

    hyperlinks prompting the reader to click for more information

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "click here" indicating links or calls to action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itialized
    -0.87
    tone
    -0.69
    omore
    -0.68
    establishment
    -0.68
    utter
    -0.67
    cig
    -0.66
    cers
    -0.65
    upuncture
    -0.65
    mong
    -0.65
    cade
    -0.64
    POSITIVE LOGITS
    tics
    1.20
    abouts
    1.09
    tical
    1.08
    tic
    0.89
     âĢº
    0.76
     guiActiveUn
    0.72
    here
    0.70
     âĸº
    0.70
     âĨij
    0.68
     Salary
    0.68
    Act Density 0.030%

    No Known Activations