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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "patch" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    igel
    -0.15
    riers
    -0.15
    zing
    -0.14
    ssue
    -0.14
    pga
    -0.14
    ICS
    -0.14
    á»įng
    -0.14
    anness
    -0.14
    ksen
    -0.14
    ties
    -0.14
    POSITIVE LOGITS
    work
    0.35
    (patch
    0.29
     Patch
    0.28
     patch
    0.26
    worked
    0.25
    y
    0.25
    Patch
    0.25
    (es
    0.24
    works
    0.23
    ery
    0.22
    Act Density 0.013%

    No Known Activations