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

    Neuronpedia

    INDEX
    Explanations

    terms related to "patch" or modifications in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    JI
    -0.16
    riers
    -0.15
    igel
    -0.15
    pga
    -0.15
    zing
    -0.14
    axis
    -0.14
    bis
    -0.14
    ssue
    -0.14
     studs
    -0.14
    rawer
    -0.14
    POSITIVE LOGITS
    work
    0.37
    (patch
    0.29
     Patch
    0.28
     patch
    0.26
    y
    0.26
    worked
    0.25
    (es
    0.25
    Patch
    0.24
    ogue
    0.24
    works
    0.23
    Act Density 0.013%

    No Known Activations