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

    Neuronpedia

    INDEX
    Explanations

    linguistic structures associated with specific terms and classifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Äĩ
    -0.16
     reuseIdentifier
    -0.15
    naz
    -0.14
    ÅĽÄĩ
    -0.14
    ä¹ĭ
    -0.14
    lbrace
    -0.14
    chwitz
    -0.14
    .pix
    -0.14
    etsk
    -0.13
    ched
    -0.13
    POSITIVE LOGITS
    etheless
    0.21
    atre
    0.17
    ogie
    0.16
    ¼åIJĪ
    0.16
    gether
    0.16
    /-
    0.15
    bsites
    0.15
    quarters
    0.15
    atomy
    0.15
    xiety
    0.15
    Act Density 0.101%

    No Known Activations