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

    Neuronpedia

    INDEX
    Explanations

    signs of editing or references in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     latter
    -0.14
    chor
    -0.14
     *
    -0.14
    orman
    -0.14
    -secondary
    -0.13
    erman
    -0.13
    ñ
    -0.13
     tactical
    -0.13
     edge
    -0.13
     Gibbs
    -0.13
    POSITIVE LOGITS
    -FIRST
    0.17
    oret
    0.16
    ibil
    0.15
    aticon
    0.14
    ãĥ³ãĤ¹
    0.14
    Ế
    0.14
    Toggle
    0.14
    ');?>"
    0.14
    aris
    0.14
    496
    0.14
    Act Density 0.007%

    No Known Activations