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

    Neuronpedia

    INDEX
    Explanations

    structured formats and elements in documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Tile
    -0.17
    .Selenium
    -0.16
    ãģĽãģ¦
    -0.15
    ContextMenu
    -0.15
    ifu
    -0.15
    rary
    -0.14
    å¥
    -0.14
    ãģıãĤī
    -0.14
     tile
    -0.14
    öm
    -0.14
    POSITIVE LOGITS
     bullet
    0.54
     Bullet
    0.45
     bullets
    0.44
    Bullet
    0.41
     bul
    0.40
    bullet
    0.37
     Bul
    0.36
    _bullet
    0.33
    bul
    0.33
     li
    0.27
    Act Density 0.146%

    No Known Activations