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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UILayout
    -0.17
    .sel
    -0.15
    uest
    -0.15
     ÐĹаг
    -0.14
    amp
    -0.14
    ford
    -0.14
    oi
    -0.14
    iston
    -0.14
    atrix
    -0.14
    cht
    -0.14
    POSITIVE LOGITS
    ote
    0.15
    defer
    0.14
    icans
    0.14
    andler
    0.14
    аÑĢÑĮ
    0.14
     Vis
    0.14
    _stdio
    0.13
     hå
    0.13
    idel
    0.13
    ToolBar
    0.13
    Act Density 0.192%

    No Known Activations