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

    Neuronpedia

    INDEX
    Explanations

    references to "box" or related terminology in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    withstanding
    -0.96
    ModelAdmin
    -0.88
     pleaſure
    -0.87
    aarrggbb
    -0.82
    DSA
    -0.80
    PerformLayout
    -0.80
    */),
    -0.77
     scuro
    -0.77
    </thead>
    -0.75
     Majefty
    -0.74
    POSITIVE LOGITS
     Box
    2.17
     box
    2.17
     BOX
    2.16
     boxes
    2.06
    box
    1.99
    BOX
    1.96
    Box
    1.90
     Boxes
    1.89
    boxes
    1.78
    Boxes
    1.58
    Act Density 0.043%

    No Known Activations