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

    Neuronpedia

    INDEX
    Explanations

    references to box structures and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    withstanding
    -0.93
    PerformLayout
    -0.89
     pleaſure
    -0.85
    aarrggbb
    -0.83
    ModelAdmin
    -0.82
    DSA
    -0.78
    prepareStatement
    -0.78
     Ciri
    -0.78
    PRET
    -0.77
    */),
    -0.75
    POSITIVE LOGITS
     BOX
    2.02
     Box
    2.00
     box
    1.99
     boxes
    1.91
    box
    1.83
    BOX
    1.80
     Boxes
    1.74
    Box
    1.74
    boxes
    1.62
    Boxes
    1.45
    Act Density 0.052%

    No Known Activations