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

    Neuronpedia

    INDEX
    Explanations

    references to a specific type of container or object structure related to boxes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    withstanding
    -0.95
     pleaſure
    -0.85
    ModelAdmin
    -0.85
    PerformLayout
    -0.84
    aarrggbb
    -0.82
    DSA
    -0.80
    */),
    -0.78
    prepareStatement
    -0.77
     Ciri
    -0.76
    rslt
    -0.74
    POSITIVE LOGITS
     BOX
    2.04
     box
    2.02
     Box
    2.02
     boxes
    1.95
    box
    1.87
    BOX
    1.84
    Box
    1.76
     Boxes
    1.76
    boxes
    1.64
    Boxes
    1.47
    Act Density 0.048%

    No Known Activations