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

    Neuronpedia

    INDEX
    Explanations

    references to box dimensions and attributes in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    withstanding
    -0.92
     pleaſure
    -0.84
    ModelAdmin
    -0.82
    aarrggbb
    -0.81
    PerformLayout
    -0.79
    */),
    -0.79
    DSA
    -0.77
     Ciri
    -0.75
    rslt
    -0.75
    PRET
    -0.74
    POSITIVE LOGITS
     Box
    2.06
     BOX
    2.06
     box
    2.06
     boxes
    1.97
    box
    1.89
    BOX
    1.86
     Boxes
    1.80
    Box
    1.79
    boxes
    1.67
    Boxes
    1.51
    Act Density 0.052%

    No Known Activations