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

    Neuronpedia

    INDEX
    Explanations

    elements related to layout and positioning in coding contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Com
    -0.61
    Com
    -0.51
     com
    -0.49
    com
    -0.47
     
    -0.44
     D
    -0.43
     co
    -0.43
     Co
    -0.42
     hex
    -0.41
     ком
    -0.40
    POSITIVE LOGITS
    bottom
    1.17
     bottom
    1.16
     top
    1.14
    top
    1.12
    Top
    1.02
     Bottom
    0.98
     Top
    0.98
    Bottom
    0.97
     BOTTOM
    0.92
     مشين
    0.89
    Act Density 0.133%

    No Known Activations