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

    Neuronpedia

    INDEX
    Explanations

    references to orders within a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    The token "order" and variations of it

    np_acts-logits-general · gemini-2.0-flash

    order followed by noun or phrase

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    jsii
    -0.83
     ModelExpression
    -0.76
     pleaſure
    -0.72
    PyExc
    -0.71
    ьаж
    -0.71
     cauſe
    -0.71
     esternos
    -0.70
    })*/
    -0.70
    المكان
    -0.69
     Italijanski
    -0.69
    POSITIVE LOGITS
    liness
    1.09
    lies
    0.68
    ly
    0.65
     placed
    0.61
    ings
    0.56
     anzu
    0.55
    er
    0.55
     getOrder
    0.54
     magnitude
    0.51
     orders
    0.49
    Act Density 0.166%

    No Known Activations