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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate purpose or intent, specifically structured as "in order to."

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

    in order to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     дописавши
    -0.59
     estekak
    -0.57
    richTextPanel
    -0.56
     nonUne
    -0.56
    VYMaps
    -0.56
    taught
    -0.53
    webElementXpaths
    -0.52
    
    -0.52
    StructEnd
    -0.52
    exitRule
    -0.52
    POSITIVE LOGITS
     order
    0.74
     afin
    0.59
    order
    0.56
    inorder
    0.55
     intend
    0.52
     جهت
    0.51
     considering
    0.50
     to
    0.50
     purposes
    0.50
     objective
    0.49
    Act Density 0.021%

    No Known Activations