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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating planning or decision-making

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     utford
    -0.46
     extending
    -0.43
     Normdatei
    -0.42
     becoming
    -0.42
     McPherson
    -0.41
     olje
    -0.40
    yorlar
    -0.40
     biografias
    -0.40
     strøm
    -0.40
     Person
    -0.40
    POSITIVE LOGITS
    
    0.82
    ьаж
    0.69
    NUMX
    0.69
     CreateTagHelper
    0.68
    GraphicsUnit
    0.67
    yntaxException
    0.65
    MenuInflater
    0.64
    EndTag
    0.61
    windowFixed
    0.61
     itinerary
    0.60
    Act Density 0.157%

    No Known Activations