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

    Neuronpedia

    INDEX
    Explanations

    the word "according" in various forms

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

    according to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
      
    -0.52
    /*
    -0.49
    X
    -0.49
    <
    -0.47
    {
    -0.46
     Tea
    -0.46
    startX
    -0.46
    ۵
    -0.45
    Tea
    -0.45
    scrollY
    -0.44
    POSITIVE LOGITS
    according
    0.87
    According
    0.84
     according
    0.84
     According
    0.80
    CloseOperation
    0.71
    SharedDtor
    0.70
     '\\;'
    0.70
    0.69
    PreferredItem
    0.65
     ACCORD
    0.65
    Act Density 0.015%

    No Known Activations