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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "different" or variations thereof

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UpInside
    -0.52
    certain
    -0.51
    معلومات
    -0.51
    สือ
    -0.50
    MLLoader
    -0.50
    chtenstein
    -0.49
    ">*
    -0.49
     Certain
    -0.49
    machten
    -0.48
     certain
    -0.48
    POSITIVE LOGITS
     coloured
    0.77
     colored
    0.76
     sized
    0.75
     kinds
    0.74
     approaches
    0.74
     ways
    0.74
    IATION
    0.73
     than
    0.70
     strokes
    0.68
     Approaches
    0.68
    Act Density 0.365%

    No Known Activations