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

    Neuronpedia

    INDEX
    Explanations

    the word "neither" and its variations, indicating a focus on negation or contrast

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ittens
    -0.64
    dotenv
    -0.60
    atelyn
    -0.58
    itson
    -0.57
     Approx
    -0.57
    stücke
    -0.57
    ا
    -0.56
    Loren
    -0.55
     susun
    -0.55
    اً
    -0.54
    POSITIVE LOGITS
    neither
    1.34
    Neither
    1.33
     Neither
    1.30
     neither
    1.30
     weder
    0.98
    تفصیلات
    0.86
     Tanto
    0.86
    AddTagHelper
    0.85
    (!__
    0.82
    GEBURTSDATUM
    0.80
    Act Density 0.016%

    No Known Activations