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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating uniqueness or one-of-a-kind qualities

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

    one of a kind and unique

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.55
    chism
    -0.54
     SwitchCompat
    -0.47
    xase
    -0.45
    olarmente
    -0.45
     resourceCulture
    -0.43
     lenker
    -0.43
    felves
    -0.42
    expandindo
    -0.41
     <=",
    -0.41
    POSITIVE LOGITS
     unique
    0.97
     uniqueness
    0.89
     Unique
    0.86
    Unique
    0.85
    unique
    0.82
     unieke
    0.80
     uniques
    0.77
     UNIQUE
    0.77
     einzigartige
    0.74
     уника
    0.71
    Act Density 0.115%

    No Known Activations