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

    Neuronpedia

    INDEX
    Explanations

    phrases related to exclusivity and special access to events or information

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

    exclusive or first presentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     voorbeeld
    -0.38
     Thoreau
    -0.38
     tevreden
    -0.37
     convencional
    -0.35
     getCustomer
    -0.34
     levens
    -0.34
     Вікі
    -0.33
     verschiedener
    -0.33
    leece
    -0.33
     fieltro
    -0.33
    POSITIVE LOGITS
    exclusive
    0.90
    Exclusive
    0.82
     exclusive
    0.82
     Exclusive
    0.79
     EXCLUSIVE
    0.76
    EXCLUSIVE
    0.76
    exclu
    0.71
     exclusives
    0.70
     exklu
    0.68
     Exclu
    0.68
    Act Density 0.005%

    No Known Activations