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

    Neuronpedia

    INDEX
    Explanations

    phrases that convey uniqueness or rarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.58
    formik
    -0.57
    acaktır
    -0.53
     CURIAM
    -0.52
     preferido
    -0.50
    tivamente
    -0.50
    middels
    -0.48
    THISDAY
    -0.48
    ContentAlignment
    -0.48
    PhysRevD
    -0.47
    POSITIVE LOGITS
     unique
    1.27
     unprecedented
    1.12
     uniqueness
    1.08
    unique
    1.01
     extraordinary
    1.00
     exceptional
    1.00
     unik
    1.00
     unusual
    0.99
     Unique
    0.99
     rare
    0.97
    Act Density 0.182%

    No Known Activations