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

    Neuronpedia

    INDEX
    Explanations

    variations of the prefix "un-"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    actively
    -0.17
    acic
    -0.16
    guard
    -0.16
    aft
    -0.15
    ноÑģ
    -0.15
    dev
    -0.15
    ä¸į足
    -0.15
    adera
    -0.15
    Ú¯ÙĪÙĨÙĩ
    -0.14
    endar
    -0.14
    POSITIVE LOGITS
    ione
    0.20
    ites
    0.18
    esco
    0.18
    ertainty
    0.17
    ión
    0.17
    IVERS
    0.17
    ecessarily
    0.16
    ives
    0.16
     certain
    0.16
    sworth
    0.16
    Act Density 0.043%

    No Known Activations