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

    Neuronpedia

    INDEX
    Explanations

    terms associated with delegation and authority structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ially
    -0.15
    ÛĮدÙĩ
    -0.15
    yal
    -0.15
    íĸ¥
    -0.15
    ro
    -0.14
    Operators
    -0.14
    icana
    -0.14
    _ADV
    -0.14
    isto
    -0.14
    æł·çļĦ
    -0.14
    POSITIVE LOGITS
     facto
    0.17
    ybrid
    0.16
    enan
    0.16
    initely
    0.15
    prung
    0.15
    ols
    0.15
     sheriff
    0.14
    ัà¸Ķส
    0.14
    evin
    0.14
    utsch
    0.14
    Act Density 0.035%

    No Known Activations