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

    Neuronpedia

    INDEX
    Explanations

    phrases related to theoretical concepts and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     amen
    -0.14
    lla
    -0.13
    itung
    -0.13
    uary
    -0.13
    rum
    -0.13
    ocz
    -0.13
     ÑĦак
    -0.13
    Ùħز
    -0.12
    ider
    -0.12
    ites
    -0.12
    POSITIVE LOGITS
    DCF
    0.16
     Cousins
    0.16
    tridge
    0.16
    ARA
    0.14
    mour
    0.14
    å¯
    0.14
    avis
    0.14
    -transitional
    0.14
     pena
    0.13
    AutoSize
    0.13
    Act Density 0.090%

    No Known Activations