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

    Neuronpedia

    INDEX
    Explanations

    proper nouns or names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rung
    -0.16
    966
    -0.16
     Haram
    -0.16
    SSION
    -0.15
    ponsive
    -0.15
    ardown
    -0.14
    æݪ
    -0.14
    ackbar
    -0.14
    entiful
    -0.14
    αÏģά
    -0.14
    POSITIVE LOGITS
    t
    0.18
    ,
    0.16
     Gle
    0.15
    aub
    0.15
    zek
    0.15
     wil
    0.14
     for
    0.14
    AND
    0.14
     Jack
    0.14
     premiere
    0.14
    Act Density 0.144%

    No Known Activations