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

    Neuronpedia

    INDEX
    Explanations

    expressions of accountability and governance issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ierge
    -0.16
    (Void
    -0.14
    çµ
    -0.14
     pek
    -0.14
     pretty
    -0.14
     ayn
    -0.14
    DESCRIPTION
    -0.13
    evin
    -0.13
     Dude
    -0.13
    ãģıãĤĵ
    -0.13
    POSITIVE LOGITS
     Morgan
    0.16
     myself
    0.15
    appings
    0.15
     finished
    0.15
    finished
    0.14
     tomorrow
    0.14
     because
    0.14
    飯
    0.13
     please
    0.13
     somebody
    0.13
    Act Density 0.141%

    No Known Activations