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

    Neuronpedia

    INDEX
    Explanations

    verbs and phrases indicating changes in status or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    urtle
    -0.18
    agara
    -0.16
    thon
    -0.15
    illon
    -0.14
    ventus
    -0.14
     punct
    -0.14
    uby
    -0.14
     Specialty
    -0.14
     myself
    -0.14
    ãĤ¦ãĥ³
    -0.14
    POSITIVE LOGITS
    ä¸įäºĨ
    0.16
    edException
    0.15
    229
    0.14
    ionario
    0.14
    isses
    0.14
    isis
    0.13
    issent
    0.13
    itched
    0.13
    ikt
    0.13
    ns
    0.13
    Act Density 0.428%

    No Known Activations