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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating plans or future actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olic
    -0.16
    pping
    -0.16
    ApiClient
    -0.16
    ult
    -0.15
     ê·Ģ
    -0.15
    isme
    -0.15
     mú
    -0.15
     cam
    -0.14
    ÙĨ
    -0.14
    öh
    -0.14
    POSITIVE LOGITS
    037
    0.19
    AndWait
    0.15
    اساÙĨ
    0.15
    ataka
    0.14
    mith
    0.14
    仪
    0.14
    ikler
    0.13
    brook
    0.13
    iferay
    0.13
    ambda
    0.13
    Act Density 0.092%

    No Known Activations