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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks and reference indicators in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    umont
    -0.18
     @}
    -0.16
     associ
    -0.16
    ManagedObject
    -0.15
    HECK
    -0.15
     Nack
    -0.15
    esModule
    -0.14
    rint
    -0.14
    iliz
    -0.14
    usk
    -0.14
    POSITIVE LOGITS
     More
    0.17
    More
    0.16
    iglia
    0.15
    gv
    0.14
    ç¿Ķ
    0.14
    \Bridge
    0.14
    èħ¾
    0.14
    ucz
    0.14
    egend
    0.13
     Toplam
    0.13
    Act Density 0.001%

    No Known Activations