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

    Neuronpedia

    INDEX
    Explanations

    quotation marks and dialogue in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    quoted questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.66
     mengatakan
    -0.64
     dieſer
    -0.63
    msgTypes
    -0.62
     Geiſt
    -0.61
     Waſſer
    -0.60
     ſeine
    -0.60
     ujednoznacz
    -0.59
     deſſen
    -0.59
     dizer
    -0.59
    POSITIVE LOGITS
     ne
    0.34
     Tuc
    0.33
    tabular
    0.32
    AccessControl
    0.32
     &
    0.32
    pho
    0.30
    0.30
    cap
    0.30
     Mish
    0.30
    u
    0.30
    Act Density 0.048%

    No Known Activations