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

    Neuronpedia

    INDEX
    Explanations

    references to authors and their works in academic contexts

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

    work followed by is/was/has

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    évaluateur
    -0.49
     ſch
    -0.46
     Monfieur
    -0.46
    Tikang
    -0.42
     ſta
    -0.42
     purpoſe
    -0.41
    +#+#
    -0.41
     Verſ
    -0.40
     المعيارى
    -0.40
     ſtand
    -0.38
    POSITIVE LOGITS
    mycin
    0.44
    sor
    0.44
     properly
    0.44
    properly
    0.44
    roup
    0.44
    Personendaten
    0.42
    HAN
    0.42
    MLLoader
    0.42
    buru
    0.42
     Neutral
    0.42
    Act Density 0.002%

    No Known Activations