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

    Neuronpedia

    INDEX
    Explanations

    mathematical symbols and variables related to functions and dimensions in a mathematical context

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

    mathematical notation with Greek letters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ↵
    -0.44
     rep
    -0.44
     "
    -0.43
     Mahoney
    -0.42
     Wilkinson
    -0.41
     separate
    -0.40
     hat
    -0.39
     dat
    -0.39
    is
    -0.38
     dis
    -0.38
    POSITIVE LOGITS
    parsedMessage
    0.90
     ſtate
    0.80
     myſelf
    0.75
     ainfi
    0.73
     zijne
    0.70
     dezelve
    0.70
     ſta
    0.68
     $_"
    0.68
     feroit
    0.68
    PreferredItem
    0.67
    Act Density 0.759%

    No Known Activations