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

    Neuronpedia

    INDEX
    Explanations

    mathematical or programming structures and operations related to data and algorithms

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

    Variable indexing notation for sequences, typically representing a time step or position increment, often in mathematical equations or algorithms. Most commonly "_t+1" or similar notation indicating the next element in a sequence.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Negative Logits
    MemoryWarning
    -0.60
     protoimpl
    -0.49
    +#+
    -0.48
     ped
    -0.48
     utafitiHapana
    -0.44
    Wyd
    -0.43
     gom
    -0.43
    Activité
    -0.43
     fred
    -0.43
     Mio
    -0.43
    POSITIVE LOGITS
     sappi
    0.45
     bautizo
    0.44
     Infór
    0.42
    yntaxException
    0.40
    createNewFile
    0.39
     tatuagem
    0.37
    thâu
    0.37
     Regelung
    0.36
     Kesehatan
    0.36
    iprot
    0.36
    Act Density 0.146%

    No Known Activations