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

    Neuronpedia

    INDEX
    Explanations

    instances of punctuation and symbols commonly used in technical writing or coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aps
    -0.16
    undle
    -0.15
     column
    -0.15
    OW
    -0.14
    odynam
    -0.14
    phas
    -0.14
    earer
    -0.14
    APS
    -0.14
    eries
    -0.14
    ampaign
    -0.14
    POSITIVE LOGITS
     Chat
    0.21
     Rooms
    0.20
     chat
    0.20
     rooms
    0.19
     chatting
    0.18
    (Chat
    0.17
    Rooms
    0.17
    Chat
    0.17
     online
    0.17
     IRC
    0.17
    Act Density 0.007%

    No Known Activations