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

    Neuronpedia

    INDEX
    Explanations

    references to chat applications and chatbots

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hower
    -0.17
    ÏĤ
    -0.17
    uv
    -0.17
    olis
    -0.17
    ahy
    -0.16
    halb
    -0.16
    umberland
    -0.15
    edList
    -0.15
    chair
    -0.15
    swire
    -0.15
    POSITIVE LOGITS
    ting
    0.35
    roulette
    0.31
    anooga
    0.30
    rooms
    0.28
    bots
    0.26
    room
    0.25
    bot
    0.25
     rooms
    0.24
    ROOM
    0.21
    -room
    0.20
    Act Density 0.019%

    No Known Activations