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

    Neuronpedia

    INDEX
    Explanations

    references to geographic locations or spatial contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÙĪج
    -0.15
    ercul
    -0.15
    ewood
    -0.15
    .deck
    -0.15
    mps
    -0.14
    Urban
    -0.14
    ÙĪغ
    -0.14
    unic
    -0.14
    umbo
    -0.14
    rh
    -0.14
    POSITIVE LOGITS
    eldo
    0.16
    äl
    0.15
    habit
    0.15
    оза
    0.15
    daki
    0.14
    852
    0.14
    Thunk
    0.14
    اÙĨÙĬا
    0.14
     dây
    0.14
    .mvc
    0.14
    Act Density 0.013%

    No Known Activations