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

    Neuronpedia

    INDEX
    Explanations

    mentions of different types of rooms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unma
    -0.16
    uet
    -0.15
     Maul
    -0.15
    ropy
    -0.15
    roti
    -0.14
    omas
    -0.14
    оÑĤа
    -0.14
    063
    -0.14
    ÑĢап
    -0.14
    748
    -0.14
    POSITIVE LOGITS
    sville
    0.19
    hattan
    0.17
    pez
    0.17
    aled
    0.15
    igan
    0.15
    elijke
    0.15
    keepers
    0.14
    mary
    0.14
    ChangeListener
    0.13
    theon
    0.13
    Act Density 0.023%

    No Known Activations