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

    Neuronpedia

    INDEX
    Explanations

    references to rooms or spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    )";
    -1.02
    )');
    -0.94
    !")
    -0.92
    ]})
    -0.88
    ()]
    -0.88
    )");
    -0.88
    ')));
    -0.85
    )";
    -0.85
    ]';
    -0.84
    )».
    -0.83
    POSITIVE LOGITS
     Room
    1.68
     rooms
    1.68
     Rooms
    1.64
    Rooms
    1.54
     room
    1.53
     ROOM
    1.51
    Room
    1.50
    rooms
    1.46
    room
    1.31
    ROOM
    1.28
    Act Density 0.056%

    No Known Activations