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

    Neuronpedia

    INDEX
    Explanations

    references to indoor and outdoor environments

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    </em>
    -0.91
    '));
    -0.84
    ]');
    -0.80
    ]').
    -0.79
    >{@
    -0.74
     ');
    -0.73
    '));
    -0.72
     '))
    -0.72
    ())));
    -0.71
    ')));
    -0.70
    POSITIVE LOGITS
     Indoor
    1.16
    Indoor
    0.99
     indoor
    0.99
    outdoor
    0.92
    indoor
    0.92
    
    0.90
     indoors
    0.87
    Outdoor
    0.86
    DOOR
    0.86
     Dord
    0.83
    Act Density 0.002%

    No Known Activations