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

    Neuronpedia

    INDEX
    Explanations

    references to walls and wall structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    })));
    -0.75
     Judson
    -0.73
    Prat
    -0.73
    Anson
    -0.72
    selbe
    -0.70
    êmio
    -0.70
     âgées
    -0.69
     foncé
    -0.69
     noires
    -0.69
    észetes
    -0.69
    POSITIVE LOGITS
     wall
    1.73
     WALL
    1.71
     Wall
    1.63
     walls
    1.56
    Wall
    1.51
    wall
    1.47
     Walls
    1.45
    WALL
    1.44
    Walls
    1.33
    walls
    1.30
    Act Density 0.104%

    No Known Activations