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

    Neuronpedia

    INDEX
    Explanations

    references to walls or wall structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     inoxydable
    -0.76
     Judson
    -0.74
    })));
    -0.73
    észetes
    -0.72
     noires
    -0.71
    Prat
    -0.71
     foncé
    -0.71
    êmio
    -0.71
     temprana
    -0.71
    CDMA
    -0.70
    POSITIVE LOGITS
     wall
    1.78
     WALL
    1.77
     Wall
    1.67
     walls
    1.63
    Wall
    1.54
     Walls
    1.50
    wall
    1.50
    WALL
    1.47
    walls
    1.36
    Walls
    1.35
    Act Density 0.067%

    No Known Activations