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

    Neuronpedia

    INDEX
    Explanations

    references to "wall" in various contexts, particularly related to structures or locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     noires
    -0.77
    epam
    -0.62
    ocino
    -0.62
    StoryboardSegue
    -0.61
     تكبرها
    -0.60
    akterysty
    -0.60
    Hentet
    -0.60
    存于互联网档案馆
    -0.60
    Datuak
    -0.59
     otomatig
    -0.58
    POSITIVE LOGITS
     WALL
    0.75
     Wall
    0.69
     wall
    0.65
     Mur
    0.64
    PAPER
    0.63
    Wall
    0.60
    wall
    0.59
    papers
    0.57
    WALL
    0.57
    Mur
    0.57
    Act Density 0.140%

    No Known Activations