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

    Neuronpedia

    INDEX
    Explanations

    references to walls or wall-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.75
     errands
    -0.70
     Judson
    -0.69
     Fides
    -0.68
    })));
    -0.68
    gheny
    -0.68
     Plural
    -0.68
     ujednoznacz
    -0.67
    Prat
    -0.66
    epam
    -0.66
    POSITIVE LOGITS
     wall
    2.88
     Wall
    2.68
     WALL
    2.65
    Wall
    2.54
    wall
    2.51
     walls
    2.45
    WALL
    2.32
     Walls
    2.22
    walls
    2.08
    Walls
    2.03
    Act Density 0.042%

    No Known Activations