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

    Neuronpedia

    INDEX
    Explanations

    terms related to hierarchical structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    +
    -0.81
    ════
    -0.77
     Pardon
    -0.74
    श्चित
    -0.73
     désolés
    -0.73
    :✨
    -0.73
    +#+
    -0.73
     insuffisamment
    -0.73
    doria
    -0.71
     Sinal
    -0.70
    POSITIVE LOGITS
     Hierarchy
    1.08
     hierarchies
    1.08
    hierarchy
    1.07
     hierarchy
    1.02
    Hierarchical
    1.00
     hierarch
    0.94
    hier
    0.92
    Hierarchy
    0.92
     hierarchical
    0.91
     HIER
    0.89
    Act Density 0.001%

    No Known Activations