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

    Neuronpedia

    INDEX
    Explanations

    words related to structural attributes or properties

    oai_token-act-pair · gpt-3.5-turbo

    references to structural integrity and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Furious
    -0.75
    yah
    -0.75
    zig
    -0.74
    kin
    -0.73
     Dos
    -0.71
     Carbuncle
    -0.70
    hood
    -0.69
    edited
    -0.66
    kins
    -0.66
     Awakens
    -0.65
    POSITIVE LOGITS
     integrity
    1.04
    ural
    1.01
    urally
    0.94
     components
    0.91
     elements
    0.91
     pillars
    0.90
     structural
    0.87
     engineering
    0.85
     structures
    0.84
     barriers
    0.83
    Act Density 0.015%

    No Known Activations