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

    Neuronpedia

    INDEX
    Explanations

    terms related to structural components or properties

    oai_token-act-pair · gpt-3.5-turbo

    terms related to structural integrity and engineering

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    zig
    -0.73
    hood
    -0.73
    nery
    -0.71
     Furious
    -0.71
    yah
    -0.71
     Lauder
    -0.69
    kin
    -0.68
    cow
    -0.68
     Garland
    -0.67
    cart
    -0.65
    POSITIVE LOGITS
    urally
    1.20
    ural
    1.12
     integrity
    0.88
     components
    0.81
     barriers
    0.80
     elements
    0.77
     structural
    0.77
     pillars
    0.76
     engineering
    0.75
     repairs
    0.75
    Act Density 0.030%

    No Known Activations