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

    Neuronpedia

    INDEX
    Explanations

    words related to organization, structure, and hierarchy

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of order and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    tek
    -0.72
    rolet
    -0.69
    tu
    -0.69
    laus
    -0.69
    sonian
    -0.68
    ãĤ©
    -0.67
     Sporting
    -0.67
    cit
    -0.67
    vae
    -0.66
    aye
    -0.65
    POSITIVE LOGITS
    lies
    1.25
    liness
    1.14
    etary
    0.90
    eering
    0.77
    eous
    0.77
    ality
    0.76
    ylum
    0.70
    xual
    0.68
    cloth
    0.68
     anarchy
    0.67
    Act Density 0.027%

    No Known Activations