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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governance structures and divisions of power

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of separation across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dding
    -0.68
    nor
    -0.63
    ior
    -0.63
    arcity
    -0.61
     DOI
    -0.59
     nud
    -0.58
    hement
    -0.58
    idon
    -0.57
    lihood
    -0.57
     Archdemon
    -0.57
    POSITIVE LOGITS
     sexes
    1.08
     evenly
    0.97
     between
    0.87
     geographically
    0.81
     spo
    0.81
     responsibilities
    0.80
     hairs
    0.78
     disparate
    0.78
     factions
    0.74
     divides
    0.73
    Act Density 0.176%

    No Known Activations