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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal principles and regulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     atmosphere
    -0.18
     coquine
    -0.17
     ordeal
    -0.17
     locale
    -0.17
     presente
    -0.16
     moderne
    -0.14
    taire
    -0.14
    homme
    -0.14
     extrem
    -0.14
     econom
    -0.14
    POSITIVE LOGITS
     prem
    0.21
    qu
    0.20
    ilia
    0.19
     principales
    0.18
     ye
    0.17
    cente
    0.17
     uns
    0.17
     dern
    0.17
     domain
    0.17
    criptions
    0.16
    Act Density 0.027%

    No Known Activations