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

    Neuronpedia

    INDEX
    Explanations

    phrases related to restrictions and permissions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢÑĥÑĩ
    -0.17
    ILT
    -0.15
    agner
    -0.15
    è¦ļ
    -0.15
    bek
    -0.14
    ãģĭãģĦ
    -0.14
    æĿIJ
    -0.14
    \Migrations
    -0.14
    ÛĮز
    -0.14
    иÑĩеÑģкий
    -0.14
    POSITIVE LOGITS
     freely
    0.30
     access
    0.23
     participate
    0.21
     Particip
    0.20
    access
    0.20
     use
    0.19
     legally
    0.19
    AccessException
    0.19
     vote
    0.18
    fre
    0.18
    Act Density 0.184%

    No Known Activations