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

    Neuronpedia

    INDEX
    Explanations

    phrases related to permissions and restrictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ÑĢÑĥÑĩ
    -0.15
    ppv
    -0.15
    gw
    -0.15
    bek
    -0.15
    agner
    -0.14
    عات
    -0.14
    muÅŁ
    -0.13
    бав
    -0.13
    æk
    -0.13
    è¦ļ
    -0.13
    POSITIVE LOGITS
     participate
    0.28
     Particip
    0.27
     freely
    0.22
     particip
    0.20
     access
    0.20
     enter
    0.20
     vote
    0.19
     participates
    0.19
     participating
    0.18
    AccessException
    0.18
    Act Density 0.175%

    No Known Activations