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

    Neuronpedia

    INDEX
    Explanations

    concepts related to regulatory frameworks and social structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ,.↵↵
    -0.14
    ,,
    -0.13
    aks
    -0.13
    ,...↵↵
    -0.13
    .,
    -0.13
    .uml
    -0.13
    qv
    -0.12
     (↵
    -0.12
    ,...
    -0.12
    ,\↵
    -0.12
    POSITIVE LOGITS
     :↵
    0.23
    :↵
    0.23
    :The
    0.22
     ï¼ļ
    0.20
     :
    0.19
     ç¼ĸè¾ij
    0.19
    ï¼ļ↵
    0.19
     :↵↵
    0.18
    ¶
    0.18
    :↵↵
    0.18
    Act Density 0.296%

    No Known Activations