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

    Neuronpedia

    INDEX
    Explanations

    references to capabilities and potential actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    emean
    -0.17
    оÑĢож
    -0.16
    lez
    -0.16
    ubl
    -0.15
     Uhr
    -0.14
    ActionCreators
    -0.14
    _trim
    -0.14
    à¹Īà¸Ńà¸Ļ
    -0.14
    oggles
    -0.14
    uele
    -0.14
    POSITIVE LOGITS
     hopefully
    0.27
     can
    0.19
     doesn
    0.18
    ä¸įè¦ģ
    0.18
     avoid
    0.18
    hopefully
    0.18
    asty
    0.18
     wouldn
    0.17
     won
    0.17
     later
    0.16
    Act Density 0.104%

    No Known Activations