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

    Neuronpedia

    INDEX
    Explanations

    references to political alignment and endorsements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    帯
    -0.17
    ullo
    -0.16
    ãĥ¨
    -0.16
    aton
    -0.15
    rame
    -0.15
    jectories
    -0.15
    lü
    -0.15
     tặng
    -0.14
    ìļ
    -0.14
    ibold
    -0.14
    POSITIVE LOGITS
    erial
    0.16
     var
    0.16
    227
    0.15
     Brewing
    0.15
    574
    0.15
    avez
    0.14
    iper
    0.14
     Tomb
    0.14
     nim
    0.14
    oma
    0.14
    Act Density 0.101%

    No Known Activations