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

    Neuronpedia

    INDEX
    Explanations

    connections to various forms of entertainment and social media references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     himself
    -0.22
     beaten
    -0.18
     Mirror
    -0.17
     he
    -0.16
    he
    -0.15
     flown
    -0.15
    /her
    -0.15
    idend
    -0.15
     Adoles
    -0.14
     Tunnel
    -0.14
    POSITIVE LOGITS
    Ñĩила
    0.26
    ovala
    0.23
    äºĨä¸Ģ
    0.23
    овала
    0.23
    ела
    0.22
    ila
    0.20
    ноÑģи
    0.20
    ила
    0.20
    Ñĥвала
    0.19
     могла
    0.19
    Act Density 0.046%

    No Known Activations