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

    Neuronpedia

    INDEX
    Explanations

    social media references and engagements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onder
    -0.17
    eer
    -0.16
    ternet
    -0.16
    odian
    -0.15
    alous
    -0.14
    алÑİ
    -0.14
    smarty
    -0.14
    oris
    -0.14
    ledge
    -0.14
    oning
    -0.14
    POSITIVE LOGITS
     Dud
    0.15
    ãĥ¼ãĥģ
    0.14
    .Modules
    0.14
    δε
    0.14
    jin
    0.14
    qui
    0.14
    ITTE
    0.14
    à¹ģส
    0.13
    aket
    0.13
    ìŀIJê°Ģ
    0.13
    Act Density 0.005%

    No Known Activations