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

    Neuronpedia

    INDEX
    Explanations

    pronouns and expressions of personal involvement or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     équilibr
    -0.54
     faccio
    -0.52
     arşivlendi
    -0.52
    </table>
    -0.52
    astéro
    -0.51
    MENAFN
    -0.51
     pourriez
    -0.51
    Priv
    -0.51
     soudain
    -0.51
     模拟
    -0.51
    POSITIVE LOGITS
    EndContext
    0.87
     CreateTagHelper
    0.78
    ImageContext
    0.62
     YES
    0.61
     yes
    0.61
    Yes
    0.59
     BoxFit
    0.58
     Yes
    0.58
    oa̍t
    0.58
    YES
    0.58
    Act Density 0.073%

    No Known Activations