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

    Neuronpedia

    INDEX
    Explanations

    phrases related to governance and political statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orne
    -0.15
    argin
    -0.14
    ipl
    -0.14
    ater
    -0.14
    icast
    -0.14
    تÙĬÙĨ
    -0.14
    aeda
    -0.13
     deemed
    -0.13
    ãĤ¤ãĥ³ãĥĪ
    -0.13
    rente
    -0.13
    POSITIVE LOGITS
     DG
    0.18
     replies
    0.17
    åij½
    0.17
    ÛĮÙģ
    0.16
     Replies
    0.16
    ücken
    0.16
    ’ll
    0.16
     tasks
    0.16
     others
    0.15
     carpets
    0.15
    Act Density 0.038%

    No Known Activations