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

    Neuronpedia

    INDEX
    Explanations

    references to desks or desk-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WriteLiteral
    -0.86
     Cloudy
    -0.81
    Cloudy
    -0.75
     vertes
    -0.74
     globos
    -0.74
    ruptedException
    -0.72
     harmonie
    -0.71
     Drapeau
    -0.71
    LÄ
    -0.70
     Theſe
    -0.68
    POSITIVE LOGITS
     desk
    2.83
     Desk
    2.52
     desks
    2.23
    desk
    2.21
    Desk
    2.15
     DESK
    1.89
    DESK
    1.33
    デスク
    0.94
     bureau
    0.90
     Bureau
    0.89
    Act Density 0.074%

    No Known Activations