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

    Neuronpedia

    INDEX
    Explanations

    references to a "cabinet" or "CAD" related concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     bpy
    -0.90
    })*/
    -0.84
     Stearns
    -0.79
     Theron
    -0.77
     urea
    -0.76
     Xing
    -0.76
     Perugia
    -0.75
    uxxxx
    -0.75
    ThroughAttribute
    -0.75
    %)$
    -0.74
    POSITIVE LOGITS
     CAD
    1.06
    Cad
    1.03
     Cad
    1.02
    CAD
    0.92
     cabinets
    0.91
     cabinet
    0.90
     Cabinets
    0.90
     CAB
    0.90
     Cabral
    0.90
     cabine
    0.90
    Act Density 0.015%

    No Known Activations