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

    Neuronpedia

    INDEX
    Explanations

    phrases or expressions that denote relationships or concepts expressed in "terms of."

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ẤT
    -0.59
    RenderAtEndOf
    -0.55
     suivantes
    -0.54
    breviations
    -0.52
    çalves
    -0.52
     read
    -0.51
     conformidad
    -0.51
     intérieure
    -0.50
     pouvoirs
    -0.50
     everything
    -0.49
    POSITIVE LOGITS
    脚注の使い方
    0.79
    =$?
    0.77
     IBOutlet
    0.72
     الحره
    0.70
     تانيه
    0.67
    ocino
    0.67
    OGND
    0.64
     sánh
    0.64
     незавершена
    0.63
     Jefus
    0.60
    Act Density 0.011%

    No Known Activations