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

    Neuronpedia

    INDEX
    Explanations

    references to shape and form in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.96
     Monfieur
    -0.93
     acorns
    -0.91
     $_"
    -0.88
    CodedInputStream
    -0.87
     Efq
    -0.86
     Munro
    -0.85
    wój
    -0.85
     MenuView
    -0.85
     ſeveral
    -0.84
    POSITIVE LOGITS
     shape
    1.76
     SHAPE
    1.75
     Shape
    1.63
     shapes
    1.62
    shape
    1.57
    SHAPE
    1.56
     Shapes
    1.55
    Shape
    1.53
    shapes
    1.46
    Shapes
    1.36
    Act Density 0.056%

    No Known Activations