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

    Neuronpedia

    INDEX
    Explanations

    mentions of geometric shapes, particularly triangles, in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to geometric shapes, particularly triangles and rectangles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cook
    -0.75
     Brock
    -0.66
     Acting
    -0.66
     offline
    -0.66
     Moff
    -0.66
    Mill
    -0.66
    gress
    -0.65
    amer
    -0.65
    infect
    -0.65
    Premium
    -0.65
    POSITIVE LOGITS
     triangle
    4.01
     Triangle
    3.23
     triangles
    2.94
     triangular
    1.96
    tri
    1.69
     rectangle
    1.57
    Tri
    1.52
     circle
    1.21
    circle
    1.10
     vertex
    1.06
    Act Density 0.023%

    No Known Activations