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

    Neuronpedia

    INDEX
    Explanations

    references to spiral structures or concepts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     noDo
    -0.81
    NameInMap
    -0.75
    HasForeignKey
    -0.72
    DeleteBehavior
    -0.69
     Dalla
    -0.68
    moud
    -0.67
    rawtypes
    -0.66
     newOwner
    -0.66
    rophoto
    -0.65
     EQ
    -0.64
    POSITIVE LOGITS
     Spiral
    1.54
     spiral
    1.48
    Spiral
    1.43
     spirals
    1.34
    spiral
    1.34
     Spir
    1.22
     spir
    1.20
     espiral
    1.18
     Helix
    1.11
    螺旋
    0.98
    Act Density 0.005%

    No Known Activations