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

    Neuronpedia

    INDEX
    Explanations

    references to spatial data and geometric shapes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    å¸
    -0.16
    itti
    -0.16
    ScrollIndicator
    -0.14
    immel
    -0.14
     Babe
    -0.14
    ptrdiff
    -0.14
    .Guna
    -0.14
    uze
    -0.14
    FRAME
    -0.14
    ande
    -0.14
    POSITIVE LOGITS
     feature
    0.30
     Feature
    0.30
     geometry
    0.29
    Feature
    0.28
    feature
    0.26
     features
    0.26
    .geometry
    0.25
    .feature
    0.25
     Features
    0.24
     FEATURE
    0.24
    Act Density 0.036%

    No Known Activations