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

    Neuronpedia

    INDEX
    Explanations

    phrases related to layers or layering concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sen
    -0.17
    ÑĮко
    -0.16
    Å¡en
    -0.16
    orners
    -0.16
    ive
    -0.15
    ibrary
    -0.15
    /assert
    -0.15
    sell
    -0.15
    _callable
    -0.15
    ubo
    -0.15
    POSITIVE LOGITS
    次
    0.24
    .Layer
    0.23
    (layer
    0.21
    -layer
    0.20
     layers
    0.20
    [layer
    0.19
    å±Ĥ
    0.19
     thickness
    0.19
    edImage
    0.18
     layer
    0.18
    Act Density 0.017%

    No Known Activations