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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    roads
    -0.17
    ows
    -0.17
    ought
    -0.16
    лиÑĪком
    -0.16
    /loose
    -0.15
    aul
    -0.15
    _locations
    -0.15
    538
    -0.15
    ends
    -0.15
    roc
    -0.14
    POSITIVE LOGITS
    ally
    0.34
    RelativeTo
    0.24
    ality
    0.22
    ational
    0.21
    ALLY
    0.21
    .href
    0.21
    tion
    0.19
    nement
    0.18
    entiful
    0.18
    /time
    0.18
    Act Density 0.042%

    No Known Activations