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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     already
    -0.24
    already
    -0.23
     Already
    -0.22
     artık
    -0.22
    Already
    -0.20
     már
    -0.19
     suddenly
    -0.18
     bereits
    -0.18
    å·²
    -0.17
    soon
    -0.17
    POSITIVE LOGITS
    born
    0.33
    ness
    0.29
    birth
    0.24
    NESS
    0.19
     plenty
    0.19
    s
    0.19
     alive
    0.18
    /rss
    0.18
    alive
    0.18
    çĦ¶
    0.17
    Act Density 0.085%

    No Known Activations