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

    Neuronpedia

    INDEX
    Explanations

    concepts related to interpersonal values and qualities that promote collaboration and community well-being

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tslib
    -0.15
    qa
    -0.14
    ýš
    -0.14
    AUSE
    -0.14
    MDB
    -0.14
    izik
    -0.14
    272
    -0.13
    áºŃu
    -0.13
    à¥Īद
    -0.13
    ause
    -0.13
    POSITIVE LOGITS
    /or
    0.15
     expression
    0.14
     expansion
    0.14
     broadly
    0.14
     armed
    0.14
     amp
    0.13
    ante
    0.13
    rai
    0.13
     detail
    0.13
     Sne
    0.13
    Act Density 0.191%

    No Known Activations