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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating importance or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.53
    featureID
    -0.47
     دیکھیے
    -0.46
    杓
    -0.42
    पया
    -0.42
    SourceChecksum
    -0.41
    RegistryLite
    -0.41
    存于互联网档案馆
    -0.40
    gewä
    -0.40
    الحياه
    -0.37
    POSITIVE LOGITS
     wise
    1.23
     best
    1.12
     wisest
    1.06
     advisable
    1.04
     smartest
    0.96
     advised
    0.94
     recommended
    0.91
     smart
    0.90
     prudent
    0.88
     wiser
    0.88
    Act Density 0.291%

    No Known Activations