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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     intStringLen
    -0.57
     tartalomajánló
    -0.55
    HasForeignKey
    -0.54
    сылкі
    -0.52
    ParallelGroup
    -0.52
     تعالى
    -0.51
    ]';
    -0.49
    ametro
    -0.49
    -0.49
    Sucesor
    -0.48
    POSITIVE LOGITS
     pleaſure
    0.77
     greateſt
    0.73
     houſe
    0.72
     Majefty
    0.70
     purpoſe
    0.66
     بيها
    0.66
     ſtate
    0.66
     Diſ
    0.65
     ſtre
    0.65
     leaſt
    0.63
    Act Density 0.019%

    No Known Activations