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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the conjunction "and" to indicate lists or connections between concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ječ
    -0.57
     mulighed
    -0.54
     pamoja
    -0.53
    boar
    -0.49
    ้า
    -0.49
     dian
    -0.48
     perbaikan
    -0.47
    Wc
    -0.47
     xperia
    -0.46
    чих
    -0.46
    POSITIVE LOGITS
    Архівовано
    0.83
     *)__
    0.81
    +:+
    0.78
     MainAxisSize
    0.77
    تقاوى
    0.77
    EndProject
    0.73
     <=",
    0.72
    OrEqualTo
    0.71
    tvguidetime
    0.70
    ]:
    0.69
    Act Density 0.221%

    No Known Activations