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

    Neuronpedia

    INDEX
    Explanations

    keywords or phrases that indicate a change in context or topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.84
    postsleuth
    -0.83
     שוליים
    -0.81
    脚注の使い方
    -0.78
    elemField
    -0.77
     avoient
    -0.76
    Diweddarwch
    -0.75
     pinulongan
    -0.74
     MainAxisSize
    -0.73
     thérape
    -0.72
    POSITIVE LOGITS
     minh
    0.44
     Black
    0.43
     auto
    0.42
    сля
    0.42
     La
    0.41
    Base
    0.40
    appspot
    0.40
     sti
    0.40
     formula
    0.40
    конструк
    0.39
    Act Density 0.278%

    No Known Activations