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

    Neuronpedia

    INDEX
    Explanations

    phrases and words indicating simplicity and ease of use

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    WireFormatLite
    -1.14
    XmlAccessorType
    -1.12
    sidemargin
    -1.08
     <=",
    -1.06
    хьтан
    -1.05
     propOrder
    -1.05
    TypedDataSet
    -1.04
     ProtoMessage
    -1.01
    AndEndTag
    -0.99
     ModelExpression
    -0.99
    POSITIVE LOGITS
     easy
    2.42
     Easy
    2.25
    Easy
    2.24
    easy
    2.17
     EASY
    2.09
    EASY
    1.96
     easier
    1.62
     easily
    1.50
     eas
    1.45
     easiest
    1.39
    Act Density 0.069%

    No Known Activations