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

    Neuronpedia

    INDEX
    Explanations

    negative phrases and experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    not followed by certain words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EconPapers
    -0.54
     <<<<<<<<<<<<<<
    -0.53
    InputTagHelper
    -0.51
    fromnode
    -0.50
     wireType
    -0.50
     transférez
    -0.49
    roek
    -0.49
     للمعارف
    -0.49
    UnitTesting
    -0.46
     Scotsman
    -0.46
    POSITIVE LOGITS
     ModelExpression
    0.40
    TypedDataSet
    0.37
     والم
    0.36
    SourceChecksum
    0.35
    ParallelGroup
    0.35
     Porém
    0.34
    MessageTagHelper
    0.34
    собенности
    0.33
    Etimología
    0.33
    MERCE
    0.33
    Act Density 0.068%

    No Known Activations