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

    Neuronpedia

    INDEX
    Explanations

    instances of the suffix 'er' and variations of the word "erase."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mess
    -0.76
     Mess
    -0.57
     excess
    -0.52
    DotNet
    -0.52
     cas
    -0.50
    Catalog
    -0.50
     enterprise
    -0.48
     reform
    -0.48
     extra
    -0.48
    眞
    -0.47
    POSITIVE LOGITS
     er
    2.43
     Er
    1.83
    Er
    1.83
     ER
    1.26
    Personendaten
    1.16
     виправивши
    1.06
     Erm
    1.04
    SourceChecksum
    1.03
     eru
    1.00
     للاسماء
    0.97
    Act Density 0.052%

    No Known Activations