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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "keep" in different forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    digm
    -0.63
    ValueStyle
    -0.63
    -0.60
     przem
    -0.59
    trand
    -0.59
    mainAxisSize
    -0.57
     hvilken
    -0.57
     Ges
    -0.57
    queryInterface
    -0.57
     TResult
    -0.56
    POSITIVE LOGITS
     keeping
    3.35
     Keeping
    3.30
    Keeping
    3.23
     keep
    3.17
    keeping
    3.17
    keep
    3.04
     kept
    3.02
     KEEP
    2.97
     keeps
    2.93
     Keep
    2.92
    Act Density 0.060%

    No Known Activations