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

    Neuronpedia

    INDEX
    Explanations

    sentences that express comparisons or similarities

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

    like and unlike

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pier
    -0.29
     Ans
    -0.27
    équilibre
    -0.26
     balance
    -0.26
     Stro
    -0.26
    Balance
    -0.25
    RefNanny
    -0.25
    Batis
    -0.25
     dise
    -0.24
     बीच
    -0.24
    POSITIVE LOGITS
    styleType
    0.64
    unlike
    0.62
    setof
    0.61
     مشين
    0.61
     EconPapers
    0.60
     TextInputType
    0.60
    endregion
    0.60
    woofer
    0.59
    Like
    0.59
    LIKE
    0.58
    Act Density 0.130%

    No Known Activations