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

    Neuronpedia

    INDEX
    Explanations

    terms related to comparing or evaluating differences

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

    compare and comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IZONT
    -0.52
    ReusableCell
    -0.50
     bertanggung
    -0.48
     <<<<<<<<<<<<<<
    -0.48
    WriteTagHelper
    -0.46
     AppBundle
    -0.46
    genheim
    -0.45
     geho
    -0.45
     שוליים
    -0.45
    Dermott
    -0.45
    POSITIVE LOGITS
     comparison
    1.65
     comparisons
    1.57
     compare
    1.54
     compares
    1.52
     comparing
    1.51
     Comparison
    1.48
     Compare
    1.48
    comparison
    1.42
     Comparisons
    1.41
    Comparison
    1.39
    Act Density 0.086%

    No Known Activations