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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "same" and its variations in context

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

    sameness and comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bort
    -0.34
     no
    -0.31
     anything
    -0.30
     ни
    -0.30
     Hotel
    -0.29
    儉
    -0.29
     above
    -0.29
     ч
    -0.29
     ship
    -0.29
    Discard
    -0.29
    POSITIVE LOGITS
    aarrggbb
    0.71
    ⟬
    0.68
    Gambas
    0.68
    ynb
    0.67
    enterOuterAlt
    0.65
     المعيارى
    0.64
    JspWriter
    0.59
    MessageOf
    0.59
     Wicidata
    0.56
    romyalgia
    0.56
    Act Density 0.011%

    No Known Activations