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

    Neuronpedia

    INDEX
    Explanations

    terms related to counting or numerical values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    PhysRev
    -0.72
    antity
    -0.65
    ✨:
    -0.63
     spont
    -0.60
     $("<
    -0.58
    SaveChangesAsync
    -0.57
    LoS
    -0.57
     Dage
    -0.57
     malang
    -0.57
    逅
    -0.56
    POSITIVE LOGITS
     counting
    1.62
     counted
    1.48
    counting
    1.39
     Counting
    1.38
     counts
    1.35
    Counting
    1.31
    counted
    1.17
     count
    1.05
     Counts
    1.03
     contando
    0.87
    Act Density 0.114%

    No Known Activations