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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "sum" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     summary
    -0.74
    wiſe
    -0.64
     Summary
    -0.63
    "]).
    -0.62
     ſp
    -0.58
     Eſ
    -0.57
     ProtoMessage
    -0.57
    "]="
    -0.56
     Stevenson
    -0.56
     houſe
    -0.55
    POSITIVE LOGITS
     sum
    3.61
     Sum
    3.17
    sum
    3.17
    Sum
    3.02
     SUM
    2.52
    SUM
    2.43
     sums
    2.38
     suma
    2.04
    sums
    2.02
    Sums
    1.96
    Act Density 0.122%

    No Known Activations