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

    Neuronpedia

    INDEX
    Explanations

    references to randomization and probability in decision-making contexts

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

    Probability, picking letters/numbers from a set

    np_acts-logits-general · gemini-2.0-flash

    random selection probabilities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    saraba
    -0.55
     ThemeData
    -0.53
    ArgumentParser
    -0.47
     ligiloj
    -0.47
     otomatig
    -0.47
     vigne
    -0.46
    weile
    -0.46
     Kig
    -0.45
     Arca
    -0.45
    ypress
    -0.45
    POSITIVE LOGITS
     roll
    1.47
     rolls
    1.43
     rolled
    1.39
     rolling
    1.29
     dice
    1.27
     Roll
    1.24
     ROLL
    1.22
    roll
    1.21
    Roll
    1.20
     Rolling
    1.18
    Act Density 0.225%

    No Known Activations