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

    Neuronpedia

    INDEX
    Explanations

    terms related to randomness or random processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Efq
    -0.76
    تقاوى
    -0.67
    aarrggbb
    -0.66
    NameInMap
    -0.66
     RIPRODUZIONE
    -0.65
     Theſe
    -0.65
    ☸
    -0.64
     Houſe
    -0.62
    Felic
    -0.62
     Juri
    -0.61
    POSITIVE LOGITS
    random
    1.09
     random
    1.02
    rand
    0.93
    Random
    0.88
     randomly
    0.87
     Random
    0.83
    随机
    0.80
     RANDOM
    0.78
     rand
    0.76
     randomized
    0.71
    Act Density 0.122%

    No Known Activations