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

    Neuronpedia

    INDEX
    Explanations

    terms related to randomness and random variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     random
    -0.67
    random
    -0.67
    Random
    -0.66
     متحده
    -0.57
     automatisch
    -0.56
     randomly
    -0.56
    TagMode
    -0.55
     '\\;'
    -0.53
    随机
    -0.52
     Random
    -0.50
    POSITIVE LOGITS
    AccessFile
    0.91
    walk
    0.74
     walk
    0.74
    nly
    0.73
    ize
    0.71
     Walk
    0.70
    izer
    0.70
    Walk
    0.68
    WALK
    0.64
     WALK
    0.64
    Act Density 0.334%

    No Known Activations