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

    Neuronpedia

    INDEX
    Explanations

    phrases related to randomness or selection without a specific pattern

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "randomly."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     efforts
    -0.66
    bear
    -0.63
    alf
    -0.63
     revision
    -0.60
    aphael
    -0.60
     Zionism
    -0.59
    ds
    -0.59
    acements
    -0.58
     Atkins
    -0.57
     reckoning
    -0.56
    POSITIVE LOGITS
     randomly
    3.61
     arbitrarily
    1.86
     spontaneously
    1.83
     dynamically
    1.61
    random
    1.56
     randomized
    1.50
     blindly
    1.41
     proced
    1.39
     random
    1.38
     magically
    1.38
    Act Density 0.034%

    No Known Activations