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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "random"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to randomness and random occurrences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gur
    -0.85
    ModLoader
    -0.81
    helle
    -0.80
    ports
    -0.78
    dain
    -0.77
    nai
    -0.73
    ippi
    -0.73
    raints
    -0.72
    ossier
    -0.72
    hid
    -0.70
    POSITIVE LOGITS
     assortment
    1.05
    istically
    1.04
    izer
    0.91
    ised
    0.91
    izable
    0.89
    aneously
    0.87
    isable
    0.83
    ization
    0.82
     randomly
    0.81
    ish
    0.79
    Act Density 0.020%

    No Known Activations