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

    Neuronpedia

    INDEX
    Explanations

    words with the prefix "ru-" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the substance "ru" or its variations in different contexts, particularly in relation to risks and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    raints
    -0.75
    note
    -0.70
     CPC
    -0.66
    smart
    -0.63
     EntityItem
    -0.63
     Solitaire
    -0.63
    enegger
    -0.62
    notes
    -0.61
     Mavericks
    -0.61
     GOODMAN
    -0.60
    POSITIVE LOGITS
    pees
    1.15
    nd
    1.01
    uer
    0.98
    gment
    0.98
    uth
    0.98
    ille
    0.93
    nder
    0.93
    pee
    0.93
    ijn
    0.93
    llor
    0.92
    Act Density 0.010%

    No Known Activations