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

    Neuronpedia

    INDEX
    Explanations

    mentions of memory specifications, particularly RAM

    oai_token-act-pair · gpt-3.5-turbo

    mentions of RAM

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iquette
    -0.72
    illes
    -0.71
    Nat
    -0.70
    oral
    -0.66
    bre
    -0.64
     Spirit
    -0.63
    cos
    -0.63
     Feldman
    -0.62
     Nat
    -0.62
    ichi
    -0.61
    POSITIVE LOGITS
     RAM
    3.69
    RAM
    2.32
     ROM
    1.60
     ram
    1.58
    Ram
    1.57
     memory
    1.53
     DDR
    1.46
    memory
    1.38
    Memory
    1.34
     RAID
    1.33
    Act Density 0.019%

    No Known Activations