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

    Neuronpedia

    INDEX
    Explanations

    instances where the word "remember" or "ozo" appears

    oai_token-act-pair · gpt-3.5-turbo

    references to memory and recollection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Thumbnail
    -0.74
    resses
    -0.71
    visory
    -0.70
    ãĥīãĥ©ãĤ´ãĥ³
    -0.65
    inen
    -0.64
    ãĤ¢ãĥ«
    -0.64
    akeru
    -0.62
    ãĥĨãĤ£
    -0.60
    iary
    -0.59
    itsch
    -0.58
    POSITIVE LOGITS
    remember
    1.59
    nexus
    0.90
    ufact
    0.85
    esters
    0.72
    ozo
    0.68
     experien
    0.68
     irrig
    0.66
    anthrop
    0.65
    ustom
    0.64
    agon
    0.62
    Act Density 0.005%

    No Known Activations