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

    Neuronpedia

    INDEX
    Explanations

    memories or related words

    oai_token-act-pair · gpt-3.5-turbo

    references to memories, particularly traumatic or impactful experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Galile
    -0.70
    annis
    -0.69
    ModLoader
    -0.68
    mans
    -0.67
    ahime
    -0.66
    retty
    -0.66
    jab
    -0.66
     penal
    -0.65
     nomine
    -0.65
    ats
    -0.64
    POSITIVE LOGITS
     Memories
    1.16
     memories
    1.07
     recollection
    1.03
    remember
    1.01
     remembered
    0.95
     remem
    0.94
     remembrance
    0.90
     vividly
    0.90
    abilia
    0.90
     vivid
    0.87
    Act Density 0.037%

    No Known Activations