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

    Neuronpedia

    INDEX
    Explanations

    memories or mentions of memories

    oai_token-act-pair · gpt-3.5-turbo

    references to memory and memories, particularly those that are emotional or significant

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    annis
    -0.76
    ats
    -0.75
    ahime
    -0.75
    ModLoader
    -0.71
    OPLE
    -0.68
    jab
    -0.68
    assi
    -0.67
     Galile
    -0.65
    ouk
    -0.64
    qa
    -0.64
    POSITIVE LOGITS
     memories
    1.03
     Memories
    1.03
    remember
    0.99
     recollection
    0.96
     remembered
    0.92
     nostalg
    0.91
     remem
    0.89
     remembrance
    0.88
    fulness
    0.86
     vividly
    0.86
    Act Density 0.047%

    No Known Activations