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

    Neuronpedia

    INDEX
    Explanations

    words related to positive memories and sentiments

    oai_token-act-pair · gpt-3.5-turbo

    expressions of fondness and nostalgia related to memories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irrel
    -0.74
    udder
    -0.68
    adesh
    -0.67
    ulhu
    -0.66
    soDeliveryDate
    -0.65
    pta
    -0.62
     helicop
    -0.62
    iphate
    -0.61
    DoS
    -0.60
    uzzle
    -0.60
    POSITIVE LOGITS
     fond
    1.11
    uously
    0.96
     memories
    0.92
    ness
    0.90
    iously
    0.87
    nesses
    0.86
     Memories
    0.85
    est
    0.84
     remem
    0.83
    ries
    0.82
    Act Density 0.011%

    No Known Activations