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

    Neuronpedia

    INDEX
    Explanations

    adjectives and nouns related to positive emotional memories

    oai_token-act-pair · gpt-3.5-turbo

    expressions of fondness or nostalgia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irrel
    -0.74
    adesh
    -0.69
    UGH
    -0.68
    udder
    -0.67
    pta
    -0.64
     helicop
    -0.63
    FT
    -0.63
    opers
    -0.62
    NG
    -0.62
    IDER
    -0.62
    POSITIVE LOGITS
     fond
    1.13
    uously
    0.99
    nesses
    0.94
    ness
    0.94
     memories
    0.89
    iously
    0.88
    entimes
    0.84
     remem
    0.83
    uous
    0.80
    ré
    0.79
    Act Density 0.012%

    No Known Activations