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

    Neuronpedia

    INDEX
    Explanations

    symbols or symbolic representations

    oai_token-act-pair · gpt-3.5-turbo

    references to symbols or symbolic meanings in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hari
    -0.74
     Oaks
    -0.68
     Mans
    -0.68
    alsh
    -0.67
     Lank
    -0.67
    ECK
    -0.64
     Bed
    -0.64
     oats
    -0.63
    Far
    -0.63
    rog
    -0.62
    POSITIVE LOGITS
     symbol
    1.30
     symbols
    1.24
    icons
    1.03
    mbol
    1.02
     Symbol
    0.98
     emblem
    0.97
    ically
    0.92
     symbolism
    0.91
    leader
    0.84
     Meaning
    0.84
    Act Density 0.013%

    No Known Activations