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

    phrases that denote symbols or representations of concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cker
    -0.65
     Oaks
    -0.63
    ieri
    -0.62
    ventus
    -0.61
    kus
    -0.61
     Bucks
    -0.59
     oats
    -0.58
    hari
    -0.58
    alsh
    -0.58
    isode
    -0.57
    POSITIVE LOGITS
    ically
    1.00
     symbols
    0.93
    hips
    0.89
    ized
    0.89
     Meaning
    0.89
    izes
    0.88
     symbol
    0.88
     symbolism
    0.86
    icons
    0.85
     Symbol
    0.82
    Act Density 0.041%

    No Known Activations