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

    Neuronpedia

    INDEX
    Explanations

    words related to symbolism

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     intrigu
    -0.72
     psg
    -0.69
     jurassic
    -0.69
     pikachu
    -0.68
     disagre
    -0.66
     rtx
    -0.65
     inconce
    -0.65
     intersper
    -0.64
     Machia
    -0.64
     blackpink
    -0.63
    POSITIVE LOGITS
     symbol
    1.43
    symbol
    1.38
     Symbol
    1.35
    Symbol
    1.32
     symbols
    1.30
     SYMBOL
    1.17
    symbols
    1.17
     Symbols
    1.11
     symbole
    1.10
    Symbols
    1.08
    Act Density 0.101%

    No Known Activations