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

    Neuronpedia

    INDEX
    Explanations

    references to beers or related terms like hops, brewery, or craft beer

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     hek
    -0.73
    BeginInit
    -0.67
     krab
    -0.65
     republi
    -0.61
     minimalis
    -0.61
     meras
    -0.59
    Xuất
    -0.58
     Mathem
    -0.56
     Sucher
    -0.55
     psychiat
    -0.55
    POSITIVE LOGITS
     beer
    1.31
     Beer
    1.20
     BEER
    1.15
     beers
    1.13
    Beer
    1.09
    beer
    1.07
     brewery
    0.93
    beers
    0.87
     Beers
    0.87
     cerveza
    0.79
    Act Density 0.080%

    No Known Activations