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

    Neuronpedia

    INDEX
    Explanations

    website URLs

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     BART
    -0.84
    NESS
    -0.75
     Awakens
    -0.66
    INESS
    -0.66
    ERY
    -0.66
    LEY
    -0.65
    ĪĴ
    -0.64
     DAC
    -0.62
     DRAG
    -0.61
     Centauri
    -0.61
    POSITIVE LOGITS
    orthern
    1.08
    cs
    1.07
    cd
    1.04
    bm
    1.04
    fs
    1.03
    fc
    1.02
    cc
    1.02
    ovember
    1.02
    bc
    1.02
    otor
    1.02
    Act Density 0.104%

    No Known Activations