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

    Neuronpedia

    INDEX
    Explanations

    locations or objects hidden under or beneath something

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ERG
    -0.77
    eln
    -0.69
    och
    -0.69
    QL
    -0.65
    yah
    -0.64
    DN
    -0.62
    izu
    -0.61
    okin
    -0.61
    ãĥ£
    -0.61
    Ê
    -0.59
    POSITIVE LOGITS
    neath
    1.26
     layers
    1.04
    sea
    1.03
    pants
    1.03
    coat
    1.00
    brush
    0.97
    growth
    0.94
     coats
    0.89
     bushes
    0.88
     blankets
    0.88
    Act Density 0.075%

    No Known Activations