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

    Neuronpedia

    INDEX
    Explanations

    words related to whispers

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     mindfulness
    -0.66
    sm
    -0.64
     chrom
    -0.62
    ESS
    -0.61
    noon
    -0.60
     privately
    -0.59
     vacuum
    -0.59
    OME
    -0.58
     adm
    -0.58
     confounding
    -0.58
    POSITIVE LOGITS
    oples
    1.25
    cific
    1.24
    rer
    1.20
    rers
    1.15
    anut
    1.14
    ptin
    1.03
    cial
    1.03
    ller
    1.01
    llers
    1.01
    cies
    1.01
    Act Density 0.023%

    No Known Activations