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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and companies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    lda
    -0.97
    EStreamFrame
    -0.88
    ngth
    -0.87
    dden
    -0.81
     eleph
    -0.78
    senal
    -0.76
    rero
    -0.72
     membrane
    -0.72
    EStream
    -0.71
    nces
    -0.71
    POSITIVE LOGITS
    ihil
    1.41
    iversary
    1.38
    ihilation
    1.35
    abis
    1.29
    ibal
    1.19
    enberg
    1.18
    igans
    1.16
    igan
    1.10
    ounce
    1.10
    apolis
    1.05
    Act Density 7.421%

    No Known Activations