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

    Neuronpedia

    INDEX
    Explanations

    items related to light sources

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     postp
    -0.63
    reports
    -0.60
     disgu
    -0.59
     patched
    -0.59
     refunds
    -0.59
     licenses
    -0.59
     instit
    -0.59
     regards
    -0.58
     aborted
    -0.55
     fares
    -0.55
    POSITIVE LOGITS
    ggles
    1.66
    wered
    1.36
    ilet
    1.17
    ppers
    1.13
    pload
    1.11
    asted
    1.08
    lling
    1.05
    othy
    1.04
    pping
    1.04
    ilings
    1.03
    Act Density 0.197%

    No Known Activations