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

    Neuronpedia

    INDEX
    Explanations

    references to deviations from expected values or standards

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     Goodrich
    -0.73
     mit
    -0.68
     Mit
    -0.66
    sizeCache
    -0.62
    WriteTagHelper
    -0.62
    Fuk
    -0.61
     InputDecoration
    -0.61
    readFileSync
    -0.60
    рија
    -0.60
     Mitch
    -0.60
    POSITIVE LOGITS
     deviations
    1.45
     Deviation
    1.38
     deviation
    1.35
    deviation
    1.28
    Deviation
    1.26
     deviate
    1.19
     Deviant
    1.13
     devi
    1.06
     deviant
    1.06
    viations
    1.02
    Act Density 0.019%

    No Known Activations