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

    Neuronpedia

    INDEX
    Explanations

    terms related to software or technical interfaces

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of interfaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ucks
    -0.90
    wagen
    -0.86
    omore
    -0.81
    onna
    -0.81
    hur
    -0.79
    fam
    -0.75
    oil
    -0.71
    sis
    -0.70
    yd
    -0.70
    nen
    -0.69
    POSITIVE LOGITS
     interface
    1.02
     interfaces
    1.00
     Interface
    0.88
     mund
    0.82
     layout
    0.82
    eering
    0.80
     elements
    0.79
     layouts
    0.78
     design
    0.76
    eers
    0.74
    Act Density 0.026%

    No Known Activations