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

    Neuronpedia

    INDEX
    Explanations

    references to items or components in technical descriptions

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    InSection
    -0.84
    RegistryLite
    -0.83
    InjectAttribute
    -0.82
     unknownFields
    -0.80
    HtmlAttribute
    -0.78
     '\\;'
    -0.77
    tagext
    -0.75
     <>",
    -0.75
     Signalez
    -0.74
    AndroidJUnit
    -0.73
    POSITIVE LOGITS
     principal
    0.52
     foremost
    0.50
    何より
    0.49
     source
    0.48
    online
    0.47
     included
    0.46
    input
    0.46
    jed
    0.45
     Sensitivity
    0.45
    招待
    0.45
    Act Density 0.035%

    No Known Activations