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

    Neuronpedia

    INDEX
    Explanations

    references to modules and their definitions within a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Goodrich
    -0.46
    EDEFAULT
    -0.42
     Venedig
    -0.37
    </b>
    -0.36
    <b>
    -0.35
    Sainte
    -0.35
     Úl
    -0.34
    Getty
    -0.34
     Navidad
    -0.32
     Prensa
    -0.32
    POSITIVE LOGITS
     module
    2.66
     Module
    2.64
     modules
    2.44
    Module
    2.44
    module
    2.44
     Modules
    2.41
     MODULE
    2.17
    Modules
    2.06
    MODULE
    2.05
    modules
    2.03
    Act Density 0.081%

    No Known Activations