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

    Neuronpedia

    INDEX
    Explanations

    terms related to the definitions and uses of words, particularly in a nuanced or specialized context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     désert
    -0.47
     calendriers
    -0.46
    Desired
    -0.46
     Dostupné
    -0.45
     Scaling
    -0.44
    copy
    -0.44
    Plan
    -0.44
     /*
    -0.43
    mtable
    -0.42
    क्र
    -0.42
    POSITIVE LOGITS
     term
    1.00
     definition
    0.81
     terms
    0.77
    WriteAttribute
    0.72
    verwijspagina
    0.69
     word
    0.69
    gucigalpa
    0.66
    begriff
    0.65
    قایناقلار
    0.65
     meaning
    0.65
    Act Density 0.401%

    No Known Activations