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

    Neuronpedia

    INDEX
    Explanations

    terms and their definitions, particularly in legal and educational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wakilan
    -0.51
    dine
    -0.48
    Życiorys
    -0.48
     unwra
    -0.45
     múl
    -0.45
    纲
    -0.43
    Bakgrunnsstoff
    -0.41
    綜合報導
    -0.41
     odkry
    -0.40
     piedi
    -0.40
    POSITIVE LOGITS
     words
    1.18
     word
    1.13
     terms
    1.11
    Words
    1.09
     vocabulary
    1.04
     Words
    1.03
     terminology
    1.01
     definitions
    1.01
     Terms
    0.99
     term
    0.98
    Act Density 0.393%

    No Known Activations