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

    Neuronpedia

    INDEX
    Explanations

    phrases related to factual assertions and evidence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    factual, facile, factorization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Montgomery
    -0.50
    Qry
    -0.48
    rott
    -0.47
     Kingfisher
    -0.45
    ேன்
    -0.45
     Nuestro
    -0.44
     Dougherty
    -0.44
     betweenstory
    -0.44
    Primitive
    -0.44
     Gummi
    -0.44
    POSITIVE LOGITS
     Fac
    2.38
    Fac
    2.27
    fac
    2.16
     fac
    2.03
     FAC
    1.78
    FAC
    1.76
     Fak
    1.13
     Facilit
    1.13
    Facet
    1.07
     facilitation
    1.07
    Act Density 0.009%

    No Known Activations