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

    Neuronpedia

    INDEX
    Explanations

    references to scientific journals and their abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Roskov
    -0.75
     disambiguazione
    -0.74
     resourceCulture
    -0.62
    étranger
    -0.56
    cèse
    -0.55
    istoitu
    -0.54
    SharedCtor
    -0.53
     émissions
    -0.53
    ItemBackground
    -0.53
     degrés
    -0.52
    POSITIVE LOGITS
    atively
    0.75
    alt
    0.72
    ala
    0.66
    PhysRev
    0.57
    cot
    0.55
    SourceChecksum
    0.54
     bare
    0.54
    ges
    0.53
    ContainerState
    0.52
    boxed
    0.51
    Act Density 2.200%

    No Known Activations