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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, especially names and technical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Dodson
    -0.77
     Jaz
    -0.71
     Gómez
    -0.68
     Huber
    -0.65
     Adop
    -0.65
    Hel
    -0.65
     tred
    -0.65
     adop
    -0.64
     meg
    -0.64
     rever
    -0.64
    POSITIVE LOGITS
     Pind
    1.07
    protoimpl
    0.99
     Bragg
    0.95
     XP
    0.94
    WithMany
    0.93
     RADIUS
    0.92
    Personensuche
    0.91
     متعلقه
    0.90
     Aung
    0.87
     Quaternary
    0.86
    Act Density 2.274%

    No Known Activations