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

    Neuronpedia

    INDEX
    Explanations

    references to specific central entities or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Trooper
    -0.83
    Rüyada
    -0.80
     Yugos
    -0.80
     Laos
    -0.77
     Filipinas
    -0.76
     Phry
    -0.76
     moons
    -0.76
     Roskov
    -0.75
     Uttarakhand
    -0.75
     tø
    -0.74
    POSITIVE LOGITS
     Central
    2.22
    Central
    2.12
     central
    2.02
    central
    1.97
     CENTRAL
    1.96
    CENTRAL
    1.95
     centrales
    1.56
     centrale
    1.53
     Centra
    1.53
    entral
    1.47
    Act Density 0.045%

    No Known Activations