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

    Neuronpedia

    INDEX
    Explanations

    references to "world" and related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ])):
    -0.70
    rungsseite
    -0.65
     méri
    -0.63
    AddTagHelper
    -0.61
    Amos
    -0.61
     Pilate
    -0.58
     Réponses
    -0.58
     ESR
    -0.58
     Mortar
    -0.58
    ../../
    -0.57
    POSITIVE LOGITS
     World
    1.00
     WORLD
    0.99
     Worlds
    0.95
     world
    0.94
    Worlds
    0.94
    worlds
    0.91
     worlds
    0.89
    WORLD
    0.85
    World
    0.82
    Wide
    0.78
    Act Density 0.062%

    No Known Activations