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

    Neuronpedia

    INDEX
    Explanations

    terms associated with different worlds or dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Gaulle
    -0.54
     jsPsych
    -0.50
     forman
    -0.49
    Forme
    -0.49
    clat
    -0.48
     inso
    -0.47
     formen
    -0.46
     leçons
    -0.46
    allos
    -0.46
     asado
    -0.46
    POSITIVE LOGITS
     realm
    1.21
     worlds
    1.19
     world
    1.13
     realms
    1.11
    realm
    1.03
     Realm
    1.00
     universe
    0.98
     wereld
    0.95
     Realms
    0.94
    worlds
    0.90
    Act Density 0.226%

    No Known Activations