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

    Neuronpedia

    INDEX
    Explanations

    discussions about the concept of "worlds" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     jsPsych
    -0.49
     Gaulle
    -0.48
     taşı
    -0.48
     inhuman
    -0.47
    clat
    -0.46
     africana
    -0.46
     nő
    -0.46
     keseluruhan
    -0.45
     impré
    -0.45
    APPLAUSE
    -0.44
    POSITIVE LOGITS
     realm
    1.22
     realms
    1.10
     Realm
    1.02
    realm
    1.01
     Realms
    1.00
     worlds
    0.96
     EconPapers
    0.89
    Realm
    0.86
    worlds
    0.84
     mundos
    0.83
    Act Density 0.290%

    No Known Activations