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

    Neuronpedia

    INDEX
    Explanations

    references to specific academic or research fields and disciplines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     rito
    -0.63
     sabbia
    -0.58
     fallu
    -0.54
    postsleuth
    -0.53
     riuscito
    -0.52
     graphique
    -0.50
     ki
    -0.49
     Faithful
    -0.49
     peur
    -0.48
     sitting
    -0.48
    POSITIVE LOGITS
     domaines
    1.02
    Areas
    1.00
     areas
    0.99
     حوزه
    0.96
     ámbito
    0.94
    mbito
    0.93
     Areas
    0.93
     domaine
    0.93
     ámbitos
    0.92
     domains
    0.92
    Act Density 0.200%

    No Known Activations