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

    Neuronpedia

    INDEX
    Explanations

    references to citations and legal documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     enfans
    -0.72
     varandra
    -0.64
     élevées
    -0.64
     allmän
    -0.60
     utafitiHapana
    -0.60
     roligt
    -0.60
     sauvages
    -0.59
     WHICH
    -0.58
    enumii
    -0.58
     säll
    -0.57
    POSITIVE LOGITS
     still
    0.85
     available
    0.80
     included
    0.79
     found
    0.77
     not
    0.77
     held
    0.74
     shown
    0.73
     will
    0.72
     used
    0.72
     referenties
    0.69
    Act Density 0.468%

    No Known Activations