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

    Neuronpedia

    INDEX
    Explanations

    terms related to legal institutions and events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     eigenvectors
    -0.83
     disambiguazione
    -0.81
     excuses
    -0.77
     bonté
    -0.77
    Pratique
    -0.75
     poffible
    -0.75
    IntoConstraints
    -0.74
     screenshots
    -0.74
     dignité
    -0.74
    tvguidetime
    -0.74
    POSITIVE LOGITS
     standpoint
    0.58
     pair
    0.56
     version
    0.55
     situation
    0.54
     series
    0.53
     strategy
    0.53
     émissions
    0.52
     that
    0.51
     approach
    0.51
     package
    0.50
    Act Density 2.579%

    No Known Activations