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

    Neuronpedia

    INDEX
    Explanations

    terms related to global issues or entities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     romain
    -0.57
    InjectAttribute
    -0.54
     Cinéma
    -0.50
     unve
    -0.49
     POETRY
    -0.48
     vété
    -0.48
     disreg
    -0.48
     aggress
    -0.48
    carus
    -0.48
     pettico
    -0.48
    POSITIVE LOGITS
     global
    1.02
     Global
    0.96
    global
    0.96
    Global
    0.94
     globales
    0.92
     GLOBAL
    0.82
     globale
    0.81
    lobal
    0.80
    GLOBAL
    0.79
     globe
    0.67
    Act Density 0.081%

    No Known Activations