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

    Neuronpedia

    INDEX
    Explanations

    mentions of locations and names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    frastructure
    -0.69
    tainable
    -0.69
    tempts
    -0.67
    sterious
    -0.66
     bağlantılar
    -0.62
    complished
    -0.62
    mentable
    -0.61
     saites
    -0.61
    Personendaten
    -0.59
    quested
    -0.59
    POSITIVE LOGITS
     vété
    0.88
     spé
    0.82
     génie
    0.81
     maneu
    0.81
     shenan
    0.78
     mépris
    0.77
     intitulée
    0.76
     Souha
    0.75
     Jusqu
    0.75
     Kün
    0.74
    Act Density 0.600%

    No Known Activations