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

    Neuronpedia

    INDEX
    Explanations

    proper nouns of places or people

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    ienced
    -0.93
    ships
    -0.86
    ents
    -0.85
    yrinth
    -0.81
    omez
    -0.70
    iences
    -0.69
    iants
    -0.69
    uminati
    -0.68
    IAN
    -0.68
     Katherine
    -0.67
    POSITIVE LOGITS
    qual
    0.95
    çīĪ
    0.85
    opy
    0.83
    ograp
    0.82
    ographed
    0.79
    eful
    0.77
    uren
    0.76
     rall
    0.75
    ograph
    0.75
     Enterprises
    0.75
    Act Density 0.365%

    No Known Activations