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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, specifically names of individuals, likely related to news or entertainment

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    xual
    -0.94
    ensical
    -0.93
    acebook
    -0.79
     glim
    -0.78
    yrinth
    -0.76
    ibilities
    -0.75
     disadvant
    -0.75
    rival
    -0.74
    nces
    -0.74
    joined
    -0.73
    POSITIVE LOGITS
     Slater
    0.89
    Anne
    0.89
     Sue
    0.83
    town
    0.81
    eland
    0.79
     Clarkson
    0.75
     Loll
    0.73
    terson
    0.72
    edge
    0.71
    sey
    0.70
    Act Density 8.291%

    No Known Activations