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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names and titles

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ing
    -1.68
    ING
    -1.14
    ––––
    -1.03
    ی
    -0.91
    ة
    -0.84
    ים
    -0.81
    .’
    -0.81
     Valladolid
    -0.75
    ー
    -0.74
     Parke
    -0.72
    POSITIVE LOGITS
     Koss
    1.02
     restTemplate
    0.87
     Shepard
    0.84
     beginnetje
    0.84
     Fenne
    0.80
    chrän
    0.79
     RestTemplate
    0.79
    érêt
    0.78
    lehem
    0.77
     chilen
    0.77
    Act Density 0.347%

    No Known Activations