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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to specific locations or historical figures

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ictions
    -0.82
     crate
    -0.76
    cms
    -0.73
     clutch
    -0.72
     chorus
    -0.71
    iction
    -0.69
    ilogy
    -0.69
     sentence
    -0.69
     package
    -0.68
    eared
    -0.67
    POSITIVE LOGITS
     Augusta
    1.03
     Theodore
    0.93
     Helena
    0.92
     Ferdinand
    0.91
     Herod
    0.89
     Hu
    0.89
     Sina
    0.88
     George
    0.88
     Kat
    0.88
     Sof
    0.88
    Act Density 0.153%

    No Known Activations