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

    Neuronpedia

    INDEX
    Explanations

    people's names and titles, especially in news articles and reports

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    yond
    -0.56
    $.
    -0.56
     eternity
    -0.52
    Lear
    -0.51
    access
    -0.50
    soType
    -0.48
    ãĥ¬
    -0.47
    ãĥĥãĤ¯
    -0.47
    dden
    -0.47
    -+
    -0.46
    POSITIVE LOGITS
     meanwhile
    1.11
     has
    1.03
     took
    1.01
     gave
    1.01
     weighs
    0.99
     consists
    0.99
     consisted
    0.97
     reacted
    0.96
     went
    0.96
     recognizes
    0.95
    Act Density 1.204%

    No Known Activations