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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names of people and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IntoConstraints
    -0.71
    原始内容存档于
    -0.57
    mergeFrom
    -0.56
     ‘
    -0.54
    protoc
    -0.53
    Portail
    -0.53
    AddTagHelper
    -0.52
     “
    -0.51
     насељу
    -0.50
    __*/
    -0.50
    POSITIVE LOGITS
     nahilalakip
    1.00
     Majefty
    0.75
     myſelf
    0.69
     quæ
    0.65
     للاسماء
    0.63
    wdriver
    0.63
     replied
    0.63
     LoggerFactory
    0.62
     chofe
    0.62
     Monfieur
    0.61
    Act Density 0.191%

    No Known Activations