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

    Neuronpedia

    INDEX
    Explanations

    apostrophes and contractions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .*")]
    -0.51
    ’
    -0.47
     metų
    -0.46
    oarece
    -0.46
    quakes
    -0.45
     AspNetCore
    -0.45
     
    -0.43
     lisäksi
    -0.43
     aikana
    -0.43
     ?>>
    -0.42
    POSITIVE LOGITS
    oredCriteria
    1.01
    parsedMessage
    0.94
     myſelf
    0.91
     Monfieur
    0.88
     juſt
    0.86
     pleaſure
    0.86
     Roskov
    0.85
     leaſt
    0.83
    ſelf
    0.81
     Reſ
    0.80
    Act Density 0.252%

    No Known Activations