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

    Neuronpedia

    INDEX
    Explanations

    the presence of specific structural components in the text, likely related to mathematical or scientific symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſever
    -0.84
     ſeveral
    -0.84
     themſelves
    -0.83
     Monfieur
    -0.83
    CloseOperation
    -0.82
     viſ
    -0.79
     verte
    -0.78
     Alcal
    -0.77
     Pey
    -0.75
     dieß
    -0.75
    POSITIVE LOGITS
     S
    2.18
     s
    1.67
    S
    1.66
     getS
    1.57
    getS
    1.39
    cS
    1.36
    pS
    1.16
     Ss
    1.13
    mS
    1.13
     س
    1.13
    Act Density 0.209%

    No Known Activations