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

    Neuronpedia

    INDEX
    Explanations

    mathematical terms and expressions involving variables and constants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſever
    -0.92
     themſelves
    -0.91
     ſeveral
    -0.88
     faſt
    -0.86
     myſelf
    -0.85
     pegat
    -0.83
     ſhall
    -0.82
     Theſe
    -0.81
     viſ
    -0.81
     dieß
    -0.81
    POSITIVE LOGITS
     S
    1.69
     s
    1.56
     getS
    1.38
    S
    1.31
    getS
    1.23
    cS
    1.16
     P
    1.05
    pS
    1.03
     d
    1.02
     M
    1.00
    Act Density 0.213%

    No Known Activations