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

    Neuronpedia

    INDEX
    Explanations

    references to mathematical equations and their components

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     g
    -0.55
     
    -0.53
     l
    -0.53
    ,
    -0.52
     .
    -0.51
     f
    -0.49
     I
    -0.49
     Sta
    -0.48
     la
    -0.47
     at
    -0.47
    POSITIVE LOGITS
     itſelf
    1.16
    Personendaten
    1.10
     Monfieur
    1.09
     Diſ
    1.09
     Reſ
    1.09
     Houſe
    1.06
    RenderAtEndOf
    1.05
     &___
    1.05
     reaſon
    1.05
     Anſ
    1.05
    Act Density 0.565%

    No Known Activations