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

    Neuronpedia

    INDEX
    Explanations

    structured hierarchical data or markup

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     myſelf
    -1.15
     Majefty
    -1.13
     himſelf
    -1.09
     itſelf
    -1.05
     Houſe
    -1.05
     houſe
    -0.97
     Shakspeare
    -0.97
     themſelves
    -0.96
     photolibrary
    -0.96
     againſt
    -0.95
    POSITIVE LOGITS
     
    0.59
     brand
    0.45
    DrawerLayout
    0.45
    ########.
    0.45
     most
    0.39
    wechs
    0.39
     And
    0.38
    上下
    0.38
     pro
    0.38
     they
    0.38
    Act Density 0.003%

    No Known Activations