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

    Neuronpedia

    INDEX
    Explanations

    references to programming instructions or troubleshooting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    irit
    -0.16
     pornôs
    -0.16
    اÙĨÙĪÙĨ
    -0.15
    pNet
    -0.15
    artz
    -0.15
     Erotik
    -0.14
    uerdo
    -0.14
    acci
    -0.14
    valu
    -0.14
    stell
    -0.14
    POSITIVE LOGITS
     é
    0.31
     tem
    0.30
     possui
    0.26
     age
    0.26
     usa
    0.25
     fica
    0.25
     dá
    0.25
     segue
    0.25
     serve
    0.25
     está
    0.24
    Act Density 0.017%

    No Known Activations