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

    Neuronpedia

    INDEX
    Explanations

    repeated characters or symbols in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     vuotta
    -0.46
    Vay
    -0.44
     cuchar
    -0.44
     tarko
    -0.42
     blive
    -0.42
    couvrir
    -0.39
     couverts
    -0.39
     término
    -0.38
     lí
    -0.38
     bumbu
    -0.38
    POSITIVE LOGITS
    ########.
    1.14
    lamabad
    1.00
     Pakistan
    0.99
     Pakistani
    0.94
    Pakistan
    0.89
     Lahore
    0.85
     pakistan
    0.82
     Islamabad
    0.79
     Cæsar
    0.78
     ARY
    0.78
    Act Density 0.050%

    No Known Activations