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

    Neuronpedia

    INDEX
    Explanations

    URL references

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    ScopeManager
    -0.65
    }}^{(
    -0.50
    Datuak
    -0.47
    serviceWorker
    -0.47
    Portale
    -0.44
     rendu
    -0.44
    нні
    -0.44
    รา
    -0.43
     särsk
    -0.43
    })`
    -0.43
    POSITIVE LOGITS
     Jefus
    0.92
     للمعارف
    0.88
     pleaſure
    0.84
     Majefty
    0.77
     myſelf
    0.74
    RegressionTest
    0.73
     purpoſe
    0.73
     houſe
    0.69
     Monfieur
    0.68
     ſtate
    0.67
    Act Density 0.001%

    No Known Activations