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

    Neuronpedia

    INDEX
    Explanations

    references to privacy or account-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſta
    -0.91
    ſelf
    -0.88
     myſelf
    -0.87
     ſtate
    -0.87
     faſt
    -0.87
    ſelves
    -0.84
     Majefty
    -0.82
     houſe
    -0.82
     ſche
    -0.82
     Jefus
    -0.80
    POSITIVE LOGITS
     за
    0.93
     при
    0.91
     по
    0.90
     под
    0.89
     от
    0.89
     с
    0.79
     za
    0.72
     przy
    0.70
     из
    0.69
     над
    0.69
    Act Density 0.103%

    No Known Activations