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

    Neuronpedia

    INDEX
    Explanations

    expressions related to medical evaluations and outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mergeFrom
    -0.94
     betweenstory
    -0.92
     ComVisible
    -0.83
    ########.
    -0.82
     Monfieur
    -0.81
    脚注の使い方
    -0.78
     houſe
    -0.77
    uxxxx
    -0.77
    Tikang
    -0.76
    Tembelea
    -0.76
    POSITIVE LOGITS
     idea
    0.49
     chắc
    0.48
     nổi
    0.47
    ówn
    0.47
    рун
    0.47
     billede
    0.43
     blij
    0.43
     possibilidade
    0.42
     fø
    0.42
     निर्
    0.42
    Act Density 1.477%

    No Known Activations