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

    Neuronpedia

    INDEX
    Explanations

    terms related to health and medical metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Parcelize
    -0.57
    <bos>
    -0.55
    '];?>
    -0.52
    elsen
    -0.50
    )),
    -0.50
     a
    -0.49
    }{*}{
    -0.49
    ddha
    -0.48
     ple
    -0.48
    。』
    -0.48
    POSITIVE LOGITS
     ujednoznacz
    0.68
     kasarigan
    0.68
    Nationalité
    0.67
     betweenstory
    0.63
     itſelf
    0.63
     myſelf
    0.61
     يتيمه
    0.59
     etc
    0.56
     iconTwitter
    0.55
     Monfieur
    0.55
    Act Density 0.678%

    No Known Activations