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

    Neuronpedia

    INDEX
    Explanations

    pronouns that indicate subjects or objects in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     idéia
    -0.63
     sauvages
    -0.62
    cta
    -0.57
     hjär
    -0.56
    <h4>
    -0.56
     ajan
    -0.56
     économies
    -0.56
     vontade
    -0.56
    hamm
    -0.54
     attiv
    -0.54
    POSITIVE LOGITS
     ahogy
    0.87
    WriteBarrier
    0.76
     patr
    0.74
    AutoScaleMode
    0.74
     ExecuteAsync
    0.73
    readAs
    0.72
    AsUp
    0.72
    HomeAsUpEnabled
    0.69
     Moraes
    0.68
     Astrid
    0.67
    Act Density 0.070%

    No Known Activations