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

    Neuronpedia

    INDEX
    Explanations

    references to relational phrases and communities within legal or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    AddHtmlAttribute
    -0.49
     from
    -0.49
     препратки
    -0.46
     صوتيه
    -0.46
    abestanden
    -0.46
     dazu
    -0.44
    地看着
    -0.44
     @"/
    -0.42
     subjecting
    -0.40
    TagMode
    -0.40
    POSITIVE LOGITS
    🔕
    0.56
     يتيمه
    0.50
    ariConfig
    0.46
     derives
    0.44
     korzyst
    0.43
     derived
    0.42
     wynika
    0.41
    kwij
    0.40
    "}")
    0.38
    derived
    0.38
    Act Density 0.250%

    No Known Activations