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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the interpretation and meaning of words and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     externi
    -0.79
    ьаж
    -0.69
    HasForeignKey
    -0.66
    RTLU
    -0.64
    تقاوى
    -0.64
    Rhestr
    -0.63
     nakalista
    -0.63
    IntoConstraints
    -0.61
    GEBURTSDATUM
    -0.61
     Италијани
    -0.60
    POSITIVE LOGITS
     meaning
    2.62
     meanings
    2.34
    meaning
    2.10
     Meaning
    2.05
     interpretation
    1.99
    Meaning
    1.98
     significado
    1.80
     Interpretation
    1.74
     interpretations
    1.69
    interpretation
    1.67
    Act Density 0.433%

    No Known Activations