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

    Neuronpedia

    INDEX
    Explanations

    variations of the verb "to be" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ſtate
    -0.79
     houſe
    -0.79
     ſever
    -0.75
     ſeveral
    -0.73
     whoſe
    -0.73
     themſelves
    -0.70
     Houſe
    -0.69
     Diſ
    -0.69
     Majefty
    -0.68
     Reſ
    -0.67
    POSITIVE LOGITS
     that
    0.96
    :
    0.70
     bahwa
    0.68
     to
    0.68
    invokeLater
    0.61
    ว่า
    0.60
     ότι
    0.57
    的就是
    0.56
     kwamba
    0.55
    在于
    0.54
    Act Density 0.345%

    No Known Activations