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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating types or qualities, particularly those that express a sense of categorization or classification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases indicating a classification or description, particularly involving the word "kind" or "sort."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     totalité
    -0.55
     Aal
    -0.54
    )}+
    -0.52
     Eternal
    -0.52
     "]";
    -0.51
     cauſe
    -0.50
    !("{}",
    -0.49
    Eternal
    -0.49
    USART
    -0.49
     enqueue
    -0.48
    POSITIVE LOGITS
     sorta
    1.00
    Kinda
    0.87
     Kinda
    0.84
     kinda
    0.84
    kinda
    0.78
    Somewhat
    0.78
    tagext
    0.68
     рода
    0.68
    complexContent
    0.66
     Somewhat
    0.66
    Act Density 0.113%

    No Known Activations