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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal experiences and enjoyment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    IsContent
    -0.79
    脚注の使い方
    -0.63
    AndEndTag
    -0.62
    jsdelivr
    -0.54
    FTFY
    -0.51
    elemField
    -0.50
     Arrivals
    -0.50
    ViewImports
    -0.50
    ]--;
    -0.50
    worse
    -0.50
    POSITIVE LOGITS
     Highly
    1.30
    Highly
    1.17
     highly
    1.08
    highly
    1.05
     Strongly
    0.98
     Would
    0.93
     Recommended
    0.93
     Recommend
    0.91
     would
    0.89
    Strongly
    0.89
    Act Density 0.085%

    No Known Activations