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

    Neuronpedia

    INDEX
    Explanations

    phrases pertaining to film and television production details

    oai_token-act-pair · gpt-3.5-turbo

    sentences or statements that indicate the end of a thought or idea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mosqu
    -0.93
     concess
    -0.85
     depreciation
    -0.83
     mathemat
    -0.83
     worthless
    -0.81
     squats
    -0.80
     transact
    -0.80
     unman
    -0.79
     municip
    -0.79
     professions
    -0.78
    POSITIVE LOGITS
     Featuring
    1.51
     Fans
    1.44
     Released
    1.40
     Along
    1.35
     Though
    1.35
     Originally
    1.31
     Thankfully
    1.23
     Following
    1.22
     Sadly
    1.21
     Meanwhile
    1.21
    Act Density 0.295%

    No Known Activations