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

    Neuronpedia

    INDEX
    Explanations

    legal and official terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or governmental processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     nonetheless
    -0.54
     moreover
    -0.52
     rejoice
    -0.52
     kidding
    -0.52
     patiently
    -0.51
     rightly
    -0.51
     boldly
    -0.51
     instinctively
    -0.50
    fortunately
    -0.50
    âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦âĢ¦
    -0.49
    POSITIVE LOGITS
    interstitial
    0.65
     respective
    0.58
     fame
    0.57
     Antiqu
    0.53
     Portug
    0.51
     mosqu
    0.49
    tnc
    0.49
     Liberation
    0.48
     Gw
    0.48
     township
    0.47
    Act Density 1.218%

    No Known Activations