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

    Neuronpedia

    INDEX
    Explanations

    sentences ending with periods

    oai_token-act-pair · gpt-3.5-turbo

    sentences that conclude with a period

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     brill
    -0.90
     nodd
    -0.79
     glim
    -0.73
     mushroom
    -0.72
     rubbish
    -0.72
     silly
    -0.71
     chip
    -0.70
     antique
    -0.69
     darts
    -0.68
     bom
    -0.68
    POSITIVE LOGITS
    âĢ
    1.83
     âĢ
    1.55
     Additionally
    1.46
     Furthermore
    1.40
     Moreover
    1.34
    âĢł
    1.33
     Accordingly
    1.30
    âģ
    1.29
     Specifically
    1.27
     Therefore
    1.26
    Act Density 0.461%

    No Known Activations