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

    Neuronpedia

    INDEX
    Explanations

    phrases related to time and actions taking place over time

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing or repeated actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Apart
    -0.62
     Anyway
    -0.59
     Phar
    -0.58
     Canal
    -0.57
     Carth
    -0.57
     Nielsen
    -0.56
     panel
    -0.55
     Useful
    -0.55
     Palm
    -0.55
     Window
    -0.54
    POSITIVE LOGITS
     been
    1.35
     become
    1.21
    been
    1.13
     gotten
    1.10
     undergone
    1.01
     struggled
    1.00
     endeav
    0.97
     begun
    0.97
     risen
    0.96
     gone
    0.94
    Act Density 0.336%

    No Known Activations