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

    Neuronpedia

    INDEX
    Explanations

    adverbs indicating time (e.g., "just", "now", "often")

    oai_token-act-pair · gpt-3.5-turbo

    adverbs indicating time or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     successor
    -0.68
     Mats
    -0.66
    Subject
    -0.64
     chants
    -0.60
     omn
    -0.59
    ++++
    -0.57
     jokes
    -0.55
     Subject
    -0.54
     prone
    -0.54
    hander
    -0.53
    POSITIVE LOGITS
    been
    1.49
     been
    1.15
     undergone
    0.99
     Been
    0.92
    gone
    0.91
     fallen
    0.86
    gotten
    0.86
     gotten
    0.85
     become
    0.83
     gone
    0.82
    Act Density 0.169%

    No Known Activations