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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions, specifically references to events occurring 'later'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "later" indicating the passage of time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hab
    -0.64
    rament
    -0.63
    owship
    -0.61
    kind
    -0.59
     unpop
    -0.57
     juices
    -0.57
    ãĥ«
    -0.57
    gpu
    -0.56
    VALUE
    -0.55
    Sund
    -0.55
    POSITIVE LOGITS
    forth
    0.75
     onwards
    0.75
    .............
    0.71
    ,
    0.67
     than
    0.67
     succumbed
    0.65
     when
    0.64
    ettings
    0.62
    .,
    0.61
     regretted
    0.61
    Act Density 0.043%

    No Known Activations