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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions indicating a future event

    oai_token-act-pair · gpt-3.5-turbo

    references to the passage of time marked by the word "later."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hab
    -0.71
    owship
    -0.67
    rament
    -0.66
    lua
    -0.60
    VALUE
    -0.58
     membr
    -0.57
     TOD
    -0.57
     unpop
    -0.56
     Scal
    -0.56
    olan
    -0.56
    POSITIVE LOGITS
    forth
    0.73
     Pats
    0.71
     than
    0.70
     when
    0.66
    ettings
    0.63
     graduation
    0.63
     succumbed
    0.63
    irement
    0.62
     regretted
    0.61
    aneously
    0.61
    Act Density 0.042%

    No Known Activations