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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases or durations

    oai_token-act-pair · gpt-3.5-turbo

    phrases referring to future time frames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     1956
    -0.76
     Chosen
    -0.74
     1958
    -0.73
     1959
    -0.73
     Inher
    -0.70
     1986
    -0.70
     reinvent
    -0.70
    1989
    -0.69
     1989
    -0.69
     1955
    -0.69
    POSITIVE LOGITS
     afternoon
    1.21
     week
    1.19
     hours
    1.12
    Tuesday
    1.12
    Monday
    1.11
    Wednesday
    1.11
     morning
    1.10
     hour
    1.09
     Wednesday
    1.09
     Monday
    1.08
    Act Density 0.295%

    No Known Activations