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

    Neuronpedia

    INDEX
    Explanations

    time-related expressions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to time durations and measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enburg
    -0.57
     Franch
    -0.54
     infl
    -0.52
    kef
    -0.52
     Haram
    -0.51
     Thornton
    -0.51
     visually
    -0.49
     mechanically
    -0.47
     physically
    -0.47
     advoc
    -0.46
    POSITIVE LOGITS
     ago
    1.22
     Ago
    1.08
     elapsed
    0.70
    ago
    0.70
     olds
    0.66
     Views
    0.64
    ynthesis
    0.62
     msec
    0.60
    maxwell
    0.60
     old
    0.59
    Act Density 0.077%

    No Known Activations