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

    Neuronpedia

    INDEX
    Explanations

    dates and periods of time

    oai_token-act-pair · gpt-3.5-turbo

    references to time durations and intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    YES
    -0.64
     unfocusedRange
    -0.62
    yes
    -0.60
    Merit
    -0.60
    Exactly
    -0.59
    UCT
    -0.58
    oux
    -0.57
    anos
    -0.55
     transporter
    -0.55
     stakes
    -0.55
    POSITIVE LOGITS
     ago
    1.01
    pring
    0.89
    hift
    0.86
     Ago
    0.82
    ilk
    0.70
     abroad
    0.67
    rued
    0.63
    hips
    0.63
    ween
    0.63
    */(
    0.63
    Act Density 0.088%

    No Known Activations