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

    Neuronpedia

    INDEX
    Explanations

    phrases related to leisure activities and hobbies

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
    elfth
    -0.65
    displayText
    -0.64
    2020
    -0.62
    ridor
    -0.61
     2020
    -0.60
     reinstated
    -0.58
     2022
    -0.58
     mandate
    -0.57
    ordable
    -0.53
     cornerstone
    -0.53
    POSITIVE LOGITS
    pmwiki
    1.00
     occasionally
    0.83
     kinda
    0.80
     quirks
    0.78
     assorted
    0.78
    Anyway
    0.76
     weird
    0.76
     occasional
    0.75
     annoy
    0.75
     Occasionally
    0.74
    Act Density 1.317%

    No Known Activations