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

    Neuronpedia

    INDEX
    Explanations

    verbs in the past participle form

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    eers
    -0.75
    lich
    -0.73
    tions
    -0.66
    ulo
    -0.65
    tor
    -0.61
    lag
    -0.60
    vine
    -0.58
     insurg
    -0.58
    cape
    -0.58
     icing
    -0.58
    POSITIVE LOGITS
     aback
    1.43
    aways
    1.29
     advantage
    1.01
     care
    0.99
     away
    0.92
    away
    0.88
     cogn
    0.86
     hostage
    0.81
    OVER
    0.81
    offs
    0.80
    Act Density 0.058%

    No Known Activations