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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or being taken

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "taken" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eers
    -0.71
    ichick
    -0.68
    glers
    -0.67
    lich
    -0.63
    tions
    -0.60
    gian
    -0.60
    vine
    -0.56
    itte
    -0.55
     icing
    -0.55
     Trees
    -0.55
    POSITIVE LOGITS
     aback
    1.59
    aways
    1.12
     advantage
    1.06
     care
    0.97
     seriously
    0.89
     hostage
    0.88
     orally
    0.82
    oqu
    0.78
     Seriously
    0.77
     captive
    0.77
    Act Density 0.034%

    No Known Activations