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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal stories or testimonies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cosponsors
    -0.80
    doi
    -0.71
    rencies
    -0.66
    irlf
    -0.65
    advertisement
    -0.64
     NETWORK
    -0.61
     Mehran
    -0.61
    digit
    -0.59
    ©¶æ
    -0.59
     overpowered
    -0.58
    POSITIVE LOGITS
     Matthews
    0.64
     tigers
    0.60
     ILCS
    0.60
    uity
    0.60
    ette
    0.60
    ello
    0.60
    udeau
    0.60
     Veterinary
    0.58
    enegger
    0.58
     Grill
    0.58
    Act Density 0.176%

    No Known Activations