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

    Neuronpedia

    INDEX
    Explanations

    time-related phrases

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    SG
    -0.58
    YING
    -0.58
    Subject
    -0.58
     Digest
    -0.57
    Rap
    -0.57
    idding
    -0.55
     weap
    -0.55
    etting
    -0.54
    Behind
    -0.54
     Useful
    -0.54
    POSITIVE LOGITS
    been
    1.67
     been
    1.54
     undergone
    1.31
     gotten
    1.26
     Been
    1.13
     fallen
    1.09
     gone
    1.07
     begun
    1.06
     become
    1.06
     risen
    1.00
    Act Density 0.673%

    No Known Activations