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

    Neuronpedia

    INDEX
    Explanations

    phrases related to laws, regulations, and historical events

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     RAND
    -0.18
     pseudonym
    -0.18
     DPR
    -0.18
     dot
    -0.17
     MIT
    -0.16
     unsigned
    -0.16
     undrafted
    -0.16
     improv
    -0.16
     DOT
    -0.16
     Telegram
    -0.16
    POSITIVE LOGITS
    ranean
    0.20
    ancers
    0.20
    ittees
    0.19
    agascar
    0.19
    ippi
    0.19
    aceae
    0.18
    groups
    0.18
    assies
    0.18
    ividual
    0.18
    ependence
    0.18
    Act Density 0.001%

    No Known Activations