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

    Neuronpedia

    INDEX
    Explanations

    descriptions or explanations within text

    oai_token-act-pair · gpt-3.5-turbo

    instances of descriptions or elaborations of events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    osponsors
    -0.70
    onga
    -0.67
     Governors
    -0.61
    allery
    -0.60
     Events
    -0.60
     Releases
    -0.60
     Cases
    -0.60
    inances
    -0.59
     Posts
    -0.59
     Facilities
    -0.58
    POSITIVE LOGITS
     reminiscent
    1.08
     laced
    1.03
     resembling
    1.02
     explaining
    1.01
     headlined
    0.98
     detailing
    0.95
     outlining
    0.94
     illustrating
    0.92
     denouncing
    0.92
     describing
    0.91
    Act Density 0.394%

    No Known Activations