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

    Neuronpedia

    INDEX
    Explanations

    words related to changes or developments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "have" and its variations indicating possession or existence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Penal
    -0.70
     territ
    -0.67
     Commun
    -0.66
     recalls
    -0.65
     Deliver
    -0.63
     hears
    -0.62
     observing
    -0.61
     possessing
    -0.60
     conceive
    -0.59
     juggling
    -0.59
    POSITIVE LOGITS
     risen
    1.40
     been
    1.39
     plummeted
    1.30
     become
    1.21
     soared
    1.20
     deteriorated
    1.19
     fallen
    1.19
    been
    1.17
     dwind
    1.16
     begun
    1.15
    Act Density 0.147%

    No Known Activations