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

    Neuronpedia

    INDEX
    Explanations

    phrases describing the current state or progress of various projects or developments

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     alike
    -0.74
    ignty
    -0.73
     summed
    -0.68
    gdala
    -0.67
    aturday
    -0.67
    »Ĵ
    -0.67
    MpServer
    -0.64
    lez
    -0.62
    nces
    -0.60
    deen
    -0.60
    POSITIVE LOGITS
     infancy
    1.16
     stages
    1.13
     preliminary
    1.09
     development
    1.07
     developmental
    1.06
     nascent
    1.02
     explor
    1.02
     progress
    1.01
     gestation
    0.99
     prototype
    0.98
    Act Density 0.205%

    No Known Activations