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

    Neuronpedia

    INDEX
    Explanations

    phrases related to change and development

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    ength
    -0.73
     goodness
    -0.70
    erity
    -0.70
    ongyang
    -0.69
    inately
    -0.68
    bell
    -0.66
    inarily
    -0.65
    ramid
    -0.65
    idth
    -0.64
     Cran
    -0.64
    POSITIVE LOGITS
     extinct
    1.11
     entangled
    1.00
     accustomed
    0.94
     embroiled
    0.94
     obsolete
    0.94
     synonymous
    0.89
     acquainted
    0.88
     increasingly
    0.84
     indistinguishable
    0.83
     irrelevant
    0.81
    Act Density 0.513%

    No Known Activations