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

    Neuronpedia

    INDEX
    Explanations

    phrases related to the concept of importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    references to various important or noteworthy items or topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    geon
    -0.74
    ICO
    -0.67
    geons
    -0.66
    083
    -0.66
    iary
    -0.65
     Examination
    -0.65
    oir
    -0.64
     largeDownload
    -0.63
    awar
    -0.63
    bern
    -0.62
    POSITIVE LOGITS
     happen
    1.21
     happening
    1.20
     happened
    1.10
     happens
    1.00
     happ
    0.94
     Happ
    0.83
     pertaining
    0.79
     transpired
    0.78
     occurring
    0.75
    uits
    0.75
    Act Density 0.059%

    No Known Activations