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

    Neuronpedia

    INDEX
    Explanations

    Proper nouns, particularly related to organizations and personnel

    oai_token-act-pair · gpt-3.5-turbo

    abbreviations or acronyms related to organizations or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aved
    -0.71
    aline
    -0.67
    ilts
    -0.66
    ages
    -0.61
     Faul
    -0.61
    ores
    -0.59
    eline
    -0.59
    ien
    -0.58
     WCS
    -0.57
     Dia
    -0.56
    POSITIVE LOGITS
    INESS
    0.86
    ODUCT
    0.86
    SHIP
    0.73
    WARE
    0.73
    IUM
    0.72
    WAYS
    0.69
    WAY
    0.69
    kefeller
    0.68
    udic
    0.67
    estern
    0.66
    Act Density 0.097%

    No Known Activations