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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences separated by dots

    oai_token-act-pair · gpt-3.5-turbo

    numerical data, particularly related to software versioning and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     affili
    -0.72
     embell
    -0.66
     attendance
    -0.65
     likeness
    -0.65
     penned
    -0.65
     gull
    -0.65
     frequ
    -0.64
     chant
    -0.64
     ris
    -0.64
     sit
    -0.63
    POSITIVE LOGITS
    0
    1.31
    dylib
    1.24
    jar
    1.20
    gz
    1.18
    tar
    1.18
    1
    1.14
    rc
    1.12
    20439
    1.11
    yip
    1.10
    7601
    1.10
    Act Density 0.042%

    No Known Activations