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

    Neuronpedia

    INDEX
    Explanations

    references to celestial bodies

    oai_token-act-pair · gpt-3.5-turbo

    references to spatial or physical locations and boundaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asus
    -0.80
    CHAR
    -0.68
    DCS
    -0.68
    ¸
    -0.66
    nce
    -0.66
    \\\\\\\\
    -0.65
    zo
    -0.65
    ALLY
    -0.64
    Statement
    -0.62
    EG
    -0.62
    POSITIVE LOGITS
    creen
    1.04
    mith
    1.00
    cape
    0.99
    pring
    0.99
    ystem
    0.96
    chool
    0.95
    heet
    0.94
    paces
    0.94
    itters
    0.89
    pace
    0.88
    Act Density 0.238%

    No Known Activations