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

    Neuronpedia

    INDEX
    Explanations

    phrases related to retro aesthetics

    oai_token-act-pair · gpt-3.5-turbo

    references to retro themes or styles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    holder
    -0.73
    gow
    -0.73
    avanaugh
    -0.72
    gans
    -0.70
    RAW
    -0.66
    illary
    -0.65
    FUL
    -0.65
    holders
    -0.65
     Marketable
    -0.65
     Parenthood
    -0.65
    POSITIVE LOGITS
    actively
    1.44
    active
    1.21
    spective
    1.19
    fitted
    1.04
    gradation
    1.01
     retro
    0.97
    spection
    0.96
    grade
    0.94
    fit
    0.94
    spect
    0.92
    Act Density 0.018%

    No Known Activations