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

    Neuronpedia

    INDEX
    Explanations

    mentions of vintage items

    oai_token-act-pair · gpt-3.5-turbo

    references to vintage or antique items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    olulu
    -0.89
    lee
    -0.78
    hra
    -0.73
    letal
    -0.72
    hips
    -0.72
    ermanent
    -0.71
    ulty
    -0.70
    ophers
    -0.69
    avanaugh
    -0.69
    iant
    -0.68
    POSITIVE LOGITS
    intage
    0.85
     fashioned
    0.74
    vre
    0.70
     classics
    0.68
     vintage
    0.67
     Classic
    0.67
     Revival
    0.66
     Century
    0.64
     Classics
    0.63
    isable
    0.63
    Act Density 0.020%

    No Known Activations