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

    Neuronpedia

    INDEX
    Explanations

    numeric references to years or dates

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years and seasons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Skinner
    -0.72
    acci
    -0.72
     bip
    -0.64
     fret
    -0.61
     brut
    -0.58
     monop
    -0.57
     crate
    -0.57
    obbies
    -0.56
    vertisement
    -0.56
     cumbers
    -0.55
    POSITIVE LOGITS
    GV
    0.82
    âĢ¢âĢ¢
    0.80
    é¾į
    0.74
     edition
    0.71
    igation
    0.69
    å¹
    0.69
     editions
    0.67
    yond
    0.65
    GAN
    0.64
     Nicol
    0.63
    Act Density 0.197%

    No Known Activations