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

    Neuronpedia

    INDEX
    Explanations

    dates and time periods

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating time that reference recent events or statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    bart
    -0.84
    abus
    -0.75
    anie
    -0.74
    potion
    -0.73
    bear
    -0.71
    BILITIES
    -0.70
    aves
    -0.68
    pta
    -0.66
    isons
    -0.66
    obic
    -0.64
    POSITIVE LOGITS
     inception
    1.14
    rely
    1.14
     2009
    0.94
     1978
    0.93
     2005
    0.93
     2006
    0.92
     1950
    0.92
     1998
    0.92
     1999
    0.92
     2010
    0.92
    Act Density 0.050%

    No Known Activations