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

    Neuronpedia

    INDEX
    Explanations

    years or dates mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years and significant time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Joined
    -0.73
    Eva
    -0.66
    Sov
    -0.65
    UTF
    -0.64
     Loch
    -0.62
    atem
    -0.61
    utf
    -0.60
     Pwr
    -0.60
    Allows
    -0.59
    yrights
    -0.59
    POSITIVE LOGITS
     progresses
    0.82
     edition
    0.81
     onwards
    0.80
     anniversary
    0.79
    eve
    0.78
    iversary
    0.76
     ain
    0.74
     festivities
    0.74
     Anniversary
    0.73
    date
    0.73
    Act Density 0.399%

    No Known Activations