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

    Neuronpedia

    INDEX
    Explanations

    dates expressed in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    specific mentions of the month of January

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ographed
    -0.73
    atcher
    -0.69
    estern
    -0.68
    adiator
    -0.66
    atics
    -0.64
    atic
    -0.63
    ioch
    -0.63
    inances
    -0.63
     VIDEOS
    -0.62
    Reviewer
    -0.62
    POSITIVE LOGITS
    esville
    0.89
     2019
    0.88
    vier
    0.84
    ruary
    0.83
    iversary
    0.81
    nard
    0.79
     2017
    0.79
     Madness
    0.78
     2015
    0.78
    ween
    0.77
    Act Density 0.019%

    No Known Activations