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

    Neuronpedia

    INDEX
    Explanations

    dates in the format of month/day/year

    oai_token-act-pair · gpt-3.5-turbo

    elements related to date and version formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inyl
    -0.78
     expansion
    -0.67
     expansions
    -0.65
     indifference
    -0.64
    aldi
    -0.62
     adversely
    -0.62
     Improvement
    -0.62
    nia
    -0.61
     arteries
    -0.60
     srfAttach
    -0.59
    POSITIVE LOGITS
    07
    0.91
    08
    0.91
    09
    0.87
    06
    0.85
    04
    0.84
    05
    0.82
    02
    0.80
    2004
    0.80
    03
    0.79
    01
    0.78
    Act Density 0.064%

    No Known Activations