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

    Neuronpedia

    INDEX
    Explanations

    Twitter handles with associated dates

    oai_token-act-pair · gpt-3.5-turbo

    mentions of dates and associated usernames

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    merga
    -0.74
    hiba
    -0.68
    bas
    -0.67
    tri
    -0.67
    (-
    -0.66
    relative
    -0.66
    agar
    -0.66
    CON
    -0.66
    dri
    -0.66
    arg
    -0.65
    POSITIVE LOGITS
     September
    1.04
     July
    0.98
     October
    0.97
     August
    0.96
     June
    0.94
     November
    0.92
     April
    0.89
     February
    0.88
     December
    0.88
     January
    0.86
    Act Density 0.031%

    No Known Activations