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

    Neuronpedia

    INDEX
    Explanations

    dates in the format of month followed by day and year

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Somali
    -0.80
     stim
    -0.78
     Mog
    -0.77
     Sv
    -0.77
    tm
    -0.75
     Harriet
    -0.71
     Stim
    -0.69
    uchin
    -0.68
     Mish
    -0.68
    izo
    -0.67
    POSITIVE LOGITS
    21
    0.93
    221
    0.92
     221
    0.90
     21
    0.90
     22
    0.85
    æĸ¹
    0.84
    isons
    0.80
     71
    0.78
    71
    0.78
    222
    0.78
    Act Density 0.355%

    No Known Activations