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

    Neuronpedia

    INDEX
    Explanations

    PM (night time) references

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the abbreviation "PM" indicating time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ³ãĤ¸
    -0.86
    tyard
    -0.81
    ãĤ¢ãĥ«
    -0.81
    ãĥ¼ãĤ¯
    -0.80
     Norn
    -0.78
    leans
    -0.77
    kefeller
    -0.75
    ãĤ¨ãĥ«
    -0.74
    wikipedia
    -0.74
    come
    -0.73
    POSITIVE LOGITS
     PM
    1.15
    PM
    1.09
    essage
    0.95
     pm
    0.84
     EST
    0.83
     EDT
    0.81
     Modi
    0.80
    MER
    0.77
    PD
    0.76
    MAR
    0.74
    Act Density 0.008%

    No Known Activations