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

    Neuronpedia

    INDEX
    Explanations

    dates or numbers in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific numerical or coded data references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    itory
    -0.73
    ãĥ¤
    -0.69
     Beir
    -0.69
    itionally
    -0.69
    acements
    -0.67
    arians
    -0.66
    ipation
    -0.65
    rade
    -0.64
    irrel
    -0.64
     EntityItem
    -0.64
    POSITIVE LOGITS
    teenth
    1.43
    teen
    1.37
    th
    0.96
    34
    0.89
    36
    0.89
     months
    0.88
    012
    0.87
    04
    0.86
    03
    0.85
    31
    0.85
    Act Density 0.096%

    No Known Activations