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

    Neuronpedia

    INDEX
    Explanations

    dates in specific formats

    oai_token-act-pair · gpt-3.5-turbo

    references to dates and financial values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTA
    -0.95
     Ott
    -0.91
     KH
    -0.85
     Panc
    -0.82
     Tak
    -0.81
    ota
    -0.80
     ak
    -0.79
     Tav
    -0.75
     Mong
    -0.74
     Titus
    -0.73
    POSITIVE LOGITS
    29
    1.53
     29
    1.43
    30
    1.33
    28
    1.30
     30
    1.26
    31
    1.25
     28
    1.23
     31
    1.14
    27
    1.11
    297
    1.08
    Act Density 0.268%

    No Known Activations