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

    Neuronpedia

    INDEX
    Explanations

    phrases related to dates and social media handles

    oai_token-act-pair · gpt-3.5-turbo

    recurring data patterns and specific identifiers, particularly in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hert
    -0.89
     Hua
    -0.80
     Alc
    -0.78
     Slovakia
    -0.75
     Luxembourg
    -0.73
     Johnston
    -0.71
     Heaven
    -0.70
     Meridian
    -0.70
     Jill
    -0.69
     Henderson
    -0.69
    POSITIVE LOGITS
    4
    1.38
     4
    1.20
    ģ
    0.89
    5
    0.87
    four
    0.85
     Four
    0.83
    âĺħ
    0.82
    oto
    0.79
    Four
    0.78
     IV
    0.77
    Act Density 0.179%

    No Known Activations