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

    Neuronpedia

    INDEX
    Explanations

    dates and events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Charlie
    -0.83
    uta
    -0.81
     Bahá
    -0.81
     Ao
    -0.79
    oat
    -0.78
     Mata
    -0.77
     Aval
    -0.76
    dos
    -0.75
     Bat
    -0.75
     Bean
    -0.72
    POSITIVE LOGITS
    iri
    0.97
    2013
    0.95
    iris
    0.95
    irs
    0.90
    13
    0.89
     2013
    0.88
     1913
    0.85
    313
    0.85
    rist
    0.83
     77
    0.83
    Act Density 0.376%

    No Known Activations