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

    Neuronpedia

    INDEX
    Explanations

    dates or days of the week

    oai_token-act-pair · gpt-3.5-turbo

    periods at the end of sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     challeng
    -0.72
     mosqu
    -0.69
     emanc
    -0.67
     pudding
    -0.66
     tyr
    -0.66
     predec
    -0.64
     metic
    -0.64
     defe
    -0.62
     prey
    -0.60
     nodd
    -0.60
    POSITIVE LOGITS
     Specifically
    0.95
     Their
    0.87
     They
    0.87
     Though
    0.86
     Its
    0.85
     Whether
    0.84
     Officials
    0.83
     However
    0.83
     According
    0.82
     But
    0.82
    Act Density 0.894%

    No Known Activations