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

    Neuronpedia

    INDEX
    Explanations

    information related to achievements, awards, and leadership positions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to achievements and significance in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Anyway
    -0.78
     Anyway
    -0.78
     Nope
    -0.76
    quickShipAvailable
    -0.71
    Someone
    -0.69
     Someone
    -0.69
     nicer
    -0.68
     somebody
    -0.68
     Somebody
    -0.66
    Alternatively
    -0.65
    POSITIVE LOGITS
     spanning
    1.15
     throughout
    1.07
     encomp
    1.05
     ranging
    1.05
     including
    1.03
     consisting
    1.02
     utilizing
    1.02
     unmatched
    0.99
     comprising
    0.98
     unparalleled
    0.96
    Act Density 0.793%

    No Known Activations