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-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     unwarran
    -1.86
     impractica
    -1.82
     increa
    -1.74
     unlaw
    -1.71
     encomp
    -1.69
     desir
    -1.68
     swarovski
    -1.65
     disagre
    -1.64
     purcha
    -1.60
     intersper
    -1.60
    POSITIVE LOGITS
     October
    0.71
     June
    0.70
     February
    0.70
     September
    0.69
     November
    0.69
     December
    0.68
     April
    0.67
     July
    0.66
     January
    0.65
     August
    0.65
    Act Density 0.212%

    No Known Activations