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

    Neuronpedia

    INDEX
    Explanations

    scientific terms and concepts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of 'scientific' and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coni
    -0.70
    zik
    -0.68
    drops
    -0.66
    atra
    -0.64
    torn
    -0.62
    trap
    -0.62
    aders
    -0.62
    matched
    -0.61
    inho
    -0.61
    steps
    -0.61
    POSITIVE LOGITS
     literacy
    1.04
     fiction
    1.04
     curiosity
    0.91
     research
    0.89
     Fiction
    0.84
    ĨĴ
    0.84
     misconduct
    0.82
     illiter
    0.82
     literature
    0.81
     underpin
    0.81
    Act Density 0.036%

    No Known Activations