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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    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
     induct
    -0.82
     affili
    -0.81
     literacy
    -0.73
     patron
    -0.70
     sexism
    -0.70
     grounding
    -0.69
     reception
    -0.69
     recreational
    -0.68
     maternity
    -0.68
     bonuses
    -0.68
    POSITIVE LOGITS
    txt
    1.73
    png
    1.64
    exe
    1.62
    html
    1.62
    jpg
    1.60
    htm
    1.57
    xml
    1.54
    zip
    1.54
    dll
    1.48
    php
    1.46
    Act Density 0.099%

    No Known Activations