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

    Neuronpedia

    INDEX
    Explanations

    sections of text indicated by special characters

    oai_token-act-pair · gpt-3.5-turbo

    instances of text formatted as notes or excerpts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     confir
    -0.89
     tram
    -0.79
     probation
    -0.77
     cone
    -0.72
     capability
    -0.72
     county
    -0.72
     bloc
    -0.71
     fiat
    -0.70
     placement
    -0.70
     mandate
    -0.70
    POSITIVE LOGITS
    Introduction
    1.68
    Enlarge
    1.43
    Reviewed
    1.40
    Overview
    1.39
    THE
    1.37
    Born
    1.33
    Written
    1.33
    Advertisements
    1.32
    Throughout
    1.31
    Chapter
    1.31
    Act Density 0.505%

    No Known Activations