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

    Neuronpedia

    INDEX
    Explanations

    references to specific fields of study or expertise

    oai_token-act-pair · gpt-3.5-turbo

    references to specific academic or professional fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĹĺ
    -0.85
     nodd
    -0.72
    gement
    -0.69
    ividual
    -0.69
    bian
    -0.68
    gements
    -0.66
     vest
    -0.65
     recip
    -0.64
    borgh
    -0.64
     suspic
    -0.62
    POSITIVE LOGITS
    fields
    0.87
    naires
    0.83
    places
    0.83
    sheet
    0.83
    ftime
    0.80
    lights
    0.80
    field
    0.79
    side
    0.77
    FIELD
    0.75
    finder
    0.75
    Act Density 0.019%

    No Known Activations