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

    Neuronpedia

    INDEX
    Explanations

    words indicating lack of significance or value

    oai_token-act-pair · gpt-3.5-turbo

    terms that express lack of value or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    asio
    -0.91
    arthy
    -0.79
    orthy
    -0.72
    orah
    -0.70
    deck
    -0.69
    insula
    -0.68
    alez
    -0.68
    arta
    -0.67
    bors
    -0.67
    ornia
    -0.66
    POSITIVE LOGITS
     waste
    0.95
     filler
    0.93
     anymore
    0.86
     distractions
    0.84
     garbage
    0.82
     except
    0.81
     gimm
    0.81
     unless
    0.80
     clutter
    0.79
     nonsense
    0.79
    Act Density 0.139%

    No Known Activations