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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating value judgment or importance

    oai_token-act-pair · gpt-3.5-turbo

    expressions emphasizing the importance or value of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Oops
    -0.66
     Vehicles
    -0.66
    gdala
    -0.64
     Nou
    -0.64
     Sierra
    -0.63
     Dogs
    -0.62
     Equipment
    -0.62
     Breast
    -0.62
     Underground
    -0.61
    baugh
    -0.60
    POSITIVE LOGITS
    folios
    0.88
    iness
    0.86
    orth
    0.86
    ily
    0.85
    otine
    0.77
    olulu
    0.77
     consideration
    0.77
     careful
    0.75
    ensing
    0.74
    entin
    0.74
    Act Density 0.016%

    No Known Activations