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

    Neuronpedia

    INDEX
    Explanations

    personal opinions or comments in text

    oai_token-act-pair · gpt-3.5-turbo

    expressions of frustration or annoyance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    aneers
    -0.69
     Skydragon
    -0.66
    bard
    -0.65
    krit
    -0.64
    irtual
    -0.62
     giveaway
    -0.61
     Siber
    -0.60
     Balk
    -0.60
     razor
    -0.59
    DragonMagazine
    -0.58
    POSITIVE LOGITS
    ortal
    1.04
    umbai
    1.03
    agine
    1.00
    selves
    0.99
    ighty
    0.99
    ploy
    0.89
    mediately
    0.86
    otor
    0.85
    useum
    0.84
    brace
    0.82
    Act Density 0.030%

    No Known Activations