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

    Neuronpedia

    INDEX
    Explanations

    changes in values such as increase, rise, decline, and growth

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    tta
    -0.72
    ãĥīãĥ©
    -0.72
    finished
    -0.69
     Founding
    -0.66
    sol
    -0.66
     sar
    -0.62
    tein
    -0.61
    minecraft
    -0.61
    Assembly
    -0.60
    eatured
    -0.60
    POSITIVE LOGITS
     exponentially
    1.17
     dramatically
    1.16
     sharply
    1.10
     markedly
    1.10
     considerably
    1.05
     steadily
    1.03
     drastically
    1.03
     noticeably
    0.98
     substantially
    0.95
     tremendously
    0.95
    Act Density 0.862%

    No Known Activations