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

    Neuronpedia

    INDEX
    Explanations

    websites or links

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     Parenthood
    -0.78
     progress
    -0.70
     magnitude
    -0.68
     Goldberg
    -0.64
     ageing
    -0.64
     doubling
    -0.64
     contrary
    -0.62
     nationally
    -0.61
     damaging
    -0.61
     cosmetic
    -0.61
    POSITIVE LOGITS
    /?
    1.52
    /#
    1.33
    /,
    1.29
    /.
    1.19
    /)
    1.15
    /-
    1.06
    cdn
    1.05
    /_
    1.02
    biz
    0.97
    /
    0.93
    Act Density 0.026%

    No Known Activations