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

    Neuronpedia

    INDEX
    Explanations

    different variations of the word 'interesting'

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    gypt
    -0.74
    è¦ļéĨĴ
    -0.74
    ciating
    -0.73
    jriwal
    -0.72
     resil
    -0.71
    OAD
    -0.69
     millenn
    -0.69
     psychiat
    -0.66
    brates
    -0.65
     livest
    -0.65
    POSITIVE LOGITS
    ellect
    1.14
    ypes
    1.01
    elligent
    0.97
    eki
    0.86
    illation
    0.85
    angible
    0.84
    ribution
    0.83
    essential
    0.80
    ér
    0.79
    inho
    0.78
    Act Density 0.018%

    No Known Activations