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

    Neuronpedia

    INDEX
    Explanations

    references to scientific theories

    oai_token-act-pair · gpt-3.5-turbo

    references to scientific theories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ibaba
    -0.65
    cler
    -0.62
    ienced
    -0.60
    iencies
    -0.59
    Interstitial
    -0.58
    æĸ¹
    -0.58
     Mous
    -0.57
     Pradesh
    -0.57
    ãģį
    -0.57
    Numbers
    -0.57
    POSITIVE LOGITS
    icist
    1.28
     underpin
    1.01
    sonian
    0.98
     theories
    0.98
     predicts
    0.97
     theor
    0.93
    ologies
    0.93
     hypothes
    0.90
     formulated
    0.88
     predicting
    0.87
    Act Density 0.048%

    No Known Activations