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

    Neuronpedia

    INDEX
    Explanations

    words related to software commands or coding instructions

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical or statistical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hement
    -0.89
     brunt
    -0.69
     scrap
    -0.61
     WRITE
    -0.60
     intending
    -0.58
     estranged
    -0.58
    iott
    -0.58
     advertisers
    -0.57
     Dollar
    -0.57
     inund
    -0.56
    POSITIVE LOGITS
    ³³³
    0.93
    ³³³³³³³³³³³³³³³³
    0.88
    ³³³³³³³³
    0.86
    ³³³³
    0.84
    PRESS
    0.78
    FactoryReloaded
    0.78
    ³³
    0.77
    BuyableInstoreAndOnline
    0.75
    SCP
    0.75
    00200000
    0.75
    Act Density 0.261%

    No Known Activations