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

    Neuronpedia

    INDEX
    Explanations

    technical or scholarly terms

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "technically" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ieties
    -0.71
     Vaj
    -0.63
     Cities
    -0.63
     Sparkle
    -0.61
    oday
    -0.61
     Gore
    -0.60
    agents
    -0.60
     Collection
    -0.59
     Seasons
    -0.59
     Neighbor
    -0.59
    POSITIVE LOGITS
     speaking
    0.90
     correct
    0.81
     inclined
    0.80
     minded
    0.76
    ename
    0.75
     incorrect
    0.75
    netflix
    0.69
    BuyableInstoreAndOnline
    0.68
     inaccurate
    0.67
    ãĤ©
    0.67
    Act Density 0.035%

    No Known Activations