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

    Neuronpedia

    INDEX
    Explanations

    phrases related to judgments or opinions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of judgment and significant actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erity
    -0.59
    ensibly
    -0.57
    nesday
    -0.56
    enta
    -0.56
    oaded
    -0.52
    then
    -0.52
    ensing
    -0.51
    erence
    -0.51
    sts
    -0.51
    reements
    -0.50
    POSITIVE LOGITS
     urban
    0.59
     doping
    0.55
     recreational
    0.55
     culinary
    0.55
     international
    0.54
     academic
    0.52
     sports
    0.52
     tourist
    0.51
     artistic
    0.51
     commercial
    0.51
    Act Density 1.761%

    No Known Activations