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

    Neuronpedia

    INDEX
    Explanations

    phrases related to socio-political context and commentary

    oai_token-act-pair · gpt-3.5-turbo

    definite articles and references to authority or significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Alert
    -0.82
    nb
    -0.76
    NB
    -0.75
    atto
    -0.75
     besides
    -0.73
    poke
    -0.72
    nr
    -0.70
    leased
    -0.69
    specified
    -0.69
    tesy
    -0.69
    POSITIVE LOGITS
     greatest
    1.07
     stakes
    1.07
     wealthiest
    1.06
     notion
    1.05
     richest
    1.04
    resa
    1.03
     nation
    1.03
     economy
    1.02
     elites
    1.02
     pend
    1.01
    Act Density 0.438%

    No Known Activations