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

    Neuronpedia

    INDEX
    Explanations

    mentions of monuments or landmarks

    oai_token-act-pair · gpt-3.5-turbo

    references to monuments and significant landmarks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erm
    -0.79
    FP
    -0.68
    ENG
    -0.67
    comes
    -0.67
    Roy
    -0.66
    Liquid
    -0.65
    ooters
    -0.63
    iencies
    -0.63
    cery
    -0.63
    rosso
    -0.62
    POSITIVE LOGITS
     monuments
    1.14
     monument
    1.09
     erected
    0.98
    alist
    0.84
    ajo
    0.81
    anan
    0.81
     statues
    0.80
    arium
    0.78
     commemor
    0.77
     paintings
    0.77
    Act Density 0.016%

    No Known Activations