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

    Neuronpedia

    INDEX
    Explanations

    references to the Eiffel Tower

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Eiffel Tower

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    qqa
    -0.80
    thia
    -0.71
     Vulkan
    -0.68
    ctica
    -0.67
     Sochi
    -0.63
     shatter
    -0.63
     propagate
    -0.63
    adra
    -0.62
     Gree
    -0.62
    ©¶æ
    -0.61
    POSITIVE LOGITS
    iculty
    1.10
    ness
    0.98
    erences
    0.98
    iff
    0.95
    inois
    0.93
    doms
    0.89
    icult
    0.88
    yll
    0.85
    ield
    0.84
    essed
    0.82
    Act Density 0.008%

    No Known Activations