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

    Neuronpedia

    INDEX
    Explanations

    specific keywords used to emphasize importance or distinction within a sentence or text

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing notable or significant mentions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eways
    -0.76
    enary
    -0.71
    atures
    -0.69
     sorts
    -0.69
    inea
    -0.68
    ories
    -0.67
    ature
    -0.65
    udicrous
    -0.63
    reads
    -0.63
    ircraft
    -0.62
    POSITIVE LOGITS
     Micha
    0.72
    lez
    0.66
    asio
    0.64
     اÙĦ
    0.63
     Dani
    0.62
    APD
    0.62
     evidenced
    0.61
    ectomy
    0.61
     Adin
    0.61
     Cyrus
    0.61
    Act Density 0.095%

    No Known Activations