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

    Neuronpedia

    INDEX
    Explanations

    people's last names

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the substring "oe" in names or terms, suggesting a focus on specific proper nouns or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ifiers
    -0.85
    ifiable
    -0.79
    ifier
    -0.79
     glim
    -0.76
    ãĥĥãĤ¯
    -0.72
     à¨
    -0.70
    amaz
    -0.68
    arians
    -0.67
     Chandra
    -0.66
    rons
    -0.64
    POSITIVE LOGITS
    ppel
    1.09
    zie
    1.04
    zzi
    1.03
    cean
    0.99
    lect
    0.96
    hner
    0.89
    ze
    0.88
    hler
    0.88
    utenant
    0.87
    cker
    0.85
    Act Density 0.018%

    No Known Activations