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

    Neuronpedia

    INDEX
    Explanations

    names of individuals ending with a specific character sequence

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Maria
    -0.77
    ipl
    -0.62
    /_
    -0.59
    naissance
    -0.57
    edition
    -0.56
    uate
    -0.56
     Heidi
    -0.55
     Pats
    -0.54
    relations
    -0.53
    unity
    -0.53
    POSITIVE LOGITS
     QC
    0.79
    ovich
    0.79
     Sr
    0.76
    kson
    0.73
     III
    0.72
    zik
    0.70
    kowski
    0.70
    iewicz
    0.69
    ersen
    0.69
    bard
    0.68
    Act Density 0.144%

    No Known Activations