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

    Neuronpedia

    INDEX
    Explanations

    proper nouns, particularly names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    last names with a common pattern: "uddin"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     Wilde
    -0.70
     Judith
    -0.66
     dime
    -0.66
     Hayden
    -0.64
     contribut
    -0.63
    ck
    -0.62
     protection
    -0.61
     plate
    -0.61
     Schmidt
    -0.60
     companion
    -0.60
    POSITIVE LOGITS
    ciating
    1.17
    tenance
    1.11
    xual
    1.03
    istics
    0.96
    tyard
    0.94
    lihood
    0.92
    ous
    0.91
    anova
    0.91
    ó
    0.90
    ukong
    0.88
    Act Density 0.032%

    No Known Activations