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

    Neuronpedia

    INDEX
    Explanations

    proper nouns related to people and places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    coon
    -0.16
     Wick
    -0.15
    eration
    -0.15
    iola
    -0.14
     unh
    -0.14
    -dot
    -0.14
     Uhr
    -0.14
    quam
    -0.14
    rary
    -0.14
    yne
    -0.14
    POSITIVE LOGITS
    ething
    0.23
    -called
    0.23
    ftware
    0.20
    theast
    0.20
    etimes
    0.19
    iedade
    0.18
     sánh
    0.17
    raž
    0.15
    iedad
    0.15
    cial
    0.15
    Act Density 0.039%

    No Known Activations