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

    Neuronpedia

    INDEX
    Explanations

    words and phrases indicating experience and expertise in various professional fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    gon
    -0.17
    eturn
    -0.16
    estro
    -0.15
    Td
    -0.15
    ering
    -0.14
    ÙĦاÙĦ
    -0.14
     Gloss
    -0.14
    istrovstvÃŃ
    -0.14
    оном
    -0.14
    ellas
    -0.14
    POSITIVE LOGITS
     know
    0.16
     ëħ¸íķĺìļ°
    0.16
     expertise
    0.16
    orney
    0.15
    illes
    0.15
     Spirits
    0.15
    .scalablytyped
    0.15
    pai
    0.14
    alez
    0.14
     Lid
    0.14
    Act Density 0.110%

    No Known Activations