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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "so" used for emphasis or intensification

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    dera
    -0.17
    acle
    -0.17
    mans
    -0.17
    kk
    -0.16
    ÑĤÑı
    -0.16
    kening
    -0.16
    ltk
    -0.15
    edBy
    -0.15
    lands
    -0.15
    ucch
    -0.15
    POSITIVE LOGITS
     so
    0.23
     many
    0.22
    apy
    0.22
    oth
    0.21
    jour
    0.20
     much
    0.20
    vre
    0.20
     called
    0.19
    aps
    0.19
    ley
    0.19
    Act Density 0.043%

    No Known Activations