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

    Neuronpedia

    INDEX
    Explanations

    linguistically significant or thematic expressions in multiple languages or scripts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    opal
    -0.17
    versible
    -0.15
    füg
    -0.15
    platz
    -0.15
    otechn
    -0.15
    aments
    -0.14
    quist
    -0.14
    för
    -0.14
    ensa
    -0.14
    arium
    -0.14
    POSITIVE LOGITS
    uat
    0.16
    rish
    0.15
    utex
    0.15
    .qt
    0.14
    culus
    0.14
     kle
    0.14
    icker
    0.13
    erea
    0.13
    аблиÑĨ
    0.13
    clado
    0.13
    Act Density 0.009%

    No Known Activations