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

    Neuronpedia

    INDEX
    Explanations

    words associated with presiding or leadership roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Hicks
    -0.17
    æŁĦ
    -0.16
     Hue
    -0.16
    .googleapis
    -0.16
    ypes
    -0.16
     Ging
    -0.15
    ideas
    -0.14
     éĩİ
    -0.14
    redo
    -0.14
    iversit
    -0.14
    POSITIVE LOGITS
    keiten
    0.16
    SOLE
    0.15
    azzi
    0.15
     Ros
    0.14
    amiento
    0.14
     weekly
    0.14
    legant
    0.14
    amd
    0.14
    ampler
    0.14
    CHAN
    0.14
    Act Density 0.004%

    No Known Activations