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

    Neuronpedia

    INDEX
    Explanations

    references to "other" and "others."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    \Bundle
    -0.17
    raft
    -0.15
    ella
    -0.15
    ioni
    -0.15
     Hol
    -0.15
     Hoch
    -0.14
     sit
    -0.14
     Dob
    -0.14
     Synd
    -0.14
    RAFT
    -0.14
    POSITIVE LOGITS
    adows
    0.15
    .cm
    0.15
    kı
    0.15
    iah
    0.15
    .lesson
    0.14
     Picker
    0.14
     Tie
    0.14
    ìļ±
    0.14
    Picker
    0.14
     آبÛĮ
    0.14
    Act Density 0.087%

    No Known Activations