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

    Neuronpedia

    INDEX
    Explanations

    specific names, terms, and punctuation that indicate engagement or interaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivent
    -0.15
    iffin
    -0.15
     Cop
    -0.15
    ForObject
    -0.14
    errer
    -0.14
    ies
    -0.14
    oulder
    -0.14
    cop
    -0.14
     cop
    -0.14
    ück
    -0.14
    POSITIVE LOGITS
    Above
    0.18
    _above
    0.18
     above
    0.18
     ABOVE
    0.18
    above
    0.17
    onus
    0.17
     Above
    0.16
    Ìģc
    0.15
    енÑģ
    0.14
    GBT
    0.14
    Act Density 0.024%

    No Known Activations