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

    Neuronpedia

    INDEX
    Explanations

    instances of repetition and emphasis in phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    edd
    -0.15
    mayan
    -0.14
    ÑĦÑĦ
    -0.14
     Constant
    -0.14
    orc
    -0.14
    ël
    -0.13
     hải
    -0.13
    enou
    -0.13
     combust
    -0.13
    /fw
    -0.13
    POSITIVE LOGITS
    ucci
    0.17
    خت
    0.15
    415
    0.15
    çĵľ
    0.14
     again
    0.14
    ovich
    0.14
    ilha
    0.14
    PCP
    0.14
    istle
    0.14
    .oauth
    0.14
    Act Density 0.227%

    No Known Activations