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

    Neuronpedia

    INDEX
    Explanations

    positive assertions about capabilities or success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erli
    -0.15
    licht
    -0.14
    ems
    -0.14
    109
    -0.14
     cod
    -0.14
    å®
    -0.13
    ali
    -0.13
    UU
    -0.13
     racial
    -0.13
     Portfolio
    -0.13
    POSITIVE LOGITS
    bid
    0.15
    ypi
    0.15
    ç
    0.14
    é¾
    0.14
     columnName
    0.14
    ertino
    0.14
    bu
    0.14
    uten
    0.13
    Uvs
    0.13
    à¤ĺ
    0.13
    Act Density 0.025%

    No Known Activations