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

    Neuronpedia

    INDEX
    Explanations

    phrases related to awards and accolades

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ëĭ¤ê°Ģ
    -0.19
     Credential
    -0.15
    IGHL
    -0.14
    ermal
    -0.14
    aille
    -0.14
    è¬
    -0.14
    /jav
    -0.14
    -sided
    -0.14
    keit
    -0.14
    kle
    -0.14
    POSITIVE LOGITS
    -winning
    0.20
    ry
    0.17
    anas
    0.17
    ÙĨاÙħÙĩ
    0.17
    loon
    0.16
    renc
    0.16
    helm
    0.16
    edList
    0.16
    ongsTo
    0.15
    ing
    0.15
    Act Density 0.047%

    No Known Activations