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

    Neuronpedia

    INDEX
    Explanations

    descriptive adjectives and phrases that convey positive attributes or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ean
    -0.15
    å¼ı
    -0.15
    IBE
    -0.15
    pic
    -0.14
    bare
    -0.14
    Ưá»
    -0.14
    _rq
    -0.13
    FileSync
    -0.13
    IBC
    -0.13
    lluminate
    -0.13
    POSITIVE LOGITS
    ness
    0.30
     enough
    0.25
    NESS
    0.21
     Enough
    0.19
    nes
    0.18
    lest
    0.18
     nhất
    0.17
     جدا
    0.16
    keit
    0.15
    ëĭĪìĬ¤
    0.15
    Act Density 0.705%

    No Known Activations