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

    Neuronpedia

    INDEX
    Explanations

    symbols and formatting related to coding or programming elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    GI
    -0.15
     ÙĨÚ¯
    -0.14
     Bent
    -0.14
     oppos
    -0.14
    Cha
    -0.14
    oru
    -0.13
    елениÑı
    -0.13
    åº
    -0.13
    ãİ
    -0.13
    unda
    -0.13
    POSITIVE LOGITS
    zhou
    0.17
    amedi
    0.17
    cheng
    0.16
     vak
    0.16
    hait
    0.15
    passport
    0.15
     hakk
    0.14
    trak
    0.14
    pherd
    0.14
     Pruitt
    0.14
    Act Density 0.009%

    No Known Activations