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

    Neuronpedia

    INDEX
    Explanations

    heavily repeated terms or phrases, indicating significance in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oter
    -0.17
     Gaul
    -0.15
    fir
    -0.15
    ê°Ŀ
    -0.15
    ximity
    -0.15
    gregated
    -0.14
    mere
    -0.14
    Äł
    -0.14
    _DEPRECATED
    -0.14
    ,eg
    -0.14
    POSITIVE LOGITS
    idan
    0.15
    ights
    0.15
     opponent
    0.15
    lech
    0.15
    iche
    0.15
    ond
    0.14
    TURE
    0.14
     Mond
    0.14
    caff
    0.14
     profiling
    0.14
    Act Density 0.012%

    No Known Activations