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

    Neuronpedia

    INDEX
    Explanations

    references to academic publications and proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ære
    -0.18
    san
    -0.15
    ida
    -0.14
     gram
    -0.14
    eral
    -0.14
    koneksi
    -0.14
    ãĤ
    -0.14
    idi
    -0.14
    xes
    -0.14
    lector
    -0.14
    POSITIVE LOGITS
    ÅŁk
    0.14
     King
    0.14
    867
    0.13
    ksen
    0.13
    exus
    0.13
    iaux
    0.13
    Ïĥα
    0.13
    å¼ı
    0.13
    weets
    0.13
    ives
    0.13
    Act Density 0.016%

    No Known Activations