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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "once" and phrases indicating moments of realization or understanding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    intree
    -0.17
    å°ļ
    -0.15
    жÑĥ
    -0.14
    abant
    -0.14
    ycin
    -0.14
    isode
    -0.14
    itti
    -0.14
     QMainWindow
    -0.14
    ales
    -0.13
    isi
    -0.13
    POSITIVE LOGITS
     ResourceBundle
    0.15
    axon
    0.15
    tru
    0.15
    Sharper
    0.14
    emiz
    0.14
    ÙħاÙĦ
    0.14
    arian
    0.14
    adv
    0.13
    more
    0.13
     vz
    0.13
    Act Density 0.067%

    No Known Activations