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

    Neuronpedia

    INDEX
    Explanations

    phrases related to explanations and definitions in a technical or scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ted
    -0.56
    žka
    -0.53
     veiks
    -0.50
    fs
    -0.49
    ávat
    -0.48
     pæ
    -0.48
    nique
    -0.48
    ienė
    -0.47
    vellous
    -0.46
    ffen
    -0.46
    POSITIVE LOGITS
    клопе
    0.81
     AssemblyCompany
    0.80
    UnsafeEnabled
    0.73
     GenerationType
    0.72
    HostException
    0.72
    WithMany
    0.65
    хьтан
    0.62
    ContentAlignment
    0.61
     configureStore
    0.60
    WebVitals
    0.58
    Act Density 1.425%

    No Known Activations