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

    Neuronpedia

    INDEX
    Explanations

    phrases related to promoting or supporting a specific cause

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     дописавши
    -0.80
    }\]
    -0.49
    ByVersion
    -0.49
    GeoNames
    -0.48
    podob
    -0.47
    awtextra
    -0.47
     service
    -0.46
     doInBackground
    -0.46
    URLConnection
    -0.46
     Audiodateien
    -0.45
    POSITIVE LOGITS
     AssemblyCulture
    0.84
    :✨
    0.76
     HasFactory
    0.58
    Vidite
    0.56
    CreateInfo
    0.56
    ьаж
    0.55
     vPvB
    0.53
     ResNet
    0.52
    ímp
    0.51
    ✭✭
    0.51
    Act Density 0.327%

    No Known Activations