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

    Neuronpedia

    INDEX
    Explanations

    words that indicate confirmation or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Middle
    -0.52
     ditemui
    -0.47
     خارجية
    -0.47
    Middle
    -0.47
     or
    -0.46
     sementara
    -0.46
     aidé
    -0.45
    BrowserModule
    -0.45
    ırl
    -0.45
     combina
    -0.44
    POSITIVE LOGITS
     о
    1.13
     об
    1.10
    IntoConstraints
    0.92
     عن
    0.92
     apie
    0.86
     về
    0.85
    Για
    0.81
     Tentang
    0.80
     despre
    0.80
     ostavi
    0.79
    Act Density 0.051%

    No Known Activations