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

    Neuronpedia

    INDEX
    Explanations

    patterns related to legal agreements and technical specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    similarly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.73
     يتيمه
    -0.64
    extAlignment
    -0.63
    ſammen
    -0.59
     Geſch
    -0.57
     Audiodateien
    -0.57
    pushFollow
    -0.56
     للمعارف
    -0.56
     Waſſer
    -0.56
    awtextra
    -0.55
    POSITIVE LOGITS
    Same
    0.42
    同样
    0.39
    こちらも
    0.38
     too
    0.37
     same
    0.37
     similarly
    0.37
     Same
    0.36
     equally
    0.35
     separately
    0.34
     ebenfalls
    0.33
    Act Density 0.421%

    No Known Activations