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

    Neuronpedia

    INDEX
    Explanations

    concepts related to violence and loyalty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.64
    ckså
    -0.59
     архивлан
    -0.57
     الرياضيه
    -0.57
     kasarigan
    -0.57
     ſche
    -0.57
    DockStyle
    -0.56
     ſind
    -0.56
     pungkas
    -0.56
    ſelves
    -0.54
    POSITIVE LOGITS
     faithful
    0.73
     loyal
    0.60
     meeting
    0.52
    Options
    0.51
    WebElementEntity
    0.51
     working
    0.49
     heavily
    0.48
    faithful
    0.47
     law
    0.46
    IsMutable
    0.46
    Act Density 0.243%

    No Known Activations