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

    Neuronpedia

    INDEX
    Explanations

    references to individuals with former roles or positions of authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.69
    ckså
    -0.66
     pleaſure
    -0.65
    DockStyle
    -0.64
    IntoConstraints
    -0.59
     ſtre
    -0.56
    inephrine
    -0.55
    MeasureSpec
    -0.55
    setVerticalGroup
    -0.54
     faſt
    -0.54
    POSITIVE LOGITS
     former
    0.96
     Former
    0.88
    Former
    0.81
    former
    0.70
     ehemaligen
    0.59
     ehemalige
    0.58
     mantan
    0.57
     ex
    0.56
     previous
    0.54
     formerly
    0.54
    Act Density 0.074%

    No Known Activations