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

    Neuronpedia

    INDEX
    Explanations

    references to fugitives and runaways

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

    fugitive, runaway

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    LabelTagHelper
    -0.64
    awtextra
    -0.60
     للاسماء
    -0.59
     houſe
    -0.56
     willy
    -0.54
    IntoConstraints
    -0.54
    Personendaten
    -0.53
     Ender
    -0.52
    zdy
    -0.51
     Grammar
    -0.51
    POSITIVE LOGITS
     fug
    2.16
     Fug
    2.05
    Fug
    2.00
    fug
    1.85
     fugitive
    1.84
     fuga
    1.16
     runaway
    0.76
    fuge
    0.72
     escaped
    0.69
     escape
    0.67
    Act Density 0.010%

    No Known Activations