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

    Neuronpedia

    INDEX
    Explanations

    references to escapes from imprisonment or incarceration

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

    escape and escape attempts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    MigrationBuilder
    -0.40
    HttpFoundation
    -0.39
     dezelve
    -0.38
    Bean
    -0.36
     vnnd
    -0.34
     transfieras
    -0.34
     świ
    -0.34
     karbon
    -0.34
     AssemblyCulture
    -0.33
     ModelExpression
    -0.33
    POSITIVE LOGITS
     escape
    0.84
     escaped
    0.72
     escaping
    0.65
     Flucht
    0.61
     Escape
    0.60
     escapes
    0.59
    escape
    0.59
     ESCAPE
    0.57
     ब्रेकडाउन
    0.57
    逃
    0.56
    Act Density 0.021%

    No Known Activations