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

    Neuronpedia

    INDEX
    Explanations

    frequent outputs or print statements in programming contexts

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

    system.out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyCulture
    -0.81
    RegressionTest
    -0.67
    Tikang
    -0.64
     Италијани
    -0.60
    AndEndTag
    -0.60
    ⟬
    -0.60
     Савезне
    -0.60
     ब्रेकडाउन
    -0.59
    ❹
    -0.59
     Photocase
    -0.59
    POSITIVE LOGITS
    out
    1.39
    Out
    1.01
     out
    0.99
    OUT
    0.99
     OUT
    0.94
     Out
    0.93
    outs
    0.82
    getOut
    0.81
     outs
    0.75
     output
    0.69
    Act Density 0.002%

    No Known Activations