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

    Neuronpedia

    INDEX
    Explanations

    references to corruption and its associated terms

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

    corruption scheme allegations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    See
    -0.42
    View
    -0.40
    -
    -0.39
    view
    -0.38
    able
    -0.37
    ##
    -0.36
    Clas
    -0.36
    ◡
    -0.36
    Lou
    -0.35
    Step
    -0.35
    POSITIVE LOGITS
     corruption
    2.09
     Corruption
    2.03
    Corruption
    1.97
    corruption
    1.95
     corrupción
    1.51
     corrupted
    1.41
     corrup
    1.03
     corrom
    1.02
     corrupt
    0.99
     corrosion
    0.92
    Act Density 0.002%

    No Known Activations