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

    Neuronpedia

    INDEX
    Explanations

    terms related to sabotage and subversion

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

    sabotage and subvert

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.58
     kasarigan
    -0.56
    SpringRunner
    -0.53
    liski
    -0.50
     beliau
    -0.50
     therefrom
    -0.49
    extrême
    -0.49
     thereon
    -0.47
    fassen
    -0.47
    canestro
    -0.46
    POSITIVE LOGITS
     sabotage
    1.52
     Sabo
    1.27
     sabo
    1.20
     sab
    0.72
    破坏
    0.58
    oteur
    0.56
     sabato
    0.55
     spy
    0.52
     undermining
    0.50
     thwart
    0.49
    Act Density 0.012%

    No Known Activations