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

    Neuronpedia

    INDEX
    Explanations

    references to political corruption and calls for reform within government systems

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

    Negative sentiment towards organizations

    np_acts-logits-general · gemini-2.0-flash

    critical of corrupt or deceptive entities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Nazionale
    -0.56
    الحياه
    -0.55
    principalTable
    -0.55
     respecte
    -0.53
    oa̍t
    -0.53
     meilleures
    -0.52
    ślę
    -0.51
    MLLoader
    -0.51
     étoient
    -0.51
     myſelf
    -0.50
    POSITIVE LOGITS
     propaganda
    0.86
     impunity
    0.81
     corrupt
    0.80
     hypocritical
    0.78
     mindless
    0.77
     artificially
    0.77
     bogus
    0.76
     shameful
    0.76
     greedy
    0.75
     shameless
    0.75
    Act Density 1.170%

    No Known Activations