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

    Neuronpedia

    INDEX
    Explanations

    discussions around political accountability and criticism

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

    Follows a quote and said

    np_acts-logits-general · gemini-2.0-flash

    politicians and public figures speaking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Perſ
    -0.72
     Majefty
    -0.67
     Houſe
    -0.66
     Reſ
    -0.63
     Perfon
    -0.63
     fubject
    -0.62
     ſche
    -0.62
     ſever
    -0.61
     Anſ
    -0.61
     perfons
    -0.60
    POSITIVE LOGITS
    anyahu
    0.65
    celotti
    0.59
     Musk
    0.58
     Trump
    0.57
     ostavi
    0.56
     Biden
    0.55
     Dhoni
    0.55
    Obama
    0.55
     Mc
    0.54
    Trump
    0.54
    Act Density 1.135%

    No Known Activations