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

    Neuronpedia

    INDEX
    Explanations

    themes of systemic corruption and manipulation for power

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    overrides
    -0.18
    кан
    -0.17
    otes
    -0.17
    reten
    -0.16
    ÑĴ
    -0.16
    ji
    -0.15
    éĢĥ
    -0.14
    amel
    -0.14
    OLUMNS
    -0.14
    rink
    -0.14
    POSITIVE LOGITS
    soever
    0.18
     Pla
    0.15
    esson
    0.15
    å°Ķ
    0.15
    owitz
    0.15
     Gong
    0.14
    kening
    0.14
    162
    0.14
     Pil
    0.13
     Kens
    0.13
    Act Density 0.252%

    No Known Activations