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

    Neuronpedia

    INDEX
    Explanations

    references to political resistance and authority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Responder
    -0.15
    ysi
    -0.15
    KIT
    -0.15
    ÏģοÏĤ
    -0.14
    moz
    -0.14
    hlen
    -0.14
    енз
    -0.14
     Theft
    -0.14
     ghi
    -0.14
     Indo
    -0.14
    POSITIVE LOGITS
     compact
    0.17
    adlo
    0.17
     ener
    0.16
     measures
    0.16
     disfr
    0.15
     kuk
    0.15
    olia
    0.15
    olumbia
    0.15
     retro
    0.15
     guar
    0.15
    Act Density 0.061%

    No Known Activations