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

    Neuronpedia

    INDEX
    Explanations

    phrases and words related to political power and legal terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     InputDecoration
    -0.62
     FAVOR
    -0.61
    ---*/
    -0.61
     favor
    -0.58
     außerdem
    -0.58
     étoient
    -0.56
     beginnetje
    -0.56
     favors
    -0.55
    يًا
    -0.55
     weißt
    -0.54
    POSITIVE LOGITS
     hitherto
    0.65
    paksa
    0.63
    ungguhnya
    0.62
    ঙ
    0.62
     eminently
    0.61
     manifestly
    0.61
     reckon
    0.60
     Incidentally
    0.59
     aberrations
    0.59
    QueryString
    0.58
    Act Density 0.258%

    No Known Activations