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

    Neuronpedia

    INDEX
    Explanations

    phrases related to causes and effects

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     impra
    -1.11
     reluct
    -1.08
     ineffec
    -1.06
     resear
    -1.05
     unspeak
    -1.05
     strick
    -1.03
     disagre
    -1.02
     desir
    -1.00
     unwarran
    -1.00
     apprehen
    -1.00
    POSITIVE LOGITS
    <bos>
    0.87
    Autoritní
    0.74
    Tikang
    0.67
    Vidite
    0.65
     Италијани
    0.63
     <>",
    0.63
     >=",
    0.62
     enrique
    0.61
    IndentedString
    0.61
     <",
    0.61
    Act Density 0.714%

    No Known Activations