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

    Neuronpedia

    INDEX
    Explanations

    phrases related to imprisonment or detainment

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     vuol
    -0.60
     gouver
    -0.57
     gius
    -0.56
     ricor
    -0.56
     cresce
    -0.55
    Rhestr
    -0.55
    ьаж
    -0.54
     affez
    -0.54
     vernac
    -0.53
    IndentedString
    -0.51
    POSITIVE LOGITS
     unspeak
    0.97
     gaily
    0.91
     unwarran
    0.88
     tolerably
    0.86
     ingrat
    0.85
     apprehen
    0.85
     indescri
    0.83
     wanderer
    0.83
     withal
    0.83
     outlander
    0.80
    Act Density 0.318%

    No Known Activations