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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "company" and related terms

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     adal
    -0.95
     lele
    -0.94
     Sén
    -0.89
     kac
    -0.86
     NKC
    -0.83
     hcm
    -0.81
     saha
    -0.80
     bera
    -0.79
     istan
    -0.79
     ché
    -0.78
    POSITIVE LOGITS
    Denote
    0.63
     Qualquer
    0.63
     😌
    0.60
    zonder
    0.60
    Einfach
    0.57
     withal
    0.57
     dintr
    0.57
     🙃
    0.56
     lmfao
    0.56
     geforce
    0.56
    Act Density 0.419%

    No Known Activations