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

    Neuronpedia

    INDEX
    Explanations

    terms related to former or past positions and affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     sneeze
    -0.81
     Marburg
    -0.79
     Kull
    -0.69
    PushMatrix
    -0.68
    стоин
    -0.66
    subsubsection
    -0.65
     tannins
    -0.64
     Angio
    -0.64
     Sien
    -0.63
     épis
    -0.63
    POSITIVE LOGITS
     former
    1.24
     Former
    1.20
    Former
    1.18
    former
    1.00
     ex
    0.97
     ehemaligen
    0.96
     ehemalige
    0.93
     ancien
    0.89
    bootstrapcdn
    0.88
    ancien
    0.88
    Act Density 0.077%

    No Known Activations