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

    Neuronpedia

    INDEX
    Explanations

    references to specific institutions or organizations

    oai_token-act-pair · gpt-3.5-turbo

    keywords and entities related to institutions and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    wat
    -0.85
    bye
    -0.84
    kees
    -0.84
    fman
    -0.82
    oway
    -0.80
    drawn
    -0.79
    cox
    -0.76
    baugh
    -0.76
    legged
    -0.75
    worms
    -0.75
    POSITIVE LOGITS
     Univers
    1.21
     Franç
    1.11
     Portug
    1.11
     Libre
    1.11
     Democr
    1.08
     Mex
    1.07
     Indust
    1.07
     Instit
    1.04
     de
    1.01
     univers
    1.01
    Act Density 0.175%

    No Known Activations