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

    Neuronpedia

    INDEX
    Explanations

    descriptions of locations and settings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     consistency
    -0.82
     biological
    -0.82
     epigen
    -0.80
     vind
    -0.79
     aven
    -0.78
     involuntary
    -0.78
     renegoti
    -0.78
     extinct
    -0.78
     biologically
    -0.78
     impuls
    -0.77
    POSITIVE LOGITS
     Located
    1.58
     Visitors
    1.41
     Residents
    1.38
    Located
    1.33
     Dozens
    1.31
     Guests
    1.22
     Tickets
    1.20
     Featuring
    1.15
     Hundreds
    1.14
     Afterwards
    1.14
    Act Density 0.665%

    No Known Activations