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

    Neuronpedia

    INDEX
    Explanations

    names of specific locations and organizations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     dises
    -1.86
     mef
    -1.80
     dispen
    -1.73
     emphat
    -1.73
     affez
    -1.69
     sappi
    -1.69
     fta
    -1.66
     applau
    -1.65
     lyon
    -1.65
     ordina
    -1.65
    POSITIVE LOGITS
     and
    0.85
     for
    0.83
     as
    0.83
     during
    0.82
     in
    0.82
     which
    0.82
     while
    0.81
     to
    0.80
     by
    0.79
     with
    0.79
    Act Density 0.284%

    No Known Activations