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

    Neuronpedia

    INDEX
    Explanations

    references to subway systems and related topics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     lara
    -0.94
     ciao
    -0.90
     nicolas
    -0.90
     ?...
    -0.90
     embra
    -0.89
     blos
    -0.89
     encomp
    -0.87
     inev
    -0.87
     !...
    -0.86
     accla
    -0.86
    POSITIVE LOGITS
     transit
    0.92
     subway
    0.89
    transit
    0.76
     Transit
    0.71
     rail
    0.70
     train
    0.69
    Transit
    0.67
     trains
    0.63
     transportation
    0.61
     Metro
    0.60
    Act Density 0.116%

    No Known Activations