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

    Neuronpedia

    INDEX
    Explanations

    phrases related to historical discoveries, economic activities, and public governance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     solidar
    -0.74
     anse
    -0.69
     ché
    -0.68
     antik
    -0.67
     minimalis
    -0.66
     dì
    -0.64
     dè
    -0.62
     robus
    -0.62
     bont
    -0.62
     utop
    -0.62
    POSITIVE LOGITS
     shenan
    0.75
     nevertheless
    0.70
     unspeak
    0.65
     disreg
    0.62
     nonetheless
    0.61
     motherfucker
    0.60
     unlaw
    0.60
     politiet
    0.60
     miscon
    0.60
     fortunately
    0.59
    Act Density 0.236%

    No Known Activations