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

    Neuronpedia

    INDEX
    Explanations

    mentions of political positions and historical events

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     parteci
    -1.11
     minimalis
    -0.95
     alkoh
    -0.88
     intende
    -0.88
     kriminal
    -0.86
     kön
    -0.84
     trovo
    -0.84
     voleva
    -0.84
     kosme
    -0.83
     keramik
    -0.83
    POSITIVE LOGITS
     and
    0.84
     
    0.80
     etc
    0.77
     pathfinder
    0.68
    ,
    0.67
     &
    0.64
     ,
    0.63
    etc
    0.62
     or
    0.61
     и
    0.60
    Act Density 0.145%

    No Known Activations