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

    Neuronpedia

    INDEX
    Explanations

    mentions of significant events, reports, and publications

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    cult
    -0.61
     lux
    -0.61
    idents
    -0.57
    natureconservancy
    -0.57
    train
    -0.56
    erness
    -0.55
    ries
    -0.55
    xes
    -0.55
     warmth
    -0.55
    viron
    -0.55
    POSITIVE LOGITS
     titled
    1.21
     outlining
    1.08
     detailing
    1.07
     whereby
    1.03
     indicating
    1.02
     illustrating
    0.98
     wherein
    0.97
     dated
    0.94
    uggest
    0.94
     entitled
    0.93
    Act Density 0.906%

    No Known Activations