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

    Neuronpedia

    INDEX
    Explanations

    mentions of historical events or political contexts

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Negative Logits
     forbids
    -0.73
    buster
    -0.71
     reproduce
    -0.70
    arten
    -0.70
     differs
    -0.70
     thereof
    -0.69
     understands
    -0.69
    ooth
    -0.69
     identifies
    -0.69
     differed
    -0.69
    POSITIVE LOGITS
     fact
    1.27
     plight
    1.13
     plethora
    1.02
     myriad
    1.00
     horrors
    0.98
     sheer
    0.98
     countless
    0.97
     multitude
    0.97
     dangers
    0.93
     infamous
    0.92
    Act Density 0.634%

    No Known Activations