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

    Neuronpedia

    INDEX
    Explanations

    references to specific programs or initiatives

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
    anță
    -0.74
    矶
    -0.74
    ității
    -0.73
     histó
    -0.71
    șit
    -0.70
    ulfate
    -0.68
    ății
    -0.65
    ționale
    -0.65
    ăț
    -0.64
    郸
    -0.64
    POSITIVE LOGITS
     endeavouring
    1.31
     endeavoured
    1.27
     McLaugh
    1.22
     civilised
    1.19
     shenan
    1.17
     shewn
    1.15
     apprehen
    1.14
     disagre
    1.13
     intersper
    1.12
     disreg
    1.11
    Act Density 0.316%

    No Known Activations