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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of novelty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    новниш
    -0.50
     censiti
    -0.50
     kaarangay
    -0.48
    httphttps
    -0.47
     препратки
    -0.46
    hoeddwyd
    -0.46
    GTCX
    -0.44
     يتيمه
    -0.44
    ScopeManager
    -0.43
     ffilmiau
    -0.42
    POSITIVE LOGITS
     Je
    0.73
    sie
    0.66
    sey
    0.63
     Pour
    0.62
    Je
    0.62
    novel
    0.57
     POUR
    0.57
     novel
    0.56
    pour
    0.55
     Sum
    0.55
    Act Density 0.327%

    No Known Activations