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

    Neuronpedia

    INDEX
    Explanations

    expressions of agreement or opinion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     abstrato
    -0.41
     laikā
    -0.40
     yalnızca
    -0.39
     zís
    -0.37
     entraîner
    -0.36
    さまざまな
    -0.35
     çeşitli
    -0.35
     ferons
    -0.34
     almofada
    -0.34
     alcançar
    -0.34
    POSITIVE LOGITS
     referrerpolicy
    1.01
    httphttps
    0.96
     BTW
    0.91
    FTFY
    0.90
     btw
    0.88
     שוליים
    0.87
     IMHO
    0.85
     Thx
    0.82
    Witam
    0.82
     prolly
    0.81
    Act Density 6.507%

    No Known Activations