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

    Neuronpedia

    INDEX
    Explanations

    keywords related to programming functions and their definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ắ
    -0.58
     will
    -0.53
    ಿದೆ
    -0.51
    っております
    -0.51
    ează
    -0.49
    ছে
    -0.49
     feels
    -0.49
    っていますが
    -0.48
     proszę
    -0.48
    ází
    -0.48
    POSITIVE LOGITS
     hadn
    1.05
     era
    1.02
     eran
    0.98
     was
    0.91
     estaba
    0.90
     tinha
    0.90
     tenía
    0.89
     wasn
    0.89
     had
    0.88
     était
    0.88
    Act Density 0.025%

    No Known Activations