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

    Neuronpedia

    INDEX
    Explanations

    conditional statements and their implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by conditional tense markers

    np_acts-logits-general · gemini-2.0-flash

    hypothetical or conditional statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     fidé
    -0.41
     doigt
    -0.39
    ţiei
    -0.39
     sienta
    -0.36
     muere
    -0.35
    ienes
    -0.35
     constater
    -0.35
     fidèle
    -0.35
    "]);
    -0.35
    guiente
    -0.35
    POSITIVE LOGITS
     Would
    0.95
    Would
    0.95
     would
    0.92
    would
    0.88
     WOULD
    0.84
     gdyby
    0.76
     würde
    0.68
    Wouldn
    0.67
     hätte
    0.66
     Wouldn
    0.66
    Act Density 0.612%

    No Known Activations