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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate changes or increases in various parameters

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

    increase of value

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pleaſure
    -0.48
     ſur
    -0.47
     ſol
    -0.46
     Majefty
    -0.44
     paſſ
    -0.43
     tranſ
    -0.41
    CppMethod
    -0.40
     تضيفلها
    -0.40
     discriminator
    -0.40
     EconPapers
    -0.40
    POSITIVE LOGITS
    increase
    0.53
     StatefulWidget
    0.50
    Increase
    0.50
     Increase
    0.49
     StatelessWidget
    0.47
     increase
    0.47
     aumentar
    0.46
     افزایش
    0.46
    Increased
    0.46
    increased
    0.46
    Act Density 0.154%

    No Known Activations