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

    Neuronpedia

    INDEX
    Explanations

    terms related to numerical increases and comparisons in various contexts

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

    magnitude and comparison

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    msgTypes
    -0.62
    fjspx
    -0.55
    ंदीखरीदारी
    -0.52
     jsPsych
    -0.51
     ervan
    -0.51
    PYX
    -0.50
     considered
    -0.48
     Dowling
    -0.48
    CppMethod
    -0.47
    SharedCtor
    -0.47
    POSITIVE LOGITS
    Improved
    0.42
    Better
    0.40
     BETTER
    0.40
     bessere
    0.39
     فريبيس
    0.39
     mejorado
    0.38
    improved
    0.38
    increased
    0.36
     verbess
    0.36
    Easier
    0.36
    Act Density 0.051%

    No Known Activations