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

    Neuronpedia

    INDEX
    Explanations

    terms related to measurement and analysis of data or statistics

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

    preceding adverbs

    np_acts-logits-general · gemini-2.0-flash

    predicting correctly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    出版年
    -0.77
     ligiloj
    -0.67
    msgTypes
    -0.54
    outSlope
    -0.51
    devant
    -0.49
    arXiv
    -0.48
    djangoproject
    -0.47
     obstante
    -0.46
    ReusableCell
    -0.46
    alleria
    -0.46
    POSITIVE LOGITS
     efficiently
    1.43
     correctly
    1.39
     satisfactorily
    1.33
     accurately
    1.33
     adequately
    1.32
     differently
    1.31
     properly
    1.27
     admirably
    1.26
     flawlessly
    1.24
     perfectly
    1.22
    Act Density 1.573%

    No Known Activations