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

    Neuronpedia

    INDEX
    Explanations

    words related to logic or reasoning

    oai_token-act-pair · gemini-2.0-flash

    occurrences of the word 'times'

    np_token-act-pair-logits · gpt-4o-mini

    multiplication

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    RegressionTest
    -0.50
     তারিখ
    -0.48
     voldoende
    -0.43
     الدولى
    -0.43
     ?",
    -0.43
    ChildScrollView
    -0.41
    -0.41
    Backbone
    -0.41
     =>
    -0.41
    越好
    -0.40
    POSITIVE LOGITS
     times
    1.94
     twice
    1.93
     Twice
    1.80
    twice
    1.76
    Twice
    1.66
    Times
    1.55
     TIMES
    1.51
     Times
    1.51
     thrice
    1.42
     TWICE
    1.41
    Act Density 2.616%

    No Known Activations