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

    Neuronpedia

    INDEX
    Explanations

    numerical data and statistics related to analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     "..\..\..\
    -0.53
    ренко
    -0.51
    стье
    -0.51
    hace
    -0.49
     hotell
    -0.46
     combina
    -0.45
     unangemessene
    -0.44
    OfWeek
    -0.44
     Bezirks
    -0.44
     durata
    -0.43
    POSITIVE LOGITS
     statistics
    1.52
     figures
    1.41
     stats
    1.34
     statistic
    1.32
     numbers
    1.29
    statistics
    1.24
     Statistics
    1.23
    figures
    1.22
    Statistics
    1.19
     STATISTICS
    1.18
    Act Density 0.517%

    No Known Activations