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

    Neuronpedia

    INDEX
    Explanations

    patterns or sequences involving numerical values or calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -0.95
     onCreateView
    -0.89
     onCancelled
    -0.88
     itſelf
    -0.87
     ་་
    -0.87
    SPATH
    -0.83
    السكان
    -0.81
     متحده
    -0.78
    σιμοποι
    -0.76
     Efq
    -0.75
    POSITIVE LOGITS
     two
    1.02
     three
    0.94
     big
    0.83
    two
    0.82
     four
    0.80
     deux
    0.78
     zwei
    0.77
     five
    0.75
    TWO
    0.74
     Two
    0.73
    Act Density 0.362%

    No Known Activations