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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to measurements or observations, indicating the importance of data and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ―――――
    -1.12
     itſelf
    -1.10
     houſe
    -1.05
     fubject
    -1.05
     auffi
    -1.03
     ་་
    -1.03
     ſche
    -1.02
     purpoſe
    -0.98
     ſtate
    -0.98
     uſed
    -0.97
    POSITIVE LOGITS
     two
    1.02
     
    0.94
     three
    0.84
     big
    0.78
     Two
    0.77
     new
    0.76
    two
    0.75
     A
    0.75
     deux
    0.75
     four
    0.74
    Act Density 0.219%

    No Known Activations