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

    Neuronpedia

    INDEX
    Explanations

    numerical representations and values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ’
    -0.57
    -
    -0.54
     
    -0.47
     (
    -0.46
     Re
    -0.45
    '
    -0.45
    ↵↵
    -0.44
     der
    -0.44
     a
    -0.44
    ,
    -0.44
    POSITIVE LOGITS
     Савезне
    1.04
    ſelves
    1.01
     ſtate
    0.99
     purpoſe
    0.98
    ſelf
    0.98
     iſt
    0.94
    neſs
    0.93
     auffi
    0.93
     kaarangay
    0.92
     myſelf
    0.92
    Act Density 0.344%

    No Known Activations