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

    Neuronpedia

    INDEX
    Explanations

    technical terms and specific numerical data in a scientific or engineering context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     '
    -0.80
     "
    -0.74
     vs
    -0.68
     V
    -0.67
     v
    -0.64
     L
    -0.64
     ber
    -0.63
    =[]
    -0.63
     f
    -0.63
     ”
    -0.62
    POSITIVE LOGITS
    //
    1.56
    if
    1.31
     myſelf
    1.22
    //.
    1.01
     itſelf
    1.00
     purpoſe
    0.99
     themſelves
    0.99
     greateſt
    0.98
     pleaſure
    0.97
     reaſon
    0.97
    Act Density 0.344%

    No Known Activations