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

    Neuronpedia

    INDEX
    Explanations

    sequences related to numerical and time-based values

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
     g
    -0.54
      
    -0.53
     ar
    -0.51
     v
    -0.50
     
    -0.48
     an
    -0.47
    ",
    -0.47
     '
    -0.46
     vis
    -0.46
     dem
    -0.45
    POSITIVE LOGITS
     myſelf
    1.24
     itſelf
    1.08
     ſmall
    1.07
     ſeveral
    1.05
     faſt
    1.03
     iſt
    1.02
     Reſ
    1.02
     pleaſure
    1.02
     houſe
    1.01
     purpoſe
    1.01
    Act Density 0.011%

    No Known Activations