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

    Neuronpedia

    INDEX
    Explanations

    mathematical operations and their results

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
      
    -0.60
     
    -0.59
    de
    -0.53
     b
    -0.48
     –
    -0.47
       
    -0.45
     c
    -0.45
     E
    -0.44
    ↵
    -0.44
     n
    -0.43
    POSITIVE LOGITS
     Jefus
    1.13
     Efq
    1.09
     незавершена
    0.98
    ſelf
    0.97
     iſt
    0.96
     itſelf
    0.94
     ་་
    0.94
     calendriers
    0.94
     Houſe
    0.94
     themſelves
    0.93
    Act Density 0.034%

    No Known Activations