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

    Neuronpedia

    INDEX
    Explanations

    indicators of statistical data or metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     XNUMX
    -0.89
     "¡
    -0.78
    ].)
    -0.73
     Efq
    -0.73
    NUMX
    -0.70
     itſelf
    -0.69
     Joko
    -0.68
     myſelf
    -0.68
     figur
    -0.67
    úrate
    -0.67
    POSITIVE LOGITS
     diatas
    0.74
     dolayı
    0.68
      
    0.66
     didalam
    0.65
     execução
    0.65
     finalidad
    0.63
       
    0.63
     equipments
    0.62
    事です
    0.59
    MemoryWarning
    0.58
    Act Density 0.102%

    No Known Activations