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

    Neuronpedia

    INDEX
    Explanations

    references to dates ('th', 'nd'), likely related to specific events or occurrences

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Negative Logits
     maksi
    -0.58
    DataPropertyName
    -0.54
    TextInputLayout
    -0.53
    ChatColor
    -0.53
    CrossOrigin
    -0.53
    ControllerAdvice
    -0.53
     especias
    -0.52
     autunno
    -0.51
    CodeAnalysis
    -0.51
     teras
    -0.50
    POSITIVE LOGITS
     milf
    0.96
     shenan
    0.94
     inext
    0.93
     inconce
    0.91
     indestru
    0.90
     nth
    0.89
     cuck
    0.87
     lamborghini
    0.85
     caucasian
    0.85
     vagu
    0.85
    Act Density 0.097%

    No Known Activations