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

    Neuronpedia

    INDEX
    Explanations

    historical references and positions held by individuals in government or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     purpoſe
    -0.86
     houſe
    -0.70
     myſelf
    -0.69
     ſte
    -0.68
     Monfieur
    -0.67
     diſt
    -0.65
     pleaſure
    -0.64
     eſt
    -0.64
     ſche
    -0.64
     revanche
    -0.63
    POSITIVE LOGITS
     then
    1.71
     puis
    1.54
    then
    1.33
     Then
    1.32
    Then
    1.31
     later
    1.25
     затем
    1.21
     THEN
    1.18
     kemudian
    1.18
     سپس
    1.10
    Act Density 0.331%

    No Known Activations