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

    Neuronpedia

    INDEX
    Explanations

    transitions or sequences marked by the word "Then."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     itſelf
    -0.71
     himſelf
    -0.68
     Irm
    -0.66
    noinspection
    -0.62
     purpoſe
    -0.62
    Unmanaged
    -0.61
    __/
    -0.61
     Harlow
    -0.60
    neſs
    -0.60
    Kaieteur
    -0.60
    POSITIVE LOGITS
     then
    3.17
     Then
    3.12
    Then
    3.07
    then
    2.87
     THEN
    2.76
    THEN
    2.62
     entonces
    2.16
     então
    1.95
     dann
    1.90
    Entonces
    1.86
    Act Density 0.115%

    No Known Activations