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

    Neuronpedia

    INDEX
    Explanations

    phrases or terms commonly related to the concept of time, particularly the word "after"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    migrationBuilder
    -0.94
     AttributeSet
    -0.84
     Jefus
    -0.79
    MessageTagHelper
    -0.78
     Theſe
    -0.78
    mặt
    -0.75
     Shakspeare
    -0.74
     myſelf
    -0.74
    itecture
    -0.74
     himſelf
    -0.73
    POSITIVE LOGITS
     after
    2.07
    after
    1.90
     After
    1.87
    After
    1.84
     dopo
    1.63
     após
    1.59
     после
    1.58
     AFTER
    1.55
    AFTER
    1.54
     après
    1.51
    Act Density 0.220%

    No Known Activations