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

    Neuronpedia

    INDEX
    Explanations

    phrases related to action or events with specific outcomes

    oai_token-act-pair · gpt-3.5-turbo

    references to actions and events that imply conflict or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    yip
    -0.64
     nor
    -0.59
     and
    -0.58
     et
    -0.53
    elong
    -0.51
     And
    -0.48
    DonaldTrump
    -0.48
     compr
    -0.48
     Versus
    -0.48
     AND
    -0.47
    POSITIVE LOGITS
     accordingly
    1.37
     thereafter
    1.18
     afterward
    0.98
     afterwards
    0.97
     alike
    0.95
    .
    0.88
     attRot
    0.87
    .[
    0.86
     therein
    0.85
     thereof
    0.84
    Act Density 1.266%

    No Known Activations