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

    Neuronpedia

    INDEX
    Explanations

    phrases related to movements or actions like "stepped out of the room" or "pulled around him"

    oai_token-act-pair · gpt-3.5-turbo

    sentences ending with punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     extinct
    -0.88
    uly
    -0.84
     affili
    -0.78
     honoured
    -0.77
     induct
    -0.77
    thal
    -0.74
    vre
    -0.74
     inherited
    -0.72
     trait
    -0.72
     underrated
    -0.71
    POSITIVE LOGITS
     Afterwards
    1.28
     Then
    1.25
     Eventually
    1.24
     Luckily
    1.20
     Immediately
    1.19
     Suddenly
    1.18
     Moments
    1.12
     Fortunately
    1.10
     Slowly
    1.08
     Thankfully
    1.05
    Act Density 0.430%

    No Known Activations