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

    Neuronpedia

    INDEX
    Explanations

    events or actions happening at a later time

    oai_token-act-pair · gpt-3.5-turbo

    the word "Later" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     calculated
    -0.62
     merit
    -0.59
     noise
    -0.56
     jugg
    -0.56
     statistically
    -0.56
     temp
    -0.55
     outweigh
    -0.55
     juggling
    -0.55
     crime
    -0.54
     breed
    -0.54
    POSITIVE LOGITS
     Later
    3.62
    Later
    2.91
    later
    2.34
     later
    2.02
     Afterwards
    1.91
     Eventually
    1.61
     Then
    1.48
    Soon
    1.48
     Soon
    1.47
    Eventually
    1.45
    Act Density 0.012%

    No Known Activations