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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating events or actions that will occur or not occur in the future

    oai_token-act-pair · gpt-3.5-turbo

    references to events or situations that are anticipated to occur in the future

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cius
    -0.59
     rather
    -0.59
     respectively
    -0.58
    alis
    -0.56
    rather
    -0.56
     Emin
    -0.56
    igl
    -0.55
    GD
    -0.55
     caution
    -0.55
    verbs
    -0.55
    POSITIVE LOGITS
     until
    1.78
    until
    1.56
     till
    1.52
     unless
    1.41
     anytime
    1.35
    til
    1.27
    unless
    1.25
     overnight
    1.21
     Until
    1.20
     anymore
    1.17
    Act Density 0.274%

    No Known Activations