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

    Neuronpedia

    INDEX
    Explanations

    phrases related to actions or events happening at a specific time

    oai_token-act-pair · gpt-3.5-turbo

    uses of the word "when" in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    agin
    -0.79
    aido
    -0.75
    rolet
    -0.69
    entry
    -0.68
    abal
    -0.68
    andal
    -0.66
    Í
    -0.66
    oslov
    -0.66
    sonian
    -0.65
    alin
    -0.64
    POSITIVE LOGITS
    soever
    1.30
     transitioning
    0.90
     encountering
    0.88
     calculating
    0.87
     evaluating
    0.86
     applying
    0.85
     confronted
    0.85
     viewed
    0.82
     faced
    0.81
     deciding
    0.81
    Act Density 0.126%

    No Known Activations