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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "soon"

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating future actions or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eret
    -0.76
    76561
    -0.73
    didn
    -0.73
     lately
    -0.72
     yesterday
    -0.69
     recent
    -0.66
     lasted
    -0.66
    ItemTracker
    -0.65
    soType
    -0.64
     lasts
    -0.63
    POSITIVE LOGITS
     surpass
    0.96
     unveil
    0.89
     realize
    0.89
     overtake
    0.87
     realise
    0.83
     become
    0.80
     unleash
    0.79
     revisit
    0.78
     unle
    0.77
     replace
    0.76
    Act Density 0.231%

    No Known Activations