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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the timing of events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Earlier" to indicate time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     peace
    -0.68
    Oracle
    -0.67
    Sov
    -0.67
    Bloom
    -0.67
     confidence
    -0.66
    Chance
    -0.66
    IRC
    -0.65
    NW
    -0.65
     observers
    -0.64
     caution
    -0.64
    POSITIVE LOGITS
     Though
    1.87
     Previously
    1.87
     Currently
    1.80
     Several
    1.79
     Despite
    1.78
     Originally
    1.77
     Although
    1.77
     Already
    1.76
     Earlier
    1.74
     Since
    1.70
    Act Density 0.129%

    No Known Activations