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

    Neuronpedia

    INDEX
    Explanations

    specific dates and information related to historical events

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     hug
    -0.74
     extinct
    -0.68
     affili
    -0.66
    unts
    -0.65
     aggress
    -0.63
    ubes
    -0.63
     alliances
    -0.62
     bargain
    -0.62
    roph
    -0.62
     roundup
    -0.62
    POSITIVE LOGITS
     It
    1.19
     Its
    1.16
     Previously
    1.06
     Initially
    1.04
     Afterwards
    1.01
     Then
    1.01
     Later
    1.01
     However
    0.97
     Shortly
    0.93
     That
    0.92
    Act Density 0.538%

    No Known Activations