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

    Neuronpedia

    INDEX
    Explanations

    phrases related to past events

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and transitional phrases that connect thoughts or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    cel
    -0.74
    omorphic
    -0.68
    oint
    -0.64
     premium
    -0.62
     package
    -0.62
     wage
    -0.61
    doi
    -0.61
    opathy
    -0.61
    ore
    -0.60
     recy
    -0.60
    POSITIVE LOGITS
    ourning
    0.76
     Revelations
    0.71
     Stim
    0.70
     Burk
    0.70
     recalled
    0.68
     Janeiro
    0.68
     Afterwards
    0.68
     Meaning
    0.67
     Canaver
    0.66
     Deaths
    0.66
    Act Density 0.951%

    No Known Activations