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

    Neuronpedia

    INDEX
    Explanations

    specific instances of events happening at a particular time of day

    oai_token-act-pair · gpt-3.5-turbo

    the word "that" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pass
    -0.66
     Parties
    -0.65
    Pass
    -0.65
    Rex
    -0.58
    Edge
    -0.56
    Tax
    -0.56
     Corps
    -0.56
    Ne
    -0.55
     Offline
    -0.54
    Burn
    -0.54
    POSITIVE LOGITS
     fateful
    1.02
     way
    0.90
     night
    0.89
    soever
    0.89
     day
    0.87
     evening
    0.86
    ched
    0.85
     morning
    0.85
     mattered
    0.83
     afternoon
    0.82
    Act Density 0.286%

    No Known Activations