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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a span of time in the recent past and topics related to political actions or movements

    oai_token-act-pair · gpt-3.5-turbo

    references to specific time durations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    erella
    -0.74
     srfAttach
    -0.64
     Controls
    -0.63
    angan
    -0.62
    ashtra
    -0.61
    igham
    -0.61
    erville
    -0.60
     Based
    -0.59
     moderator
    -0.59
    Collect
    -0.58
    POSITIVE LOGITS
     generations
    0.97
     millennium
    0.95
     installments
    0.95
     years
    0.94
     weeks
    0.93
     months
    0.90
     decades
    0.90
     millennia
    0.89
    imester
    0.85
     iterations
    0.84
    Act Density 0.043%

    No Known Activations