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

    Neuronpedia

    INDEX
    Explanations

    references to periods of ten years, particularly when emphasizing their significance

    oai_token-act-pair · gpt-3.5-turbo

    references to decades and time periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Pack
    -0.73
    amina
    -0.70
    ooter
    -0.65
    iqu
    -0.65
    Package
    -0.65
    Kick
    -0.64
    mber
    -0.63
    Board
    -0.63
    kell
    -0.63
    spe
    -0.62
    POSITIVE LOGITS
     ago
    1.01
    arily
    0.82
     ILCS
    0.80
    arios
    0.74
    oths
    0.74
     spanning
    0.72
     onward
    0.71
    ĸļ
    0.69
     nostalg
    0.68
    icity
    0.68
    Act Density 0.040%

    No Known Activations