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

    Neuronpedia

    INDEX
    Explanations

    significant years

    oai_token-act-pair · gpt-3.5-turbo

    references to specific years, particularly 1993 and 1994

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Tu
    -0.75
    tro
    -0.69
    holder
    -0.66
    strings
    -0.65
    lying
    -0.64
    ledged
    -0.64
    edge
    -0.64
    hang
    -0.63
    sing
    -0.62
    hed
    -0.62
    POSITIVE LOGITS
    ĸļ
    0.82
    uncture
    0.79
    -'
    0.74
    achine
    0.74
    ovies
    0.71
    å¹
    0.70
     kHz
    0.68
    theless
    0.68
    ixties
    0.67
    ohydrate
    0.66
    Act Density 0.024%

    No Known Activations