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

    Neuronpedia

    INDEX
    Explanations

    dates and years in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    elements of lists or sequences, particularly dates and numerical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     evid
    -0.71
     speeches
    -0.66
     Proposition
    -0.65
     plank
    -0.64
     fathers
    -0.64
    ogy
    -0.64
     Assembly
    -0.64
     assembly
    -0.62
     duel
    -0.62
     nod
    -0.62
    POSITIVE LOGITS
    ãĤ¨ãĥ«
    1.05
    Pg
    1.02
    Flickr
    1.02
    1000
    1.01
    6000
    1.01
    oct
    1.00
    2000
    0.97
    etc
    0.95
    2003
    0.94
    OSS
    0.93
    Act Density 0.047%

    No Known Activations