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

    Neuronpedia

    INDEX
    Explanations

    items or lists in a sentence marked by the presence of "etc"

    oai_token-act-pair · gpt-3.5-turbo

    references to lists or items in various formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Divinity
    -0.69
     Moor
    -0.67
    deep
    -0.64
     eye
    -0.63
     Liqu
    -0.63
     CPR
    -0.62
     Spirit
    -0.61
     flirt
    -0.60
     holidays
    -0.60
     Lav
    -0.60
    POSITIVE LOGITS
    ÃĥÃĤÃĥÃĤ
    1.12
    ÃĥÃĤ
    1.09
    %),
    1.01
    %,
    1.00
    %).
    0.99
    %)
    0.99
    .):
    0.98
    .,
    0.98
    %-
    0.94
    ĸļ士
    0.93
    Act Density 0.145%

    No Known Activations