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

    Neuronpedia

    INDEX
    Explanations

    phrases involving time or chronological order

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used to connect ideas or clauses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .–
    -0.75
    ãĥķãĤ¡
    -0.69
    NULL
    -0.69
    istant
    -0.67
    offensive
    -0.67
    Times
    -0.65
    RAW
    -0.65
    rug
    -0.64
    rain
    -0.63
    ensor
    -0.62
    POSITIVE LOGITS
     then
    0.98
     thence
    0.89
     secondly
    0.86
     luckily
    0.82
     oversaw
    0.80
     consequently
    0.79
     proceeded
    0.79
     THEN
    0.78
     toured
    0.77
     wondered
    0.76
    Act Density 0.329%

    No Known Activations