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

    Neuronpedia

    INDEX
    Explanations

    timestamped data and their associated attributes or details

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    //
    -0.55
     …
    -0.51
    [++
    -0.51
     r
    -0.48
    DoubleQuotes
    -0.47
    localctx
    -0.47
     Numerade
    -0.47
    kt
    -0.46
     [
    -0.45
     [*]
    -0.45
    POSITIVE LOGITS
     ſind
    0.63
    cknow
    0.62
    parian
    0.62
     contextLoads
    0.62
    omiast
    0.61
    esterday
    0.59
    olesale
    0.58
    álise
    0.58
     ibid
    0.58
     οπο
    0.57
    Act Density 2.086%

    No Known Activations