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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "such"

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce examples

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orem
    -0.60
    oret
    -0.59
     somew
    -0.59
    rique
    -0.57
    onel
    -0.55
    olute
    -0.54
    YR
    -0.54
     Accessed
    -0.53
     succeeding
    -0.53
    achus
    -0.50
    POSITIVE LOGITS
     as
    0.94
    as
    0.92
    ties
    0.84
    ities
    0.70
    asma
    0.67
    Flag
    0.64
    As
    0.63
    MpServer
    0.62
     As
    0.62
    Marx
    0.61
    Act Density 0.041%

    No Known Activations