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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a discovery or revelation

    oai_token-act-pair · gpt-3.5-turbo

    phrases that include the phrase "turned out to be."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     pauses
    -0.69
    accompan
    -0.67
    aer
    -0.64
     culminated
    -0.64
    sterdam
    -0.62
     piv
    -0.60
     Forward
    -0.60
    ellation
    -0.59
    tymology
    -0.59
    cham
    -0.58
    POSITIVE LOGITS
    othy
    0.93
     satisfy
    0.86
    asty
    0.77
     be
    0.77
    osen
    0.69
    mor
    0.69
     nominate
    0.69
    OE
    0.69
     resemble
    0.69
    ggles
    0.68
    Act Density 0.068%

    No Known Activations