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

    Neuronpedia

    INDEX
    Explanations

    phrases containing the word "so"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "so-called."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    theless
    -0.79
     Halls
    -0.62
     Burg
    -0.59
     Mock
    -0.59
     resemblance
    -0.58
     redundancy
    -0.58
     Madness
    -0.56
     bachelor
    -0.56
     footprint
    -0.54
     Customs
    -0.54
    POSITIVE LOGITS
    oths
    1.36
    apy
    1.23
    aps
    1.12
    iled
    1.08
    iling
    1.03
    bs
    1.01
    bered
    0.98
    othe
    0.98
    aring
    0.97
    pping
    0.95
    Act Density 0.035%

    No Known Activations