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

    Neuronpedia

    INDEX
    Explanations

    phrases related to a specific action or event happening "just" before something else

    oai_token-act-pair · gpt-3.5-turbo

    the word "just" and expressions emphasizing proximity or immediacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    glomer
    -0.65
     cous
    -0.64
    aea
    -0.64
    idon
    -0.62
    pora
    -0.62
     contention
    -0.62
     seiz
    -0.62
     confir
    -0.62
     Correction
    -0.59
    xual
    -0.59
    POSITIVE LOGITS
    ifications
    1.30
    ifiable
    1.12
    ices
    1.04
    if
    1.00
    itia
    0.94
    IFIC
    0.91
    IFIED
    0.90
    ifi
    0.90
    ifier
    0.85
    ICES
    0.85
    Act Density 0.083%

    No Known Activations