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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the implementation of rules or laws

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "go into effect."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Corpus
    -0.67
     Primordial
    -0.67
    asca
    -0.67
    Side
    -0.64
    ides
    -0.64
     Stain
    -0.64
    pi
    -0.62
     Crus
    -0.60
     stained
    -0.60
    IDES
    -0.60
    POSITIVE LOGITS
    uate
    0.92
    uation
    0.89
    uated
    0.86
    angering
    0.85
    uating
    0.83
    ional
    0.80
    ||||
    0.77
    ures
    0.74
     curfew
    0.73
    ually
    0.72
    Act Density 0.049%

    No Known Activations