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

    Neuronpedia

    INDEX
    Explanations

    references to trailers for movies or other productions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "for" and related phrases indicating purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ATH
    -0.80
    mare
    -0.74
    KK
    -0.72
    âĶĢ
    -0.72
    met
    -0.70
    é¾
    -0.68
    ÃŁ
    -0.68
    Amb
    -0.67
    RT
    -0.67
    6000
    -0.65
    POSITIVE LOGITS
    gery
    1.17
    geries
    1.15
    bidden
    1.11
     sale
    0.96
     purposes
    0.92
    ked
    0.90
     instance
    0.87
     starters
    0.85
    gotten
    0.85
     example
    0.83
    Act Density 0.295%

    No Known Activations